Published July 19, 2026 | Version 1

QSM-CI method: BFRnet (v1)

Description

Deep-learning background field removal (BFRnet), a 3D Octave-convolution DAG network trained to predict the background field of the brain — including brains with significant pathological susceptibility sources (haemorrhage, calcification). Consumes the total field (ppm) and predicts the background field; the local tissue field is total − background, masked. The MATLAB Deep Learning Toolbox network is compiled with the MATLAB Compiler and run on the license-free MATLAB Runtime.

QSM-CI reconstruction method matlab-bfrnet. Browse and run it at https://qsmxt.github.io/QSM-CI/submission.html?method=matlab-bfrnet.

Files

matlab-bfrnet.zip

Files (7.4 kB)

Name Size
md5:b1545eacefb0583741e240e585722681
7.4 kB Preview Download

Additional details