Department of Radiology and Radiological Science, Division of Cardiovascular Imaging, Medical University of South Carolina, 25 Courtenay Dr MSC 226, Charleston, SC 29425.
Institute of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany.
AJR Am J Roentgenol. 2020 May;214(5):1065-1071. doi: 10.2214/AJR.19.21572. Epub 2020 Mar 4.
The purpose of this study was to evaluate an artificial intelligence (AI)-based prototype algorithm for fully automated quantification of emphysema on chest CT compared with pulmonary function testing (spirometry). A total of 141 patients (72 women, mean age ± SD of 66.46 ± 9.7 years [range, 23-86 years]; 69 men, mean age of 66.72 ± 11.4 years [range, 27-91 years]) who underwent both chest CT acquisition and spirometry within 6 months were retrospectively included. The spirometry-based Tiffeneau index (TI; calculated as the ratio of forced expiratory volume in the first second to forced vital capacity) was used to measure emphysema severity; a value less than 0.7 was considered to indicate airway obstruction. Segmentation of the lung based on two different reconstruction methods was carried out by using a deep convolution image-to-image network. This multilayer convolutional neural network was combined with multilevel feature chaining and depth monitoring. To discriminate the output of the network from ground truth, an adversarial network was used during training. Emphysema was quantified using spatial filtering and attenuation-based thresholds. Emphysema quantification and TI were compared using the Spearman correlation coefficient. The mean TI for all patients was 0.57 ± 0.13. The mean percentages of emphysema using reconstruction methods 1 and 2 were 9.96% ± 11.87% and 8.04% ± 10.32%, respectively. AI-based emphysema quantification showed very strong correlation with TI (reconstruction method 1, ρ = -0.86; reconstruction method 2, ρ = -0.85; both < 0.0001), indicating that AI-based emphysema quantification meaningfully reflects clinical pulmonary physiology. AI-based, fully automated emphysema quantification shows good correlation with TI, potentially contributing to an image-based diagnosis and quantification of emphysema severity.
本研究旨在评估一种基于人工智能（AI）的原型算法，用于与肺功能测试（肺活量测定法）相比，对胸部 CT 上的肺气肿进行全自动量化。共纳入 141 例患者（72 例女性，平均年龄±标准差为 66.46±9.7 岁[范围 23-86 岁]；69 例男性，平均年龄为 66.72±11.4 岁[范围 27-91 岁]），这些患者在 6 个月内均同时接受了胸部 CT 采集和肺活量测定法检查。使用基于肺活量测定法的 Tiffeneau 指数（TI；计算为第一秒用力呼气量与用力肺活量的比值）来衡量肺气肿严重程度；小于 0.7 被认为表明气道阻塞。使用深度卷积图像到图像网络对基于两种不同重建方法的肺部进行分割。该多层卷积神经网络与多级特征链和深度监测相结合。在训练过程中，使用对抗网络来区分网络输出与真实值。使用空间滤波和基于衰减的阈值来量化肺气肿。使用 Spearman 相关系数比较肺气肿定量和 TI。所有患者的平均 TI 为 0.57±0.13。使用重建方法 1 和 2 的平均肺气肿百分比分别为 9.96%±11.87%和 8.04%±10.32%。基于 AI 的肺气肿定量与 TI 具有很强的相关性（重建方法 1，ρ=-0.86；重建方法 2，ρ=-0.85；均<0.0001），表明基于 AI 的肺气肿定量能够有意义地反映临床肺生理学。基于 AI 的全自动肺气肿定量与 TI 具有良好的相关性，可能有助于基于图像的肺气肿严重程度诊断和定量。
