Inter-Scanner Harmonization of High Angular Resolution DW-MRI using Null Space Deep Learning
This work addresses the issue of scanner variability in brain imaging for medical researchers, offering a practical method to enhance reproducibility and generalizability, though it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of low reproducibility in diffusion-weighted MRI across different scanners by proposing a null space deep network (NSDN) that learns from both MRI-histology pairs and repeated scans without known truths. The result was significant improvements: absolute performance increased by 3.87% over CSD and 1.42% over a recent deep learning method, reproducibility improved by 21.19% and 10.09%, and generalizability to an unseen scanner improved by 16.08% and 10.41%.
Diffusion-weighted magnetic resonance imaging (DW-MRI) allows for non-invasive imaging of the local fiber architecture of the human brain at a millimetric scale. Multiple classical approaches have been proposed to detect both single (e.g., tensors) and multiple (e.g., constrained spherical deconvolution, CSD) fiber population orientations per voxel. However, existing techniques generally exhibit low reproducibility across MRI scanners. Herein, we propose a data-driven tech-nique using a neural network design which exploits two categories of data. First, training data were acquired on three squirrel monkey brains using ex-vivo DW-MRI and histology of the brain. Second, repeated scans of human subjects were acquired on two different scanners to augment the learning of the network pro-posed. To use these data, we propose a new network architecture, the null space deep network (NSDN), to simultaneously learn on traditional observed/truth pairs (e.g., MRI-histology voxels) along with repeated observations without a known truth (e.g., scan-rescan MRI). The NSDN was tested on twenty percent of the histology voxels that were kept completely blind to the network. NSDN significantly improved absolute performance relative to histology by 3.87% over CSD and 1.42% over a recently proposed deep neural network approach. More-over, it improved reproducibility on the paired data by 21.19% over CSD and 10.09% over a recently proposed deep approach. Finally, NSDN improved gen-eralizability of the model to a third in vivo human scanner (which was not used in training) by 16.08% over CSD and 10.41% over a recently proposed deep learn-ing approach. This work suggests that data-driven approaches for local fiber re-construction are more reproducible, informative and precise and offers a novel, practical method for determining these models.