Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Lightweight Quantum-Enhanced ResNet for Coronary Angiography Classification: A Hybrid Quantum-Classical Feature Enhancement Framework

Jingsong Xia

TL;DR

We address the challenge of operator-dependent interpretation in coronary angiography and the limits of purely classical feature mappings by proposing a lightweight hybrid quantum–classical framework (LQER) that inserts a small 4-qubit PQC into the high-level feature space of a ResNet backbone. A linear projection reduces a rich ResNet feature to a compact representation, which is then processed by a shallow quantum circuit and fused back with classical features for final prediction. Empirical results on LRSE-Net datasets show that LQER achieves accuracy of 0.950 and AUC of 0.987, substantially outperforming purely quantum or classical baselines, while maintaining a CPU-friendly, end-to-end training regime. This work demonstrates a practical pathway for deploying quantum feature enhancement in medical imaging, offering potential for real-time intraoperative support and deployment in resource-constrained clinical environments.

Abstract

Background: Coronary angiography (CAG) is the cornerstone imaging modality for evaluating coronary artery stenosis and guiding interventional decision-making. However, interpretation based on single-frame angiographic images remains highly operator-dependent, and conventional deep learning models still face challenges in modeling complex vascular morphology and fine-grained texture patterns.Methods: We propose a Lightweight Quantum-Enhanced ResNet (LQER) for binary classification of coronary angiography images. A pretrained ResNet18 is employed as a classical feature extractor, while a parameterized quantum circuit (PQC) is introduced at the high-level semantic feature space for quantum feature enhancement. The quantum module utilizes data re-uploading and entanglement structures, followed by residual fusion with classical features, enabling end-to-end hybrid optimization with a strictly controlled number of qubits.Results: On an independent test set, the proposed LQER outperformed the classical ResNet18 baseline in accuracy, AUC, and F1-score, achieving a test accuracy exceeding 90%. The results demonstrate that lightweight quantum feature enhancement improves discrimination of positive lesions, particularly under class-imbalanced conditions.Conclusion: This study validates a practical hybrid quantum--classical learning paradigm for coronary angiography analysis, providing a feasible pathway for deploying quantum machine learning in medical imaging applications.

Lightweight Quantum-Enhanced ResNet for Coronary Angiography Classification: A Hybrid Quantum-Classical Feature Enhancement Framework

TL;DR

We address the challenge of operator-dependent interpretation in coronary angiography and the limits of purely classical feature mappings by proposing a lightweight hybrid quantum–classical framework (LQER) that inserts a small 4-qubit PQC into the high-level feature space of a ResNet backbone. A linear projection reduces a rich ResNet feature to a compact representation, which is then processed by a shallow quantum circuit and fused back with classical features for final prediction. Empirical results on LRSE-Net datasets show that LQER achieves accuracy of 0.950 and AUC of 0.987, substantially outperforming purely quantum or classical baselines, while maintaining a CPU-friendly, end-to-end training regime. This work demonstrates a practical pathway for deploying quantum feature enhancement in medical imaging, offering potential for real-time intraoperative support and deployment in resource-constrained clinical environments.

Abstract

Background: Coronary angiography (CAG) is the cornerstone imaging modality for evaluating coronary artery stenosis and guiding interventional decision-making. However, interpretation based on single-frame angiographic images remains highly operator-dependent, and conventional deep learning models still face challenges in modeling complex vascular morphology and fine-grained texture patterns.Methods: We propose a Lightweight Quantum-Enhanced ResNet (LQER) for binary classification of coronary angiography images. A pretrained ResNet18 is employed as a classical feature extractor, while a parameterized quantum circuit (PQC) is introduced at the high-level semantic feature space for quantum feature enhancement. The quantum module utilizes data re-uploading and entanglement structures, followed by residual fusion with classical features, enabling end-to-end hybrid optimization with a strictly controlled number of qubits.Results: On an independent test set, the proposed LQER outperformed the classical ResNet18 baseline in accuracy, AUC, and F1-score, achieving a test accuracy exceeding 90%. The results demonstrate that lightweight quantum feature enhancement improves discrimination of positive lesions, particularly under class-imbalanced conditions.Conclusion: This study validates a practical hybrid quantum--classical learning paradigm for coronary angiography analysis, providing a feasible pathway for deploying quantum machine learning in medical imaging applications.
Paper Structure (16 sections, 6 equations, 4 figures)

This paper contains 16 sections, 6 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Methods
  3. Overall Architecture
  4. Lightweight Quantum Feature Encoding
  5. Quantum Feature Enhancement Module
  6. Quantum-to-Classical Feature Projection and Classification
  7. Lightweight Design and Optimization Strategy
  8. Dataset and Preprocessing
  9. Implementation Details
  10. Results
  11. Overall Performance Comparison with Baseline Models
  12. Training Dynamics and Clinical Performance Evolution
  13. Comprehensive Training Analysis
  14. Independent Test Set Evaluation
  15. Discussion
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Performance comparison between LQER and baseline models.
  • Figure 2: Clinical performance metrics and training dynamics of the LQER model.
  • Figure 3: Comprehensive training analysis of the LQER model.
  • Figure 4: Test set evaluation results of the LQER model.