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/

Zendy Plus

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

Zendy Tools

Zendy Open

Deep model-based architectures (DMBAs) integrating physical measurementmodels and learned image regularizers are widely used in parallel magneticresonance imaging (PMRI). Traditional DMBAs for PMRI rely on pre-estimated coilsensitivity maps (CSMs) as a component of the measurement model. However,estimation of accurate CSMs is a challenging problem when measurements arehighly undersampled. Additionally, traditional training of DMBAs requireshigh-quality groundtruth images, limiting their use in applications wheregroundtruth is difficult to obtain. This paper addresses these issues bypresenting SPICE as a new method that integrates self-supervised learning andautomatic coil sensitivity estimation. Instead of using pre-estimated CSMs,SPICE simultaneously reconstructs accurate MR images and estimates high-qualityCSMs. SPICE also enables learning from undersampled noisy measurements withoutany groundtruth. We validate SPICE on experimentally collected data, showingthat it can achieve state-of-the-art performance in highly accelerated dataacquisition settings (up to 10x).

SPICER: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation and Reconstruction