An improved 3-D attention CNN with hybrid loss and feature fusion for pulmonary nodule classification. (February 2023)

• Record Type: Journal Article
• Authors: Huang, Yao-Sian; Wang, Teh-Chen; Huang, Sheng-Zhi; Zhang, Jun; Chen, Hsin-Ming; Chang, Yeun-Chung; Chang, Ruey-Feng
• Is Part Of: Computer methods and programs in biomedicine. Volume 229(2023)
• Publication Date: 2023-02
• Subjects: Lung nodules -- Computer-aided diagnosis -- Residual network -- Attention mechanism -- Feature pyramid network -- Hybrid loss; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107278
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: An efficient 3-D computer-aided classification (CADx) model improved from the split-transform-merge convolution neural network (CNN) architecture is used for automatic nodule classification. The attention scheme, feature fusion, and hybrid loss are employed to enhance the performance in nodule classification. According to experiments, each employed method has potential for achieving the higher accuracy and AUC. In addition, the hybrid loss could allow more malignant nodules to be correctly classified and may also be an option to improve the sensitivity of model. Abstract: Background and Objective: Lung 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. Methods: The proposed CADx system consists of image preprocessing and a 3-D CNN-based classification model for pulmonary nodule classification. First, the image preprocessing was executed to generate the normalized volumn of interest (VOI) only including nodule information and a few surrounding tissues. Then, the extracted VOI was forwarded to the 3-D nodule classification model. In the classification model, the RestNext was employed as the backbone and the attention scheme was embedded to focus on the important features. Moreover, a multi-level feature fusion network incorporating feature information of different scales was used to enhance the prediction accuracy of small malignant nodules. Finally, a hybrid loss based on channel optimization which make the network learn more detailed information was empolyed to replace a binary cross-entropy (BCE) loss. Results: In this research, there were a total of 880 low-dose CT images including 440 benign and 440 malignant nodules from the American National Lung Screening Trial (NLST) for system evaluation. The results showed that our system could achieve the accuracy of 85.3%, the sensitivity of 86.8%, the specificity of 83.9%, and the area-under-curve (AUC) value was 0.9042. It was confirmed that the designed system had a good diagnostic ability. Conclusion: In this study, a CADx composed of the image preprocessing and a 3-D nodule classification model with attention scheme, feature fusion, and hybrid loss was proposed for pulmonary nodule classification in LDCT. The results indicated that the proposed CADx system had potential for achieving high performance in classifying lung nodules as benign and malignant.