Abstract
Background/Objectives: Sarcopenia and muscle composition have emerged as significant indicators in the fields of musculoskeletal and metabolic research. The objective of this study was to develop and validate a fully automated, deep learning-based method for segmenting thigh muscles into three functional groups (extensor, flexor, and adductor) using non-contrast computed tomography (CT) images and to quantitatively evaluate the thigh muscles. Methods: In order to ascertain the most efficacious architecture for automated thigh muscle segmentation, three deep learning models (Dense U-Net, MANet, and SegFormer) were implemented and subsequently compared. Each model was trained using 136 manually labeled non-contrast thigh CT scans and externally validated with 40 scans from another institution. The performance of the segmentation was evaluated using the Dice similarity coefficient (DSC), sensitivity, specificity, and accuracy. Quantitative indices, including total muscle volume, lean muscle volume, and intra-/intermuscular fat volumes, were automatically calculated and compared with manual measurements. Results: All three models exhibited high segmentation accuracy, with the mean DSC exceeding 96%. The MANet model demonstrated optimal performance in internal validation, while the SegFormer model exhibited superior volumetric agreement in external validation, as indicated by an intraclass correlation coefficient (ICC) of at least 0.995 and a p-value less than 0.01. Conclusions: A CT-based deep learning framework enables accurate and reproducible segmentation of functional thigh muscle groups. A comparative evaluation of convolutional attention- and transformer-based architectures supports the feasibility of CT-based quantitative muscle assessment for sarcopenia and musculoskeletal research.