Deep Learning Innovations in Diagnosing Diabetic Retinopathy: The Potential of Transfer Learning and the DiaCNN Model

TL;DR

This paper addresses diabetic retinopathy (DR) diagnosis by combining transfer learning from pre-trained InceptionResNetv2 and InceptionV3 models with a novel DiaCNN architecture tailored for eye-disease classification. It implements a fusion-based feature pipeline where pre-trained features are adapted via selective fine-tuning, and contrasts it with a custom residual CNN (DiaCNN) trained from scratch. On the ODIR dataset, the transfer-learning models achieve high accuracy (up to ~97–99% training, ~97% testing), while DiaCNN variants reach the highest testing accuracy (~98.3%) with perfect sensitivity and specificity in one configuration. The study demonstrates the practical potential of domain-specific CNNs and transfer learning for accurate, efficient DR diagnosis, though it notes dataset size as a limitation and points to data augmentation and segmentation-driven extensions as future directions.

Abstract

Diabetic retinopathy (DR) is a significant cause of vision impairment, emphasizing the critical need for early detection and timely intervention to avert visual deterioration. Diagnosing DR is inherently complex, as it necessitates the meticulous examination of intricate retinal images by experienced specialists. This makes the early diagnosis of DR essential for effective treatment and the prevention of eventual blindness. Traditional diagnostic methods, relying on human interpretation of these medical images, face challenges in terms of accuracy and efficiency. In the present research, we introduce a novel method that offers superior precision in DR diagnosis, compared to these traditional methods, by employing advanced deep learning techniques. Central to this approach is the concept of transfer learning. This entails using pre-existing, well-established models, specifically InceptionResNetv2 and Inceptionv3, to extract features and fine-tune select layers to cater to the unique requirements of this specific diagnostic task. Concurrently, we also present a newly devised model, DiaCNN, which is tailored for the classification of eye diseases. To validate the efficacy of the proposed methodology, we leveraged the Ocular Disease Intelligent Recognition (ODIR) dataset, which comprises eight different eye disease categories. The results were promising. The InceptionResNetv2 model, incorporating transfer learning, registered an impressive 97.5% accuracy in both the training and testing phases. Its counterpart, the Inceptionv3 model, achieved an even more commendable 99.7% accuracy during training, and 97.5% during testing. Remarkably, the DiaCNN model showcased unparalleled precision, achieving 100% accuracy in training and 98.3\% in testing.

Figures (24)

• Figure 1: Samples of ODIR dataset used for DR detection.
• Figure 2: Visualization of the dataset in the form of a bar chart.
• Figure 3: The basic architecture of InceptionResnetv2.
• Figure 4: The basic architecture of Inception-v3.
• Figure 5: Block diagram of the proposed method for DR detection.