Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.9
3.8
Journals
Diagnostics
Special Issues
Artificial Intelligence in Eye Disease, Fifth Edition
share announcement

Artificial Intelligence in Eye Disease, Fifth Edition

A Special Issue of Diagnostics (ISSN 2075-4418) belonging to the section "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 2604

Editor

Prof. Dr. Jae-Ho Han

E-Mail Website
Guest Editor
1. Department of Brain and Cognitive Engineering, Korea University, Seoul 136-701, Republic of Korea
2. Department of Artificial Intelligence, Korea University, Seoul 136-701, Republic of Korea
Interests: artificial intelligence in biomedicine; diagnosis of retinal diseases; deep learning for ophthalmology images; neuroscience research
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

While the use of artificial intelligence (AI) is rapidly spreading to the medical world amid the vortex of the Fourth Industrial Revolution, the use of AI in ophthalmology is attracting attention for the diagnosis of various ophthalmic diseases, including optic nerve diseases, which are difficult to diagnose. In particular, AI could aid in diagnosis accuracy when applied to fundus photographs, optical coherence tomography, and the visual field, enabling a strong classification performance in the detection of ocular and retinal diseases. In ocular imaging, AI can be used as a possible solution for screening, diagnosing, and monitoring patients with major eye diseases in primary care and community settings. For instance, using deep learning algorithms that read retinal images, various diseases can be observed, such as bleeding, macular abnormalities (e.g., drusen) choroidal abnormalities, retinal vessel abnormalities, nerve fiber layer defects, and glaucomatous optic nerve papilla changes. Therefore, deep learning architectures can learn to recognize eye diseases, thereby increasing the diagnosis rate with clinically acceptable performance. In other words, AI serves as a safety device for both patients and doctors, as well as an auxiliary tool to quickly judge results. It prevents the possibility of an initial misdiagnosis, provides treatment efficiency, and increases patient reliability. Consequently, AI could potentially revolutionize the way that ophthalmology is practiced in the future. Thus, the aim of this Special Issue is to highlight the recent progress and trends in utilizing AI techniques, such as machine learning and deep learning, for detecting, screening, diagnosing, and monitoring numerous eye diseases, not only in diverse clinical practice, but also in basic research on ophthalmology.

Prof. Dr. Jae-Ho Han
Guest Editor

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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics 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

  • medical diagnosis
  • artificial intelligence
  • deep learning
  • fundus image
  • optical coherence tomography
  • ophthalmology
  • retinal vessel
  • glaucoma
  • retinopathy
  • macular degeneration
  • image segmentation

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 1402 KB  
Article
Knowledge Distillation and Explainability Analysis for Lightweight Retinal Disease Classification Using MultiEYE Fundus Images
by Gülşen Türker and Arif Koyun
Diagnostics 2026, 16(18), 2945; https://doi.org/10.3390/diagnostics16182945 - 11 Sep 2026
Viewed by 185
Abstract
Background/Objectives: Class imbalance and probabilistic prediction quality are important considerations in lightweight retinal classification. We evaluated whether knowledge distillation (KD) from a ConvNeXtV2-Base teacher improved an EfficientNet-B0 student in nine-class MultiEYE fundus classification. Methods: Exact-content screening quarantined 131 of 58,036 records [...] Read more.
Background/Objectives: Class imbalance and probabilistic prediction quality are important considerations in lightweight retinal classification. We evaluated whether knowledge distillation (KD) from a ConvNeXtV2-Base teacher improved an EfficientNet-B0 student in nine-class MultiEYE fundus classification. Methods: Exact-content screening quarantined 131 of 58,036 records because of exact-content duplication or label conflicts. Six prespecified seeds were evaluated in no-KD, label-smoothing, and KD arms (18 runs) under matched training conditions. Within the controlled experiment, TEST data were not used for training, hyperparameter tuning, checkpoint or model selection, or protocol modification. The primary endpoint was the KD−no-KD macro-F1 difference on decontaminated TEST (n = 11,573), assessed by paired image-level bootstrap (10,000 replicates). Grad-CAM and Grad-CAM++ were examined qualitatively using one deterministically selected case per class and six-seed consensus maps. Results: Mean macro-F1 was 0.593, 0.597, and 0.633 for no-KD, label smoothing, and KD. KD exceeded no-KD by 0.039 (95% CI, 0.025–0.053; p < 0.001), with positive paired differences in all six seeds, and label smoothing by 0.036 (Holm-adjusted p < 0.001); label smoothing did not differ from no-KD (Holm-adjusted p = 0.554). Class-wise F1 differences were non-negative across all nine classes, with six remaining significant after correction for multiple comparisons. The Brier score difference was −0.077 (95% CI, −0.081 to −0.072; Holm-adjusted p < 0.001), while ECE decreased descriptively from 0.171 to 0.084. Nine-class Grad-CAM and direct Grad-CAM++ consensus maps enabled qualitative no-KD versus KD comparison without establishing lesion-localization superiority. Conclusions: KD improved macro-F1 and lowered the Brier score while retaining the same EfficientNet-B0 student at inference. The evaluated label-smoothing configuration did not reproduce the macro-F1 gain; clinical superiority and external generalizability remain unestablished. Full article
(This article belongs to the Special Issue Artificial Intelligence in Eye Disease, Fifth Edition)
►▼ Show Figures

Figure 1

21 pages, 1161 KB  
Article
Uncertainty-Aware AI-Assisted Diabetic Retinopathy Grading from Fundus Images with Ordinal Conformal Prediction
by Umar Hasan, Muhammad Ali Nayeem and Turki G. Alghamdi
Diagnostics 2026, 16(16), 2645; https://doi.org/10.3390/diagnostics16162645 - 19 Aug 2026
Viewed by 364
Abstract
Background: Artificial intelligence (AI) systems for diabetic retinopathy (DR) grading require reliable uncertainty estimates when applied to fundus images outside the development dataset. We evaluated whether conformal prediction can provide structured set-valued outputs and whether internal uncertainty calibration remains reliable during external evaluation. [...] Read more.
Background: Artificial intelligence (AI) systems for diabetic retinopathy (DR) grading require reliable uncertainty estimates when applied to fundus images outside the development dataset. We evaluated whether conformal prediction can provide structured set-valued outputs and whether internal uncertainty calibration remains reliable during external evaluation. Methods: EfficientNet-B0, ResNet-50, and Vision Transformer (ViT-Base) classifiers were trained on APTOS 2019. Split-conformal predictors were calibrated exclusively on held-out APTOS images using three categorical scores, LAC, APS, and RAPS, and an ordinal score restricted to adjacent severity grades. Performance was assessed internally on APTOS and externally on IDRiD, with an independent five-seed ViT replication extending evaluation to Messidor-2, at target coverages of 90% and 95%. Results: Coverage was approximately nominal internally but decreased on both external datasets. On IDRiD, the largest deficit occurred for severe DR (grade 3). The ordinal method produced contiguous intervals in 100% of cases and achieved the highest grade-3 coverage in every tested backbone–risk configuration. For ResNet-50 at 95% target coverage, grade-3 coverage increased from 0.750 with APS to 0.945 with the ordinal method, while average set size increased from 2.89 to 3.03. In the independent ViT replication on Messidor-2, ordinal marginal coverage exceeded APS at both targets (0.676 versus 0.632 and 0.741 versus 0.714). Conclusions: Internal calibration did not ensure reliable class-specific uncertainty during external evaluation. Ordinal prediction sets improved structural coherence and mitigated severe-grade undercoverage, but did not restore formal coverage guarantees after dataset shift. Full article
(This article belongs to the Special Issue Artificial Intelligence in Eye Disease, Fifth Edition)
►▼ Show Figures

Figure 1

16 pages, 1718 KB  
Article
Smartphone-Assisted Placido Ring Imaging for K1 Stratification in Keratoconus: A Deep Learning Study
by Enes Eroglu, Nicholas Tomaras, Kabir Anand Pathak, Jaron Sanchez, Rafael Alejandro Pinto-Colmenarez, Juan Carlos Prieto, Lucie Dole, Rohith Erukulla, Michael Maizel, Ali R. Djalilian and Mohammad Soleimani
Diagnostics 2026, 16(13), 2076; https://doi.org/10.3390/diagnostics16132076 - 2 Jul 2026
Cited by 1 | Viewed by 1698
Abstract
Background/Objectives: Keratoconus (KC) is a chronic disease that causes progressive corneal thinning and steepening, thereby negatively impacting visual acuity. Although corneal topography and keratometry are the primary measures to diagnose KC, access to these methods can be limited by various factors. To [...] Read more.
Background/Objectives: Keratoconus (KC) is a chronic disease that causes progressive corneal thinning and steepening, thereby negatively impacting visual acuity. Although corneal topography and keratometry are the primary measures to diagnose KC, access to these methods can be limited by various factors. To address these limitations, this study evaluates a novel low-cost deep-learning algorithm that infers keratometric categories from smartphone-assisted Placido ring photographs. Methods: Development utilized 1240 healthy control eye images and 188 K1-labeled KC images for pretraining, without using their K1 labels. A Variational Autoencoder with KL divergence regularization (AutoEncoderKL) was trained on this pool; its encoder generated latent features for KC images (n = 535). A held-out set (n = 70) with Pentacam keratometry was labeled by K1 into <40 D, 40–47 D, and >47 D. An ensemble classifier chosen via grid search and cross-validation used the encoder features. Performance was assessed for accuracy, precision, recall, and F1-score. Results: The model achieved 91% accuracy across all classes. Precision of the model was 0.77 (<40 D), 0.98 (40–47 D), and 0.86 (>47 D); recall was 0.83, 0.91, and 1.00; and F1-scores were 0.80, 0.94, and 0.92, respectively. Notably, the model achieved perfect recall for the >47 D K1 category. Conclusions: A smartphone-assisted Placido ring imaging approach was able to predict K1-based keratometric categories without requiring tomographic or keratometric measurements as model inputs at inference. These findings provide preliminary proof-of-concept for the potential use of smartphone-assisted Placido ring images as a low-cost approach for K1-based stratification. Larger externally validated studies across different sites, devices, operators, printed Placido discs, acquisition conditions, and patient populations are required before clinical utility can be assessed. Full article
(This article belongs to the Special Issue Artificial Intelligence in Eye Disease, Fifth Edition)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop