computer science based research papers

computer science Recently Published Documents

Total documents.

• Latest Documents
• Most Cited Documents
• Contributed Authors
• Related Sources
• Related Keywords

Hiring CS Graduates: What We Learned from Employers

Computer science ( CS ) majors are in high demand and account for a large part of national computer and information technology job market applicants. Employment in this sector is projected to grow 12% between 2018 and 2028, which is faster than the average of all other occupations. Published data are available on traditional non-computer science-specific hiring processes. However, the hiring process for CS majors may be different. It is critical to have up-to-date information on questions such as “what positions are in high demand for CS majors?,” “what is a typical hiring process?,” and “what do employers say they look for when hiring CS graduates?” This article discusses the analysis of a survey of 218 recruiters hiring CS graduates in the United States. We used Atlas.ti to analyze qualitative survey data and report the results on what positions are in the highest demand, the hiring process, and the resume review process. Our study revealed that a software developer was the most common job the recruiters were looking to fill. We found that the hiring process steps for CS graduates are generally aligned with traditional hiring steps, with an additional emphasis on technical and coding tests. Recruiters reported that their hiring choices were based on reviewing resume’s experience, GPA, and projects sections. The results provide insights into the hiring process, decision making, resume analysis, and some discrepancies between current undergraduate CS program outcomes and employers’ expectations.

A Systematic Literature Review of Empiricism and Norms of Reporting in Computing Education Research Literature

Context. Computing Education Research (CER) is critical to help the computing education community and policy makers support the increasing population of students who need to learn computing skills for future careers. For a community to systematically advance knowledge about a topic, the members must be able to understand published work thoroughly enough to perform replications, conduct meta-analyses, and build theories. There is a need to understand whether published research allows the CER community to systematically advance knowledge and build theories. Objectives. The goal of this study is to characterize the reporting of empiricism in Computing Education Research literature by identifying whether publications include content necessary for researchers to perform replications, meta-analyses, and theory building. We answer three research questions related to this goal: (RQ1) What percentage of papers in CER venues have some form of empirical evaluation? (RQ2) Of the papers that have empirical evaluation, what are the characteristics of the empirical evaluation? (RQ3) Of the papers that have empirical evaluation, do they follow norms (both for inclusion and for labeling of information needed for replication, meta-analysis, and, eventually, theory-building) for reporting empirical work? Methods. We conducted a systematic literature review of the 2014 and 2015 proceedings or issues of five CER venues: Technical Symposium on Computer Science Education (SIGCSE TS), International Symposium on Computing Education Research (ICER), Conference on Innovation and Technology in Computer Science Education (ITiCSE), ACM Transactions on Computing Education (TOCE), and Computer Science Education (CSE). We developed and applied the CER Empiricism Assessment Rubric to the 427 papers accepted and published at these venues over 2014 and 2015. Two people evaluated each paper using the Base Rubric for characterizing the paper. An individual person applied the other rubrics to characterize the norms of reporting, as appropriate for the paper type. Any discrepancies or questions were discussed between multiple reviewers to resolve. Results. We found that over 80% of papers accepted across all five venues had some form of empirical evaluation. Quantitative evaluation methods were the most frequently reported. Papers most frequently reported results on interventions around pedagogical techniques, curriculum, community, or tools. There was a split in papers that had some type of comparison between an intervention and some other dataset or baseline. Most papers reported related work, following the expectations for doing so in the SIGCSE and CER community. However, many papers were lacking properly reported research objectives, goals, research questions, or hypotheses; description of participants; study design; data collection; and threats to validity. These results align with prior surveys of the CER literature. Conclusions. CER authors are contributing empirical results to the literature; however, not all norms for reporting are met. We encourage authors to provide clear, labeled details about their work so readers can use the study methodologies and results for replications and meta-analyses. As our community grows, our reporting of CER should mature to help establish computing education theory to support the next generation of computing learners.

Light Diacritic Restoration to Disambiguate Homographs in Modern Arabic Texts

Diacritic restoration (also known as diacritization or vowelization) is the process of inserting the correct diacritical markings into a text. Modern Arabic is typically written without diacritics, e.g., newspapers. This lack of diacritical markings often causes ambiguity, and though natives are adept at resolving, there are times they may fail. Diacritic restoration is a classical problem in computer science. Still, as most of the works tackle the full (heavy) diacritization of text, we, however, are interested in diacritizing the text using a fewer number of diacritics. Studies have shown that a fully diacritized text is visually displeasing and slows down the reading. This article proposes a system to diacritize homographs using the least number of diacritics, thus the name “light.” There is a large class of words that fall under the homograph category, and we will be dealing with the class of words that share the spelling but not the meaning. With fewer diacritics, we do not expect any effect on reading speed, while eye strain is reduced. The system contains morphological analyzer and context similarities. The morphological analyzer is used to generate all word candidates for diacritics. Then, through a statistical approach and context similarities, we resolve the homographs. Experimentally, the system shows very promising results, and our best accuracy is 85.6%.

A genre-based analysis of questions and comments in Q&A sessions after conference paper presentations in computer science

Gender diversity in computer science at a large public r1 research university: reporting on a self-study.

With the number of jobs in computer occupations on the rise, there is a greater need for computer science (CS) graduates than ever. At the same time, most CS departments across the country are only seeing 25–30% of women students in their classes, meaning that we are failing to draw interest from a large portion of the population. In this work, we explore the gender gap in CS at Rutgers University–New Brunswick, a large public R1 research university, using three data sets that span thousands of students across six academic years. Specifically, we combine these data sets to study the gender gaps in four core CS courses and explore the correlation of several factors with retention and the impact of these factors on changes to the gender gap as students proceed through the CS courses toward completing the CS major. For example, we find that a significant percentage of women students taking the introductory CS1 course for majors do not intend to major in CS, which may be a contributing factor to a large increase in the gender gap immediately after CS1. This finding implies that part of the retention task is attracting these women students to further explore the major. Results from our study include both novel findings and findings that are consistent with known challenges for increasing gender diversity in CS. In both cases, we provide extensive quantitative data in support of the findings.

Designing for Student-Directedness: How K–12 Teachers Utilize Peers to Support Projects

Student-directed projects—projects in which students have individual control over what they create and how to create it—are a promising practice for supporting the development of conceptual understanding and personal interest in K–12 computer science classrooms. In this article, we explore a central (and perhaps counterintuitive) design principle identified by a group of K–12 computer science teachers who support student-directed projects in their classrooms: in order for students to develop their own ideas and determine how to pursue them, students must have opportunities to engage with other students’ work. In this qualitative study, we investigated the instructional practices of 25 K–12 teachers using a series of in-depth, semi-structured interviews to develop understandings of how they used peer work to support student-directed projects in their classrooms. Teachers described supporting their students in navigating three stages of project development: generating ideas, pursuing ideas, and presenting ideas. For each of these three stages, teachers considered multiple factors to encourage engagement with peer work in their classrooms, including the quality and completeness of shared work and the modes of interaction with the work. We discuss how this pedagogical approach offers students new relationships to their own learning, to their peers, and to their teachers and communicates important messages to students about their own competence and agency, potentially contributing to aims within computer science for broadening participation.

Creativity in CS1: A Literature Review

Computer science is a fast-growing field in today’s digitized age, and working in this industry often requires creativity and innovative thought. An issue within computer science education, however, is that large introductory programming courses often involve little opportunity for creative thinking within coursework. The undergraduate introductory programming course (CS1) is notorious for its poor student performance and retention rates across multiple institutions. Integrating opportunities for creative thinking may help combat this issue by adding a personal touch to course content, which could allow beginner CS students to better relate to the abstract world of programming. Research on the role of creativity in computer science education (CSE) is an interesting area with a lot of room for exploration due to the complexity of the phenomenon of creativity as well as the CSE research field being fairly new compared to some other education fields where this topic has been more closely explored. To contribute to this area of research, this article provides a literature review exploring the concept of creativity as relevant to computer science education and CS1 in particular. Based on the review of the literature, we conclude creativity is an essential component to computer science, and the type of creativity that computer science requires is in fact, a teachable skill through the use of various tools and strategies. These strategies include the integration of open-ended assignments, large collaborative projects, learning by teaching, multimedia projects, small creative computational exercises, game development projects, digitally produced art, robotics, digital story-telling, music manipulation, and project-based learning. Research on each of these strategies and their effects on student experiences within CS1 is discussed in this review. Last, six main components of creativity-enhancing activities are identified based on the studies about incorporating creativity into CS1. These components are as follows: Collaboration, Relevance, Autonomy, Ownership, Hands-On Learning, and Visual Feedback. The purpose of this article is to contribute to computer science educators’ understanding of how creativity is best understood in the context of computer science education and explore practical applications of creativity theory in CS1 classrooms. This is an important collection of information for restructuring aspects of future introductory programming courses in creative, innovative ways that benefit student learning.

CATS: Customizable Abstractive Topic-based Summarization

Neural sequence-to-sequence models are the state-of-the-art approach used in abstractive summarization of textual documents, useful for producing condensed versions of source text narratives without being restricted to using only words from the original text. Despite the advances in abstractive summarization, custom generation of summaries (e.g., towards a user’s preference) remains unexplored. In this article, we present CATS, an abstractive neural summarization model that summarizes content in a sequence-to-sequence fashion while also introducing a new mechanism to control the underlying latent topic distribution of the produced summaries. We empirically illustrate the efficacy of our model in producing customized summaries and present findings that facilitate the design of such systems. We use the well-known CNN/DailyMail dataset to evaluate our model. Furthermore, we present a transfer-learning method and demonstrate the effectiveness of our approach in a low resource setting, i.e., abstractive summarization of meetings minutes, where combining the main available meetings’ transcripts datasets, AMI and International Computer Science Institute(ICSI) , results in merely a few hundred training documents.

Exploring students’ and lecturers’ views on collaboration and cooperation in computer science courses - a qualitative analysis

Factors affecting student educational choices regarding oer material in computer science, export citation format, share document.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals

Computer science articles from across Nature Portfolio

Computer science is the study and development of the protocols required for automated processing and manipulation of data. This includes, for example, creating algorithms for efficiently searching large volumes of information or encrypting data so that it can be stored and transmitted securely.

Latest Research and Reviews

A multimodal screening system for elderly neurological diseases based on deep learning

• Sangyoung Park

TransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records

Using AI to predict disease can improve interventions slow down or prevent disease. Here, the authors show that generative AI models built on the framework of Transformer, the model that also empowers ChatGPT, can achieve state-of-the-art performance on disease predictions based on longitudinal electronic records.

• Zhichao Yang
• Avijit Mitra

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach

• Juan M. Zambrano Chaves
• Andrew L. Wentland
• Bhavik N. Patel

Scaling deep learning for materials discovery

A protocol using large-scale training of graph networks enables high-throughput discovery of novel stable structures and led to the identification of 2.2 million crystal structures, of which 381,000 are newly discovered stable materials.

• Amil Merchant
• Simon Batzner
• Ekin Dogus Cubuk

Deep asymmetric extraction and aggregation for infrared small target detection

• Zhongwu Lin

On the reduction of mixed Gaussian and impulsive noise in heavily corrupted color images

• Bogdan Smolka
• Damian Kusnik
• Krystian Radlak

News and Comment

ChatGPT for chemistry: AI and robots join forces to build new materials

Google DeepMind tool predicts nearly 400,000 stable substances, and an autonomous system learns to make them in the lab.

• Mark Peplow

Beyond the clinic: the rise of wearables and smartphones in decentralising healthcare

Navigating contemporary healthcare, wearable technology and smartphones are marking the dawn of a transformative era in patient observation and personalised care. Wearables, equipped with various sensing technologies (e.g., accelerometer for movement, optics for heart rate), are increasingly being recognised for their expansive potential in (remote) patient monitoring, diagnostics, and therapeutic applications which suggests a plausible move towards a more decentralised healthcare system. This shift is evident as healthcare providers and patients alike are becoming increasingly accepting of wearable-driven tools, as they enable continuous health monitoring outside of traditional clinical settings. Equally, the ubiquitous nature of smartphones, now more than mere communication tools, is being harnessed to serve as pivotal health monitoring instruments. Their added sensing capabilities with Internet of Things (IoT) driven connectivity enable a (relatively) seamless transition from conventional health practices to a more interconnected, digital age. However, this evolving landscape is not without its challenges, with concerns surrounding data privacy, security, and ensuring equitable access to digital advances. As we delve deeper into digital healthcare, we must harness the full potential of those technologies and ensure their ethical and equitable implementation, envisioning a future where healthcare is not just hospital-centric but is part of our daily lives.

• Victoria Hetherington
• Alan Godfrey

What the OpenAI drama means for AI progress — and safety

A debacle at the company that built ChatGPT highlights concern that commercial forces are acting against the responsible development of artificial-intelligence systems.

• Nicola Jones

How AI is expanding art history

From identifying disputed artworks to reconstructing lost masterpieces, artificial intelligence is enriching how we interpret our cultural heritage.

• David G. Stork

Presentation matters for AI-generated clinical advice

If mistakes are made in clinical settings, patients suffer. Artificial intelligence (AI) generally — and large language models specifically — are increasingly used in health settings, but the way that physicians use AI tools in this high-stakes environment depends on how information is delivered. AI toolmakers have a responsibility to present information in a way that minimizes harm.

• Marzyeh Ghassemi

This hot AI summer will impact Brazil’s democracy

The current debate surrounding the use and regulation of artificial intelligence (AI) in Brazil has social and political implications. We summarize these discussions, advocate for balance in the current debate around AI and fake news, and caution against preemptive AI regulation.

• Cristina Godoy B. de Oliveira
• Fabio G. Cozman
• João Paulo C. Veiga

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Subscribe to the PwC Newsletter

Join the community, trending research, increasing fps for single board computers and embedded computers in 2021 (jetson nano and yovov4-tiny). practice and review.

This manuscript provides a review of methods for increasing the frame per second of single-board computers.

Distributed, Parallel, and Cluster Computing

Advancing Mixture Models for Least Squares Optimization

TUC-ProAut/libRSF • 3 Mar 2021

Gaussian mixtures are a powerful and widely used tool to model non-Gaussian estimation problems.

Unikraft: Fast, Specialized Unikernels the Easy Way

unikraft/unikraft • 26 Apr 2021

Unikernels are famous for providing excellent performance in terms of boot times, throughput and memory consumption, to name a few metrics.

Operating Systems

SimLOD: Simultaneous LOD Generation and Rendering

m-schuetz/simlod • 5 Oct 2023

Background: LOD construction is typically implemented as a preprocessing step that requires users to wait before they are able to view the results in real time.

Non-iterative SLAM for Warehouse Robots Using Ground Textures

sair-lab/ni-slam • 16 Oct 2017

We present a novel visual SLAM method for the warehouse robot with a single downward-facing camera using ground textures.

Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems.

Sound Audio and Speech Processing

Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis

Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis.

Sound Multimedia Audio and Speech Processing

MSCEqF: A Multi State Constraint Equivariant Filter for Vision-aided Inertial Navigation

aau-cns/msceqf • 20 Nov 2023

This letter re-visits the problem of visual-inertial navigation system (VINS) and presents a novel filter design we dub the multi state constraint equivariant filter (MSCEqF, in analogy to the well known MSCKF).

Robotics Systems and Control Systems and Control

cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation

This paper explores the problem of collision-free motion generation for manipulators by formulating it as a global motion optimization problem.

Robotics Hardware Architecture Distributed, Parallel, and Cluster Computing

WhisperX: Time-Accurate Speech Transcription of Long-Form Audio

Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages.

Journal of Computer Science

Aims and scope.

The Journal of Computer Science (JCS) is dedicated to advancing computer science by publishing high-quality research and review articles that span both theoretical foundations and practical applications in information, computation, and computer systems. With a commitment to excellence, JCS offers a platform for researchers, scholars, and industry professionals to share their insights and contribute to the ongoing evolution of computer science. Published on a monthly basis, JCS provides up-to-date insights into this ever-evolving discipline.

Science Publications is pleased to announce the launch of a new open access journal, Journal of Adaptive Structures. JAS brings together emerging technologies for adaptive smart structures, including advanced materials, smart actuation, sensing and control, to pursue the progressive adoption of the major scientific achievements in this multidisciplinary field on-board of commercial aircraft. 

It is with great pleasure that we announce the SGAMR Annual Awards 2020. This award is given annually to Researchers and Reviewers of International Journal of Structural Glass and Advanced Materials Research (SGAMR) who have shown innovative contributions and promising research as well as others who have excelled in their Editorial duties.

This special issue "Neuroinflammation and COVID-19" aims to provide a space for debate in the face of the growing evidence on the affectation of the nervous system by COVID-19, supported by original studies and case series.

• Recently Published
• Most Viewed
• Most Downloaded

Showing papers in "Computer Science Review in 2021"

Citation Count

408  citations

229  citations

179  citations

107  citations

87  citations

82  citations

77  citations

68  citations

65  citations

This paper is in the following e-collection/theme issue:

Published on 29.11.2023 in Vol 25 (2023)

Developing and Evaluating an AI-Based Computer-Aided Diagnosis System for Retinal Disease: Diagnostic Study for Central Serous Chorioretinopathy

Authors of this article:

Original Paper

• Jeewoo Yoon 1, 2 * , DPhil   ; 
• Jinyoung Han 1, 3 * , DPhil   ; 
• Junseo Ko 1, 2 , MSc   ; 
• Seong Choi 1, 2 , MSc   ; 
• Ji In Park 4 , MD, DPhil   ; 
• Joon Seo Hwang 5 , MD   ; 
• Jeong Mo Han 6 , MD   ; 
• Daniel Duck-Jin Hwang 7, 8 , MD, DPhil  

1 Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul, Republic of Korea

2 Raondata, Seoul, Republic of Korea

3 Department of Human-Artificial Intelligence Interaction, Sungkyunkwan University, Seoul, Republic of Korea

4 Department of Medicine, Kangwon National University School of Medicine, Kangwon National University Hospital, Chuncheon, Republic of Korea

5 Seoul Plus Eye Clinic, Seoul, Republic of Korea

6 Seoul Bombit Eye Clinic, Sejong, Republic of Korea

7 Department of Ophthalmology, Hangil Eye Hospital, Incheon, Republic of Korea

8 Lux Mind, Incheon, Republic of Korea

*these authors contributed equally

Corresponding Author:

Daniel Duck-Jin Hwang, MD, DPhil

Department of Ophthalmology

Hangil Eye Hospital

35 Bupyeong-daero, Bupyeong-gu, Incheon

Incheon, 21388

Republic of Korea

Phone: 82 327175808

Email: [email protected]

Background: Although previous research has made substantial progress in developing high-performance artificial intelligence (AI)–based computer-aided diagnosis (AI-CAD) systems in various medical domains, little attention has been paid to developing and evaluating AI-CAD system in ophthalmology, particularly for diagnosing retinal diseases using optical coherence tomography (OCT) images.

Objective: This diagnostic study aimed to determine the usefulness of a proposed AI-CAD system in assisting ophthalmologists with the diagnosis of central serous chorioretinopathy (CSC), which is known to be difficult to diagnose, using OCT images.

Methods: For the training and evaluation of the proposed deep learning model, 1693 OCT images were collected and annotated. The data set included 929 and 764 cases of acute and chronic CSC, respectively. In total, 66 ophthalmologists (2 groups: 36 retina and 30 nonretina specialists) participated in the observer performance test. To evaluate the deep learning algorithm used in the proposed AI-CAD system, the training, validation, and test sets were split in an 8:1:1 ratio. Further, 100 randomly sampled OCT images from the test set were used for the observer performance test, and the participants were instructed to select a CSC subtype for each of these images. Each image was provided under different conditions: (1) without AI assistance, (2) with AI assistance with a probability score, and (3) with AI assistance with a probability score and visual evidence heatmap. The sensitivity, specificity, and area under the receiver operating characteristic curve were used to measure the diagnostic performance of the model and ophthalmologists.

Results: The proposed system achieved a high detection performance (99% of the area under the curve) for CSC, outperforming the 66 ophthalmologists who participated in the observer performance test. In both groups, ophthalmologists with the support of AI assistance with a probability score and visual evidence heatmap achieved the highest mean diagnostic performance compared with that of those subjected to other conditions (without AI assistance or with AI assistance with a probability score). Nonretina specialists achieved expert-level diagnostic performance with the support of the proposed AI-CAD system.

Conclusions: Our proposed AI-CAD system improved the diagnosis of CSC by ophthalmologists, which may support decision-making regarding retinal disease detection and alleviate the workload of ophthalmologists.

Introduction

Computer-aided diagnosis (CAD) is a software system that assists in the diagnostic decision-making of clinicians [ 1 ]. CAD systems can be used to support clinicians in various tasks, such as detecting breast cancer [ 2 ], lung cancer [ 3 ], colorectal cancer [ 4 ], and even Alzheimer disease [ 5 ]. Thus, these systems potentially alleviate the heavy workload of clinicians, resulting in the improved quality of clinical services [ 6 , 7 ].

With recent advancements in computer vision and deep learning techniques, deep neural networks have been reported to achieve expert-level performance in clinical diagnoses [ 8 - 10 ]. This, in turn, has led researchers to construct CAD systems involving artificial intelligence (AI) models, such as AI-based computer-aided diagnosis (AI-CAD), to assist with clinical diagnosis, for example, by detecting major thoracic diseases on chest radiographs [ 6 ] and classifying skin cancer using skin photographs [ 11 ]. Although prior studies have made valuable progress in developing high-performance AI-CAD systems in various medical domains, minimal attention has been focused on developing and evaluating AI-CAD systems in ophthalmology, especially for the diagnosis of retinal diseases using optical coherence tomography (OCT) images.

Following age-related macular degeneration (AMD), diabetic retinopathy, and branch retinal vein occlusion, central serous chorioretinopathy (CSC) is the fourth most prevalent vision-threatening retinopathy and is characterized by serous detachment of the neurosensory retina at the posterior pole [ 8 , 12 ]. Most patients with CSC are male, and they experience decreased or distorted vision with altered color sensitivity and persistent subretinal fluid (SRF) damage to the retinal outer layer, resulting in permanent vision loss, which degrades their quality of life [ 13 , 14 ]. When diagnosing CSC, assessing the chronicity of the disease is difficult but critical for the formulation of a treatment strategy or the prediction of its prognosis [ 8 , 15 ]. A patient with chronic CSC with or without sustained sensory retinal detachment may already have irreversible poor vision or require active intervention; hence, preventing permanent visual disturbance that can reduce a patient’s quality of life [ 15 ] is important.

In ophthalmology, OCT is a noninvasive, rapid, and accurate test that produces highly reproducible outcomes [ 8 , 16 , 17 ]. It is frequently used to evaluate structural abnormalities associated with retinal disease, including CSC, without requiring physical contact [ 17 ]. It is now considered the imaging modality of choice for the diagnosis and follow-up of patients with CSC [ 18 , 19 ]. OCT has been used to examine the alterations in CSC's retinal pigment epithelium (RPE) and outer retina morphology [ 20 ]. Further, OCT can assess and quantify the presence of SRF, which can aid in estimating the episode duration and determine the subsequent treatment [ 17 ].

Herein, we propose an AI-CAD system that can alleviate the heavy workloads and improve the diagnostic performance of retinal disease for ophthalmologists. We tried to find out whether AI could really help ophthalmologists’ diagnostic activities through a CAD system in the field of ophthalmology, and we selected CSC, one of the representative macular diseases, and built a CAD system. In particular, the proposed AI-CAD system may support ophthalmologists in distinguishing the subtypes of CSC. To investigate the effectiveness of the proposed system, we conducted a within-subject user study involving 66 ophthalmologists.

Ethical Considerations

This study was conducted in accordance with the 1964 Declaration of Helsinki guidelines. The Ethics Committee of Hangil Eye Hospital approved the research protocol (IRB 21018) and its implementation and waived the requirement for informed consent as this study was retrospective and observational in nature and used medical records to extract the required data.

AI-CAD System Construction for CSC-Subtype Detection

Data collection and csc labeling.

To train and evaluate the proposed deep learning model, 1693 OCT images of patients who visited Hangil Eye Hospital between June 2017 and June 2021 were collected and annotated. This study aimed to construct an AI-CAD system that identifies CSC subtypes.

All CSC cases were diagnosed by independent retinal specialists using fundus examinations, fluorescein angiography (FA), indocyanine green angiography (ICGA), and OCT images. On all CSC cases, FA and ICGA were performed simultaneously using a Heidelberg Retina Angiograph (Heidelberg Engineering) confocal scanning laser ophthalmoscope. Other potentially conflicting retinal pathologies such as AMD, polypoidal choroidal vasculopathy, pachychoroid neovasculopathy, and pachychoroid pigment epitheliopathy were excluded from our analysis.

Acute CSC was diagnosed based on the presence of serous retinal detachment involving the macula, as demonstrated by OCT, and the leakage at the level of the RPE on FA [ 16 , 17 , 21 ]. In the acute CSC cohort, only classic, acute CSC with a symptom duration of less than 4 months since the first episode was included. Chronic CSC was diagnosed based on the RPE status and was defined as chronic chorioretinopathy with widespread RPE decompensation, with or without subretinal detachment, and with or without an active leakage site, according to the Daruich et al [ 22 ] classification scheme [ 21 ]. Chronic CSC was diagnosed when extensive RPE atrophy was observed, independently of SRF, according to their definition [ 15 , 22 ]. Further, 2 retina experts (JSH and DDJH) reviewed the images from OCT, FA, and ICGA imaging techniques and also assessed the medical records. If there was a difference in opinions, another retina expert (JMH) stepped in to identify the inconsistency and consulted with the others. Any differences were settled through mutual agreement. Representative CSC cases are illustrated in Multimedia Appendix 1 .

User Interface of AI-CAD System

The proposed AI-CAD system formulated in this study ( Figure 1 ) comprises three components: (1) an AI probability panel, (2) an evidence heatmap panel, and (3) a status panel. Further, we designed the user interface of the proposed AI-CAD system using HTML, CSS, and JavaScript, while implementing the server-side functionality with Python and Flask [ 23 ].

The AI probability panel displays the probability score for each retinal disease (acute or chronic CSC). These scores are generated from the last fully connected layer of the proposed deep learning model using the softmax activation function and allow users to measure the confidence of the AI model with its decision. The probabilities are illustrated with progress bars to enable users to intuitively perceive the model’s confidence.

The evidence heatmap panel reveals important regions in the OCT image while the model classifies the target label (eg, acute or chronic CSC). Gradient-weighted class activation mapping was adopted to highlight the important regions [ 24 ]. The activated regions were calculated using the feature-map gradients of the convolutional neural network (CNN) layer. The heatmap highlights the area of the image wherein the proposed model was used for classification. Moreover, users can zoom in or zoom out of the OCT images in the panel to observe the details of the pathologic regions.

The status panel displays the patient information of the current sample. Patient information included identification number, sex, and age. Users were able to identify the demographic information of a patient while analyzing a given image.

AI-CAD System CSC-Subtype Detection Model

To automatically classify a given OCT image into 2 different CSC subtypes, we use CNN-based architecture, VGG-16 [ 25 ]. The convolutional filters in CNN layers learn local patterns such as edges and textures, which is crucial for image recognition. Although other well-known CNN architectures, including VGG-19 and Resnet-50 [ 26 ], have been used previously, VGG-16 was selected in this study as it outperforms the others in our validation set. The proposed model uses spectral domain OCT (SD-OCT) images as input and predicts 1 of the 2 subtypes, that is, acute or chronic CSC. The detailed architecture of the proposed model is illustrated in Multimedia Appendix 2 .

To train and evaluate the AI model, the data were randomly split into the training, validation, and test sets in an 8:1:1 ratio. The validation set was exclusively used to tune the hyperparameters of the model, and the test set was singularly used to evaluate the final performance of the model. We trained the proposed model using batch sizes of 64 and 30 epochs and Adam optimization [ 27 ] (learning rate: 0.0002). Moreover, we leverage transfer learning method to avoid overfitting. The details of transfer learning, data set construction, including collection, labeling, and preprocessing, are described in Multimedia Appendix 3 .

Observer Performance Test

To investigate whether each component of the proposed system can assist in improving the diagnostic performance of ophthalmologists, a web-based experiment was conducted in which each participant was instructed to classify CSC subtypes from a given SD-OCT image. The experimental procedure comprised 3 steps ( Figure 2 ). In the first step, observers had to identify the possible CSC subtype based on the SD-OCT image. The observers diagnosed retinal disease without artificial intelligence assistance (ie, No AI ). In the subsequent step, an AI probability panel was provided to the observers (ie, artificial intelligence assistance with a probability score [ AI Prob ]). The AI probability panel shows the probability score of each retinal disease (acute or chronic). At the end of the step, both the AI probability panel and AI evidence heatmap panel were added to the system to provide a visual explanation to the observers (ie, artificial intelligence assistance with a probability score and visual evidence heatmap [ AI Prob+Evid ]).

In each step, all observers had to determine whether the given OCT image reflected acute or chronic CSC by selecting a button on the web system. The same OCT image was used in the 3 steps. As 100 SD-OCT images were used in our experiment, each participant assessed 300 cases (ie, 3 steps × 100 images) in total. The 100 images were randomly extracted from the test set that was not used to train our model. The step-by-step user interface for the observer performance test is illustrated in Multimedia Appendix 4 .

The study recruited 66 participants, including 36 retina and 30 nonretina specialists. The retina specialists were medical doctors who had completed 1-2 years of the retina fellowship training program. In contrast, nonretina specialists were board-certified ophthalmologists who were not specialized in the retina. The detailed information of the 66 participants is summarized Multimedia Appendix 5 .

Statistical Analysis

Receiver operating characteristic analysis was conducted to evaluate the performance of the proposed model and ophthalmologists in classifying the CSC subtypes. Thereafter, the receiver operating characteristic curve with the true-positive and false-positive rates was plotted to measure the area under the receiver operating characteristic curve (AUROC) score. Friedman [ 28 ] test, followed by the Wilcoxon signed-rank test, was used to quantify the differences among the 3 different conditions (ie, No AI , AI Prob , and AI Prob+Evid ) [ 29 ]. A 2-tailed t test was used to compare diagnostic performance between the nonretina and retina specialists.

CSC-Subtype Detection Model Performance

The proposed model exhibited high accuracy, sensitivity, and specificity values of 96.3%, 97.1%, and 95.7%, respectively (n=163). The model achieved 98.4% (n=163) of the AUROC which outperforms Resnet-50 (n=163; AUROC 87.9%) and VGG-19 (n=163; AUROC 96.1%). The model failed to accurately predict 6 cases only in our test set. Importantly, the training AUROC of 95.6% (n=163) indicates that our model strikes a balance between avoiding overfitting and underfitting, further affirming its reliability.

Performance Comparison Between the AI-CAD System and Ophthalmologists

The diagnostic performance of the AI-CAD system was compared with that of ophthalmologists. The AUROCs were calculated to evaluate the AI-CAD and human predictive abilities for 100 images randomly extracted from the test set. The AI-CAD system (AUROC 99.5%; n=100) outperformed both retina (AUROC 92.1%; n-36) and nonretina (AUROC 87.8%; n=30) specialists.

Diagnostic Performance of Ophthalmologists

The retinal-disease detection performance of the 36 retina and 30 nonretina specialists were evaluated under 3 different conditions (ie, No AI , AI Prob, and AI Prob+Evid ; Table 1 ). The results of the Friedman test followed by the Wilcoxon signed-rank test revealed significant differences in diagnostic performance among the 3 different conditions for retina (statistic=59.5, df =2; P <.001) and nonretina (statistic=44.4, df =2; P <.001) specialists. In particular, the retina specialists who were provided with the AI probability panel and AI evidence heatmap panel (ie, AI Prob+Evid ) achieved the highest mean diagnostic performance (AUROC 95.8%, 95% CI 0.948-0.969; n=36) compared with those subjected to other conditions ( No AI : 0.921, 95% CI 0.907-0.935; P <.001; and AI Prob : 0.956, 95% CI 0.946-0.967; P <.05). The nonretina specialists also displayed their best performance (0.929, 95% CI 0.913-0.946) with numerical and visual information compared with when they were subjected to other conditions ( No AI : 0.878, 95% CI 0.860-0.895; P <.001; and AI Prob : 0.922, 95% CI 0.905-0.940; P <.001).

a AUROC: area under the receiver operating characteristic curve.

b No AI : without artificial intelligence assistance.

c AI Prob : artificial intelligence assistance with a probability score.

d AI Prob+Evid : artificial intelligence assistance with a probability score and visual evidence heatmap.

Benefits of the AI-CAD System in CSC-Subtype Classification

This study investigated how the AI-CAD system can help nonretina specialists detect retinal diseases. The t test results revealed no significant differences in AUROC between the nonretina specialists supported by the AI-CAD system ( AI Prob : 0.922, 95% CI 0.905-0.940; P =.88; and AI Prob+Evid : 0.929, 95% CI 0.913-0.946; P =.42) and retina specialists not supported by the AI-CAD system ( No AI : 0.921, 95% CI 0.907-0.935). This finding demonstrates that nonretina specialists can achieve expert-level diagnostic performance with the support of the proposed AI CAD system ( Figure 3 ).

Changes in Clinical Diagnosis With the Support of the AI-CAD System

To evaluate the proposed system’s positive effect in assisting ophthalmologists, the number of positive (ie, false negative to true positive and false positive to true negative) and negative (ie, true positive to false negative and true negative to false positive) changes that could be observed between the No AI and AI Prob+Evid conditions were recorded. Chronic CSC was set as the positive class. Overall, 42.8% (307/718) of the misclassified cases under the No AI condition were accurately classified in the AI Prob+Evid condition ( Table 2 ). In particular, 106 false-negative cases turned into true positives after using the proposed AI-CAD system, implying that the proposed system is useful for ophthalmologists in distinguishing between acute and chronic CSC.

a AI-CAD: artificial intelligence–based computer-aided diagnosis system.

b AI: artificial intelligence.

c FN: false negative.

d TP: true positive.

e FP: false positive.

f TN: true negative.

Principal Findings

This study proposed the development of an AI-CAD system to assist ophthalmologists in distinguishing chronic from acute CSC. In particular, the proposed system provides (1) the probability of retinal disease and (2) visual evidence to effectively assist ophthalmologists in their clinical decisions. To evaluate the effectiveness of the proposed AI-CAD system in enhancing ophthalmologists’ clinical decision-making, a within-subject user study involving 66 ophthalmologists was conducted. The extensive experiments demonstrated that the proposed AI-CAD system effectively assists ophthalmologists in improving their diagnostic performance for retinal disease.

The proposed deep neural network in the AI-CAD system achieved a high retinal-disease detection performance of 99.5% (n=100) of the AUROC, outperforming all 66 ophthalmologists who participated in the experiment. The high performance of the proposed AI-CAD model implies that it can lessen the heavy workloads and reduce potential errors by clinicians [ 8 , 9 ]. The quality of clinical services can be improved by using a deep learning model that guarantees consistent and high-level detection performance for retinal disease.

The observer performance test revealed that the proposed AI-CAD system can effectively help ophthalmologists diagnose retinal disease. The experimental results revealed that the diagnostic performance of the retina specialists and nonretina specialists increased by 3.5% (n=36) and 4.4% (n=30), respectively ( Table 1 ). This signifies that the proposed system successfully improved the ability of ophthalmologists to detect retinal disease. In particular, the performance difference between cases with and without the AI-CAD system was higher in the nonretina specialist group (n=30; 4.4%) than that in the retina specialist group (n=36; 3.5%), implying that the nonretina specialist group tended to receive support more than the retina specialist group. This finding is consistent with that of a prior study, which revealed that relatively less-skilled physicians exhibited greater improvement in the detection of pulmonary disease compared with that of skilled physicians [ 6 , 7 ]. Moreover, ophthalmologists achieved an even higher AUROC (retina specialists: 0.958; nonretina specialists: 0.929) if AI diagnosis information was availed with its visual explanation (gradient-weighted class activation mapping). This indicates that providing probability scores with a visual explanation is more useful for ophthalmologists than simply displaying the probability scores alone, thereby exhibiting consistency with prior work that revealed the usefulness of visual modality in detecting diseases [ 7 ].

Practical Issues

Deploying a clinical decision support system (CDSS) in real-world health care settings presents a set of practical challenges. Chief among these concerns is the system’s susceptibility to errors, which can undermine trust in AI-driven solutions. To address this, a dynamic training model becomes indispensable. In the realm of academia, researchers have embraced the “Human-In-the-Loop” paradigm to tackle this issue [ 30 - 32 ]. This approach involves the seamless integration of human oversight and intervention into the CDSS’s decision-making processes. By empowering human experts to review and amend the system's outputs, we expedite the identification and rectification of errors. Consequently, this iterative feedback mechanism bolsters the CDSS's trustworthiness and reliability in real-world applications, bringing it into closer alignment with user expectations and requirements.

Another pivotal concern pertains to the system's security. Safeguarding patient data and upholding the integrity of the CDSS is paramount within the health care domain. This demands the implementation of robust encryption, stringent access controls, and regular security audits to protect sensitive information and prevent unauthorized access or data breaches. Furthermore, continuous monitoring and timely updates to the CDSS are essential for addressing emerging security threats and vulnerabilities, ensuring a high level of security in real-world applications.

By concurrently addressing error mitigation and security, CDSS developers and health care professionals can collaborate in creating a more dependable and trustworthy system that serves the best interests of both patients and medical practitioners.

Limitations

This study has some limitations. First, all images were acquired from a single OCT device located at a single academic center. Although the data set was sufficient to train and validate the proposed model for distinguishing between CSC subtypes, external validation with a different center is needed. Second, experiments were conducted using the web-based AI-CAD system developed in this study. Thus, the environment was relatively different from that of actual clinical practice. However, we attempted to design and develop a user-friendly AI-CAD system under the supervision of retina specialists. Third, considering that the model's training data comprises images taken exclusively by the Heidelberg Spectralis device (Heidelberg Engineering Inc), its performance might be insufficient when dealing with images from different devices. Future studies should prioritize (1) extending the proposed AI-CAD system to other retinal diseases, such as AMD and diabetic retinopathy; (2) developing strategies to improve the reliability of doctors when using the AI-CAD system; and (3) exploring the application of transfer learning techniques to address the challenges arising from variations in devices.

Comparison With Prior Work

This study has several implications. First, to the best of our knowledge, this study is the first attempt to develop and evaluate an AI-CAD system for the detection of retinal disease using OCT. Prior studies have developed AI-CAD systems for the detection of pulmonary disease and evaluated their effectiveness [ 6 , 33 , 34 ]. However, minimal attention has been focused on the application of an AI-CAD system for the diagnosis of retinal diseases, such as CSC and AMD. In this study, an AI-CAD system that can assist ophthalmologists in identifying retinal diseases was developed and its usefulness in detecting retinal disease was evaluated.

Second, the proposed AI-CAD system is potentially useful for small or local medical care centers where retina specialists are unavailable. Unlike in large-scale medical care centers or hospitals, retina specialists are rarely found in small or local centers. Diagnosing subtypes of retinal diseases (ie, acute vs chronic CSC [ 8 ] and polypoidal choroidal vasculopathy vs retinal angiomatous proliferation [ 10 ]) requires more elaborate expertise than simply screening abnormal cases (ie, normal vs CSC [ 8 ]), and the proposed AI-CAD system exhibits higher performance than that of retina specialists with over 10 years of experience, implying that the proposed system potentially plays an important role in such cases. In CSC, assessing the chronicity of the disease at the time of diagnosis is crucial for selecting an appropriate course of treatment or forecasting its prognosis [ 8 , 15 , 22 ]. Acute CSC typically follows a self-limiting natural course, whereas chronic CSC with or without sustained SRF may be associated with irreversible vision loss or may require active intervention, such as intravitreal antivascular endothelial growth factor injections or photodynamic therapy, all of which are intended to prevent long-term visual loss that can lower the patient’s quality of life. Further, on comparing diagnostic performance between nonretina and retina specialists, the experimental results of this study demonstrate that nonretina specialists can achieve retina specialist-level performance with the support of the proposed AI-CAD system ( Figure 3 ). This implies that the proposed system can alleviate the heavy workload of ophthalmologists who have expert-level diagnostic performance and facilitate the decision-making process of less-skilled ophthalmologists (nonretina specialists) by improving their diagnostic performance.

Conclusions

To the best of our knowledge, this study is the first attempt to design, develop, and evaluate an AI-CAD system for the detection of retinal disease using OCT. First, an AI-CAD system was developed with a high-performance deep learning model. Thereafter, an observer performance test was conducted with the proposed system to determine the ability of the system to assist ophthalmologists in diagnosing retinal diseases. The results indicated that the proposed AI-CAD system can provide retinal expert-level diagnostic performance and help ophthalmologists improve their diagnostic performance in detecting CSC subtypes. Thus, the proposed AI-CAD system can alleviate the heavy workload of ophthalmologists and help in the decision-making process involved in detecting CSC subtypes. As a base study, this study demonstrates the usefulness and effectiveness of using an AI-CAD system in detecting retinal diseases, particularly CSC subtypes. In the future, the proposed AI-CAD system may be easily extended to the detection of other retinal diseases, such as AMD, diabetic retinopathy, and branch retinal vein occlusion.

Acknowledgments

The authors thank the 66 ophthalmologists who participated in our study. This work was supported in part by the National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science and Information and Communications Technology) (2023R1A2C2007625) and in part by Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean government (23ZT1100, Development of Information and Communications Technology Convergence Technology based on Urban Area).

Data Availability

The data are not available for public access because of patient privacy concerns but are available from the corresponding author upon reasonable request.

Authors' Contributions

JY worked on the methodology, software, writing of the original draft, visualization, and investigation. JH did the methodology, writing review and editing; JK also worked on the methodology and software. SC and JIP performed on the investigation and validation. JSH worked on the data curation and validation. JMH did the data curation and validation. DDJH performed on the methodology, writing review and editing, supervision, data curation, and validation.

Conflicts of Interest

JH and SC own stock of RAON DATA Inc. DDJH and JH own stock of Lux Mind Inc. All other authors declare no competing interests.

Representative cases of acute and chronic central serous chorioretinopathy.

An illustration of the proposed deep learning model based on VGG-16 architecture.

Method details.

A step-by-step illustration of the observer performance test.

Information and test results of the ophthalmologists who participated in the observer performance test.

• Doi K. Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 2007;31(4-5):198-211 [ https://europepmc.org/abstract/MED/17349778 ] [ CrossRef ] [ Medline ]
• Chan HP, Samala RK, Hadjiiski LM. CAD and AI for breast cancer-recent development and challenges. Br J Radiol 2020;93(1108):20190580 [ https://www.birpublications.org/doi/10.1259/bjr.20190580 ] [ CrossRef ] [ Medline ]
• Brown MS, Lo P, Goldin JG, Barnoy E, Kim GHJ, McNitt-Gray MF, et al. Toward clinically usable CAD for lung cancer screening with computed tomography. Eur Radiol 2014;24(11):2719-2728 [ CrossRef ] [ Medline ]
• Mittal A, Kaur M. Computer-aided-diagnosis in colorectal cancer: a survey of state of the art techniques. 2016 Presented at: 2016 International Conference on Inventive Computation Technologies (ICICT); August 26-27, 2016; Coimbatore, India p. 1-6 [ CrossRef ]
• Martínez-Murcia FJ, Górriz JM, Ramírez J, Puntonet CG, Salas-González D. Computer aided diagnosis tool for Alzheimer's disease based on Mann-Whitney-Wilcoxon U-Test. Expert Syst Appl 2012;39(10):9676-9685 [ CrossRef ]
• Hwang EJ, Park S, Jin KN, Kim JI, Choi SY, Lee JH, et al. Development and validation of a deep learning-based automated detection algorithm for major thoracic diseases on chest radiographs. JAMA Netw Open 2019;2(3):e191095 [ https://europepmc.org/abstract/MED/30901052 ] [ CrossRef ] [ Medline ]
• Choi SY, Park S, Kim M, Park J, Choi YR, Jin KN. Evaluation of a deep learning-based computer-aided detection algorithm on chest radiographs: case-control study. Medicine (Baltimore) 2021;100(16):e25663 [ https://europepmc.org/abstract/MED/33879750 ] [ CrossRef ] [ Medline ]
• Yoon J, Han J, Park JI, Hwang JS, Han JM, Sohn J, et al. Optical coherence tomography-based deep-learning model for detecting central serous chorioretinopathy. Sci Rep 2020;10(1):18852 [ https://www.nature.com/articles/s41598-020-75816-w ] [ CrossRef ] [ Medline ]
• Yoon J, Han J, Ko J, Choi S, Park JI, Hwang JS, et al. Classifying central serous chorioretinopathy subtypes with a deep neural network using optical coherence tomography images: a cross-sectional study. Sci Rep 2022;12(1):422 [ https://www.nature.com/articles/s41598-021-04424-z ] [ CrossRef ] [ Medline ]
• Hwang DDJ, Choi S, Ko J, Yoon J, Park JI, Hwang JS, et al. Distinguishing retinal angiomatous proliferation from polypoidal choroidal vasculopathy with a deep neural network based on optical coherence tomography. Sci Rep 2021;11(1):9275 [ https://www.nature.com/articles/s41598-021-88543-7 ] [ CrossRef ] [ Medline ]
• Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;542(7639):115-118 [ https://europepmc.org/abstract/MED/28117445 ] [ CrossRef ] [ Medline ]
• Wang M, Munch IC, Hasler PW, Prünte C, Larsen M. Central serous chorioretinopathy. Acta Ophthalmol 2008;86(2):126-145 [ https://onlinelibrary.wiley.com/doi/10.1111/j.1600-0420.2007.00889.x ] [ CrossRef ] [ Medline ]
• Breukink MB, Dingemans AJ, den Hollander AI, Keunen JE, MacLaren RE, Fauser S, et al. Chronic central serous chorioretinopathy: long-term follow-up and vision-related quality of life. Clin Ophthalmol 2017;11:39-46 [ https://europepmc.org/abstract/MED/28053499 ] [ CrossRef ] [ Medline ]
• Sahin A, Bez Y, Kaya MC, Türkcü FM, Sahin M, Yüksel H. Psychological distress and poor quality of life in patients with central serous chorioretinopathy. Semin Ophthalmol 2014;29(2):73-76 [ CrossRef ] [ Medline ]
• van Rijssen TJ, van Dijk EHC, Yzer S, Ohno-Matsui K, Keunen JEE, Schlingemann RO, et al. Central serous chorioretinopathy: towards an evidence-based treatment guideline. Prog Retin Eye Res 2019;73:100770 [ https://linkinghub.elsevier.com/retrieve/pii/S1350-9462(18)30094-6 ] [ CrossRef ] [ Medline ]
• Shinojima A, Hirose T, Mori R, Kawamura A, Yuzawa M. Morphologic findings in acute central serous chorioretinopathy using spectral domain-optical coherence tomography with simultaneous angiography. Retina 2010;30(2):193-202 [ CrossRef ] [ Medline ]
• Song IS, Shin YU, Lee BR. Time-periodic characteristics in the morphology of idiopathic central serous chorioretinopathy evaluated by volume scan using spectral-domain optical coherence tomography. Am J Ophthalmol 2012;154(2):366-375.e4 [ CrossRef ] [ Medline ]
• Kaye R, Chandra S, Sheth J, Boon CJF, Sivaprasad S, Lotery A. Central serous chorioretinopathy: an update on risk factors, pathophysiology and imaging modalities. Prog Retin Eye Res 2020;79:100865 [ CrossRef ] [ Medline ]
• Ko J, Han J, Yoon J, Park JI, Hwang JS, Han JM, et al. Assessing central serous chorioretinopathy with deep learning and multiple optical coherence tomography images. Sci Rep 2022;12(1):1831 [ https://www.nature.com/articles/s41598-022-05051-y ] [ CrossRef ] [ Medline ]
• Montero JA, Ruiz-Moreno JM. Optical coherence tomography characterisation of idiopathic central serous chorioretinopathy. Br J Ophthalmol 2005;89(5):562-564 [ https://bjo.bmj.com/lookup/pmidlookup?view=long&pmid=15834085 ] [ CrossRef ] [ Medline ]
• Spaide RF, Campeas L, Haas A, Yannuzzi LA, Fisher YL, Guyer DR, et al. Central serous chorioretinopathy in younger and older adults. Ophthalmology 1996;103(12):2070-2079; discussion 2079 [ CrossRef ] [ Medline ]
• Daruich A, Matet A, Dirani A, Bousquet E, Zhao M, Farman N, et al. Central serous chorioretinopathy: recent findings and new physiopathology hypothesis. Prog Retin Eye Res 2015;48:82-118 [ https://linkinghub.elsevier.com/retrieve/pii/S1350-9462(15)00033-6 ] [ CrossRef ] [ Medline ]
• Grinberg M. Flask Web Development: Developing Web Applications with Python. Sebastopol, CA. O'Reilly Media, Inc; 2018.
• Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. 2017 Presented at: 2017 IEEE International Conference on Computer Vision (ICCV); October 22-29, 2017; Venice, Italy p. 618-626 [ CrossRef ]
• Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2015 Presented at: International Conference on Learning Representations; May 7-9, 2015; San Diego, CA, USA URL: https://arxiv.org/abs/1409.1556
• He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016 Presented at: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); June 27-30, 2016; Las Vegas, NV, USA p. 770-778 [ CrossRef ]
• Kingma DP, Ba J. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations. 2015 Presented at: International Conference on Learning Representations; May 7-9, 2015; San Diego, CA, USA URL: https://arxiv.org/abs/1412.6980
• Friedman M. The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc 1937;32(200):675-701 [ CrossRef ]
• Wilcoxon F. Individual comparisons by ranking methods. In: Kotz S, Johnson NL, editors. Springer Series in Statistics: Breakthroughs in Statistics. New York, NY. Springer; 1992:196-202
• Wu X, Xiao L, Sun Y, Zhang J, Ma T, He L. A survey of human-in-the-loop for machine learning. Future Gener Comput Syst 2022;135:364-381 [ CrossRef ]
• Sorantin E, Grasser MG, Hemmelmayr A, Tschauner S, Hrzic F, Weiss V, et al. The augmented radiologist: artificial intelligence in the practice of radiology. Pediatr Radiol 2022;52(11):2074-2086 [ https://europepmc.org/abstract/MED/34664088 ] [ CrossRef ] [ Medline ]
• Le EPV, Wang Y, Huang Y, Hickman S, Gilbert FJ. Artificial intelligence in breast imaging. Clin Radiol 2019;74(5):357-366 [ CrossRef ] [ Medline ]
• Nam JG, Park S, Hwang EJ, Lee JH, Jin KN, Lim KY, et al. Development and validation of deep learning-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs. Radiology 2019;290(1):218-228 [ https://pubs.rsna.org/doi/10.1148/radiol.2018180237 ] [ CrossRef ] [ Medline ]
• Sung J, Park S, Lee SM, Bae W, Park B, Jung E, et al. Added value of deep learning-based detection system for multiple major findings on chest radiographs: a randomized crossover study. Radiology 2021;299(2):450-459 [ https://pubs.rsna.org/doi/10.1148/radiol.2021202818 ] [ CrossRef ] [ Medline ]

Abbreviations

Edited by G Eysenbach; submitted 14.04.23; peer-reviewed by Y Zheng, W Yang, R Wei, Z Li; comments to author 25.07.23; revised version received 29.10.23; accepted 05.11.23; published 29.11.23

©Jeewoo Yoon, Jinyoung Han, Junseo Ko, Seong Choi, Ji In Park, Joon Seo Hwang, Jeong Mo Han, Daniel Duck-Jin Hwang. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 29.11.2023.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.

• Values of Inclusion
• 2020 Antiracism Task Force
• 2022 DEI Report
• Research News
• Department Life
• Listed by Recipient
• Listed by Category
• Oral History of Cornell CS
• CS 40th Anniversary Booklet
• ABC Book for Computer Science at Cornell by David Gries
• Books by Author
• Books Chronologically
• The 60's
• The 70's
• The 80's
• The 90's
• The 00's
• The 2010's
• Faculty Positions: Ithaca
• Faculty Positions: New York City
• Lecturer Position: Ithaca
• Post-doc Position: Ithaca
• Staff/Technical Positions
• Ugrad Course Staff
• Ithaca Info
• Internal info
• Graduation Information
• Cornell Tech Colloquium
• Student Colloquium
• Fall 2023 Colloquium
• Conway-Walker Lecture Series
• Salton 2023 Lecture Series
• Fall 2023 Artificial Intelligence Seminar
• Fall 2023 Robotics Seminar
• Fall 2023 Theory Seminar
• Big Red Hacks
• Cornell University High School Programming Contests 2023
• Game Design Initiative
• CSMore: The Rising Sophomore Summer Program in Computer Science
• Explore CS Research
• ACSU Research Night
• Cornell Junior Theorists' Workshop
• Researchers
• Ph.D. Students
• M.Eng. Students
• M.S. Students
• Ph.D. Alumni
• List of Courses
• Course and Room Roster
• CS Advanced Standing Exam
• Architecture

Artificial Intelligence

Computational biology, database systems, human interaction, machine learning, natural language processing, programming languages, scientific computing, software engineering, systems and networking, theory of computing.

• Contact Academic Advisor
• Your First CS Course
• Technical Electives
• CS with Other Majors/Areas
• Transfer Credits
• CS Honors Program
• CPT for International CS Undergrads
• Graduation Requirements
• Useful Forms
• Becoming a CS Major
• Requirements
• Game Design Minor
• Co-op Program
• Cornell Bowers CIS Undergraduate Research Experience (BURE)
• Independent Research (CS 4999)
• Student Groups
• UGrad Events
• Undergraduate Learning Center
• UGrad Course Staff Info
• The Review Process
• Early M.Eng Credit Approval
• Financial Aid
• Prerequisites
• The Application Process
• The Project
• Pre-approved Electives
• Degree Requirements
• The Course Enrollment Process
• Advising Tips
• Entrepreneurship
• Cornell Tech Programs
• Professional Development
• Contact MEng Office
• Career Success
• Applicant FAQ
• Computer Science Graduate Office Hours
• Exam Scheduling Guidelines
• Graduate TA Handbook
• MS Degree Checklist
• MS Student Financial Support
• Special Committee Selection
• Diversity and Inclusion
• Contact MS Office
• Ph.D. Applicant FAQ
• Graduate Housing
• Non-Degree Application Guidelines
• Ph. D. Visit Day
• Business Card Policy
• Cornell Tech
• Curricular Practical Training
• Fellowship Opportunities
• Field of Computer Science Ph.D. Student Handbook
• Field A Exam Summary Form
• Graduate School Forms
• Instructor / TA Application
• Ph.D. Requirements
• Ph.D. Student Financial Support
• Travel Funding Opportunities
• The Outside Minor Requirement
• CS Graduate Minor
• Outreach Opportunities
• Parental Accommodation Policy
• Special Masters
• Student Spotlights
• Contact PhD Office

Search form

You are here

The computing and information revolution is transforming society. Cornell Computer Science is a leader in this transformation, producing cutting-edge research in many important areas. The excellence of Cornell faculty and students, and their drive to discover and collaborate, ensure our leadership will continue to grow.

The contributions of Cornell Computer Science to research and education are widely recognized, as shown by two Turing Awards, two Von Neumann medals, two MacArthur "genius" awards, and dozens of NSF Career awards our faculty have received, among numerous other signs of success and influence.

To explore current computer science research at Cornell, follow links at the left or below.

Research Areas

Knowledge representation, machine learning, NLP and IR, reasoning, robotics, search, vision

Statistical genetics, sequence analysis, structure analysis, genome assembly, protein classification, gene networks, molecular dynamics

Computer Architecture & VLSI

Processor architecture, networking, asynchronous VLSI, distributed computing

Database systems, data-driven games, learning for database systems, voice interfaces, computational fact checking, data mining

Interactive rendering, global illumination, measurement, simulation, sound, perception

HCI, interface design, computational social science, education, computing and society

Artificial intelligence, algorithms

Programming language design and implementation, optimizing compilers, type theory, formal verification

Perception, control, learning, aerial robots, bio-inspired robots, household robots

Numerical analysis, computational geometry, physically based animation

Secure network services, language-based security, mobile code, privacy, policies, verifiable systems

The software engineering group at Cornell is interested in all aspects of research for helping developers produce high quality software.

Operating systems, distributed computing, networking, and security

The theory of computing is the study of efficient computation, models of computational processes, and their limits.

Computer vision

10 Research Papers Accepted to CVPR 2023

Research from the department has been accepted to the 2023 Computer Vision and Pattern Recognition (CVPR) Conference . The annual event explores machine learning, artificial intelligence, and computer vision research and its applications. 

CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation Samir Yitzhak Gadre Columbia University , Mitchell Wortsman University of Washington , Gabriel Ilharco University of Washington , Ludwig Schmidt University of Washington , Shuran Song Columbia University

For robots to be generally useful, they must be able to find arbitrary objects described by people (i.e., be language-driven) even without expensive navigation training on in-domain data (i.e., perform zero-shot inference). We explore these capabilities in a unified setting: language-driven zero-shot object navigation (L-ZSON). Inspired by the recent success of open-vocabulary models for image classification, we investigate a straightforward framework, CLIP on Wheels (CoW), to adapt open-vocabulary models to this task without fine-tuning. To better evaluate L-ZSON, we introduce the Pasture benchmark, which considers finding uncommon objects, objects described by spatial and appearance attributes, and hidden objects described relative to visible objects. We conduct an in-depth empirical study by directly deploying 21 CoW baselines across Habitat, RoboTHOR, and Pasture. In total, we evaluate over 90k navigation episodes and find that (1) CoW baselines often struggle to leverage language descriptions, but are proficient at finding uncommon objects. (2) A simple CoW, with CLIP-based object localization and classical exploration — and no additional training — matches the navigation efficiency of a state-of-the-art ZSON method trained for 500M steps on Habitat MP3D data. This same CoW provides a 15.6 percentage point improvement in success over a state-of-the-art RoboTHOR ZSON model.

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval  Xudong Lin Columbia University , Simran Tiwari Columbia University , Shiyuan Huang Columbia University , Manling Li UIUC , Mike Zheng Shou National University of Singapore , Heng Ji UIUC , Shih-Fu Chang Columbia University

Multi-channel video-language retrieval require models to understand information from different channels (e.g. video+question, video+speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal models are shown to be highly effective at aligning entities in images/videos and text, e.g., CLIP; text contrastive models are extensively studied recently for their strong ability of producing discriminative sentence embeddings, e.g., SimCSE. However, there is not a clear way to quickly adapt these two lines to multi-channel video-language retrieval with limited data and resources. In this paper, we identify a principled model design space with two axes: how to represent videos and how to fuse video and text information. Based on categorization of recent methods, we investigate the options of representing videos using continuous feature vectors or discrete text tokens; for the fusion method, we explore the use of a multimodal transformer or a pretrained contrastive text model. We extensively evaluate the four combinations on five video-language datasets. We surprisingly find that discrete text tokens coupled with a pretrained contrastive text model yields the best performance, which can even outperform state-of-the-art on the iVQA and How2QA datasets without additional training on millions of video-text data. Further analysis shows that this is because representing videos as text tokens captures the key visual information and text tokens are naturally aligned with text models that are strong retrievers after the contrastive pretraining process. All the empirical analysis establishes a solid foundation for future research on affordable and upgradable multimodal intelligence.

DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection  Jiawei Ma Columbia University , Yulei Niu Columbia University , Jincheng Xu Columbia University , Shiyuan Huang Columbia University , Guangxing Han Columbia University , Shih-Fu Chang Columbia University

Generalized few-shot object detection aims to achieve precise detection on both base classes with abundant annotations and novel classes with limited training data. Existing approaches enhance few-shot generalization with the sacrifice of base-class performance, or maintain high precision in base-class detection with limited improvement in novel-class adaptation. In this paper, we point out the reason is insufficient Discriminative feature learning for all of the classes. As such, we propose a new training framework, DiGeo, to learn Geometry-aware features of inter-class separation and intra-class compactness. To guide the separation of feature clusters, we derive an offline simplex equiangular tight frame (ETF) classifier whose weights serve as class centers and are maximally and equally separated. To tighten the cluster for each class, we include adaptive class-specific margins into the classification loss and encourage the features close to the class centers. Experimental studies on two few-shot benchmark datasets (VOC, COCO) and one long-tail dataset (LVIS) demonstrate that, with a single model, our method can effectively improve generalization on novel classes without hurting the detection of base classes.

Supervised Masked Knowledge Distillation for Few-Shot Transformers Han Lin Columbia University , Guangxing Han Columbia University , Jiawei Ma Columbia University , Shiyuan Huang Columbia University , Xudong Lin Columbia University , Shih-Fu Chang Columbia University

Vision Transformers (ViTs) emerge to achieve impressive performance on many data-abundant computer vision tasks by capturing long-range dependencies among local features. However, under few-shot learning (FSL) settings on small datasets with only a few labeled data, ViT tends to overfit and suffers from severe performance degradation due to its absence of CNN-alike inductive bias. Previous works in FSL avoid such problem either through the help of self-supervised auxiliary losses, or through the dextile uses of label information under supervised settings. But the gap between self-supervised and supervised few-shot Transformers is still unfilled. Inspired by recent advances in self-supervised knowledge distillation and masked image modeling (MIM), we propose a novel Supervised Masked Knowledge Distillation model (SMKD) for few-shot Transformers which incorporates label information into self-distillation frameworks. Compared with previous self-supervised methods, we allow intra-class knowledge distillation on both class and patch tokens, and introduce the challenging task of masked patch tokens reconstruction across intra-class images. Experimental results on four few-shot classification benchmark datasets show that our method with simple design outperforms previous methods by a large margin and achieves a new start-of-the-art. Detailed ablation studies confirm the effectiveness of each component of our model. Code for this paper is available here: this https URL .

FLEX: Full-Body Grasping Without Full-Body Grasps Purva Tendulkar Columbia University , Dídac Surís Columbia University , Carl Vondrick Columbia University

Synthesizing 3D human avatars interacting realistically with a scene is an important problem with applications in AR/VR, video games and robotics. Towards this goal, we address the task of generating a virtual human — hands and full body — grasping everyday objects. Existing methods approach this problem by collecting a 3D dataset of humans interacting with objects and training on this data. However, 1) these methods do not generalize to different object positions and orientations, or to the presence of furniture in the scene, and 2) the diversity of their generated full-body poses is very limited. In this work, we address all the above challenges to generate realistic, diverse full-body grasps in everyday scenes without requiring any 3D full-body grasping data. Our key insight is to leverage the existence of both full-body pose and hand grasping priors, composing them using 3D geometrical constraints to obtain full-body grasps. We empirically validate that these constraints can generate a variety of feasible human grasps that are superior to baselines both quantitatively and qualitatively. See our webpage for more details: this https URL .

Humans As Light Bulbs: 3D Human Reconstruction From Thermal Reflection Ruoshi Liu Columbia University , Carl Vondrick Columbia University

The relatively hot temperature of the human body causes people to turn into long-wave infrared light sources. Since this emitted light has a larger wavelength than visible light, many surfaces in typical scenes act as infrared mirrors with strong specular reflections. We exploit the thermal reflections of a person onto objects in order to locate their position and reconstruct their pose, even if they are not visible to a normal camera. We propose an analysis-by-synthesis framework that jointly models the objects, people, and their thermal reflections, which combines generative models with differentiable rendering of reflections. Quantitative and qualitative experiments show our approach works in highly challenging cases, such as with curved mirrors or when the person is completely unseen by a normal camera.

Tracking Through Containers and Occluders in the Wild Basile Van Hoorick Columbia University , Pavel Tokmakov Toyota Research Institute , Simon Stent Woven Planet , Jie Li Toyota Research Institute , Carl Vondrick Columbia University

Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems. In this paper, we introduce TCOW, a new benchmark and model for visual tracking through heavy occlusion and containment. We set up a task where the goal is to, given a video sequence, segment both the projected extent of the target object, as well as the surrounding container or occluder whenever one exists. To study this task, we create a mixture of synthetic and annotated real datasets to support both supervised learning and structured evaluation of model performance under various forms of task variation, such as moving or nested containment. We evaluate two recent transformer-based video models and find that while they can be surprisingly capable of tracking targets under certain settings of task variation, there remains a considerable performance gap before we can claim a tracking model to have acquired a true notion of object permanence.

Doubly Right Object Recognition: A Why Prompt for Visual Rationales Chengzhi Mao Columbia University , Revant Teotia Columbia University , Amrutha Sundar Columbia University , Sachit Menon Columbia University , Junfeng Yang Columbia University , Xin Wang Microsoft Research , Carl Vondrick Columbia University

Many visual recognition models are evaluated only on their classification accuracy, a metric for which they obtain strong performance. In this paper, we investigate whether computer vision models can also provide correct rationales for their predictions. We propose a “doubly right” object recognition benchmark, where the metric requires the model to simultaneously produce both the right labels as well as the right rationales. We find that state-of-the-art visual models, such as CLIP, often provide incorrect rationales for their categorical predictions. However, by transferring the rationales from language models into visual representations through a tailored dataset, we show that we can learn a “why prompt,” which adapts large visual representations to produce correct rationales. Visualizations and empirical experiments show that our prompts significantly improve performance on doubly right object recognition, in addition to zero-shot transfer to unseen tasks and datasets.

What You Can Reconstruct From a Shadow Ruoshi Liu Columbia University , Sachit Menon Columbia University , Chengzhi Mao Columbia University , Dennis Park Toyota Research Institute , Simon Stent Woven Planet , Carl Vondrick Columbia University

3D reconstruction is a fundamental problem in computer vision, and the task is especially challenging when the object to reconstruct is partially or fully occluded. We introduce a method that uses the shadows cast by an unobserved object in order to infer the possible 3D volumes under occlusion. We create a differentiable image formation model that allows us to jointly infer the 3D shape of an object, its pose, and the position of a light source. Since the approach is end-to-end differentiable, we are able to integrate learned priors of object geometry in order to generate realistic 3D shapes of different object categories. Experiments and visualizations show that the method is able to generate multiple possible solutions that are consistent with the observation of the shadow. Our approach works even when the position of the light source and object pose are both unknown. Our approach is also robust to real-world images where ground-truth shadow mask is unknown.

CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes From Natural Language Aditya Sanghi Autodesk Research , Rao Fu Brown University , Vivian Liu Columbia University , Karl D.D. Willis Autodesk Research , Hooman Shayani Autodesk Research , Amir H. Khasahmadi Autodesk Research , Srinath Sridhar Brown University , Daniel Ritchie Brown University

Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We introduce CLIP-Sculptor, a method to address these constraints by producing high-fidelity and diverse 3D shapes without the need for (text, shape) pairs during training. CLIP-Sculptor achieves this in a multi-resolution approach that first generates in a low-dimensional latent space and then upscales to a higher resolution for improved shape fidelity. For improved shape diversity, we use a discrete latent space which is modeled using a transformer conditioned on CLIP’s image-text embedding space. We also present a novel variant of classifier-free guidance, which improves the accuracy-diversity trade-off. Finally, we perform extensive experiments demonstrating that CLIP-Sculptor outperforms state-of-the-art baselines.

Find the COVID-19 Resource Guide here .

Computer Science at Columbia University

Upcoming events, phd coffee hours.

Wednesday 3:00 pm

Coffee and Questions

Wednesday 2:00 pm

Christmas Day - University Holiday

Monday 9:00 am

University Holiday

Tuesday 10:00 am

In the News

Press mentions, dean boyce's statement on amicus brief filed by president bollinger.

President Bollinger announced that Columbia University along with many other academic institutions (sixteen, including all Ivy League universities) filed an amicus brief in the U.S. District Court for the Eastern District of New York challenging the Executive Order regarding immigrants from seven designated countries and refugees. Among other things, the brief asserts that “safety and security concerns can be addressed in a manner that is consistent with the values America has always stood for, including the free flow of ideas and people across borders and the welcoming of immigrants to our universities.”

This recent action provides a moment for us to collectively reflect on our community within Columbia Engineering and the importance of our commitment to maintaining an open and welcoming community for all students, faculty, researchers and administrative staff. As a School of Engineering and Applied Science, we are fortunate to attract students and faculty from diverse backgrounds, from across the country, and from around the world. It is a great benefit to be able to gather engineers and scientists of so many different perspectives and talents – all with a commitment to learning, a focus on pushing the frontiers of knowledge and discovery, and with a passion for translating our work to impact humanity.

I am proud of our community, and wish to take this opportunity to reinforce our collective commitment to maintaining an open and collegial environment. We are fortunate to have the privilege to learn from one another, and to study, work, and live together in such a dynamic and vibrant place as Columbia.

Mary C. Boyce Dean of Engineering Morris A. and Alma Schapiro Professor

{{title}} {{fullname}}

Courses This Semester

• {{title}} ({{dept}} {{prefix}}{{course_num}}-{{section}})

Research Topics & Ideas: CompSci & IT

50+ Computer Science Research Topic Ideas To Fast-Track Your Project

Finding and choosing a strong research topic is the critical first step when it comes to crafting a high-quality dissertation, thesis or research project. If you’ve landed on this post, chances are you’re looking for a computer science-related research topic , but aren’t sure where to start. Here, we’ll explore a variety of CompSci & IT-related research ideas and topic thought-starters, including algorithms, AI, networking, database systems, UX, information security and software engineering.

NB – This is just the start…

The topic ideation and evaluation process has multiple steps . In this post, we’ll kickstart the process by sharing some research topic ideas within the CompSci domain. This is the starting point, but to develop a well-defined research topic, you’ll need to identify a clear and convincing research gap , along with a well-justified plan of action to fill that gap.

If you’re new to the oftentimes perplexing world of research, or if this is your first time undertaking a formal academic research project, be sure to check out our free dissertation mini-course. In it, we cover the process of writing a dissertation or thesis from start to end. Be sure to also sign up for our free webinar that explores how to find a high-quality research topic. 

Overview: CompSci Research Topics

• Algorithms & data structures
• Artificial intelligence ( AI )
• Computer networking
• Database systems
• Human-computer interaction
• Information security (IS)
• Software engineering
• Examples of CompSci dissertation & theses

Topics/Ideas: Algorithms & Data Structures

• An analysis of neural network algorithms’ accuracy for processing consumer purchase patterns
• A systematic review of the impact of graph algorithms on data analysis and discovery in social media network analysis
• An evaluation of machine learning algorithms used for recommender systems in streaming services
• A review of approximation algorithm approaches for solving NP-hard problems
• An analysis of parallel algorithms for high-performance computing of genomic data
• The influence of data structures on optimal algorithm design and performance in Fintech
• A Survey of algorithms applied in internet of things (IoT) systems in supply-chain management
• A comparison of streaming algorithm performance for the detection of elephant flows
• A systematic review and evaluation of machine learning algorithms used in facial pattern recognition
• Exploring the performance of a decision tree-based approach for optimizing stock purchase decisions
• Assessing the importance of complete and representative training datasets in Agricultural machine learning based decision making.
• A Comparison of Deep learning algorithms performance for structured and unstructured datasets with “rare cases”
• A systematic review of noise reduction best practices for machine learning algorithms in geoinformatics.
• Exploring the feasibility of applying information theory to feature extraction in retail datasets.
• Assessing the use case of neural network algorithms for image analysis in biodiversity assessment

Topics & Ideas: Artificial Intelligence (AI)

• Applying deep learning algorithms for speech recognition in speech-impaired children
• A review of the impact of artificial intelligence on decision-making processes in stock valuation
• An evaluation of reinforcement learning algorithms used in the production of video games
• An exploration of key developments in natural language processing and how they impacted the evolution of Chabots.
• An analysis of the ethical and social implications of artificial intelligence-based automated marking
• The influence of large-scale GIS datasets on artificial intelligence and machine learning developments
• An examination of the use of artificial intelligence in orthopaedic surgery
• The impact of explainable artificial intelligence (XAI) on transparency and trust in supply chain management
• An evaluation of the role of artificial intelligence in financial forecasting and risk management in cryptocurrency
• A meta-analysis of deep learning algorithm performance in predicting and cyber attacks in schools

Topics & Ideas: Networking

• An analysis of the impact of 5G technology on internet penetration in rural Tanzania
• Assessing the role of software-defined networking (SDN) in modern cloud-based computing
• A critical analysis of network security and privacy concerns associated with Industry 4.0 investment in healthcare.
• Exploring the influence of cloud computing on security risks in fintech.
• An examination of the use of network function virtualization (NFV) in telecom networks in Southern America
• Assessing the impact of edge computing on network architecture and design in IoT-based manufacturing
• An evaluation of the challenges and opportunities in 6G wireless network adoption
• The role of network congestion control algorithms in improving network performance on streaming platforms
• An analysis of network coding-based approaches for data security
• Assessing the impact of network topology on network performance and reliability in IoT-based workspaces

Topics & Ideas: Database Systems

• An analysis of big data management systems and technologies used in B2B marketing
• The impact of NoSQL databases on data management and analysis in smart cities
• An evaluation of the security and privacy concerns of cloud-based databases in financial organisations
• Exploring the role of data warehousing and business intelligence in global consultancies
• An analysis of the use of graph databases for data modelling and analysis in recommendation systems
• The influence of the Internet of Things (IoT) on database design and management in the retail grocery industry
• An examination of the challenges and opportunities of distributed databases in supply chain management
• Assessing the impact of data compression algorithms on database performance and scalability in cloud computing
• An evaluation of the use of in-memory databases for real-time data processing in patient monitoring
• Comparing the effects of database tuning and optimization approaches in improving database performance and efficiency in omnichannel retailing

Topics & Ideas: Human-Computer Interaction

• An analysis of the impact of mobile technology on human-computer interaction prevalence in adolescent men
• An exploration of how artificial intelligence is changing human-computer interaction patterns in children
• An evaluation of the usability and accessibility of web-based systems for CRM in the fast fashion retail sector
• Assessing the influence of virtual and augmented reality on consumer purchasing patterns
• An examination of the use of gesture-based interfaces in architecture
• Exploring the impact of ease of use in wearable technology on geriatric user
• Evaluating the ramifications of gamification in the Metaverse
• A systematic review of user experience (UX) design advances associated with Augmented Reality
• A comparison of natural language processing algorithms automation of customer response Comparing end-user perceptions of natural language processing algorithms for automated customer response
• Analysing the impact of voice-based interfaces on purchase practices in the fast food industry

Topics & Ideas: Information Security

• A bibliometric review of current trends in cryptography for secure communication
• An analysis of secure multi-party computation protocols and their applications in cloud-based computing
• An investigation of the security of blockchain technology in patient health record tracking
• A comparative study of symmetric and asymmetric encryption algorithms for instant text messaging
• A systematic review of secure data storage solutions used for cloud computing in the fintech industry
• An analysis of intrusion detection and prevention systems used in the healthcare sector
• Assessing security best practices for IoT devices in political offices
• An investigation into the role social media played in shifting regulations related to privacy and the protection of personal data
• A comparative study of digital signature schemes adoption in property transfers
• An assessment of the security of secure wireless communication systems used in tertiary institutions

Topics & Ideas: Software Engineering

• A study of agile software development methodologies and their impact on project success in pharmacology
• Investigating the impacts of software refactoring techniques and tools in blockchain-based developments
• A study of the impact of DevOps practices on software development and delivery in the healthcare sector
• An analysis of software architecture patterns and their impact on the maintainability and scalability of cloud-based offerings
• A study of the impact of artificial intelligence and machine learning on software engineering practices in the education sector
• An investigation of software testing techniques and methodologies for subscription-based offerings
• A review of software security practices and techniques for protecting against phishing attacks from social media
• An analysis of the impact of cloud computing on the rate of software development and deployment in the manufacturing sector
• Exploring the impact of software development outsourcing on project success in multinational contexts
• An investigation into the effect of poor software documentation on app success in the retail sector

CompSci & IT Dissertations/Theses

While the ideas we’ve presented above are a decent starting point for finding a CompSci-related research topic, they are fairly generic and non-specific. So, it helps to look at actual dissertations and theses to see how this all comes together.

Below, we’ve included a selection of research projects from various CompSci-related degree programs to help refine your thinking. These are actual dissertations and theses, written as part of Master’s and PhD-level programs, so they can provide some useful insight as to what a research topic looks like in practice.

• An array-based optimization framework for query processing and data analytics (Chen, 2021)
• Dynamic Object Partitioning and replication for cooperative cache (Asad, 2021)
• Embedding constructural documentation in unit tests (Nassif, 2019)
• PLASA | Programming Language for Synchronous Agents (Kilaru, 2019)
• Healthcare Data Authentication using Deep Neural Network (Sekar, 2020)
• Virtual Reality System for Planetary Surface Visualization and Analysis (Quach, 2019)
• Artificial neural networks to predict share prices on the Johannesburg stock exchange (Pyon, 2021)
• Predicting household poverty with machine learning methods: the case of Malawi (Chinyama, 2022)
• Investigating user experience and bias mitigation of the multi-modal retrieval of historical data (Singh, 2021)
• Detection of HTTPS malware traffic without decryption (Nyathi, 2022)
• Redefining privacy: case study of smart health applications (Al-Zyoud, 2019)
• A state-based approach to context modeling and computing (Yue, 2019)
• A Novel Cooperative Intrusion Detection System for Mobile Ad Hoc Networks (Solomon, 2019)
• HRSB-Tree for Spatio-Temporal Aggregates over Moving Regions (Paduri, 2019)

Looking at these titles, you can probably pick up that the research topics here are quite specific and narrowly-focused , compared to the generic ones presented earlier. This is an important thing to keep in mind as you develop your own research topic. That is to say, to create a top-notch research topic, you must be precise and target a specific context with specific variables of interest . In other words, you need to identify a clear, well-justified research gap.

Fast-Track Your Research Topic

If you’re still feeling a bit unsure about how to find a research topic for your Computer Science dissertation or research project, check out our Topic Kickstarter service.

You Might Also Like:

Investigating the impacts of software refactoring techniques and tools in blockchain-based developments.

Steps on getting this project topic

I want to work with this topic, am requesting materials to guide.

Information Technology -MSc program

It’s really interesting but how can I have access to the materials to guide me through my work?

Submit a Comment Cancel reply

Your email address will not be published. Required fields are marked *

Save my name, email, and website in this browser for the next time I comment.

• Print Friendly