Autonomous localization and segmentation for body composition quantization on abdominal CT. (January 2022)

• Record Type: Journal Article
• Authors: Zhang, Guyue; Yang, Yang; Xu, Shangliang; Nan, Yang; Lv, Chuanfeng; Wei, Lina; Qian, Tianwei; Han, Jun; Xie, Guotong
• Is Part Of: Biomedical signal processing and control. Volume 71(2022)Part A
• Publication Date: 2022-01
• Subjects: Body composition analysis -- Body tissue quantization -- Vertebrae localization -- Cross-Stage Attention -- Adversarial structure; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103172
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A novel cascade method is proposed for automatic localization and segmentation of L3 vertebra's body tissue. Vertebra localization network applies Gaussian cube to spine detection and infers the location of L3 vertebra through vertebra segmentation. The tissue segmentation network uses adversarial modeling with two sub-networks and a novel Cross-Stage Attention block with both spatial- and channel-wise information to quantize body tissue of the L3 vertebra. The experimental results show the outperformance of our proposed method, exceeding existing body tissue segmentation networks. Abstract: Objective: The impact of body composition on disease prognosis is increasingly recognized. Analysis of computed tomography (CT) scans at the level of the third lumbar (L3) spine is considered a standard approach to measure muscle and adipose tissue body composition parameters. However, existing approaches need manually select the L3 vertebra and then analyze body composition, which is time-consuming. Thus, how to automatically analyze body composition becomes the problem. Methods: In this paper, a novel two-step method is proposed and can automatically localize the L3 vertebra and segment body tissue accurately. Initially, the lumbar spine region is coarsely detected, and then each lumbar vertebra is determined. Secondly, the slice at the L3 vertebra is selected to quantize tissue (muscle, subcutaneous adipose tissue, visceral adipose tissue, etc.) based on a segmentation network. To achieve high performance, a Cross-Stage Attention (CSA) block and an adversarial structure are jointly utilized in tissue segmentation. Results: The experimental results show that the L3 vertebra localization result achieves 95.08 % Dice. The CSA block and adversarial structure play positive roles in improving the tissue segmentation performance with an average Dice from 95.15 % to 97.44 % . Conclusion: The results demonstrate that our method outperforms other existing body tissue segmentation approaches in terms of sensitivity, positive predictive value (PPV), Dice score, and Jaccard score. Significance: The time cost of data collection and annotation can be significantly reduced due to integrating L3 vertebra localization before tissue segmentation. Simultaneously, our method can be extended to all lumbar vertebrae and quantize each tissue volume in the abdomen.