Deep Learning-Based Medical Ultrasound Image and Video Segmentation Methods: Overview, Frontiers, and Challenges.

Journal: Sensors (Basel, Switzerland)
PMID:

Abstract

The intricate imaging structures, artifacts, and noise present in ultrasound images and videos pose significant challenges for accurate segmentation. Deep learning has recently emerged as a prominent field, playing a crucial role in medical image processing. This paper reviews ultrasound image and video segmentation methods based on deep learning techniques, summarizing the latest developments in this field, such as diffusion and segment anything models as well as classical methods. These methods are classified into four main categories based on the characteristics of the segmentation methods. Each category is outlined and evaluated in the corresponding section. We provide a comprehensive overview of deep learning-based ultrasound image segmentation methods, evaluation metrics, and common ultrasound datasets, hoping to explain the advantages and disadvantages of each method, summarize its achievements, and discuss challenges and future trends.

Authors

  • Xiaolong Xiao
    College of Mathematical Medicine, Zhejiang Normal University, Jinhua 321004, China.
  • Jianfeng Zhang
    Department of Vascular Surgery, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi 530021, P.R. China.
  • Yuan Shao
    Department of Urology, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Jialong Liu
    College of Mechanical Engineering, Yangzhou University, No. 196 West Huayang Road, Yangzhou, China.
  • Kaibing Shi
    College of Mathematical Medicine, Zhejiang Normal University, Jinhua 321004, China.
  • Chunlei He
    College of Mathematical Medicine, Zhejiang Normal University, Jinhua 321004, China.
  • Dexing Kong
    School of Mathematical Sciences, Zhejiang University, Hangzhou 310027, China. Electronic address: dkong@zju.edu.cn.