FOD-Swin-Net: angular super resolution of fiber orientation distribution using a transformer-based deep model
This work addresses a clinical bottleneck in brain imaging by enabling faster, high-resolution fiber orientation estimation, though it is incremental as it builds on existing transformer architectures.
The paper tackles the challenge of lengthy DW-MRI acquisitions for robust fiber orientation estimation by developing FOD-Swin-Net, a transformer-based deep learning model that achieves angular super resolution, reducing required directions from 288 to 32 while matching multi-shell reconstruction performance.
Identifying and characterizing brain fiber bundles can help to understand many diseases and conditions. An important step in this process is the estimation of fiber orientations using Diffusion-Weighted Magnetic Resonance Imaging (DW-MRI). However, obtaining robust orientation estimates demands high-resolution data, leading to lengthy acquisitions that are not always clinically available. In this work, we explore the use of automated angular super resolution from faster acquisitions to overcome this challenge. Using the publicly available Human Connectome Project (HCP) DW-MRI data, we trained a transformer-based deep learning architecture to achieve angular super resolution in fiber orientation distribution (FOD). Our patch-based methodology, FOD-Swin-Net, is able to bring a single-shell reconstruction driven from 32 directions to be comparable to a multi-shell 288 direction FOD reconstruction, greatly reducing the number of required directions on initial acquisition. Evaluations of the reconstructed FOD with Angular Correlation Coefficient and qualitative visualizations reveal superior performance than the state-of-the-art in HCP testing data. Open source code for reproducibility is available at https://github.com/MICLab-Unicamp/FOD-Swin-Net.