AutoLNMNet: Automated Network for Estimating Lymph-Node Metastasis in EGC Using a Pyramid Vision Transformer and Data Derived From Multiphoton Microscopy.

Journal: Microscopy research and technique
PMID:

Abstract

Lymph-node status is important in decision-making during early gastric cancer (EGC) treatment. Currently, endoscopic submucosal dissection is the mainstream treatment for EGC. However, it is challenging for even experienced endoscopists to accurately diagnose and treat EGC. Multiphoton microscopy can extract the morphological features of collagen fibers from tissues. The characteristics of collagen fibers can be used to assess the lymph-node metastasis status in patients with EGC. First, we compared the accuracy of four deep learning models (VGG16, ResNet34, MobileNetV2, and PVTv2) in training preprocessed images and test datasets. Next, we integrated the features of the best-performing model, which was PVTv2, with manual and clinical features to develop a novel model called AutoLNMNet. The prediction accuracy of AutoLNMNet for the no metastasis (Ly0) and metastasis in lymph nodes (Ly1) stages reached 0.92, which was 0.3% higher than that of PVTv2. The receiver operating characteristics of AutoLNMNet in quantifying Ly0 and Ly1 stages were 0.97 and 0.97, respectively. Therefore, AutoLNMNet is highly reliable and accurate in detecting lymph-node metastasis, providing an important tool for the early diagnosis and treatment of EGC.

Authors

  • Lin Gao
  • Wenju Liu
    National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China. Electronic address: lwj@nlpr.ia.ac.cn.
  • Bingzi Kang
    School of Science, Jimei University, Xiamen, China.
  • Han Wu
    Department of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.
  • Jiajia He
    School of Science, Jimei University, Xiamen, China.
  • Xiaolu Li
    Department of Rehabilitation Medicine, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, China.
  • Gangqin Xi
    School of Science, Jimei University, Xiamen, China.
  • Shuangmu Zhuo
    Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education and Fujian Provincial Key Laboratory of Photonics Technology, Fujian Normal University, Fuzhou, P.R. China.