New Methodologies and Ultrasound Techniques for the Diagnosis and Clinical Management of Sarcopenia: development and application of software for automated analysis of raw radiofrequency data and B-mode images data

Reduced muscle mass and function are associated with severe complications, increased morbidity, and mortality. Ultrasound (US), despite being cost-effective and portable, is still underutilized in muscle trophism assessment due to its reliance on operator expertise and measurement variability. This project aimed to overcome these limitations by developing a deep learning model that predicts muscle density, as assessed by CT, using US data, exploring the feasibility of a novel US-based parameter for muscle trophism. A sample of adult participants admitted to the San Martino University Hospital’s emergency department between May 2022 and March 2023 was enrolled in this single-center study. The rectus abdominis muscle was selected as the target muscle. US examinations were performed with a L11-3 MHz probe directly on the CT table before contrast administration. The rectus abdominis muscles were scanned in the transverse plane, recording a US image on both sides, with a region of interest (ROI) positioned within the muscle. For each participant, the same operator calculated the average target muscle density in Hounsfield Units from an axial CT slice closely matching the US scanning plane. After quality review, the final dataset included 1090 US images from 551 participants (mean age 67 ± 17, 323 males). A deep learning algorithm was developed to classify US images into three muscle density classes based on CT values. The model achieved promising performance, with a categorical accuracy of 70% and AUC values of 0.89, 0.79, and 0.90 across the three classes. This project introduces an innovative approach to automated muscle trophism assessment using US imaging. Future efforts should focus on external validation in diverse populations and clinical settings, as well as expanding its application to other muscles.