Classification of knee osteoarthritis based on quantum-to-classical transfer learning
-
Published:2023-07-17
Issue:
Volume:11
Page:
-
ISSN:2296-424X
-
Container-title:Frontiers in Physics
-
language:
-
Short-container-title:Front. Phys.
Author:
Dong Yumin,Che Xuanxuan,Fu Yanying,Liu Hengrui,Zhang Yang,Tu Yong
Abstract
Quantum machine learning takes advantage of features such as quantum computing superposition and entanglement to enable better performance of machine learning models. In this paper, we first propose an improved hybrid quantum convolutional neural network (HQCNN) model. The HQCNN model was used to pre-train brain tumor dataset (MRI) images. Next, the quantum classical transfer learning (QCTL) approach is used to fine-tune and extract features based on pre-trained weights. A hybrid quantum convolutional network structure was used to test the osteoarthritis of the knee dataset (OAI) and to quantitatively evaluate standard metrics to verify the robustness of the classifier. The final experimental results show that the QCTL method can effectively classify knee osteoarthritis with a classification accuracy of 98.36%. The quantum-to-classical transfer learning method improves classification accuracy by 1.08%. How to use different coding techniques in HQCNN models applied to medical image analysis is also a future research direction.
Publisher
Frontiers Media SA
Subject
Physical and Theoretical Chemistry,General Physics and Astronomy,Mathematical Physics,Materials Science (miscellaneous),Biophysics
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献