Year: 2025
Type: preprint
Abstract: Deployment complexity and specialized hardware requirements hinder the adoption of deep learning models in neuroimaging. We present MindGrab, a lightweight, fully convolutional model for volumetric skull stripping across all imaging modalities. MindGrab's architecture is designed from first principles using a spectral interpretation of dilated convolutions, and demonstrates state-of-the-art performance (mean Dice score across datasets and modalities: 95.9 with SD 1.6), with up to 40-fold speedups and substantially lower memory demands compared to established methods. Its minimal footprint allows for fast, full-volume processing in resource-constrained environments, including direct in-browser execution. MindGrab is delivered via the BrainChop platform as both a simple command-line tool (pip install brainchop) and a zero-installation web application (brainchop.org). By removing traditional deployment barriers without sacrificing accuracy, MindGrab makes state-of-the-art neuroimaging analysis broadly accessible.
Source: arXiv (Cornell University)
Authors: Fani, Armina, Doan, Mike, Le, Isabelle, Fedorov, Alex, Hoffmann, Malte, Rorden, Chris, Plis, Sergey
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415069606
Cites:
Cited by:
Related to: