FQPDR: Federated Quantum Neural Network for Privacy-preserving Early Detection of Diabetic Retinopathy

2026-05-08

AI Summary

This study addresses the dual challenges of early detection of microaneurysms in diabetic retinopathy (DR) and preservation of medical data privacy by proposing a lightweight collaborative training framework that integrates federated learning with quantum neural networks. For the first time, quantum neural networks are incorporated into a federated learning paradigm for early DR detection, enabling highly efficient modeling with minimal parameters and limited samples while avoiding the sharing of raw patient data. Cross-validation on the E-ophtha, Retina MNIST, and Kaggle datasets demonstrates that the proposed model consistently outperforms both conventional non-federated and traditional federated approaches in terms of detection accuracy and robustness, thereby validating the efficacy and novelty of this lightweight federated quantum architecture in medical image analysis.

Abstract

Diabetic Retinopathy (DR) is a common complication of diabetes that can lead to blindness of people. Detecting DR at the earliest stage is essential to prevent irreversible eye damage. Microaneurysm dots are the first signs of DR. As the dots are tiny and of low contrast, detecting mild DR is a very challenging task. Federated learning (FL) preserves data privacy, which is a major concern for medical image processing. FL is a collaborative learning method, which shares only the model parameters with a server, without sharing the patient data to a central server. Inspired by classical FL, we propose a federated learning-based quantum neural network (federated QNN) for this task. We implemented the models with limited samples and few learnable parameters from the E-ophtha and Retina MNIST datasets. The crossevaluation efficiency of the proposed federated quantum neural network system for privacy-preserving early detection of diabetic retinopathy (FQPDR) in Kaggle dataset images indicates the robustness of the light weight learning models. FQPDR performances are inspiring while considering existing non-FL and FL methods.

Problem

• Diabetic Retinopathy
• Early Detection
• Privacy-preserving
• Microaneurysm
• Medical Image Analysis

Innovation

• Federated Learning
• Quantum Neural Network
• Privacy-preserving
• Diabetic Retinopathy
• Early Detection