English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Quantitative mapping of magnetic resonance (MR) parameters have been shown asvaluable methods for improved assessment of a range of diseases. Due to theneed to image an anatomic structure multiple times, parameter mapping usuallyrequires long scan times compared to conventional static imaging. Therefore,accelerated parameter mapping is highly-desirable and remains a topic of greatinterest in the MR research community. While many recent deep learning methodshave focused on highly efficient image reconstruction for conventional staticMR imaging, applications of deep learning for dynamic imaging and in particularaccelerated parameter mapping have been limited. The purpose of this work wasto develop and evaluate a novel deep learning-based reconstruction frameworkcalled Model-Augmented Neural neTwork with Incoherent k-space Sampling (MANTIS)for efficient MR parameter mapping. Our approach combines end-to-end CNNmapping with k-space consistency using the concept of cyclic loss to furtherenforce data and model fidelity. Incoherent k-space sampling is used to improvereconstruction performance. A physical model is incorporated into the proposedframework, so that the parameter maps can be efficiently estimated directlyfrom undersampled images. The performance of MANTIS was demonstrated for thespin-spin relaxation time (T2) mapping of the knee joint. Compared toconventional reconstruction approaches that exploited image sparsity, MANTISyielded lower errors and higher similarity with respect to the reference in theT2 estimation. Our study demonstrated that the proposed MANTIS framework, witha combination of end-to-end CNN mapping, signal model-augmented dataconsistency, and incoherent k-space sampling, represents a promising approachfor efficient MR parameter mapping. MANTIS can potentially be extended to othertypes of parameter mapping with appropriate models.

MANTIS: Model-Augmented Neural neTwork with Incoherent k-space Sampling for efficient MR T2 mapping