Submit to JCM Review for JCM Propose a Special Issue

Journal Menu

Journal Browser

Big Data and Artificial Intelligence-Driven Research in Ophthalmology

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Journal of Clinical Medicine (ISSN 2077-0383). This special issue belongs to the section "Ophthalmology".

Deadline for manuscript submissions: closed (27 December 2022) | Viewed by 21430

Share This Special Issue

Special Issue Editors

Dr. Bum-joo Cho

E-Mail Website1 Website2
Guest Editor

1. Department of Ophthalmology, Hallym University Sacred Heart Hospital, Anyang 14068, Korea
2. Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang 14068, Korea
3. Division of Biomedical Informatics, Seoul National University Biomedical Informatics (SNUBI), Seoul National University College of Medicine, Seoul 03080, Korea
Interests: machine learning; retina; uveitis; diabetic retinopathy; age-related macular degeneration; convolutional neural network

Dr. Yong Un Shin

E-Mail Website1 Website2
Guest Editor

Department of Ophthalmology, Hanyang University College of Medicine, Seoul 04763, Korea
Interests: retinal diseases; optical coherence tomography; vitreoretinal surgery

Special Issue Information

Dear Colleagues,

In recent years, medical big data such as national health examination survey data, health insurance claim data, genome analysis data, or medical image data are being collected, and the size of data is increasing rapidly. Additionally, artificial intelligence (AI), which learns and makes decisions by computers based on data, has been introduced in various fields of medicine thanks to the improvement of computing power and mathematical algorithms. Big data and artificial intelligence are the key concepts of the 4th industrial revolution.

In ophthalmology, since the cornerstone study on the development of deep learning algorithm of fundus photographs for diabetic retinopathy in 2016, much research adopting AI for diagnosis or prognosis prediction of the diseases is actively being published. Also, a lot of studies using big data have validated several previously presented hypotheses in the general population.

Research using big data and AI has enabled automated disease screening, diagnosis or risk prediction, and strong power of verification on subtle topics, as well as a discovery of new knowledge by computer. Although it is obvious that there are still some challenges that big data analysis and machine learning technology need to overcome, these data-driven research designs are very crucial in future studies in ophthalmology. We want to activate big data and AI-driven researches in ophthalmology and become a stepping stone for the future.

This Special Issue of the Journal of Clinical Medicine will cover the following important aspects of big data and artificial intelligence-driven research in ophthalmology.

Big data-based epidemiology of ophthalmologic diseases:

prevalence, incidence, risk factors, odds ratio, relative risk, survival, etc.

Any big data analysis using a large database in ophthalmology:

national health and nutrition examination survey, health insurance claim database, routine health checkup data, electronic medical records, genomic data, or medical image data

AI research on medical images using deep learning such as convolutional neural network or generative adversarial network in ophthalmology
AI research on non-image data such as numeric, text, bio-signal, or genomic data using any type of machine learning algorithm in ophthalmology
Clinical applications of AI or machine learning technologies or systems in ophthalmology
Data extraction, manipulation, pre-processing, or curation technologies in ophthalmology

We look forward to receiving your submissions.

Dr. Bum-joo Cho
Dr. Yong Un Shin
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Clinical Medicine is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

big data
population study
artificial intelligence
deep learning
machine learning
convolutional neural network
precision medicine

Published Papers (10 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

11 pages, 1827 KiB

Open AccessArticle

The Global Burden of Glaucoma: Findings from the Global Burden of Disease 2019 Study and Predictions by Bayesian Age–Period–Cohort Analysis

by Yi Lin, Bingcai Jiang, Yuanqing Cai, Wangdu Luo, Xiaomin Zhu, Qianyi Lin, Min Tang, Xiangji Li and Lin Xie

J. Clin. Med. 2023, 12(5), 1828; https://doi.org/10.3390/jcm12051828 - 24 Feb 2023

Cited by 5 | Viewed by 4538

Abstract

This study aims to report the most up-to-date information about the global disease burden of glaucoma from 1990 to 2019 and to forecast trends in the next few years. Publicly available data from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2019 were used in this study. The prevalence and disability-adjusted life years (DALYs) of glaucoma from 1990 to 2019 were reported. Finally, trends in the years following 2019 were predicted by Bayesian age–period–cohort (BAPC) models. We showed that, globally, the number of prevalent cases was 3,881,624 [95% uncertainty interval (UI): 3,301,963 to 4,535,045] in 1990 and increased to 7,473,400 (95% UI: 6,347,183 to 8,769,520) in 2019, while the age-standardized prevalence rate decreased from 111.92 [95% uncertainty interval (UI): 94.76 to 130.28 per 100,000] in 1990 to 94.68 (95% UI: 80.42 to 110.87 per 100,000) in 2019. The DALY number of glaucoma increased between 1990 and 2019, from 442,182 (95% UI: 301,827 to 626,486) in 1990 to 748,308 (95% UI: 515,636 to 1,044,667) in 2019. There was a significantly negative association between the sociodemographic index (SDI) and age-standardized DALY rates. The BAPC showed that the age-standardized DALY rate is predicted to decrease gradually in both males and females over the next few years. In summary, from 1990 to 2019, the global burden of glaucoma increased and the age-standardized DALY rate is predicted to decrease in the next few years. With the largest burden of glaucoma found in low-SDI regions, clinical diagnosis and treatment in such areas are more challenging and may warrant more attention. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

26 pages, 8130 KiB

Open AccessArticle

Artificial Intelligence for Personalised Ophthalmology Residency Training

by George Adrian Muntean, Adrian Groza, Anca Marginean, Radu Razvan Slavescu, Mihnea Gabriel Steiu, Valentin Muntean and Simona Delia Nicoara

J. Clin. Med. 2023, 12(5), 1825; https://doi.org/10.3390/jcm12051825 - 24 Feb 2023

Cited by 1 | Viewed by 1959

Abstract

Residency training in medicine lays the foundation for future medical doctors. In real-world settings, training centers face challenges in trying to create balanced residency programs, with cases encountered by residents not always being fairly distributed among them. In recent years, there has been a tremendous advancement in developing artificial intelligence (AI)-based algorithms with human expert guidance for medical imaging segmentation, classification, and prediction. In this paper, we turned our attention from training machines to letting them train us and developed an AI framework for personalised case-based ophthalmology residency training. The framework is built on two components: (1) a deep learning (DL) model and (2) an expert-system-powered case allocation algorithm. The DL model is trained on publicly available datasets by means of contrastive learning and can classify retinal diseases from color fundus photographs (CFPs). Patients visiting the retina clinic will have a CFP performed and afterward, the image will be interpreted by the DL model, which will give a presumptive diagnosis. This diagnosis is then passed to a case allocation algorithm which selects the resident who would most benefit from the specific case, based on their case history and performance. At the end of each case, the attending expert physician assesses the resident’s performance based on standardised examination files, and the results are immediately updated in their portfolio. Our approach provides a structure for future precision medical education in ophthalmology. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

11 pages, 1187 KiB

Open AccessArticle

A Neural Network for Automated Image Quality Assessment of Optic Disc Photographs

by Ella Bouris, Tyler Davis, Esteban Morales, Lourdes Grassi, Diana Salazar Vega and Joseph Caprioli

J. Clin. Med. 2023, 12(3), 1217; https://doi.org/10.3390/jcm12031217 - 3 Feb 2023

Cited by 2 | Viewed by 1530

Abstract

This study describes the development of a convolutional neural network (CNN) for automated assessment of optic disc photograph quality. Using a code-free deep learning platform, a total of 2377 optic disc photographs were used to develop a deep CNN capable of determining optic disc photograph quality. Of these, 1002 were good-quality images, 609 were acceptable-quality, and 766 were poor-quality images. The dataset was split 80/10/10 into training, validation, and test sets and balanced for quality. A ternary classification model (good, acceptable, and poor quality) and a binary model (usable, unusable) were developed. In the ternary classification system, the model had an overall accuracy of 91% and an AUC of 0.98. The model had higher predictive accuracy for images of good (93%) and poor quality (96%) than for images of acceptable quality (91%). The binary model performed with an overall accuracy of 98% and an AUC of 0.99. When validated on 292 images not included in the original training/validation/test dataset, the model’s accuracy was 85% on the three-class classification task and 97% on the binary classification task. The proposed system for automated image-quality assessment for optic disc photographs achieves high accuracy in both ternary and binary classification systems, and highlights the success achievable with a code-free platform. There is wide clinical and research potential for such a model, with potential applications ranging from integration into fundus camera software to provide immediate feedback to ophthalmic photographers, to prescreening large databases before their use in research. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

10 pages, 1952 KiB

Open AccessArticle

Detecting Macular Disease Based on Optical Coherence Tomography Using a Deep Convolutional Network

by Jinyoung Han, Seong Choi, Ji In Park, Joon Seo Hwang, Jeong Mo Han, Junseo Ko, Jeewoo Yoon and Daniel Duck-Jin Hwang

J. Clin. Med. 2023, 12(3), 1005; https://doi.org/10.3390/jcm12031005 - 28 Jan 2023

Cited by 6 | Viewed by 1749

Abstract

Neovascular age-related macular degeneration (nAMD) and central serous chorioretinopathy (CSC) are two of the most common macular diseases. This study proposes a convolutional neural network (CNN)-based deep learning model for classifying the subtypes of nAMD (polypoidal choroidal vasculopathy, retinal angiomatous proliferation, and typical nAMD) and CSC (chronic CSC and acute CSC) and healthy individuals using single spectral–domain optical coherence tomography (SD–OCT) images. The proposed model was trained and tested using 6063 SD–OCT images from 521 patients and 47 healthy participants. We used three well-known CNN architectures (VGG–16, VGG–19, and ResNet) and two customized classification layers. Additionally, transfer learning and mix–up-based data augmentation were applied to improve robustness and accuracy. Our model demonstrated high accuracies of 99.7% and 91.1% in the nAMD and CSC classification and retinopathy (nAMD and CSC) subtype classification, including normal participants, respectively. Furthermore, we performed an external test to compare the classification accuracy with that of eight ophthalmologists, and our model showed the highest accuracy. The region determined to be important for classification by the model was confirmed using gradient-weighted class activation mapping. The model’s clinical criteria were similar to that of the ophthalmologists. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

14 pages, 4694 KiB

Open AccessArticle

A Deep Learning System Using Optical Coherence Tomography Angiography to Detect Glaucoma and Anterior Ischemic Optic Neuropathy

by Roxane Bunod, Mélanie Lubrano, Antoine Pirovano, Géraldine Chotard, Emmanuelle Brasnu, Sylvain Berlemont, Antoine Labbé, Edouard Augstburger and Christophe Baudouin

J. Clin. Med. 2023, 12(2), 507; https://doi.org/10.3390/jcm12020507 - 7 Jan 2023

Cited by 3 | Viewed by 1751

Abstract

Introduction. Glaucoma and non-arteritic anterior ischemic optic neuropathy (NAION) are optic neuropathies that can both lead to irreversible blindness. Several studies have compared optical coherence tomography angiography (OCTA) findings in glaucoma and NAION in the presence of similar functional and structural damages with contradictory results. The goal of this study was to use a deep learning system to differentiate OCTA in glaucoma and NAION. Material and methods. Sixty eyes with glaucoma (including primary open angle glaucoma, angle-closure glaucoma, normal tension glaucoma, pigmentary glaucoma, pseudoexfoliative glaucoma and juvenile glaucoma), thirty eyes with atrophic NAION and forty control eyes (NC) were included. All patients underwent OCTA imaging and automatic segmentation was used to analyze the macular superficial capillary plexus (SCP) and the radial peripapillary capillary (RPC) plexus. We used the classic convolutional neural network (CNN) architecture of ResNet50. Attribution maps were obtained using the “Integrated Gradients” method. Results. The best performances were obtained with the SCP + RPC model achieving a mean area under the receiver operating characteristics curve (ROC AUC) of 0.94 (95% CI 0.92–0.96) for glaucoma, 0.90 (95% CI 0.86–0.94) for NAION and 0.96 (95% CI 0.96–0.97) for NC. Conclusion. This study shows that deep learning architecture can classify NAION, glaucoma and normal OCTA images with a good diagnostic performance and may outperform the specialist assessment. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

12 pages, 2174 KiB

Open AccessArticle

Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning

by Bum-Joo Cho, Minwoo Lee, Jiyong Han, Soonil Kwon, Mi Sun Oh, Kyung-Ho Yu, Byung-Chul Lee, Ju Han Kim and Chulho Kim

J. Clin. Med. 2022, 11(12), 3309; https://doi.org/10.3390/jcm11123309 - 9 Jun 2022

Cited by 6 | Viewed by 2015

Abstract

Purpose: We investigated whether a deep learning algorithm applied to retinal fundoscopic images could predict cerebral white matter hyperintensity (WMH), as represented by a modified Fazekas scale (FS), on brain magnetic resonance imaging (MRI). Methods: Participants who had undergone brain MRI and health-screening fundus photography at Hallym University Sacred Heart Hospital between 2010 and 2020 were consecutively included. The subjects were divided based on the presence of WMH, then classified into three groups according to the FS grade (0 vs. 1 vs. 2+) using age matching. Two pre-trained convolutional neural networks were fine-tuned and evaluated for prediction performance using 10-fold cross-validation. Results: A total of 3726 fundus photographs from 1892 subjects were included, of which 905 fundus photographs from 462 subjects were included in the age-matched balanced dataset. In predicting the presence of WMH, the mean area under the receiver operating characteristic curve was 0.736 ± 0.030 for DenseNet-201 and 0.724 ± 0.026 for EfficientNet-B7. For the prediction of FS grade, the mean accuracies reached 41.4 ± 5.7% with DenseNet-201 and 39.6 ± 5.6% with EfficientNet-B7. The deep learning models focused on the macula and retinal vasculature to detect an FS of 2+. Conclusions: Cerebral WMH might be partially predicted by non-invasive fundus photography via deep learning, which may suggest an eye–brain association. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Graphical abstract

10 pages, 6199 KiB

Open AccessArticle

Comparison between Deep-Learning-Based Ultra-Wide-Field Fundus Imaging and True-Colour Confocal Scanning for Diagnosing Glaucoma

by Younji Shin, Hyunsoo Cho, Yong Un Shin, Mincheol Seong, Jun Won Choi and Won June Lee

J. Clin. Med. 2022, 11(11), 3168; https://doi.org/10.3390/jcm11113168 - 2 Jun 2022

Cited by 5 | Viewed by 1679

Abstract

In this retrospective, comparative study, we evaluated and compared the performance of two confocal imaging modalities in detecting glaucoma based on a deep learning (DL) classifier: ultra-wide-field (UWF) fundus imaging and true-colour confocal scanning. A total of 777 eyes, including 273 normal control eyes and 504 glaucomatous eyes, were tested. A convolutional neural network was used for each true-colour confocal scan (Eidon AF™, CenterVue, Padova, Italy) and UWF fundus image (Optomap™, Optos PLC, Dunfermline, UK) to detect glaucoma. The diagnostic model was trained using 545 training and 232 test images. The presence of glaucoma was determined, and the accuracy and area under the receiver operating characteristic curve (AUC) metrics were assessed for diagnostic power comparison. DL-based UWF fundus imaging achieved an AUC of 0.904 (95% confidence interval (CI): 0.861–0.937) and accuracy of 83.62%. In contrast, DL-based true-colour confocal scanning achieved an AUC of 0.868 (95% CI: 0.824–0.912) and accuracy of 81.46%. Both DL-based confocal imaging modalities showed no significant differences in their ability to diagnose glaucoma (p = 0.135) and were comparable to the traditional optical coherence tomography parameter-based methods (all p > 0.005). Therefore, using a DL-based algorithm on true-colour confocal scanning and UWF fundus imaging, we confirmed that both confocal fundus imaging techniques had high value in diagnosing glaucoma. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

9 pages, 625 KiB

Open AccessArticle

Menopause and the Risk of Developing Age-Related Macular Degeneration in Korean Women

by Jin-Sung Yuk and Je Hyung Hwang

J. Clin. Med. 2022, 11(7), 1899; https://doi.org/10.3390/jcm11071899 - 29 Mar 2022

Cited by 1 | Viewed by 1515

Abstract

Previous studies have shown that menopausal hormone therapy in postmenopausal women results in a higher prevalence of age-related macular degeneration. This study aimed to evaluate the effects of menopause and patient factors on the development of age-related macular degeneration in Korean women. Data between 2011 and 2014 were collected from the Korean National Health Insurance database. In this retrospective cohort study, 97,651 participants were premenopausal and 33,598 were menopausal. Participants were divided into menopausal and premenopausal groups to analyze the risk factors associated with the development of age-related macular degeneration. The prevalence of age-related macular degeneration was compared between the two groups. Other patient factors were also analyzed. Using a 1:1 propensity score matching method and adjusting for variables, the incidence of age-related macular degeneration was not significantly different between the two groups. Age and diabetes mellitus were associated with an increased risk of developing age-related macular degeneration, regardless of menopause. Menopause was not a risk factor for age-related macular degeneration. These findings may help physicians identify women with diabetes who are at a greater risk of developing age-related macular degeneration. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

8 pages, 1080 KiB

Open AccessArticle

Real-World Analysis of the Aging Effects on Visual Field Reliability Indices in Humans

by Tomoki Shirakami, Tetsuro Omura, Hiroki Fukuda, Ryo Asaoka and Masaki Tanito

J. Clin. Med. 2021, 10(24), 5775; https://doi.org/10.3390/jcm10245775 - 9 Dec 2021

Cited by 3 | Viewed by 1759

Abstract

Relationships between age and visual field (VF) reliability indices were investigated using a large real-world dataset (42,421 VF data points from 11,525 eyes of 5930 subjects). All VFs tested and stored at Shimane University Hospital between 1988 and 2019 were exported. Correlations between age, mean deviation (MD), pattern standard deviation (PSD), and reliability indices including fixation losses (FLs), false negatives (FNs), and false positives (FPs) were analyzed. The mean ± standard deviation age was 65.0 ± 15.1 years; MD—−6.9 ± 8.1 decibels (dB); PSD—6.3 ± 4.6 dB; FL—8.6 ± 11.7%; FN—5.3 ± 8.3%; and FP—2.6 ± 5.0%. Univariate analyses showed strong associations between age and FNs (correlation coefficient, ρ = 0.20, p < 0.0001) and MD (ρ = −0.21, p < 0.0001). All FLs, FNs, and FPs were lowest during the third decade (20–29 years) of life. FLs were elevated consistently after that decade, and FNs were elevated sharply after the seventh decade. FPs were relatively stable after the fourth decade (30–39 years). Mixed-effect regression analyses in subjects 40 years and older showed that older age was associated with worse FLs (p < 0.0001) and FNs (p < 0.0001) but not FPs (p = 0.4126). Aging affects FLs and FNs with different modes but had minimal effects on FPs. Decreased VF sensitivity, deteriorated macular function, and technical difficulties with testing may be mechanisms of age-related changes in FLs and FNs. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Figure 1

11 pages, 547 KiB

Open AccessArticle

Classification Tree to Analyze Factors Connected with Post Operative Complications of Cataract Surgery in a Teaching Hospital

by Michele Lanza, Robert Koprowski, Rosa Boccia, Adriano Ruggiero, Luigi De Rosa, Antonia Tortori, Sławomir Wilczyński, Paolo Melillo, Sandro Sbordone and Francesca Simonelli

J. Clin. Med. 2021, 10(22), 5399; https://doi.org/10.3390/jcm10225399 - 19 Nov 2021

Cited by 3 | Viewed by 1685

Abstract

Background: Artificial intelligence (AI) is becoming ever more frequently applied in medicine and, consequently, also in ophthalmology to improve both the quality of work for physicians and the quality of care for patients. The aim of this study is to use AI, in particular classification tree, for the evaluation of both ocular and systemic features involved in the onset of complications due to cataract surgery in a teaching hospital. Methods: The charts of 1392 eyes of 1392 patients, with a mean age of 71.3 ± 8.2 years old, were reviewed to collect the ocular and systemic data before, during and after cataract surgery, including post-operative complications. All these data were processed by a classification tree algorithm, producing more than 260 million simulations, aiming to develop a predictive model. Results: Postoperative complications were observed in 168 patients. According to the AI analysis, the pre-operative characteristics involved in the insurgence of complications were: ocular comorbidities, lower visual acuity, higher astigmatism and intra-operative complications. Conclusions: Artificial intelligence application may be an interesting tool in the physician’s hands to develop customized algorithms that can, in advance, define the post-operative complication risk. This may help in improving both the quality and the outcomes of the surgery as well as in preventing patient dissatisfaction. Full article

(This article belongs to the Special Issue Big Data and Artificial Intelligence-Driven Research in Ophthalmology)

► Show Figures

Journal Menu

Journal Browser

Big Data and Artificial Intelligence-Driven Research in Ophthalmology

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (10 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI