3D deep learning based classification of pulmonary ground glass opacity nodules with automatic segmentation. (March 2021)

• Record Type: Journal Article
• Authors: Wang, Duo; Zhang, Tao; Li, Ming; Bueno, Raphael; Jayender, Jagadeesan
• Is Part Of: Computerized medical imaging and graphics. Volume 88(2021)
• Publication Date: 2021-03
• Subjects: Pulmonary ground glass opacity nodules -- Classification -- Automatic segmentation -- Joint training -- Deep learning; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2020.101814
• Languages: English
• ISSNs: 0895-6111

Abstract

Highlights: We use the segmentation annotation at the data level for the classification of pulmonary nodules. We train a network to automatically generate the segmentation of nodules and use it to mask the input data for the classification network. We further propose a cascade architecture consisting of the segmentation and classification models with joint training. We collect a large dataset with 740 CT volumes and evaluate our method on 4 clinically significant nodule classification tasks with different pathology types using 4 classification metrics. Abstract: Classifying ground-glass lung nodules (GGNs) into atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) on diagnostic CT images is important to evaluate the therapy options for lung cancer patients. In this paper, we propose a joint deep learning model where the segmentation can better facilitate the classification of pulmonary GGNs. Based on our observation that masking the nodule to train the model results in better lesion classification, we propose to build a cascade architecture with both segmentation and classification networks. The segmentation model works as a trainable preprocessing module to provide the classification-guided 'attention' weight map to the raw CT data to achieve better diagnosis performance. We evaluate our proposed model and compare with other baseline models for 4 clinically significant nodule classification tasks, defined by a combination of pathology types, using 4 classification metrics: Accuracy, Average F1 Score, Matthews Correlation Coefficient (MCC), and Area Under the Receiver Operating Characteristic Curve (AUC). Experimental results show that the proposed method outperforms other baseline models on all the diagnostic classification tasks.