Interactively Fusing Global and Local Features for Benign and Malignant Classification of Breast Ultrasound Images.

Journal: Ultrasound in medicine & biology
Published Date: Dec 20, 2024

Abstract

OBJECTIVE: Breast ultrasound (BUS) is used to classify benign and malignant breast tumors, and its automatic classification can reduce subjectivity. However, current convolutional neural networks (CNNs) face challenges in capturing global features, while vision transformer (ViT) networks have limitations in effectively extracting local features. Therefore, this study aimed to develop a deep learning method that enables the interaction and updating of intermediate features between CNN and ViT to achieve high-accuracy BUS image classification.

Authors

  • Wenhan Wang
    School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China.
  • Jiale Zhou
    School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China.
  • Jin Zhao
    Institute of Urban Agriculture, Chinese Academy of Agricultural Sciences, 36 Lazi East Road, Tianfu New Area, Chengdu, 610000, China.
  • Xun Lin
    School of Computer Science and Engineering, Beihang University, Beijing, China.
  • Yan Zhang
    Affiliated Hospital of Liaoning University of Traditional Chinese Medicine, Shenyang, 110032, China.
  • Shan Lu
    The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
  • Wanchen Zhao
    School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China.
  • Shuai Wang
    Department of Intensive Care Unit, China-Japan Union Hospital of Jilin University, Changchun, China.
  • Wenzhong Tang
    School of Computer Science and Engineering, Beihang University, Beijing, China.
  • Xiaolei Qu

Keywords

External Resources

Popular Topics
Recent Journals