AxonNet: A self-supervised Deep Neural Network for Intravoxel Structure Estimation from DW-MRI
This addresses the challenge of reconstructing cerebral tracts from DW-MRI data for medical imaging applications, but it is incremental as it builds on existing deep learning techniques with a self-supervised strategy.
The paper tackles the problem of estimating intravoxel parameters from diffusion-weighted MRI using deep learning, achieving competitive results and faster computational times than state-of-the-art methods, with speed advantages increasing for multiple image predictions.
We present a method for estimating intravoxel parameters from a DW-MRI based on deep learning techniques. We show that neural networks (DNNs) have the potential to extract information from diffusion-weighted signals to reconstruct cerebral tracts. We present two DNN models: one that estimates the axonal structure in the form of a voxel and the other to calculate the structure of the central voxel using the voxel neighborhood. Our methods are based on a proposed parameter representation suitable for the problem. Since it is practically impossible to have real tagged data for any acquisition protocol, we used a self-supervised strategy. Experiments with synthetic data and real data show that our approach is competitive, and the computational times show that our approach is faster than the SOTA methods, even if training times are considered. This computational advantage increases if we consider the prediction of multiple images with the same acquisition protocol.