ResGloTBNet: An interpretable deep residual network with global long-range dependency for tuberculosis screening of sputum smear microscopy images.

Journal: Medical engineering & physics
PMID:

Abstract

Tuberculosis is a high-mortality infectious disease. Manual sputum smear microscopy is a common and effective method for screening tuberculosis. However, it is time-consuming, labor-intensive, and has low sensitivity. In this study, we propose ResGloTBNet, a framework that integrates convolutional neural network and graph convolutional network for sputum smear image classification with high discriminative power. In this framework, the global reasoning unit is introduced into the residual structure of ResNet to form the ResGloRe module, which not only fully extracts the local features of the image but also models the global relationship between different regions in the image. Furthermore, we applied activation maximization and class activation mapping to generate explanations for the model's predictions on the test sets. ResGloTBNet achieved remarkable results on a publicly available dataset, reaching 97.2 % accuracy and 99.0 % sensitivity. It also maintained a high level of performance on a private dataset, attaining 98.0 % accuracy and 96.6 % sensitivity. In addition, interpretable analysis demonstrated that ResGloTBNet can effectively identify the features and regions in the input images that contribute the most to the model's predictions, providing valuable insights into the decision-making process of the deep learning model.

Authors

  • Taocui Yan
    Medical Data Science Academy, College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China.
  • Yaqian Jin
    Department of Clinical Laboratory, University-Town Hospital of Chongqing Medical University, Chongqing 401331, China.
  • Shangqing Liu
    Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, No. 1838 Guangzhou Northern Avenue, Baiyun District, Guangzhou, 510515, Guangdong, China.
  • Qiuni Li
    Medical Data Science Academy, College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China.
  • Guowei Zuo
    Key Laboratory of Diagnostic Medicine Designated by the Chinese Ministry of Education, Department of Laboratory Medicine, Chongqing Medical University, Chongqing 400016, China.
  • Ziqian Ye
    Key Laboratory of Diagnostic Medicine Designated by the Chinese Ministry of Education, Department of Laboratory Medicine, Chongqing Medical University, Chongqing 400016, China.
  • Jin Li
    Mental Health Center, West China Hospital, Sichuan University, Chengdu, China.
  • Baoru Han
    Medical Data Science Academy, College of Medical Informatics, Chongqing Medical University, Chongqing, 400016, China. baoruhan@cqmu.edu.cn.