Adaptive Multiscale Retinal Diagnosis: A Hybrid Trio-Model Approach for Comprehensive Fundus Multi-Disease Detection Leveraging Transfer Learning and Siamese Networks

TL;DR

This paper introduces a hybrid trio-model approach combining transfer learning, Siamese networks, and ensemble methods for accurate, scalable, and early detection of 12 eye diseases from fundus images, outperforming previous benchmarks.

Contribution

It presents a novel hybrid trio-model architecture integrating multiple CNNs and Siamese networks for multi-disease diagnosis, enhancing accuracy and expandability over existing methods.

Findings

Achieved 97% average accuracy and 0.96 AUC score.

Over 10% F1-score improvement compared to past benchmarks.

Successfully predicted diseases like optic disc pallor with low confidence in previous studies.

Abstract

WHO has declared that more than 2.2 billion people worldwide are suffering from visual disorders, such as media haze, glaucoma, and drusen. At least 1 billion of these cases could have been either prevented or successfully treated, yet they remain unaddressed due to poverty, a lack of specialists, inaccurate ocular fundus diagnoses by ophthalmologists, or the presence of a rare disease. To address this, the research has developed the Hybrid Trio-Network Model Algorithm for accurately diagnosing 12 distinct common and rare eye diseases. This algorithm utilized the RFMiD dataset of 3,200 fundus images and the Binary Relevance Method to detect diseases separately, ensuring expandability and avoiding incorrect correlations. Each detector, incorporating finely tuned hyperparameters to optimize performance, consisted of three feature components: A classical transfer learning CNN model, a two-stage CNN model, and a Siamese Network. The diagnosis was made using features extracted through this Trio-Model with Ensembled Machine Learning algorithms. The proposed model achieved an average accuracy of 97% and an AUC score of 0.96. Compared to past benchmark studies, an increase of over 10% in the F1-score was observed for most diseases. Furthermore, using the Siamese Network, the model successfully made predictions in diseases like optic disc pallor, which past studies failed to predict due to low confidence. This diagnostic tool presents a stable, adaptive, cost-effective, efficient, accessible, and fast solution for globalizing early detection of both common and rare diseases.