Email Alert | RSS    帮助

中国防痨杂志 ›› 2022, Vol. 44 ›› Issue (1): 91-94.doi: 10.19982/j.issn.1000-6621.20210537

• 综述 • 上一篇    下一篇

深度学习在肺结核影像诊断中的应用

吴键1,2, 侯代伦1()   

  1. 1首都医科大学附属北京胸科医院影像科,北京 101149
    2陕西省结核病防治院/陕西省第五人民医院功能科,西安 710100
  • 收稿日期:2021-09-09 出版日期:2022-01-10 发布日期:2021-12-29
  • 通信作者: 侯代伦 E-mail:hou.dl@mail.ccmu.edu.cn
  • 基金资助:
    北京市医院管理中心临床医学发展专项(XMLX202146);北京市通州区高层次人才发展支持计划领军人才(YHLD2019029)

Application of deep learning in pulmonary tuberculosis imaging diagnosis

WU Jian1,2, HOU Dai-lun1()   

  1. 1Imaging Department, Beijing Chest Hospital, Capital Medical University, Beijing 101149, China
    2Department of Function, Shaanxi Provincial Tuberculosis Control Institute/The Fifth People’s Hospital of Shaanxi Province, Xi’an 710100, China
  • Received:2021-09-09 Online:2022-01-10 Published:2021-12-29
  • Contact: HOU Dai-lun E-mail:hou.dl@mail.ccmu.edu.cn
  • Supported by:
    Beijing Hospital Authority Clinical Medicine Development of Special Funding(XMLX202146);Leading Talents of Beijing Tongzhou District High-Level Talent Development of Support Program(YHLD2019029)

摘要:

肺结核的影像学形态往往呈多样性,因此,如何鉴别诊断肺结核一直以来是常规影像学研究的重点与难点。近年来,深度学习在辅助影像诊断方面有了飞快发展。深度学习擅长识别大量图像数据中的复杂模式,可大大提高医师的诊断准确性及工作效率。笔者将对深度学习在影像诊断及肺结核影像诊断中的应用、不足及展望进行综述。

关键词: 结核,肺, 放射学, 诊断, 人工智能, 综述文献(主题)

Abstract:

The imaging morphology of pulmonary tuberculosis is often diversified, therefore, how to differentiate the diagnosis of pulmonary tuberculosis has always been the focus and difficulty of conventional imaging studies.In recent years, deep learning has made rapid development in assisted image diagnosis. Deep learning is good at identifying complex patterns in a large amount of image data, which can greatly improve the diagnostic accuracy and work efficiency of doctors.This paper reviews the application, deficiency and prospect of deep learning in pulmonary tuberculosis and imaging diagnosis.

Key words: Tuberculosis,pulmonary, Radiology, Diagnosis, Artificial intelligence, Review literature as topic

中图分类号: