Hierarchical medical image report adversarial generation with hybrid discriminator.

Journal: Artificial intelligence in medicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVES: Generating coherent reports from medical images is an important task for reducing doctors' workload. Unlike traditional image captioning tasks, the task of medical image report generation faces more challenges. Current models for generating reports from medical images often fail to characterize some abnormal findings, and some models generate reports with low quality. In this study, we propose a model to generate high-quality reports from medical images.

Authors

  • Junsan Zhang
  • Ming Cheng
  • Qiaoqiao Cheng
    Qingdao Huanghai University, Qingdao, China.
  • Xiuxuan Shen
  • Yao Wan
    Huazhong University of Science and Technology, Wuhan City, China. Electronic address: wanyao@hust.edu.cn.
  • Jie Zhu
    Department of Digestive Diseases, Huashan Hospital, Fudan University, Shanghai 200040, P.R. China.
  • Mengxuan Liu
    National Institute of Occupational Health and Poison Control, Chinese Center for Disease Control and Prevention, No. 29 Nanwei Road, Xicheng District, Beijing 100050, China. liumengxuan@niohp.chinacdc.cn.