SRDTI: Deep learning-based super-resolution for diffusion tensor MRI
This work addresses the challenge of long scan times and limited signal-to-noise for high-resolution DTI in neuroimaging, but it is incremental as it applies existing deep learning techniques to a specific domain.
The authors tackled the problem of acquiring high-resolution diffusion tensor MRI (DTI) by proposing SRDTI, a deep learning-based super-resolution method that synthesizes high-resolution diffusion-weighted images from low-resolution inputs, achieving results more similar to ground truth than traditional interpolation methods.
High-resolution diffusion tensor imaging (DTI) is beneficial for probing tissue microstructure in fine neuroanatomical structures, but long scan times and limited signal-to-noise ratio pose significant barriers to acquiring DTI at sub-millimeter resolution. To address this challenge, we propose a deep learning-based super-resolution method entitled "SRDTI" to synthesize high-resolution diffusion-weighted images (DWIs) from low-resolution DWIs. SRDTI employs a deep convolutional neural network (CNN), residual learning and multi-contrast imaging, and generates high-quality results with rich textural details and microstructural information, which are more similar to high-resolution ground truth than those from trilinear and cubic spline interpolation.