Published March 22, 2023 | Version v2.1.0
Software Open

Brainchop: In-browser MRI volumetric segmentation and rendering

  • 1. Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS)
  • 2. Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), and Department of Computer Science, Georgia State University.

Description

Brainchop is a client-side web-application  for automatic segmentation of MRI volumes that brings automatic volumetric  segmentation    capability to neuroimaging  by running a robustly pre-trained deep learning model. The app does not require technical sophistication from the user and is designed for  locally and privately segmenting user’s T1 volumes.  Results of the segmentation may be easily saved locally after the computation. An intuitive interactive interface that does not require any special training nor specific instruction to run enables access to a state of the art deep learning brain segmentation for anyone with a modern browser (e.g. Firefox, Chrome etc) and commonly available hardware. Additionally, we make implementation of brainchop freely available releasing its pure Javascript code as open-source.


Online Demo: brainchop.org
Source: Github Repo

Doc: Github Wiki
For local setup please follow these instructions

In v2.1.0,  brainchop code and paper revised as per Journal of Open Source Software (JOSS) reviewers requested.

Notes

Brainchop was funded by the NIH grant RF1MH121885. Additional support from NIH R01MH123610, R01EB006841 and NSF 2112455.

Files

brainchop-v2.1.0.zip

Files (148.7 MB)

Name Size Download all
md5:a99c12151a96d067a7795ba03d587ca5
148.7 MB Preview Download

Additional details

Related works

Is published in
Journal article: 10.21105/joss.05098 (DOI)