Deep learning method for localization and segmentation of abdominal CT. (October 2020)

• Record Type: Journal Article
• Authors: Dabiri, Setareh; Popuri, Karteek; Ma, Cydney; Chow, Vincent; Feliciano, Elizabeth M. Cespedes; Caan, Bette J.; Baracos, Vickie E.; Beg, Mirza Faisal
• Is Part Of: Computerized medical imaging and graphics. Volume 85(2020)
• Publication Date: 2020-10
• Subjects: Third lumbar vertebra -- Muscle segmentation -- Fat segmentation -- CT scan -- Convolutional neural network; 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.2020.101776
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: Computed Tomography (CT) imaging is widely used for studying body composition, i.e., the proportion of muscle and fat tissues with applications in areas such as nutrition or chemotherapy dose design. In particular, axial CT slices from the 3rd lumbar (L3) vertebral location are commonly used for body composition analysis. However, selection of the third lumbar vertebral slice and the segmentation of muscle/fat in the slice is a tedious operation if performed manually. The objective of this study is to automatically find the middle axial slice at L3 level from a full or partial body CT scan volume and segment the skeletal muscle (SM), subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT) and intermuscular adipose tissue (IMAT) on that slice. The proposed algorithm includes an L3 axial slice localization network followed by a muscle-fat segmentation network. The localization network is a fully convolutional classifier trained on more than 12, 000 images. The segmentation network is a convolutional neural network with an encoder–decoder architecture. Three datasets with CT images taken for patients with different types of cancers are used for training and validation of the networks. The mean slice error of 0.87 ± 2.54 was achieved for L3 slice localization on 1748 CT scan volumes. The performance of five class tissue segmentation network evaluated on two datasets with 1327 and 1202 test samples. The mean Jaccard score of 97% was achieved for SM and VAT tissue segmentation on 1327 images. The mean Jaccard scores of 98% and 83% are corresponding to SAT and IMAT tissue segmentation on the same dataset. The localization and segmentation network performance indicates the potential for fully automated body composition analysis with high accuracy. Highlights: The proposed algorithm automatically extracts and segments the L3 CT slice. The L3 slice extraction model is a binary (L3 or non-L3) classification network. The five-class segmentation network segments muscle and fat tissues on the L3 slice. Mean slice error of 0.87 ± 2.54 achieved for L3 slice localization on 1748 CT scan. The tissue segmentation network achieved high Jaccard scores on two test datasets.