On the predictability of B0 maps at ultra-high fields using deep learning

Vidya Prasad; Sharun  S Thazhackal; Ashvin Srinivasan; Suja Saraswathy; Jaladhar Neelavalli; Umesh Rudrapatna

On the predictability of B0 maps at ultra-high fields using deep learning

Vidya Prasad, Sharun S Thazhackal, Ashvin Srinivasan, Suja Saraswathy, Jaladhar Neelavalli, Umesh Rudrapatna

Visual Analytics

Research output: Contribution to conference › Abstract › Academic

Abstract

UHF-MRI offers increased scanning sensitivity, but suffers from pronounced B0 inhomogeneities. B0 maps are essential for shimming and reconstruction at UHFs, but suffer from scanning overhead and low measurement confidence. Predicting B0 maps from survey scans can effectively address these issues. We assessed predictability of brain B0 maps at 7T and 11.7T using deep learning on a large synthetic B0 map dataset created from 540 CT images. We found that deep learning can predict 1) spherical harmonics for shimming and 2) the complete B0 maps. Our results indicate that B0 predictions work as effectively as acquiring B0 maps for shimming.

Original language	English
Publication status	Published - 20 May 2021
Event	2021 ISMRM & SMRT Annual Meeting and Exhibition - Duration: 15 May 2021 → 20 May 2021

Other

Other	2021 ISMRM & SMRT Annual Meeting and Exhibition
Period	15/05/21 → 20/05/21

Cite this

@conference{cc08770151ba4888a3b1c719054edc2f,

title = "On the predictability of B0 maps at ultra-high fields using deep learning",

abstract = "UHF-MRI offers increased scanning sensitivity, but suffers from pronounced B0 inhomogeneities. B0 maps are essential for shimming and reconstruction at UHFs, but suffer from scanning overhead and low measurement confidence. Predicting B0 maps from survey scans can effectively address these issues. We assessed predictability of brain B0 maps at 7T and 11.7T using deep learning on a large synthetic B0 map dataset created from 540 CT images. We found that deep learning can predict 1) spherical harmonics for shimming and 2) the complete B0 maps. Our results indicate that B0 predictions work as effectively as acquiring B0 maps for shimming.",

author = "Vidya Prasad and {S Thazhackal}, Sharun and Ashvin Srinivasan and Suja Saraswathy and Jaladhar Neelavalli and Umesh Rudrapatna",

year = "2021",

month = may,

day = "20",

language = "English",

note = "2021 ISMRM & SMRT Annual Meeting and Exhibition ; Conference date: 15-05-2021 Through 20-05-2021",

}

TY - CONF

T1 - On the predictability of B0 maps at ultra-high fields using deep learning

AU - Prasad, Vidya

AU - S Thazhackal, Sharun

AU - Srinivasan, Ashvin

AU - Saraswathy, Suja

AU - Neelavalli, Jaladhar

AU - Rudrapatna, Umesh

PY - 2021/5/20

Y1 - 2021/5/20

N2 - UHF-MRI offers increased scanning sensitivity, but suffers from pronounced B0 inhomogeneities. B0 maps are essential for shimming and reconstruction at UHFs, but suffer from scanning overhead and low measurement confidence. Predicting B0 maps from survey scans can effectively address these issues. We assessed predictability of brain B0 maps at 7T and 11.7T using deep learning on a large synthetic B0 map dataset created from 540 CT images. We found that deep learning can predict 1) spherical harmonics for shimming and 2) the complete B0 maps. Our results indicate that B0 predictions work as effectively as acquiring B0 maps for shimming.

AB - UHF-MRI offers increased scanning sensitivity, but suffers from pronounced B0 inhomogeneities. B0 maps are essential for shimming and reconstruction at UHFs, but suffer from scanning overhead and low measurement confidence. Predicting B0 maps from survey scans can effectively address these issues. We assessed predictability of brain B0 maps at 7T and 11.7T using deep learning on a large synthetic B0 map dataset created from 540 CT images. We found that deep learning can predict 1) spherical harmonics for shimming and 2) the complete B0 maps. Our results indicate that B0 predictions work as effectively as acquiring B0 maps for shimming.

M3 - Abstract

T2 - 2021 ISMRM & SMRT Annual Meeting and Exhibition

Y2 - 15 May 2021 through 20 May 2021

ER -

On the predictability of B0 maps at ultra-high fields using deep learning

Abstract

Other

Fingerprint

Cite this