Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automated Diabetic Screening via Anterior Segment Ocular Imaging: A Deep Learning and Explainable AI Approach

Hasaan Maqsood, Saif Ur Rehman Khan, Sebastian Vollmer, Andreas Dengel, Muhammad Nabeel Asim

Abstract

Diabetic retinopathy screening traditionally relies on fundus photography, requiring specialized equipment and expertise often unavailable in primary care and resource limited settings. We developed and validated a deep learning (DL) system for automated diabetic classification using anterior segment ocular imaging a readily accessible alternative utilizing standard photography equipment. The system leverages visible biomarkers in the iris, sclera, and conjunctiva that correlate with systemic diabetic status. We systematically evaluated five contemporary architectures (EfficientNet-V2-S with self-supervised learning (SSL), Vision Transformer, Swin Transformer, ConvNeXt-Base, and ResNet-50) on 2,640 clinically annotated anterior segment images spanning Normal, Controlled Diabetic, and Uncontrolled Diabetic categories. A tailored preprocessing pipeline combining specular reflection mitigation and contrast limited adaptive histogram equalization (CLAHE) was implemented to enhance subtle vascular and textural patterns critical for classification. SSL using SimCLR on domain specific ocular images substantially improved model performance.EfficientNet-V2-S with SSL achieved optimal performance with an F1-score of 98.21%, precision of 97.90%, and recall of 98.55% a substantial improvement over ImageNet only initialization (94.63% F1). Notably, the model attained near perfect precision (100%) for Normal classification, critical for minimizing unnecessary clinical referrals.

Automated Diabetic Screening via Anterior Segment Ocular Imaging: A Deep Learning and Explainable AI Approach

Abstract

Diabetic retinopathy screening traditionally relies on fundus photography, requiring specialized equipment and expertise often unavailable in primary care and resource limited settings. We developed and validated a deep learning (DL) system for automated diabetic classification using anterior segment ocular imaging a readily accessible alternative utilizing standard photography equipment. The system leverages visible biomarkers in the iris, sclera, and conjunctiva that correlate with systemic diabetic status. We systematically evaluated five contemporary architectures (EfficientNet-V2-S with self-supervised learning (SSL), Vision Transformer, Swin Transformer, ConvNeXt-Base, and ResNet-50) on 2,640 clinically annotated anterior segment images spanning Normal, Controlled Diabetic, and Uncontrolled Diabetic categories. A tailored preprocessing pipeline combining specular reflection mitigation and contrast limited adaptive histogram equalization (CLAHE) was implemented to enhance subtle vascular and textural patterns critical for classification. SSL using SimCLR on domain specific ocular images substantially improved model performance.EfficientNet-V2-S with SSL achieved optimal performance with an F1-score of 98.21%, precision of 97.90%, and recall of 98.55% a substantial improvement over ImageNet only initialization (94.63% F1). Notably, the model attained near perfect precision (100%) for Normal classification, critical for minimizing unnecessary clinical referrals.
Paper Structure (27 sections, 8 equations, 9 figures, 8 tables)

This paper contains 27 sections, 8 equations, 9 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Problem Formalization
  3. Contributions
  4. Related Work
  5. Materials and Methods
  6. Dataset Description
  7. Automated Data Quality Assessment and Relabeling
  8. Image Preprocessing and Augmentation
  9. Preprocessing Pipeline
  10. Data Augmentation
  11. Self-Supervised Pretraining
  12. SimCLR Framework
  13. Contrastive Loss
  14. Supervised Classification
  15. Model Architectures
  16. ...and 12 more sections

Figures (9)

  • Figure 1: Anterior segment image samples across three clinical categories and five gaze directions, before and after quality assessment relabeling.
  • Figure 2: Preprocessing pipeline: original image (left), after specular reflection removal (middle), and after CLAHE enhancement (right).
  • Figure 3: Seven clinically validated data augmentation transformations applied to anterior segment training images.
  • Figure 4: Architecture overview of the SimCLR self-supervised framework for ocular feature learning, where augmented views pass through a shared encoder and projection head optimized with NT-Xent loss ($\tau=0.5$). After 10 epochs, the loss decreases from 3.33 to 2.90, yielding pretrained encoder weights for supervised fine-tuning.
  • Figure 5: Confusion matrices comparing SSL-pretrained and baseline EfficientNetV2-S on the validation set.
  • ...and 4 more figures