An Effective CNN Method for Fully Automated Segmenting Subcutaneous and Visceral Adipose Tissue on CT Scans

• Published in: Annals of biomedical engineering Vol. 48; no. 1; pp. 312 - 328
• Main Authors: Wang, Zheng, Meng, Yu, Weng, Futian, Chen, Yinghao, Lu, Fanggen, Liu, Xiaowei, Hou, Muzhou, Zhang, Jie
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2020; Springer Nature B.V
• Subjects: Abdomen; Adipose tissue; Artificial neural networks; Automation; Biochemistry; Biological and Medical Physics; Biomarkers; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Biophysics; Classical Mechanics; Classifiers; Computed tomography; Feasibility studies; Health risks; Image processing; Image segmentation; Learning; Medical imaging; Neural networks; Standard deviation; Support vector machines; Subcutaneous adipose tissue (SAT); Visceral adipose tissue (VAT); Support vector machine (SVM); Convolutional neural network (CNN)

One major role of an accurate distribution of abdominal adipose tissue is to predict disease risk. This paper proposes a novel effective three-level convolutional neural network (CNN) approach to automate the selection of abdominal computed tomography (CT) images on large-scale CT scans and automati...