The diagnostic model from semi-supervised cross modality transformation improved the distinguished ability of X-rays for pulmonary tuberculosis.

Journal: Clinical radiology
Published Date: Jun 27, 2025

Abstract

BACKGROUND: Early diagnosis of tuberculosis is particularly difficult in resource-poor areas. Traditional chest X-rays (CXR) have limited accuracy, while CT scans are costly and involve radiation exposure. The study aims to improve the diagnostic accuracy of routine X-rays for pulmonary tuberculosis to approximate the performance of CT scans through building Artificial Intelligence (AI) model, suitable for primary healthcare settings lacking CT facilities.

Authors

  • J Zhou
    Department of Epidemiology and Health Statistics,Guangdong Pharmaceutical University,Guangzhou,China.
  • H Ke
    Department of Tuberculosis, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai Clinic and Research Center of Tuberculosis, Shanghai Key Laboratory of Tuberculosis, Shanghai, China. Electronic address: kdx5566@sina.com.
  • C Yang
  • S-J Zhang
    Department of Tuberculosis, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai Clinic and Research Center of Tuberculosis, Shanghai Key Laboratory of Tuberculosis, Shanghai, China. Electronic address: zhangshaoj1979@sina.com.
  • W-W Sun
    Department of Tuberculosis, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai Clinic and Research Center of Tuberculosis, Shanghai Key Laboratory of Tuberculosis, Shanghai, China. Electronic address: sunwenwen_1583@163.com.
  • L Chen
    College of Computing, Georgia Institute of Technology, Atlanta, GA, USA.
  • Z-M Zhang
    Department of Tuberculosis, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai Clinic and Research Center of Tuberculosis, Shanghai Key Laboratory of Tuberculosis, Shanghai, China. Electronic address: zhemindoc@163.com.
  • L Fan
    Department of Radiology, Second Affiliated Hospital of Naval Medical University, Shanghai, China. Electronic address: fanli0930@163.com.

Keywords

External Resources

Popular Topics
Recent Journals