Edge-Enhanced Knowledge Distillation System for Diabetic Retinopathy Lesions Computer-Aided Diagnosis
Journal
Machine Learning Methods in Biomedical Field : Computer-Aided Diagnostics, Healthcare and Biology Applications
ISSN
1860-949X
1860-9503
Publisher
Springer Nature Switzerland
Date Issued
2025
Author(s)
Lopez-Figueroa, Alberto
Jacome-Herrera, Sebastian
Renza, Diego
Type
text::book::book part
Abstract
This work addresses the challenge of deploying computationally intensive Deep Learning (DL) models for Diabetic Retinopathy (DR) lesion detection in clinical settings, particularly on resource-constrained edge devices. DR is a significant global health issue and a leading cause of preventable blindness, making early and accessible detection crucial. We propose a proof-of-concept system utilizing Knowledge Distillation (KD) to create a tiny, efficient DL model for DR lesion detection, specifically designed for embedding into retinal scanners via the NVIDIA Jetson Nano platform. Our novel approach employs a KD framework where a pre-trained Inception-v3 model acts as the ‘teacher,’ fine-tuned on fundus image data. This teacher model distills its knowledge into a compact ‘student’ model based on the MobileNet-v2 architecture, which is trained on a small, synthetically generated dataset optimized through an iterative distillation process using a custom loss function combining Kullback-Leibler divergence and Categorical Cross-Entropy. This method significantly reduces model size and computational requirements while maintaining high diagnostic accuracy, comparable to larger, state-of-the-art models. By enabling real-time, on-device analysis, this embedded AI solution enhances data privacy, ensures consistent performance, and improves the accessibility of advanced DR screening, particularly in remote or underserved healthcare environments. This makes AI-assisted DR detection feasible for widespread clinical adoption directly within scanning devices. ©The authors ©Springer.
License
Acceso Restringido
How to cite
Lopez-Figueroa, A., Jacome-Herrera, S., Moya-Albor, E., Renza, D., Brieva, J. (2026). Edge-Enhanced Knowledge Distillation System for Diabetic Retinopathy Lesions Computer-Aided Diagnosis. In: Moya-Albor, E., Ponce, H., Brieva, J., Gomez-Coronel, S.L., Torres, D.R. (eds) Machine Learning Methods in Biomedical Field. Studies in Computational Intelligence, vol 1218. Springer, Cham. https://doi.org/10.1007/978-3-031-96328-5_1