+ v2.0 + + Latest + +
+ +mm_util.py with support for multiple Zenodo versionsmm_gui.py and mm_segment.py to use the new Zenodo-based model loadingmm_qc_gui.py as a new QC interfacesetup.py and requirements.txt for v2.0 dependencies.gitignore to exclude large model filesREADME.md with instructions for Zenodo usage and template file setup+ v1.3 +
+ +.pth) and configuration files (.json) for mm_segment have been removed from the git history to reduce repository size. To use this release, download the model parameters from Zenodo and place them in the corresponding subfolder, e.g. scripts/models/wholebody/ or scripts/models/abdomen/.nii.gz) for mm_register_to_template have been removed from the git history to reduce repository size. To use this release, download the template images from Zenodo and place them in the corresponding subfolder, e.g. scripts/templates/abdomen/+ v1.2 +
+ ++ v1.1 +
+ ++ v1.0 +
+ +mm_segmentmm_segmentmm_extract_metrics+ v0.3 + + Pre-release + +
+ ++ v0.2 + + Pre-release + +
+ +mm_register_to_template for anatomical registration+ v0.1 + + Pre-release + +
+ +mm_segmentmm_extract_metricsmm_gui+ v0.0 + + Pre-release + +
+ ++ McKay MJ, Weber KA 2nd, Wesselink EO, Smith ZA, Abbott R, Anderson DB, Ashton-James CE, + Atyeo J, Beach AJ, Burns J, Clarke S, Collins NJ, Coppieters MW, Cornwall J, Crawford RJ, + De Martino E, Dunn AG, Eyles JP, Feng HJ, Fortin M, Franettovich Smith MM, Galloway G, + Gandomkar Z, Glastras S, Henderson LA, Hides JA, Hiller CE, Hilmer SN, Hoggarth MA, Kim B, + Lal N, LaPorta L, Magnussen JS, Maloney S, March L, Nackley AG, O'Leary SP, Peolsson A, + Perraton Z, Pool-Goudzwaard AL, Schnitzler M, Seitz AL, Semciw AI, Sheard PW, Smith AC, + Snodgrass SJ, Sullivan J, Tran V, Valentin S, Walton DM, Wishart LR, Elliott JM. + MuscleMap: An Open-Source, Community-Supported Consortium for Whole-Body Quantitative + MRI of Muscle. J Imaging. 2024;10(11):262. +
+ + + https://doi.org/10.3390/jimaging10110262 + +| MuscleMap module | +References | +
|---|---|
| mm_segment | +
+
+
+ + Whole-body — + Wesselink EO, Elliott JM, McKay M, de Martino E, Caplan N, Mackey S, + Cohen-Adad J, Bédard S, De Leener B, Naga Karthik E, Law CSW, Fortin M, + Vleggeert–Lankamp C, Di Leva A, Kim B, Hancock M, Pool-Goudzwaard A, + Pevenage P, Weber II KA. + Segment-Any-Muscle: Towards an Open-Source, Contrast-Agnostic Computer-Vision + Muscle Segmentation Model for MRI and CT. + ISMRM 2025 abstract. + + + Download BibTeX + + |
+
|
+
+
+
+
+ + Abdomen — + Wesselink EO, Pool-Goudzwaard A, De Leener B, Law CSW, Fenyo MB, Ello GM, + Coppieters MW, Elliott JM, Mackey S, Weber KA 2nd. + Investigating the associations between lumbar paraspinal muscle health and + age, BMI, sex, physical activity, and back pain using an automated + computer-vision model: a UK Biobank study. + Spine J. 2024;24(7):1253–1266. + + + Download BibTeX + +
+
+ + Wesselink EO, Elliott JM, Coppieters MW, Hancock MJ, Cronin B, + Pool-Goudzwaard A, Weber II KA. + Convolutional neural networks for the automatic segmentation of lumbar + paraspinal muscles in people with low back pain. + Sci Rep. 2022;12(1):13485. + + + Download BibTeX + + |
+ |
|
+
+
+
+
+ + Pelvis — + Wesselink EO, Elliott JM, McKay M, de Martino E, Caplan N, Mackey S, + Cohen-Adad J, Bédard S, De Leener B, Naga Karthik E, Law CSW, Fortin M, + Vleggeert–Lankamp C, Di Leva A, Kim B, Hancock M, Pool-Goudzwaard A, + Pevenage P, Weber II KA. + Segment-Any-Muscle: Towards an Open-Source, Contrast-Agnostic Computer-Vision + Muscle Segmentation Model for MRI and CT. + ISMRM 2025 abstract. + + + Download BibTeX + +
+
+ + Stewart C, Wesselink EO, Perraton Z, Weber II KA, King MG, Kemp JL, + Mentiplay BF, Crossley KM, Elliott JM, Heerey JJ, Scholes MJ, + Lawrenson PR, Calabrese C, Semciw AI. + Muscle fat and volume differences in people with hip-related pain + compared to controls: A machine learning approach. + J Cachexia Sarcopenia Muscle. 2024;15(6):2642–2650. + + + Download BibTeX + + |
+ |
|
+
+
+ + Thigh — + Wesselink EO, Elliott JM, McKay M, de Martino E, Caplan N, Mackey S, + Cohen-Adad J, Bédard S, De Leener B, Naga Karthik E, Law CSW, Fortin M, + Vleggeert–Lankamp C, Di Leva A, Kim B, Hancock M, Pool-Goudzwaard A, + Pevenage P, Weber II KA. + Segment-Any-Muscle: Towards an Open-Source, Contrast-Agnostic Computer-Vision + Muscle Segmentation Model for MRI and CT. + ISMRM 2025 abstract. + + + Download BibTeX + + |
+ |
|
+
+
+
+
+ + Leg — + Wesselink EO, Elliott JM, McKay M, de Martino E, Caplan N, Mackey S, + Cohen-Adad J, Bédard S, De Leener B, Naga Karthik E, Law CSW, Fortin M, + Vleggeert–Lankamp C, Di Leva A, Kim B, Hancock M, Pool-Goudzwaard A, + Pevenage P, Weber II KA. + Segment-Any-Muscle: Towards an Open-Source, Contrast-Agnostic Computer-Vision + Muscle Segmentation Model for MRI and CT. + ISMRM 2025 abstract. + + + Download BibTeX + +
+
+ + Smith AC, Muñoz Laguna J, Wesselink EO, Scott ZE, Jenkins H, Thornton W, + Wasielewski M, Connor J, Delp S, Chaudhari A, Parrish TB, Mackey S, + Elliott JM, Weber II KA. + Leg Muscle Volume, Intramuscular Fat, and Force Generation: + Insights from a Computer Vision Model and Fat-Water MRI. + J Cachexia Sarcopenia Muscle. 2025;16(1):e13735. + + + Download BibTeX + + |
+ |
| mm_extract_metrics | +
+
+
+ + Wesselink EO, Elliott JM, Pool-Goudzwaard A, Coppieters MW, Pevenage PP, + Di Ieva A, Weber II KA. + Quantifying lumbar paraspinal intramuscular fat: Accuracy and reliability + of automated thresholding models. + N Am Spine Soc J. 2024;17:100313. + + + Download BibTeX + + |
+
| mm_register_to_template | +
+
+
+
+
+ + Weber KA 2nd, Wesselink EO, Gutierrez J, Law CSW, Mackey S, Ratliff J, + Hu S, Chaudhari AS, Pool-Goudzwaard A, Coppieters MW, Elliott JM, + Hancock M, De Leener B. + Three-dimensional spatial distribution of lumbar paraspinal + intramuscular fat revealed by spatial parametric mapping. + Eur Spine J. 2025;34(1):27–35. + + + Download BibTeX + +
+
+ + De Leener B, Lévy S, Dupont SM, Fonov VS, Stikov N, Collins DL, + Callot V, Cohen-Adad J. + SCT: Spinal Cord Toolbox, an open-source software for processing spinal cord MRI data. + Neuroimage. 2017;145(Pt A):24–43. + + + Download BibTeX + + |
+
Open-source toolbox
++ Whole-body muscle segmentation and quantitative analysis for large-scale imaging studies. +
++ Built for researchers, clinicians, and data scientists working with MRI and CT. +
+
+ + Designed for whole-body and clinical imaging with consistent labelling + across muscles and bones, enabling large-scale, multi-region analyses. +
+
+ + Extract muscle-specific metrics such as volumes or intramuscular fat + percentage across multiple MRI contrasts and CT. +
+
+ + Visualize and calculate the 3D spatial distribution of intramuscular fat + in a standardized muscle template. +
+
+ + Includes a 3D Slicer extension to make MuscleMap easy + to run and inspect individual cases for quality control. +
+
+ + Run MuscleMap directly in your browser through Neurodesk. + Simply drag and drop NIfTI or DICOM images and click run segmentation. + No installation required and all data remains on your local workstation. +
+nvidia-smi. Also, we recommend to install Pytorch using the wheel.
+Key feature
++ MuscleMap's `mm_extract_metrics` is the command-line tool for quantitative muscle analysis, enabling automated estimation of muscle volume, cross-sectional area (CSA), intramuscular fat infiltration, and muscle density from MRI and CT images. +
+ +
+ Key feature
++ MuscleMap segmentation is performed using a deep learning–based, contrast-agnostic whole-body model trained for robust muscle and bone segmentation across MRI and CT modalities. +
+ +
+ mm_segment from the command line works as expected when MuscleMap is installed in editable mode (pip install -e .).pip install ., it may be preferable to run the script directly using python mm_segment.py.
+
+ + My research focuses on understanding how muscle morphology and quality relate to pain, function, and recovery across a range of clinical and athletic populations. MuscleMap has been an integral tool in several of my projects to date. I have used the platform to quantify changes in paraspinal and gluteal muscle morphology following exercise interventions in individuals with chronic low back pain, to investigate the relationship between paraspinal muscle strength and muscle structure, and to characterize cervical muscle morphology in athletes with and without concussion. MuscleMap has provided consistent, high-quality, and reproducible measures that have strengthened the scientific rigor of these studies. I am also planning to use the platform in an upcoming project examining leg muscle morphology in individuals with COPD. The MuscleMap consortium is collaborative, innovative, and deeply committed to advancing musculoskeletal research through cutting-edge imaging analysis methods. MuscleMap is a valuable asset to my work and catalyst for new scientific insight. +
++ My research explores the effects of metabolic benefits from weight loss therapies, and my research team is particularly interested in the relationship between adipose tissue (fat), muscle and cardiovascular health. The MuscleMap is being used in our current study investigating the effects of weight reduction with tirzepatide on muscle composition, and muscle function. The MuscleMap consortium is collaborative, invested in discovering new evidence, and forward thinking in using the most novel and innovative technologies. +
++ My research examines the effects of human deconditioning. In particular, I investigate lumbopelvic deconditioning and low back pain using a range of methodologies, including magnetic resonance imaging, electromyography, kinematic analysis, and functional tasks. MuscleMap is currently used in my ongoing studies investigating the effects of spaceflight and bed rest as a spaceflight analogue. The platform provides a robust and innovative framework for quantitative muscle and fat analysis, which is essential for addressing our research questions. The MuscleMap consortium is highly collaborative, strongly committed to generating new scientific evidence, and forward-thinking in its adoption of novel, cutting-edge technologies. I see MuscleMap as a valuable and evolving tool for musculoskeletal research in both clinical and spaceflight contexts. +
+