Eddeep: Fast eddy-current distortion correction for diffusion MRI with deep learning
This work addresses a critical preprocessing bottleneck for diffusion MRI in clinical settings, enabling faster correction and potentially wider adoption, though it is incremental as it builds on existing correction methods with a new deep learning implementation.
The paper tackles the problem of eddy-current distortion correction in diffusion MRI, which causes misalignment between volumes and disrupts analysis, by proposing a deep learning approach using two convolutional neural networks to restore correspondence and align images, achieving comparable distortion estimates to the existing FSL Eddy tool with modest training sample sizes.
Modern diffusion MRI sequences commonly acquire a large number of volumes with diffusion sensitization gradients of differing strengths or directions. Such sequences rely on echo-planar imaging (EPI) to achieve reasonable scan duration. However, EPI is vulnerable to off-resonance effects, leading to tissue susceptibility and eddy-current induced distortions. The latter is particularly problematic because it causes misalignment between volumes, disrupting downstream modelling and analysis. The essential correction of eddy distortions is typically done post-acquisition, with image registration. However, this is non-trivial because correspondence between volumes can be severely disrupted due to volume-specific signal attenuations induced by varying directions and strengths of the applied gradients. This challenge has been successfully addressed by the popular FSL~Eddy tool but at considerable computational cost. We propose an alternative approach, leveraging recent advances in image processing enabled by deep learning (DL). It consists of two convolutional neural networks: 1) An image translator to restore correspondence between images; 2) A registration model to align the translated images. Results demonstrate comparable distortion estimates to FSL~Eddy, while requiring only modest training sample sizes. This work, to the best of our knowledge, is the first to tackle this problem with deep learning. Together with recently developed DL-based susceptibility correction techniques, they pave the way for real-time preprocessing of diffusion MRI, facilitating its wider uptake in the clinic.