EUVIMEDEUVIMED entdecken
Crossref

OcuMDNet: A lightweight CNN for robust multi-disease retinal diagnosis with cross-dataset reliability

Qianjie Yang, Vijay Govindarajan, Qiyuan Li, Heding Zhou, Zaffar Ahmed Shaikh, Amel Ksibi, Jing Yang, Lip Yee Por

Experimental Eye Research · 2025-12 · 261 · 110642

DOI: 10.1016/j.exer.2025.110642 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Experimental Eye Research, 2025-12. Verfasst von Qianjie Yang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Ningbo Key Laboratory of Medical Research on Blinding Eye Diseases, Ningbo Eye Hospital, Ningbo Eye Institute, Wenzhou Medical University, Ningbo, 31…. Hauptthemen laut MEDLINE: Neural Networks, Computer, Retinal Diseases, Diagnostic Techniques, Ophthalmological. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Princess Nourah Bint Abdulrahman University, Ningbo Municipal Bureau of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aims to develop a lightweight convolutional network for the classification of multiple retinal diseases using fundus images and to evaluate cross-dataset generalization under strict label alignment. We introduce OcuMDNet (Ocular Multi-Disease Net), a compact convolutional neural network (CNN) specifically designed for fundus imagery, incorporating batch normalization and dropout for regularization. A standardized processing pipeline is employed, which includes cropping and resizing images to 224 × 224 pixels, applying contrast-limited adaptive histogram equalization (CLAHE), and performing per-channel normalization. The training process utilizes the AdamW optimizer and incorporates early stopping to enhance model performance. We propose a label-aligned evaluation protocol: (i) assesses 4-class performance (Normal, diabetic retinopathy (DR), Glaucoma, age-related macular degeneration (AMD)) on a combined dataset assembled from public sources; (ii) reports disease-specific results based on the native labels of each dataset (DR: EyePACS, Messidor; Glaucoma: ORIGA; AMD: AREDS); and (iii) evaluates cross-dataset transfer for DR (training on EyePACS and testing on Messidor). Patient-level splits are implemented to prevent data leakage, and class counts are reported for each split. Performance metrics such as accuracy, macro-F1 score, and one-vs-rest ROC-AUC are calculated with 95 % confidence intervals using stratified bootstrap (n = 1000). Paired comparisons are conducted using McNemar's test for accuracy and DeLong's method for AUC, with multiplicity control applied. The OcuMDNet demonstrates strong performance on both combined and disease-specific benchmarks, maintaining robust discrimination in cross-dataset evaluations for DR while ensuring computational efficiency suitable for large-scale screening applications. Ablation studies confirm the significance of preprocessing steps and architectural choices. In conjunction with a label-aligned protocol, the OcuMDNet provides an accurate and efficient baseline for multi-disease fundus analysis, facilitating a transparent assessment of cross-dataset reliability. The code, scripts, and trained weights will be made available to support reproducibility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerRetinal DiseasesDiagnostic Techniques, OphthalmologicalHumansReproducibility of ResultsROC CurveDiabetic RetinopathyMacular DegenerationFundus OculiGlaucoma

Stichwörter der Autor:innen

Convolutional neural networkDeep learningDiabetic retinopathyFundus imagesGlaucomaRetinal disease classification

Autor:innen und Institutionen

  • Ningbo Key Laboratory of Medical Research on Blinding Eye Diseases, Ningbo Eye Hospital, Ningbo Eye Institute, Wenzhou Medical University, Ningbo, 315040, China. Electronic address: 12118547@zju.edu.cn.
  • Distribution and Supply Technology, Expedia Group, Seattle, WA, 98119, United States. Electronic address: vigovindaraja@expediagroup.com.
  • Ningbo Key Laboratory of Medical Research on Blinding Eye Diseases, Ningbo Eye Hospital, Ningbo Eye Institute, Wenzhou Medical University, Ningbo, 315040, China. Electronic address: liqiyuan0701@163.com.
  • Ningbo Key Laboratory of Medical Research on Blinding Eye Diseases, Ningbo Eye Hospital, Ningbo Eye Institute, Wenzhou Medical University, Ningbo, 315040, China. Electronic address: zjnbzhd@126.com.
  • Department of Computer Science and Information Technology, Benazir Bhutto Shaheed University Lyari, Karachi, 75660, Pakistan; School of Engineering, École Polytechnique Fédérale de Lausanne, 1015, Lausanne, Switzerland.…
  • Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia. Electronic address: amelksibi@pnu.edu.sa.

Förderung

  • Princess Nourah Bint Abdulrahman University
  • Ningbo Municipal Bureau of Science and Technology

Zitieren

APA

Yang, Q., Govindarajan, V., Li, Q., Zhou, H., Shaikh, Z. A., Ksibi, A., Yang, J., & Por, L. Y. (2025). OcuMDNet: A lightweight CNN for robust multi-disease retinal diagnosis with cross-dataset reliability. Experimental Eye Research, 261, 110642. https://doi.org/10.1016/j.exer.2025.110642

Vancouver

Yang Q, Govindarajan V, Li Q, Zhou H, Shaikh ZA, Ksibi A, et al. OcuMDNet: A lightweight CNN for robust multi-disease retinal diagnosis with cross-dataset reliability. Experimental Eye Research. 2025;261:110642. doi:10.1016/j.exer.2025.110642

BibTeX
@article{Yang2025,
  author = {Yang, Qianjie and Govindarajan, Vijay and Li, Qiyuan and Zhou, Heding and Shaikh, Zaffar Ahmed and Ksibi, Amel and Yang, Jing and Por, Lip Yee},
  title = {OcuMDNet: A lightweight CNN for robust multi-disease retinal diagnosis with cross-dataset reliability},
  journal = {Experimental Eye Research},
  year = {2025},
  volume = {261},
  pages = {110642},
  doi = {10.1016/j.exer.2025.110642}
}
Kostenlos starten →