An effective automatic segmentation of abdominal adipose tissue using a convolution neural network. Issue 9 (September 2022)

• Record Type: Journal Article
• Authors: Micomyiza, Carine; Zou, Beiji; Li, Yang
• Is Part Of: Diabetes & metabolic syndrome. Volume 16:Issue 9(2022)
• Publication Date: 2022-09
• Subjects: Deep learning -- Convolutional neural networks (CNN) -- Semantic segmentation -- Computed tomography (CT) -- Abdominal adipose tissue (AAT); SAT: subcutaneous adipose tissue -- VAT: visceral adipose tissue -- AAT: Abdominal adipose tissue -- A-CNN: automated convolutional neural network -- CT: Computed Tomography -- CNN: Convolutional neural networks; Diabetes -- Periodicals; Metabolism -- Disorders -- Periodicals; Diabetes Mellitus -- Periodicals; Metabolic Diseases -- Periodicals; Diabète -- Périodiques; Métabolisme, Troubles du -- Périodiques; Endocrinologie -- Périodiques; Diabète -- Physiopathologie -- Périodiques; Diabetes; Metabolism -- Disorders; Electronic journals; Periodicals; 616.462
• DOI: 10.1016/j.dsx.2022.102589
• Languages: English
• ISSNs: 1871-4021

Abstract

Abstract: Background and aims: Computer-aided diagnosis and prognosis rely heavily on fully automatic segmentation of abdominal fat tissue using Emission Tomography images. The identification of subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) in abdomen fat faces two main challenges: (1) the great difficulties in comparison to multi-stage semantic segmentation (VAT and SAT), and (2) the subtle differences due to the high similarity of the two classes in abdomen fat and complicated VAT distribution. Methods: In this research, we built an automated convolutional neural network (A-CNN) for segmenting Abdominal adipose tissue (AAT) from radiology images. Results: We developed a point-to-point design for the A-CNN learning process, wherein the representing features might be learned together with a hybrid feature extraction technique. We tested the proposed model on a CT dataset and evaluated it to existing CNN models. Furthermore, our suggested approach, A-CNN, outperformed existing deep learning methods regarding segmentation outcomes, notably in the AAT segment. Conclusions: Proposed method is extremely fast with remarkable performance on limited-scale low dose CT-scanning and demonstrates the strength in providing an efficient computer-aimed tool for segmentation of AAT in the clinic. Highlights: A novel method is proposed for abdominal adipose tissue segmentation. We identify, segment and quantify the abdominal fat images. Our method has high reliability to automated segmentation of subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT). The proposed approach outperforms state-of-the-art other deep learning networks in accuracy.