Automated and accurate quantification of subcutaneous and visceral adipose tissue from magnetic resonance imaging based on machine learning.

Accurate measuring of subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) is vital for the research of many diseases. The localization and quantification of SAT and VAT by computed tomography (CT) expose patients to harmful ionizing radiation. Magnetic resonance imaging (MRI) is a safe and painless test. The aim of this paper is to explore a practical method for the segmentation of SAT and VAT based on the iterative decomposition of water and fat with echo asymmetry and least square estimation‑iron quantification (IDEAL-IQ) technology and machine learning. The approach involves two main steps. First, a deep network is designed to segment the inner and outer boundaries of SAT in fat images and the peritoneal cavity contour in water images. Second, after mapping the peritoneal cavity contour onto the fat images, the assumption-free K-means++ with a Markov chain Monte Carlo (AFK-MC2) clustering method is used to obtain the VAT content. An MRI data set from 75 subjects is utilized to construct and evaluate the new strategy. The Dice coefficients for the SAT and VAT content obtained from the proposed method and the manual measurements performed by experts are 0.96 and 0.97, respectively. The experimental results indicate that the proposed method and the manual measurements exhibit high reliability.