Unknown

Dataset Information

0

Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating Optimization.


ABSTRACT: Accelerated multi-coil magnetic resonance imaging reconstruction has seen a substantial recent improvement combining compressed sensing with deep learning. However, most of these methods rely on estimates of the coil sensitivity profiles, or on calibration data for estimating model parameters. Prior work has shown that these methods degrade in performance when the quality of these estimators are poor or when the scan parameters differ from the training conditions. Here we introduce Deep J-Sense as a deep learning approach that builds on unrolled alternating minimization and increases robustness: our algorithm refines both the magnetization (image) kernel and the coil sensitivity maps. Experimental results on a subset of the knee fastMRI dataset show that this increases reconstruction performance and provides a significant degree of robustness to varying acceleration factors and calibration region sizes.

SUBMITTER: Arvinte M 

PROVIDER: S-EPMC8767765 | biostudies-literature | 2021 Sep-Oct

REPOSITORIES: biostudies-literature

altmetric image

Publications

Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating Optimization.

Arvinte Marius M   Vishwanath Sriram S   Tewfik Ahmed H AH   Tamir Jonathan I JI  

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention 20210921


Accelerated multi-coil magnetic resonance imaging reconstruction has seen a substantial recent improvement combining compressed sensing with deep learning. However, most of these methods rely on estimates of the coil sensitivity profiles, or on calibration data for estimating model parameters. Prior work has shown that these methods degrade in performance when the quality of these estimators are poor or when the scan parameters differ from the training conditions. Here we introduce Deep J-Sense  ...[more]

Similar Datasets

| S-EPMC5311996 | biostudies-literature
| S-EPMC8095163 | biostudies-literature
| S-EPMC10716161 | biostudies-literature
| S-EPMC5424476 | biostudies-literature
| S-EPMC11790796 | biostudies-literature
| S-EPMC10703008 | biostudies-literature
| S-EPMC5876102 | biostudies-literature
| S-EPMC6435424 | biostudies-literature
| S-EPMC8331070 | biostudies-literature
| S-EPMC4200604 | biostudies-literature