MR Slice Profile Estimation by Learning to Match Internal Patch Distributions
This work addresses a specific bottleneck in medical imaging for MRI analysis, offering an incremental improvement by enabling more accurate super-resolution without assumptions about the slice profile.
The paper tackles the problem of estimating the slice selection profile in multi-slice 2D MR images, which is crucial for super-resolution, by learning to match internal patch distributions without external data, resulting in a method that improves super-resolution algorithms and serves as a resolution measurement tool.
To super-resolve the through-plane direction of a multi-slice 2D magnetic resonance (MR) image, its slice selection profile can be used as the degeneration model from high resolution (HR) to low resolution (LR) to create paired data when training a supervised algorithm. Existing super-resolution algorithms make assumptions about the slice selection profile since it is not readily known for a given image. In this work, we estimate a slice selection profile given a specific image by learning to match its internal patch distributions. Specifically, we assume that after applying the correct slice selection profile, the image patch distribution along HR in-plane directions should match the distribution along the LR through-plane direction. Therefore, we incorporate the estimation of a slice selection profile as part of learning a generator in a generative adversarial network (GAN). In this way, the slice selection profile can be learned without any external data. Our algorithm was tested using simulations from isotropic MR images, incorporated in a through-plane super-resolution algorithm to demonstrate its benefits, and also used as a tool to measure image resolution. Our code is at https://github.com/shuohan/espreso2.