Zucker Evan J, Barnes Zachary A, Lungren Matthew P, Shpanskaya Yekaterina, Seekins Jayne M, Halabi Safwan S, Larson David B
Department of Radiology, Stanford University School of Medicine, 725 Welch Road, Stanford, CA 94305, USA.
Department of Computer Science, Stanford University, 353 Serra Mall, Stanford, CA 94305, USA.
J Cyst Fibros. 2020 Jan;19(1):131-138. doi: 10.1016/j.jcf.2019.04.016. Epub 2019 May 2.
The aim of this study was to evaluate the hypothesis that a deep convolutional neural network (DCNN) model could facilitate automated Brasfield scoring of chest radiographs (CXRs) for patients with cystic fibrosis (CF), performing similarly to a pediatric radiologist.
All frontal/lateral chest radiographs (2058 exams) performed in CF patients at a single institution from January 2008-2018 were retrospectively identified, and ground-truth Brasfield scoring performed by a board-certified pediatric radiologist. 1858 exams (90.3%) were used to train and validate the DCNN model, while 200 exams (9.7%) were reserved for a test set. Five board-certified pediatric radiologists independently scored the test set according to the Brasfield method. DCNN model vs. radiologist performance was compared using Spearman correlation (ρ) as well as mean difference (MD), mean absolute difference (MAD), and root mean squared error (RMSE) estimation.
For the total Brasfield score, ρ for the model-derived results computed pairwise with each radiologist's scores ranged from 0.79-0.83, compared to 0.85-0.90 for radiologist vs. radiologist scores. The MD between model estimates of the total Brasfield score and the average score of radiologists was -0.09. Based on MD, MAD, and RMSE, the model matched or exceeded radiologist performance for all subfeatures except air-trapping and large lesions.
A DCNN model is promising for predicting CF Brasfield scores with accuracy similar to that of a pediatric radiologist.
本研究的目的是评估以下假设，即深度卷积神经网络（DCNN）模型可促进对囊性纤维化（CF）患者的胸部X光片（CXR）进行自动布拉斯菲尔德评分，其表现与儿科放射科医生相似。
回顾性识别了2008年1月至2018年在单一机构对CF患者进行的所有正位/侧位胸部X光片（2058次检查），并由一名获得委员会认证的儿科放射科医生进行了真实的布拉斯菲尔德评分。1858次检查（90.3%）用于训练和验证DCNN模型，而200次检查（9.7%）留作测试集。五名获得委员会认证的儿科放射科医生根据布拉斯菲尔德方法对测试集进行独立评分。使用斯皮尔曼相关性（ρ）以及平均差（MD）、平均绝对差（MAD）和均方根误差（RMSE）估计来比较DCNN模型与放射科医生的表现。
对于总的布拉斯菲尔德评分，模型得出的结果与每位放射科医生的评分两两计算得出的ρ范围为0.79 - 0.83，而放射科医生之间评分的ρ为0.85 - 0.90。模型对总布拉斯菲尔德评分的估计与放射科医生平均评分之间的MD为 -0.09。基于MD、MAD和RMSE，除气体潴留和大病灶外，该模型在所有子特征上的表现与放射科医生相当或更优。
DCNN模型有望以与儿科放射科医生相似的准确性预测CF布拉斯菲尔德评分。
