Validation of an Artificial Intelligence-Based Ultrasound Imaging System for Quantifying Muscle Architecture Parameters of the Rectus Femoris in Disease-Related Malnutrition (DRM)

(1) Background: The aim was to validate an AI-based system compared to the classic method of reading ultrasound images of the rectus femur (RF) muscle in a real cohort of patients with disease-related malnutrition. (2) Methods: One hundred adult patients with DRM aged 18 to 85 years were enrolled. The risk of DRM was assessed by the Global Leadership Initiative on Malnutrition (GLIM). The variation, reproducibility, and reliability of measurements for the RF subcutaneous fat thickness (SFT), muscle thickness (MT), and cross-sectional area (CSA), were measured conventionally with the incorporated tools of a portable ultrasound imaging device (method A) and compared with the automated quantification of the ultrasound imaging system (method B). (3) Results: Measurements obtained using method A (i.e., conventionally) and method B (i.e., raw images analyzed by AI), showed similar values with no significant differences in absolute values and coefficients of variation, 58.39–57.68% for SFT, 30.50–28.36% for MT, and 36.50–36.91% for CSA, respectively. The Intraclass Correlation Coefficient (ICC) for reliability and consistency analysis between methods A and B showed correlations of 0.912 and 95% CI 0.872–0.940 for SFT, 0.960 and 95% CI 0.941–0.973 for MT, and 0.995 and 95% CI 0.993–0.997 for CSA; the Bland–Altman Analysis shows that the spread of points is quite uniform around the bias lines with no evidence of strong bias for any variable. (4) Conclusions: The study demonstrated the consistency and reliability of this new automatic system based on machine learning and AI for the quantification of ultrasound imaging of the muscle architecture parameters of the rectus femoris muscle compared with the conventional method of measurement.