Chassagnon Guillaume, Vakalopoulou Maria, Régent Alexis, Zacharaki Evangelia I, Aviram Galit, Martin Charlotte, Marini Rafael, Bus Norbert, Jerjir Naïm, Mekinian Arsène, Hua-Huy Thông, Monnier-Cholley Laurence, Benmostefa Nouria, Mouthon Luc, Dinh-Xuan Anh-Tuan, Paragios Nikos, Revel Marie-Pierre
Departments of Radiology (G.C., N.J., M.P.R.) and Physiology (T.H.H., A.T.D.X.), Hôpital Cochin, and Reference Center for Rare Systemic Autoimmune Diseases of Ile de France, Hôpital Cochin (A.R., N. Benmostefa, L.M.), Assistance Publique-Hôpitaux de Paris, Université de Paris, 27 Rue du Faubourg Saint-Jacques, 75014 Paris, France; Center for Visual Computing, Ecole CentraleSupelec, Gif-sur-Yvette, France (G.C., M.V., E.I.Z., C.M., N.P.); Department of Radiology, Tel Aviv Sourasky Medical Center, Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel (G.A.); TheraPanacea, Paris, France (R.M., N. Bus, N.P.); and Departments of Internal Medicine and Inflammatory Disorders (A.M.) and Radiology (L.M.C.), Hôpital Saint-Antoine, Assistance Publique-Hôpitaux de Paris, Sorbonne Université, Paris, France.
Radiol Artif Intell. 2020 Jul 15;2(4):e190006. doi: 10.1148/ryai.2020190006. eCollection 2020 Jul.
To develop a deep learning algorithm for the automatic assessment of the extent of systemic sclerosis (SSc)-related interstitial lung disease (ILD) on chest CT images.
This retrospective study included 208 patients with SSc (median age, 57 years; 167 women) evaluated between January 2009 and October 2017. A multicomponent deep neural network (AtlasNet) was trained on 6888 fully annotated CT images (80% for training and 20% for validation) from 17 patients with no, mild, or severe lung disease. The model was tested on a dataset of 400 images from another 20 patients, independently partially annotated by three radiologist readers. The ILD contours from the three readers and the deep learning neural network were compared by using the Dice similarity coefficient (DSC). The correlation between disease extent obtained from the deep learning algorithm and that obtained by using pulmonary function tests (PFTs) was then evaluated in the remaining 171 patients and in an external validation dataset of 31 patients based on the analysis of all slices of the chest CT scan. The Spearman rank correlation coefficient (ρ) was calculated to evaluate the correlation between disease extent and PFT results.
The median DSCs between the readers and the deep learning ILD contours ranged from 0.74 to 0.75, whereas the median DSCs between contours from radiologists ranged from 0.68 to 0.71. The disease extent obtained from the algorithm, by analyzing the whole CT scan, correlated with the diffusion lung capacity for carbon monoxide, total lung capacity, and forced vital capacity (ρ -0.76, -0.70, and -0.62, respectively; < .001 for all) in the dataset for the correlation with PFT results. The disease extents correlated with diffusion lung capacity for carbon monoxide, total lung capacity, and forced vital capacity were ρ = -0.65, -0.70, and -0.57, respectively, in the external validation dataset ( < .001 for all).
The developed algorithm performed similarly to radiologists for disease-extent contouring, which correlated with pulmonary function to assess CT images from patients with SSc-related ILD.© RSNA, 2020.
开发一种深度学习算法，用于在胸部CT图像上自动评估系统性硬化症（SSc）相关间质性肺病（ILD）的范围。
这项回顾性研究纳入了2009年1月至2017年10月期间评估的208例SSc患者（中位年龄57岁；167例女性）。一个多组件深度神经网络（AtlasNet）在来自17例无、轻度或重度肺部疾病患者的6888幅全注释CT图像（80%用于训练，20%用于验证）上进行训练。该模型在来自另外20例患者的400幅图像的数据集上进行测试，这些图像由三位放射科医生读者独立进行部分注释。通过使用Dice相似系数（DSC）比较三位读者和深度学习神经网络得出的ILD轮廓。然后在其余171例患者以及基于胸部CT扫描所有层面分析的31例患者的外部验证数据集中，评估深度学习算法得出的疾病范围与通过肺功能测试（PFT）得出的疾病范围之间的相关性。计算Spearman等级相关系数（ρ）以评估疾病范围与PFT结果之间的相关性。
读者与深度学习ILD轮廓之间的中位DSC范围为0.74至0.75，而放射科医生轮廓之间的中位DSC范围为0.68至0.71。通过分析整个CT扫描从算法得出的疾病范围与一氧化碳弥散肺容量、肺总量和用力肺活量相关（在与PFT结果相关性的数据集中，ρ分别为-0.76、-0.70和-0.62；均P <.001）。在外部验证数据集中，与一氧化碳弥散肺容量、肺总量和用力肺活量相关的疾病范围的ρ分别为-0.65、-0.70和-0.57（均P <.001）。
所开发的算法在疾病范围勾勒方面的表现与放射科医生相似，该算法与肺功能相关，可用于评估SSc相关ILD患者的CT图像。© RSNA，2020。
