Deep learning-based local SAR prediction using B₁ maps and structural MRI of the head for parallel transmission at 7 T.

ABSTRACT:

Purpose

To predict subject-specific local specific absorption rate (SAR) distributions of the human head for parallel transmission (pTx) systems at 7 T.

Theory and methods

Electromagnetic energy deposition in tissues is nonuniform at 7 T, and interference patterns due to individual channels of pTx systems may result in increased local SAR values, which can only be estimated with very high safety margins. We proposed, designed, and demonstrated a multichannel 3D convolutional neural network (CNN) architecture to predict local SAR maps as well as peak-spatial SAR (ps-SAR) levels. We hypothesized that utilizing a three-channel 3D CNN, in which each channel is fed by a B 1 + $$ {B}_1^{+} $$ map, a phase-reversed B 1 + $$ {B}_1^{+} $$ map, and an MR image, would improve p

SUBMITTER: Gokyar S 

PROVIDER: S-EPMC10543469 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature