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

Background: The trend towards large-scale studies including populationimaging poses new challenges in terms of quality control (QC). This is aparticular issue when automatic processing tools, e.g. image segmentationmethods, are employed to derive quantitative measures or biomarkers for lateranalyses. Manual inspection and visual QC of each segmentation isn't feasibleat large scale. However, it's important to be able to automatically detect whena segmentation method fails so as to avoid inclusion of wrong measurements intosubsequent analyses which could lead to incorrect conclusions. Methods: Toovercome this challenge, we explore an approach for predicting segmentationquality based on Reverse Classification Accuracy, which enables us todiscriminate between successful and failed segmentations on a per-cases basis.We validate this approach on a new, large-scale manually-annotated set of 4,800cardiac magnetic resonance scans. We then apply our method to a large cohort of7,250 cardiac MRI on which we have performed manual QC. Results: We reportresults used for predicting segmentation quality metrics including DiceSimilarity Coefficient (DSC) and surface-distance measures. As initialvalidation, we present data for 400 scans demonstrating 99% accuracy forclassifying low and high quality segmentations using predicted DSC scores. Asfurther validation we show high correlation between real and predicted scoresand 95% classification accuracy on 4,800 scans for which manual segmentationswere available. We mimic real-world application of the method on 7,250 cardiacMRI where we show good agreement between predicted quality metrics and manualvisual QC scores. Conclusions: We show that RCA has the potential for accurateand fully automatic segmentation QC on a per-case basis in the context oflarge-scale population imaging as in the UK Biobank Imaging Study.

Automated Quality Control in Image Segmentation: Application to the UK Biobank Cardiac MR Imaging Study