Segmentation-aware MRI reconstruction

Date

2022-09-22

Editor(s)

Advisor

Supervisor

Co-Advisor

Co-Supervisor

Instructor

Source Title

Machine Learning for Medical Image Reconstruction

Print ISSN

Electronic ISSN

Publisher

Springer Cham

Volume

13587

Issue

Pages

53 - 61

Language

English

Journal Title

Journal ISSN

Volume Title

Citation Stats
Attention Stats
Usage Stats
9
views
68
downloads

Series

Lecture Notes in Computer Science;

Abstract

Deep learning models have been broadly adopted for accelerating MRI acquisitions in recent years. A common approach is to train deep models based on loss functions that place equal emphasis on reconstruction errors across the field-of-view. This homogeneous weighting of loss contributions might be undesirable in cases where the diagnostic focus is on tissues in a specific subregion of the image. In this paper, we propose a framework for segmentation-aware reconstruction based on segmentation as a proxy task. We leverage an end-to-end model comprising reconstruction and segmentation networks; and leverage backpropagation of segmentation error to devise a pseudo-attention effect to focus the reconstruction network. We introduce a novel stabilization method to prevent convergence onto a local minima with unacceptably poor reconstruction or segmentation performance. Our stabilization approach initiates learning on fully-sampled acquisitions, and gradually increases the undersampling rate assumed in the training set to its desired value. We validate our approach for cardiac MR reconstruction on the publicly available OCMR dataset. Segmentation-aware reconstruction significantly outperforms vanilla reconstruction for cardiac imaging.

Course

Other identifiers

Book Title

Degree Discipline

Degree Level

Degree Name

Citation

Published Version (Please cite this version)