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

As in other areas of medical image analysis, e.g. semantic segmentation, deeplearning is currently driving the development of new approaches for imageregistration. Multi-scale encoder-decoder network architectures achievestate-of-the-art accuracy on tasks such as intra-patient alignment of abdominalCT or brain MRI registration, especially when additional supervision, such asanatomical labels, is available. The success of these methods relies to a largeextent on the outstanding ability of deep CNNs to extract descriptive visualfeatures from the input images. In contrast to conventional methods, theexplicit inclusion of geometric information plays only a minor role, if at all.In this work we take a look at an exactly opposite approach by investigating adeep learning framework for registration based solely on geometric features andoptimisation. We combine graph convolutions with loopy belief message passingto enable highly accurate 3D point cloud registration. Our experimentalvalidation is conducted on complex key-point graphs of inner lung structures,strongly outperforming dense encoder-decoder networks and other point setregistration methods. Our code is publicly available athttps://github.com/multimodallearning/deep-geo-reg.

Deep learning based geometric registration for medical images: How accurate can we get without visual features?