Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Parallel Multi-Circuit Quantum Feature Fusion in Hybrid Quantum-Classical Convolutional Neural Networks for Breast Tumor Classification

Ece Yurtseven

TL;DR

This work tackles breast tumor classification by integrating two parallel variational quantum circuits encoding features via amplitude and angle schemes, fused with a classical CNN backbone. The proposed hybrid QCNN, tested on BreastMNIST, shows statistically significant improvements over a parameter-matched classical CNN (p=0.03125, d=2.14), with final testing accuracy around 86.5% versus 84.2%. The study provides a rigorous statistical validation framework and demonstrates the potential of quantum feature fusion to enhance medical image classification while outlining roadmap toward scaling and real hardware validation. Overall, the results support the viability of hybrid quantum-classical architectures for biomedical tasks and offer a structured approach for fair comparisons and future hardware-oriented research.

Abstract

Quantum machine learning has emerged as a promising approach to improve feature extraction and classification tasks in high-dimensional data domains such as medical imaging. In this work, we present a hybrid Quantum-Classical Convolutional Neural Network (QCNN) architecture designed for the binary classification of the BreastMNIST dataset, a standardized benchmark for distinguishing between benign and malignant breast tumors. Our architecture integrates classical convolutional feature extraction with two distinct quantum circuits: an amplitude-encoding variational quantum circuit (VQC) and an angle-encoding VQC circuit with circular entanglement, both implemented on four qubits. These circuits generate quantum feature embeddings that are fused with classical features to form a joint feature space, which is subsequently processed by a fully connected classifier. To ensure fairness, the hybrid QCNN is parameter-matched against a baseline classical CNN, allowing us to isolate the contribution of quantum layers. Both models are trained under identical conditions using the Adam optimizer and binary cross-entropy loss. Experimental evaluation in five independent runs demonstrates that the hybrid QCNN achieves statistically significant improvements in classification accuracy compared to the classical CNN, as validated by a one-sided Wilcoxon signed rank test (p = 0.03125) and supported by large effect size of Cohen's d = 2.14. Our results indicate that hybrid QCNN architectures can leverage entanglement and quantum feature fusion to enhance medical image classification tasks. This work establishes a statistical validation framework for assessing hybrid quantum models in biomedical applications and highlights pathways for scaling to larger datasets and deployment on near-term quantum hardware.

Parallel Multi-Circuit Quantum Feature Fusion in Hybrid Quantum-Classical Convolutional Neural Networks for Breast Tumor Classification

TL;DR

This work tackles breast tumor classification by integrating two parallel variational quantum circuits encoding features via amplitude and angle schemes, fused with a classical CNN backbone. The proposed hybrid QCNN, tested on BreastMNIST, shows statistically significant improvements over a parameter-matched classical CNN (p=0.03125, d=2.14), with final testing accuracy around 86.5% versus 84.2%. The study provides a rigorous statistical validation framework and demonstrates the potential of quantum feature fusion to enhance medical image classification while outlining roadmap toward scaling and real hardware validation. Overall, the results support the viability of hybrid quantum-classical architectures for biomedical tasks and offer a structured approach for fair comparisons and future hardware-oriented research.

Abstract

Quantum machine learning has emerged as a promising approach to improve feature extraction and classification tasks in high-dimensional data domains such as medical imaging. In this work, we present a hybrid Quantum-Classical Convolutional Neural Network (QCNN) architecture designed for the binary classification of the BreastMNIST dataset, a standardized benchmark for distinguishing between benign and malignant breast tumors. Our architecture integrates classical convolutional feature extraction with two distinct quantum circuits: an amplitude-encoding variational quantum circuit (VQC) and an angle-encoding VQC circuit with circular entanglement, both implemented on four qubits. These circuits generate quantum feature embeddings that are fused with classical features to form a joint feature space, which is subsequently processed by a fully connected classifier. To ensure fairness, the hybrid QCNN is parameter-matched against a baseline classical CNN, allowing us to isolate the contribution of quantum layers. Both models are trained under identical conditions using the Adam optimizer and binary cross-entropy loss. Experimental evaluation in five independent runs demonstrates that the hybrid QCNN achieves statistically significant improvements in classification accuracy compared to the classical CNN, as validated by a one-sided Wilcoxon signed rank test (p = 0.03125) and supported by large effect size of Cohen's d = 2.14. Our results indicate that hybrid QCNN architectures can leverage entanglement and quantum feature fusion to enhance medical image classification tasks. This work establishes a statistical validation framework for assessing hybrid quantum models in biomedical applications and highlights pathways for scaling to larger datasets and deployment on near-term quantum hardware.

Paper Structure

This paper contains 21 sections, 12 equations, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methods
  4. Dataset & Preprocessing
  5. Variational Quantum Circuit Architectures
  6. Classical Backbone (CNN Feature Extractor)
  7. Quantum Circuit 1: Amplitude Encoding
  8. Quantum Circuit 2: Angle Encoding with Circular Entanglement
  9. Quantum Feature Fusion & Classifier
  10. Training Protocol
  11. Results
  12. Performance Metrics
  13. Training and Validation
  14. Analysis of Metrics for Classical Model
  15. Analysis of Metrics for Hybrid Quantum Model
  16. ...and 6 more sections

Figures (8)

  • Figure 1: Representative training samples from the BreastMNIST dataset. Left: benign breast tissue. Right: malignant breast tissue.
  • Figure 2: Our proposed hybrid quantum-classical convolutional neural network architecture for breast cancer classification. Classical CNN features are processed through two parallel quantum pathways with different encoding schemes.
  • Figure 3: Amplitude embedding variational quantum circuit
  • Figure 4: Angle encoding variational quantum circuit with circular entanglement
  • Figure 5: Testing accuracy graph including both models
  • ...and 3 more figures