Centralized contrastive loss with weakly supervised progressive feature extraction for fine-grained common thorax disease retrieval in chest x-ray.

Journal: Medical physics
Published Date:

Abstract

BACKGROUND: Medical images have already become an essential tool for the diagnosis of many diseases. Thus a large number of medical images are being generated due to the daily routine inspection. An efficient image-based disease retrieval system will not only make full use of existing data, but also help physicians to prognosis the diseases. Medical image retrieval is represented by the classification and localization of common thorax diseases in x-ray images. Although extensive efforts have been put into this field, there are still many challenges.

Authors

  • Fang Chen
  • Lei You
  • Weiling Zhao
    Center for Systems Medicine, School of Biomedical Bioinformatics, University of Texas Health Science Center at Houston, TX 77030, USA.
  • Xiaobo Zhou
    Department of Diagnostic Radiology, Wake Forest Medical School, Winston-Salem, NC 27103, USA. Electronic address: xizhou@wakehealth.edu.