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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Image registration is a fundamental medical image analysis task, and a widevariety of approaches have been proposed. However, only a few studies havecomprehensively compared medical image registration approaches on a wide rangeof clinically relevant tasks. This limits the development of registrationmethods, the adoption of research advances into practice, and a fair benchmarkacross competing approaches. The Learn2Reg challenge addresses theselimitations by providing a multi-task medical image registration data set forcomprehensive characterisation of deformable registration algorithms. Acontinuous evaluation will be possible athttps://learn2reg.grand-challenge.org. Learn2Reg covers a wide range ofanatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR),availability of annotations, as well as intra- and inter-patient registrationevaluation. We established an easily accessible framework for training andvalidation of 3D registration methods, which enabled the compilation of resultsof over 65 individual method submissions from more than 20 unique teams. Weused a complementary set of metrics, including robustness, accuracy,plausibility, and runtime, enabling unique insight into the currentstate-of-the-art of medical image registration. This paper describes datasets,tasks, evaluation methods and results of the challenge, as well as results offurther analysis of transferability to new datasets, the importance of labelsupervision, and resulting bias. While no single approach worked best acrossall tasks, many methodological aspects could be identified that push theperformance of medical image registration to new state-of-the-art performance.Furthermore, we demystified the common belief that conventional registrationmethods have to be much slower than deep-learning-based methods.

Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning