Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection Transformers
The authors reframe characterizing white matter microstructure—fiber orientation and compartment structure—as an object detection task using a Detection Transformer (DETR) architecture. They jointly predict mean diffusivity (MD), fractional anisotropy (FA), main fiber direction, and signal fraction for a variable number of compartments from multi-shell diffusion MRI data. This method successfully recovers full sets of compartmental parameters without assuming fixed counts or solving complex inverse transforms.