brainchop
brainchop copied to clipboard
Brainchop: In-browser 3D MRI rendering and segmentation
Brainchop.org
![tfjs](https://img.shields.io/badge/tfjs-Pre--trained%20Model-blue)
![](https://github.com/neuroneural/brainchop/blob/master/css/logo/brainchop_logo.png)
Brainchop.org brings automatic 3D MRI volumetric segmentation capability to neuroimaging by running a deep learning model in the web-browser on the user side.
We make implementation of brainchop.org freely available releasing its pure javascript code as open-source. The user interface (UI) provides a web-based end-to-end solution for 3D MRI segmentation. Papaya integrated for MRI view. In version 1.3.0 Three.js is used for MRI 3D rendering. For more information on brainchop please refer to this Wiki and this Blog . For questions or sharing ideas please refere to our Discussions board.
brainchop high-level architecture
Meshnet deep learning architecture
Live Demo
To see the tool in action please click here.
Updates
brainchop V1.3.0 rendering segmentation output in 3D
brainchop V1.4.0 rendering MRI Nifti file in 3D
Citation
Mohamed Masoud, Farfalla Hu and Sergey Plis. (2022). Brainchop.org : In-browser deep learning framework for volumetric neuroimaging. Zenodo. https://doi.org/10.5281/zenodo.6565234
Funding
This work was funded by the NIH grant RF1MH121885. Additional support from NIH R01MH123610, R01EB006841 and NSF 2112455.
Mohamed Masoud - Sergey Plis - 2022