A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects

• Published in: Scientific reports Vol. 11; no. 1; pp. 34 - 12
• Main Authors: Ho, Thao Thi, Kim, Taewoo, Kim, Woo Jin, Lee, Chang Hyun, Chae, Kum Ju, Bak, So Hyeon, Kwon, Sung Ok, Jin, Gong Yong, Park, Eun-Kee, Choi, Sanghun
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 08-01-2021; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1564; 631/114/2397; 631/1647/245; 639/166/985; Allergic diseases; Chronic obstructive pulmonary disease; Classification; Computed tomography; Deep learning; Emphysema; Humanities and Social Sciences; Lung diseases; Mapping; multidisciplinary; Neural networks; Obstructive lung disease; Respiratory tract diseases; Science; Science (multidisciplinary)
• DOI: 10.1038/s41598-020-79336-5
• EISSN: 2045-2322

Chronic obstructive pulmonary disease (COPD) is a respiratory disorder involving abnormalities of lung parenchymal morphology with different severities. COPD is assessed by pulmonary-function tests and computed tomography-based approaches. We introduce a new classification method for COPD grouping based on deep learning and a parametric-response mapping (PRM) method. We extracted parenchymal functional variables of functional small airway disease percentage (fSAD%) and emphysema percentage (Emph%) with an image registration technique, being provided as input parameters of 3D convolutional neural network (CNN). The integrated 3D-CNN and PRM (3D-cPRM) achieved a classification accuracy of 89.3% and a sensitivity of 88.3% in five-fold cross-validation. The prediction accuracy of the proposed 3D-cPRM exceeded those of the 2D model and traditional 3D CNNs with the same neural network, and was comparable to that of 2D pretrained PRM models. We then applied a gradient-weighted class activation mapping (Grad-CAM) that highlights the key features in the CNN learning process. Most of the class-discriminative regions appeared in the upper and middle lobes of the lung, consistent with the regions of elevated fSAD% and Emph% in COPD subjects. The 3D-cPRM successfully represented the parenchymal abnormalities in COPD and matched the CT-based diagnosis of COPD.