An improved 3-D attention CNN with hybrid loss and feature fusion for pulmonary nodule classification

Huang, Yao-SianYao-SianHuangWang, Teh-ChenTeh-ChenWangHuang, Sheng-ZhiSheng-ZhiHuangZhang, JunJunZhangHSIN-MING CHENYEUN-CHUNG CHANGRUEY-FENG CHANG2023-03-032023-03-032023-020169-2607https://scholars.lib.ntu.edu.tw/handle/123456789/628909Lung cancer has the highest cancer-related mortality worldwide, and lung nodule usually presents with no symptom. Low-dose computed tomography (LDCT) was an important tool for lung cancer detection and diagnosis. It provided a complete three-dimensional (3-D) chest image with a high resolution.Recently, convolutional neural network (CNN) had flourished and been proven the CNN-based computer-aided diagnosis (CADx) system could extract the features and help radiologists to make a preliminary diagnosis. Therefore, a 3-D ResNeXt-based CADx system was proposed to assist radiologists for diagnosis in this study.enAttention mechanism; Computer-aided diagnosis; Feature pyramid network; Hybrid loss; Lung nodules; Residual network[SDGs]SDG3An improved 3-D attention CNN with hybrid loss and feature fusion for pulmonary nodule classificationjournal article10.1016/j.cmpb.2022.107278364636742-s2.0-85143542794WOS:000896035600003https://api.elsevier.com/content/abstract/scopus_id/85143542794