Learning Deep Linearal Transforms for MRI Reconstruction

Home

Discover

Bookmarks

Keep Up With Top Trending Papers In CS / AI / ML ...

Source arXiv

Computer Vision

Machine Learning

Image and Video Processing

Signal Processing

Medical Physics

Learning Deep Linearal Transforms for MRI Reconstruction

Accelerated MRI With Deep Linear Convolutional Transform Learning

We combine ideas from compressed sensing, transform learning and deep learning reconstructions to learn deep linear convolutional transforms as part of an algorithm unrolling approach.

Using end-to-end training, our results show that the proposed technique can reconstruct mr images to a level comparable to deep learning methods, while supporting uniform undersampling patterns unlike conventional compressed sensing methods.

Our proposed method relies on convex sparse image reconstruction with linear representation at inference time, which may be beneficial for characterizing robustness, stability and generalizability.