Big Bones Mean Big Muscles: AI Quantifies 71 Individual Muscles Across the Whole Body, Revealing Widespread Links Between Muscle, Bone, and Body Size
Riem, L.; Pinette, M.; DuCharme, O.; Pabon, V.; Coggins, A.; Harold, L.; Costanzo, K. E.; Cousins, M.; Hein, R.; Rhodes, M.; Llevens, E.; Feng, X.; Benusa, S.; Breeding, T.; Derave, W.; Blemker, S. S.
Show abstract
Body sizes and shapes vary widely, even among healthy adults, resulting in diverse muscle sizes, strengths, and performance capacities. This study developed a novel AI-driven algorithm to segment and analyze individual muscles and bones from whole-body MRI. Validated via inter- and intra-observer analyses, the algorithm created 3D segmentations of 71 muscles and 13 bones across the upper limbs, trunk, and lower limbs in 48 healthy adults (24 males, 24 females) aged 18-49 years. Muscle volume, asymmetry, length, and fat fraction were quantified. While asymmetry and fat fraction varied across muscles, they did not differ significantly between sexes. Total muscle volume was the strongest predictor of individual muscle volume, followed by bone volume, which correlated with muscle size at whole-body, regional, and individual levels. Muscle-to-body size relationships (e.g., mass, height, BMI) differed between sexes, while bone-to-body size relationships did not. These findings suggest that skeletal size ("frame size") is a key determinant of muscularity. This study provides the most comprehensive in vivo dataset of human skeletal muscle to date, offering a multi-factorial explanation for variation in muscularity and benchmarks for applications ranging from athletic performance to clinical assessments in muscle disorders. SUMMARYUnderstanding how muscle size varies across the body and what influences these differences is key to advancing both health and performance. This study uses cutting-edge AI to analyze individual muscles across the whole body from MRI scans, creating the most detailed dataset of human muscle and bone relationships to date. The findings reveal how skeletal size ("frame size") and body dimensions shape muscularity, providing new insights into why people differ in muscle size and strength. These results have broad implications, from optimizing athletic training to diagnosing and treating muscle disorders. By uncovering the intricate connections between muscles, bones, and body size, this research offers a powerful framework for understanding human movement and variability.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Multi-scale machine learning model predicts muscle and functional disease progression in FSHD 95%
- MRI-derived Articular Cartilage Strains Predict Patient-Reported Outcomes Six Months Post Anterior Cruciate Ligament Reconstruction 94%
- Foot strike pattern during running alters muscle-tendon dynamics of the gastrocnemius and the soleus 94%
Similar papers in this journal
- DeepACSA: Automatic segmentation of anatomical cross-sectional area in ultrasound images of human lower limb muscles using deep learning 93%
- Hamstrings are stretched more and faster during accelerative running compared to speed-matched constant speed running 93%
- Mechanism Of Anterior Cruciate Ligament Loading During Dynamic Motor Tasks 93%
Similar papers in this journal
- Tissue-specific changes in size and shape of the ligaments and tendons of the porcine knee during post-natal growth 96%
- Neck Musculoskeletal Model Generation through Anthropometric Scaling 94%
- A registration strategy to characterize DTI-observed changes in skeletal muscle architecture due to passive shortening 93%
Similar papers in this journal
- Ultrasound-based optimal parameter estimation improves assessment of calf muscle-tendon interaction during walking 93%
- Muscle Moment Arm-Joint Angle Relations in the Hip, Knee, and Ankle: A Visualization of Datasets 93%
- Hip and knee joint kinematics predict quadriceps hyperreflexia in people with post-stroke Stiff-Knee gait 92%
Similar papers in this journal
- Sex-Specific Function and Morphology of the Anterior Cruciate Ligament During Skeletal Growth in a Porcine Model 95%
- Soluble RANKL exaggerates hindlimb suspension-induced osteopeniabut not muscle protein balance 93%
- Cyclic Loading Induces Anabolic and Catabolic Gene Expression in ACLs in a Load-Dependent and Sex-Specific Manner 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.