Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Diabetic Retinopathy Detection Using Quantum Transfer Learning

Ankush Jain, Rinav Gupta, Jai Singhal

TL;DR

This work tackles diabetic retinopathy (DR) detection and staging by marrying classical transfer learning with quantum machine learning. It proposes a classical feature extractor (A') based on pretrained CNNs to produce 512 features, which are classified by a four-qubit dressed quantum circuit (B) in a hybrid quantum-classical framework, evaluated on the Kaggle APTOS 2019 DR dataset and other retinal datasets. The results show substantial improvements over purely classical baselines, with accuracies approaching 98% for several ResNet backbones when integrated with the quantum classifier, and detailed analyses across various gate configurations. The study demonstrates the potential of quantum transfer learning to enhance medical imaging diagnoses, offering a path toward faster, more accurate DR screening and staging in clinical settings.

Abstract

Diabetic Retinopathy (DR), a prevalent complication in diabetes patients, can lead to vision impairment due to lesions formed on the retina. Detecting DR at an advanced stage often results in irreversible blindness. The traditional process of diagnosing DR through retina fundus images by ophthalmologists is not only time-intensive but also expensive. While classical transfer learning models have been widely adopted for computer-aided detection of DR, their high maintenance costs can hinder their detection efficiency. In contrast, Quantum Transfer Learning offers a more effective solution to this challenge. This approach is notably advantageous because it operates on heuristic principles, making it highly optimized for the task. Our proposed methodology leverages this hybrid quantum transfer learning technique to detect DR. To construct our model, we utilize the APTOS 2019 Blindness Detection dataset, available on Kaggle. We employ the ResNet-18, ResNet34, ResNet50, ResNet101, ResNet152 and Inception V3, pre-trained classical neural networks, for the initial feature extraction. For the classification stage, we use a Variational Quantum Classifier. Our hybrid quantum model has shown remarkable results, achieving an accuracy of 97% for ResNet-18. This demonstrates that quantum computing, when integrated with quantum machine learning, can perform tasks with a level of power and efficiency unattainable by classical computers alone. By harnessing these advanced technologies, we can significantly improve the detection and diagnosis of Diabetic Retinopathy, potentially saving many from the risk of blindness. Keywords: Diabetic Retinopathy, Quantum Transfer Learning, Deep Learning

Diabetic Retinopathy Detection Using Quantum Transfer Learning

TL;DR

This work tackles diabetic retinopathy (DR) detection and staging by marrying classical transfer learning with quantum machine learning. It proposes a classical feature extractor (A') based on pretrained CNNs to produce 512 features, which are classified by a four-qubit dressed quantum circuit (B) in a hybrid quantum-classical framework, evaluated on the Kaggle APTOS 2019 DR dataset and other retinal datasets. The results show substantial improvements over purely classical baselines, with accuracies approaching 98% for several ResNet backbones when integrated with the quantum classifier, and detailed analyses across various gate configurations. The study demonstrates the potential of quantum transfer learning to enhance medical imaging diagnoses, offering a path toward faster, more accurate DR screening and staging in clinical settings.

Abstract

Diabetic Retinopathy (DR), a prevalent complication in diabetes patients, can lead to vision impairment due to lesions formed on the retina. Detecting DR at an advanced stage often results in irreversible blindness. The traditional process of diagnosing DR through retina fundus images by ophthalmologists is not only time-intensive but also expensive. While classical transfer learning models have been widely adopted for computer-aided detection of DR, their high maintenance costs can hinder their detection efficiency. In contrast, Quantum Transfer Learning offers a more effective solution to this challenge. This approach is notably advantageous because it operates on heuristic principles, making it highly optimized for the task. Our proposed methodology leverages this hybrid quantum transfer learning technique to detect DR. To construct our model, we utilize the APTOS 2019 Blindness Detection dataset, available on Kaggle. We employ the ResNet-18, ResNet34, ResNet50, ResNet101, ResNet152 and Inception V3, pre-trained classical neural networks, for the initial feature extraction. For the classification stage, we use a Variational Quantum Classifier. Our hybrid quantum model has shown remarkable results, achieving an accuracy of 97% for ResNet-18. This demonstrates that quantum computing, when integrated with quantum machine learning, can perform tasks with a level of power and efficiency unattainable by classical computers alone. By harnessing these advanced technologies, we can significantly improve the detection and diagnosis of Diabetic Retinopathy, potentially saving many from the risk of blindness. Keywords: Diabetic Retinopathy, Quantum Transfer Learning, Deep Learning
Paper Structure (30 sections, 16 equations, 13 figures, 5 tables)

This paper contains 30 sections, 16 equations, 13 figures, 5 tables.

Table of Contents

  1. INTRODUCTION
  2. LITERATURE REVIEW
  3. PROPOSED METHODOLOGY
  4. Quantum Computing vs. Classical Computing
  5. Quantum Transfer Learning
  6. Classical Model Foundation
  7. Quantum Circuit Integration
  8. Classical Pre-Processing
  9. Quantum Circuit for Classification
  10. Hybrid Model Structure
  11. Dual Network Integration
  12. Training & Optimization
  13. Classical - to - Quantum Transfer Learning
  14. Application to DR Detection
  15. Algorithm Steps
  16. ...and 15 more sections

Figures (13)

  • Figure 1: Normal Eye Retina
  • Figure 2: Infected Eye Retina
  • Figure 3: Architecture of Transfer Learning Model.
  • Figure 4: Variational Quantum Classifier with embedding layers $U(x)$ and variational circuit $V(\theta)$ and final measurements in classical output $f(x) \in \mathbb{C}$.
  • Figure 5: Simple case of one Qubit
  • ...and 8 more figures