MuscleMap

Whole-Body Muscle Segmentation
More Apps GitHub

Drop NIfTI, NIfTI labels, or DICOM files

50%
Preview unavailable (no WebGL2). Loading, segmentation and downloads still work.
Status Ready

About MuscleMap

MuscleMap icon
MuscleMap

Whole-body muscle segmentation in the browser

MuscleMap is a browser-based tool for automatic muscle segmentation from MRI or CT using an official MONAI 2D UNet model.

All computation runs locally in your browser using ONNX Runtime Web. Patient data is not uploaded to any server.

Muscle Anatomy Reference

MuscleMap muscle anatomy diagram

Version

MuscleMap
Selected model
Structures
Model DOI

Privacy

Your data never leaves your device.

MuscleMap runs entirely in your web browser using WebAssembly and ONNX Runtime. All processing occurs locally on your machine.

What this means

  • Patient images, voxel values, screenshots, and generated segmentations are not uploaded to any server or cloud service
  • No internet connection is required after the page loads
  • Sensitive patient data remains on your computer at all times
  • There is no need to anonymise or de-identify your data before use

How it works

MuscleMap uses ONNX Runtime Web to run deep learning models directly in the browser via WebAssembly. Your NIfTI or DICOM files are read into browser memory, processed locally, and results are displayed without any network transfer.

Third-party services

The Neurodesk hosting layer records page views only, unless your browser sends Do Not Track or Global Privacy Control. It does not send custom events, patient images, voxel values, screenshots, generated segmentations, filenames, or analysis results to Google Analytics. Other network requests load the application itself, runtime assets, and model files, which may be cached locally.

Citations

MuscleMap Code: GitHub

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 uses the following methods and tools:

Deep Learning Framework

MONAI

MONAI Consortium. (2020). MONAI: Medical Open Network for AI.

https://monai.io

Browser Inference

ONNX Runtime Web

Microsoft. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator.

https://onnxruntime.ai

Visualization

NiiVue

NiiVue Contributors. NiiVue: a WebGL2 medical image viewer.

https://github.com/niivue/niivue