Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An ensemble framework approach of hybrid Quantum convolutional neural networks for classification of breast cancer images

Dibyasree Guha, Shyamali Mitra, Somenath Kuiry, Nibaran Das

TL;DR

This paper carries out a study of three hybrid classical-quantum neural network architectures and combine them using standard ensembling techniques on a breast cancer histopathological dataset and obtains an improvement over the individual hybrid network as well as classical neural network counterparts of the hybrid network models.

Abstract

Quantum neural networks are deemed suitable to replace classical neural networks in their ability to learn and scale up network models using quantum-exclusive phenomena like superposition and entanglement. However, in the noisy intermediate scale quantum (NISQ) era, the trainability and expressibility of quantum models are yet under investigation. Medical image classification on the other hand, pertains well to applications in deep learning, particularly, convolutional neural networks. In this paper, we carry out a study of three hybrid classical-quantum neural network architectures and combine them using standard ensembling techniques on a breast cancer histopathological dataset. The best accuracy percentage obtained by an individual model is 85.59. Whereas, on performing ensemble, we have obtained accuracy as high as 86.72%, an improvement over the individual hybrid network as well as classical neural network counterparts of the hybrid network models.

An ensemble framework approach of hybrid Quantum convolutional neural networks for classification of breast cancer images

TL;DR

This paper carries out a study of three hybrid classical-quantum neural network architectures and combine them using standard ensembling techniques on a breast cancer histopathological dataset and obtains an improvement over the individual hybrid network as well as classical neural network counterparts of the hybrid network models.

Abstract

Quantum neural networks are deemed suitable to replace classical neural networks in their ability to learn and scale up network models using quantum-exclusive phenomena like superposition and entanglement. However, in the noisy intermediate scale quantum (NISQ) era, the trainability and expressibility of quantum models are yet under investigation. Medical image classification on the other hand, pertains well to applications in deep learning, particularly, convolutional neural networks. In this paper, we carry out a study of three hybrid classical-quantum neural network architectures and combine them using standard ensembling techniques on a breast cancer histopathological dataset. The best accuracy percentage obtained by an individual model is 85.59. Whereas, on performing ensemble, we have obtained accuracy as high as 86.72%, an improvement over the individual hybrid network as well as classical neural network counterparts of the hybrid network models.
Paper Structure (16 sections, 5 figures, 1 table)

This paper contains 16 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Previous Work
  3. Hybrid Neural Network Architecture
  4. Model 1(M1)
  5. Model 2(M2)
  6. Model 3(M3)
  7. Quantum Circuit
  8. Experiments
  9. Dataset Description
  10. Experimental Setup
  11. Ensemble
  12. Results
  13. Performance of individual models
  14. Performance of Ensemble Techniques
  15. Conclusion
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Hybrid Classical-Quantum Neural Network
  • Figure 2: Quantum Circuit used for Training the classifier
  • Figure 3: Images from BreakHis Dataset (a) Benign (b) Malignant
  • Figure 4: Training and Validation Loss curves of each individual model - (a) Model 1 (b) Model 2 (c) Model 3
  • Figure 5: Confusion matrix of (a) Model 1 (b) Model 2 (c) Model 3 (d) Average Probability between model 2 and 3