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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Tissue characterisation with CMR parametric mapping has the potential todetect and quantify both focal and diffuse alterations in myocardial structurenot assessable by late gadolinium enhancement. Native T1 mapping in particularhas shown promise as a useful biomarker to support diagnostic, therapeutic andprognostic decision-making in ischaemic and non-ischaemic cardiomyopathies.Convolutional neural networks with Bayesian inference are a category ofartificial neural networks which model the uncertainty of the network output.This study presents an automated framework for tissue characterisation fromnative ShMOLLI T1 mapping at 1.5T using a Probabilistic HierarchicalSegmentation (PHiSeg) network. In addition, we use the uncertainty informationprovided by the PHiSeg network in a novel automated quality control (QC) stepto identify uncertain T1 values. The PHiSeg network and QC were validatedagainst manual analysis on a cohort of the UK Biobank containing healthysubjects and chronic cardiomyopathy patients. We used the proposed method toobtain reference T1 ranges for the left ventricular myocardium in healthysubjects as well as common clinical cardiac conditions. T1 values computed fromautomatic and manual segmentations were highly correlated (r=0.97).Bland-Altman analysis showed good agreement between the automated and manualmeasurements. The average Dice metric was 0.84 for the left ventricularmyocardium. The sensitivity of detection of erroneous outputs was 91%. Finally,T1 values were automatically derived from 14,683 CMR exams from the UK Biobank.The proposed pipeline allows for automatic analysis of myocardial native T1mapping and includes a QC process to detect potentially erroneous results. T1reference values were presented for healthy subjects and common clinicalcardiac conditions from the largest cohort to date using T1-mapping images.

journal of cardiovascular magnetic resonance

Automated quantification of myocardial tissue characteristics from  native T1 mapping using neural networks with Bayesian inference for  uncertainty-based quality-control