Deep Learning Method for Automated Classification of Anteroposterior and Posteroanterior Chest Radiographs

• Published in: Journal of digital imaging 2019-12, Vol.32 (6), p.925-930
• Main Authors: Kim, Tae Kyung, Yi, Paul H., Wei, Jinchi, Shin, Ji Won, Hager, Gregory, Hui, Ferdinand K., Sair, Haris I., Lin, Cheng Ting
• Format: Article
• Language: English
• Subjects: Adult; Algorithms; Annotations; Artificial intelligence; Artificial neural networks; Automation; Chest; Child; Classification; Databases, Factual; Datasets; Deep Learning; Diagnostic systems; Humans; Image classification; Image quality; Imaging; Learning algorithms; Machine learning; Medicine; Medicine & Public Health; Neural networks; Pediatrics; Quality assurance; Quality control; Radiographic Image Interpretation, Computer-Assisted - methods; Radiographs; Radiography; Radiography, Thoracic - methods; Radiology; Reproducibility of Results; Retrospective Studies; Sensitivity; Sensitivity and Specificity; Statistical analysis
• ISSN: 0897-1889; 1618-727X
• DOI: 10.1007/s10278-019-00208-0

Ensuring correct radiograph view labeling is important for machine learning algorithm development and quality control of studies obtained from multiple facilities. The purpose of this study was to develop and test the performance of a deep convolutional neural network (DCNN) for the automated classification of frontal chest radiographs (CXRs) into anteroposterior (AP) or posteroanterior (PA) views. We obtained 112,120 CXRs from the NIH ChestX-ray14 database, a publicly available CXR database performed in adult (106,179 (95%)) and pediatric (5941 (5%)) patients consisting of 44,810 (40%) AP and 67,310 (60%) PA views. CXRs were used to train, validate, and test the ResNet-18 DCNN for classification of radiographs into anteroposterior and posteroanterior views. A second DCNN was developed in the same manner using only the pediatric CXRs (2885 (49%) AP and 3056 (51%) PA). Receiver operating characteristic (ROC) curves with area under the curve (AUC) and standard diagnostic measures were used to evaluate the DCNN’s performance on the test dataset. The DCNNs trained on the entire CXR dataset and pediatric CXR dataset had AUCs of 1.0 and 0.997, respectively, and accuracy of 99.6% and 98%, respectively, for distinguishing between AP and PA CXR. Sensitivity and specificity were 99.6% and 99.5%, respectively, for the DCNN trained on the entire dataset and 98% for both sensitivity and specificity for the DCNN trained on the pediatric dataset. The observed difference in performance between the two algorithms was not statistically significant ( p  = 0.17). Our DCNNs have high accuracy for classifying AP/PA orientation of frontal CXRs, with only slight reduction in performance when the training dataset was reduced by 95%. Rapid classification of CXRs by the DCNN can facilitate annotation of large image datasets for machine learning and quality assurance purposes.