Department of Medical Imaging Center, Nanfang Hospital, Southern Medical University, No. 1838 Guangzhou Avenue North, Guangzhou, 510515, Guangdong, China.
The D-Lab, Department of Precision Medicine, GROW-School for Oncology and Developmental Biology, Maastricht University, 6229ER, Maastricht, The Netherlands.
Eur Radiol. 2022 Apr;32(4):2188-2199. doi: 10.1007/s00330-021-08365-z. Epub 2021 Nov 29.
An accurate and rapid diagnosis is crucial for the appropriate treatment of pulmonary tuberculosis (TB). This study aims to develop an artificial intelligence (AI)-based fully automated CT image analysis system for detection, diagnosis, and burden quantification of pulmonary TB.
From December 2007 to September 2020, 892 chest CT scans from pathogen-confirmed TB patients were retrospectively included. A deep learning-based cascading framework was connected to create a processing pipeline. For training and validation of the model, 1921 lesions were manually labeled, classified according to six categories of critical imaging features, and visually scored regarding lesion involvement as the ground truth. A "TB score" was calculated based on a network-activation map to quantitively assess the disease burden. Independent testing datasets from two additional hospitals (dataset 2, n = 99; dataset 3, n = 86) and the NIH TB Portals (n = 171) were used to externally validate the performance of the AI model.
CT scans of 526 participants (mean age, 48.5 ± 16.5 years; 206 women) were analyzed. The lung lesion detection subsystem yielded a mean average precision of the validation cohort of 0.68. The overall classification accuracy of six pulmonary critical imaging findings indicative of TB of the independent datasets was 81.08-91.05%. A moderate to strong correlation was demonstrated between the AI model-quantified TB score and the radiologist-estimated CT score.
The proposed end-to-end AI system based on chest CT can achieve human-level diagnostic performance for early detection and optimal clinical management of patients with pulmonary TB.
• Deep learning allows automatic detection, diagnosis, and evaluation of pulmonary tuberculosis. • Artificial intelligence helps clinicians to assess patients with tuberculosis. • Pulmonary tuberculosis disease activity and treatment management can be improved.
准确、快速的诊断对于肺结核（TB）的恰当治疗至关重要。本研究旨在开发一种基于人工智能（AI）的全自动 CT 图像分析系统，用于检测、诊断和量化肺结核的负担。
回顾性纳入 2007 年 12 月至 2020 年 9 月期间经病原体确诊的肺结核患者 892 例胸部 CT 扫描。连接基于深度学习的级联框架，创建处理流水线。为了对模型进行训练和验证，手动标记了 1921 个病灶，根据六个关键影像学特征类别进行分类，并根据病变受累情况进行视觉评分作为金标准。根据网络激活图计算“TB 评分”，以定量评估疾病负担。使用来自另外两家医院的独立测试数据集（数据集 2，n=99；数据集 3，n=86）和 NIH TB 门户（n=171）对 AI 模型的性能进行外部验证。
分析了 526 名参与者（平均年龄 48.5±16.5 岁；206 名女性）的 CT 扫描。肺部病变检测子系统在验证队列中的平均平均精度为 0.68。独立数据集六种提示肺结核的肺部关键影像学表现的整体分类准确性为 81.08-91.05%。AI 模型量化的 TB 评分与放射科医生估计的 CT 评分之间表现出中度至强相关性。
基于胸部 CT 的端到端 AI 系统可以实现对肺结核患者的早期检测和最佳临床管理的人类水平的诊断性能。
•深度学习允许自动检测、诊断和评估肺结核。•人工智能有助于临床医生评估结核病患者。•可以改善肺结核的疾病活动和治疗管理。
Zotero 插件
