Improvements of Liver MR Imaging Clinical Protocols to Simultaneously Quantify Steatosis and Iron Overload

Improved Ultrasound Attenuation Measurement Method for the Non-invasive Evaluation of Hepatic Steatosis Using FibroScan

Controlled attenuation parameter (CAP) is a measurement of ultrasound attenuation used to assess liver steatosis non-invasively. However, the standard method has some limitations. This study assessed the performance of a new CAP method by ex vivo and in vivo assessments. The major difference with the new method is that it uses ultrasound data continuously acquired during the imaging phase of the FibroScan examination. Seven reference tissue-mimicking phantoms were used to test the performance. In vivo performance was assessed in two cohorts (in total 195 patients) of patients using magnetic resonance imaging proton density fat fraction (MRI-PDFF) as a reference. The precision of CAP was improved by more than 50% on tissue-mimicking phantoms and 22%-41% in the in vivo cohort studies. The agreement between both methods was excellent, and the correlation between CAP and MRI-PDFF improved in both studies (0.71 to 0.74; 0.70 to 0.76). Using MRI-PDFF as a reference, the diagnostic performance of the new method was at least equal or superior (area under the receiver operating curve 0.889-0.900, 0.835-0.873). This study suggests that the new continuous CAP method can significantly improve the precision of CAP measurements ex vivo and in vivo.

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.