深度学习用于精确诊断和分型选耐药结核病的胸部计算机断层扫描
Shufan Liang1, Xiuyuan Xu2, Zhe Yang2
1Department of Pulmonary and Critical Care Medicine State Key Laboratory of Respiratory Health and Multimorbidity, Targeted Tracer Research and Development Laboratory, Med-X Center for Manufacturing, Frontiers Science Center for Disease-related Molecular Network, West China Hospital, West China School of Medicine, Sichuan University Chengdu China.
一个深度学习系统,DeepTB,有效地从胸部CT扫描中识别耐药结核病 (DR-TB). 这种自动诊断有助于临床医生区分DR-TB及其亚型,改善患者的护理.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 放射学 放射学是一门学科.
背景情况:
- 使用胸部CT扫描,区分耐药结核病 (DR-TB) 和药物敏感结核病 (DS-TB) 面临临临床挑战.
- 在CT扫描中胸部异常的形态差异具有差异诊断的潜力.
研究的目的:
- 开发和评估基于深度学习 (DeepTB) 的系统,用于从胸部CT图像中自动识别和分类DR-TB亚型.
- 协助放射科医生解释胸部CT扫描和做出明智的临床决策.
主要方法:
- 使用了1176个来自结核病 (TB) 患者的胸部CT卷.
- 开发了一种深度学习模型,用于结核病耐药性识别和亚型分类.
- 手动注释胸部病变,以提高模型的稳定性和可解释性.
- 采用Circos可视化来探索胸部异常与DR-TB类型之间的关系.
主要成果:
- 深度结核病实现了0.930的曲线下的区域 (AUC) 对于胸部异常检测和0.943的DR-TB诊断.
- 该系统在DR-TB亚型分类中表现出强的性能,AUC从0.880到0.928.9不等.
- 类激活地图被生成为模型的预测提供视觉解释.
结论:
- DeepTB系统显示了对DR-TB及其亚型的准确和自动诊断的巨大潜力.
- 该模型能够协助图像解释并提供视觉解释,这在DR-TB管理的临床决策中是非常有价值的.
更多相关视频
07:53Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
10:04Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates
Published on: September 5, 2017
相关概念视频
Pulmonary Tuberculosis IV
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
Pulmonary Tuberculosis V
Latent tuberculosis infection occurs when TB bacteria are present in a person's body, but are not causing illness or symptoms. It is not contagious, and preventive treatment is crucial to avoid the...
Computed Tomography
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
Pulmonary Tuberculosis III
The first classification is based on the development of the disease, and it includes the following categories:
