Progressive Subsampling for Oversampled Data - Application to Quantitative MRI

TL;DR

PROSUB is a deep learning method that progressively subsamples oversampled data, such as multi-channeled 3D MRI images, with minimal information loss, improving stability and performance over previous approaches.

Contribution

It introduces a recursive feature elimination approach combined with neural architecture search to enhance subsampling stability and accuracy in MRI measurement reconstruction.

Findings

Outperforms the MICCAI MUDI challenge winner with >18% MSE improvement

Provides qualitative improvements for clinical downstream applications

Demonstrates generalizability beyond MRI measurement selection-reconstruction

Abstract

We present PROSUB: PROgressive SUBsampling, a deep learning based, automated methodology that subsamples an oversampled data set (e.g. multi-channeled 3D images) with minimal loss of information. We build upon a recent dual-network approach that won the MICCAI MUlti-DIffusion (MUDI) quantitative MRI measurement sampling-reconstruction challenge, but suffers from deep learning training instability, by subsampling with a hard decision boundary. PROSUB uses the paradigm of recursive feature elimination (RFE) and progressively subsamples measurements during deep learning training, improving optimization stability. PROSUB also integrates a neural architecture search (NAS) paradigm, allowing the network architecture hyperparameters to respond to the subsampling process. We show PROSUB outperforms the winner of the MUDI MICCAI challenge, producing large improvements >18% MSE on the MUDI challenge sub-tasks and qualitative improvements on downstream processes useful for clinical applications. We also show the benefits of incorporating NAS and analyze the effect of PROSUB's components. As our method generalizes to other problems beyond MRI measurement selection-reconstruction, our code is https://github.com/sbb-gh/PROSUB