Research Area:  Machine Learning

Abstract:

With the outstanding superposition and entanglement properties of quantum computing, quantum machine learning has attracted widespread attention in many fields, such as medical image analysis, password cracking, and pattern recognition. Although classical machine learning is widely used and has shown great potential in medical image analysis, the bottlenecks of insufficient labeled data and low processing efficiency still exist. To overcome these challenges, massive studies combined quantum computing with machine learning to explore more advanced algorithms, which have achieved distinguished improvements in parameter optimization, execution efficiency, and the reduction of error rates. Quantum machine learning provides new insights for the intersectional research of quantum technology and medical image analysis and contributes to the future development of medical image analysis. This review delivers an overview of the definition and taxonomy of quantum machine learning, as well as summarizes various quantum machine learning methods and their applications in medical image analysis over the past decade.

Keywords:  

Author(s) Name:  Lin Wei, Haowen Liu, Jing Xu, Lei Shi, Zheng Shan, Bo Zhao, and Yufei Gao

Publisher name:  ACM Digital Library

DOI:  10.1016/j.neucom.2023.01.049

Volume Information:  Volume 525, Pages 42-53, (2023)

Paper Link:   https://dl.acm.org/doi/10.1016/j.neucom.2023.01.049