Abstract
Distinguishing subcutaneous adipose tissue (SAT) from intermuscular adipose tissue (IMAT) is clinically important because IMAT infiltration is strongly associated with age-related functional decline, sarcopenia, diabetes, cardiovascular disease, and obesity. Current assessments rely on MRI or CT, which are stationary, costly, and labor-intensive. Portable ultrasound-based solutions could enable broader, proactive screening. This model study investigated the feasibility of differentially assessing SAT and IMAT using features extracted from propagating ultrasound signals. Twenty-five phantoms were constructed using gelatin as a muscle-mimicking matrix and oil as the SAT and IMAT compartments, arranged to provide gradual variations in fat fractions ranging from 0% to 50%. Ultrasound measurements were collected at 0.8 MHz and 2.2 MHz, and multiple evaluation criteria were computed, including ultrasound velocity and parameters derived from the signal intensity. Classification domains were then generated from intersecting decision rules associated with these criteria. In parallel, artificial neural networks (ANN/LSTM) were trained and tested on identical phantom subsets to evaluate data-driven classification performance. Both the rule-based and ANN/LSTM approaches achieved diagnostically meaningful separation of SAT and IMAT. The aim of this work was to perform an experimental proof-of-concept study on idealized tissue models to demonstrate that ultrasound measurements can reliably differentiate SAT and IMAT, supporting the development of future screening devices.