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

Free Point Transformer (FPT) has been proposed as a data-driven, non-rigidpoint set registration approach using deep neural networks. As FPT does notassume constraints based on point vicinity or correspondence, it may be trainedsimply and in a flexible manner by minimizing an unsupervised loss based on theChamfer Distance. This makes FPT amenable to real-world medical imagingapplications where ground-truth deformations may be infeasible to obtain, or inscenarios where only a varying degree of completeness in the point sets to bealigned is available. To test the limit of the correspondence finding abilityof FPT and its dependency on training data sets, this work explores thegeneralizability of the FPT from well-curated non-medical data sets to medicalimaging data sets. First, we train FPT on the ModelNet40 dataset to demonstrateits effectiveness and the superior registration performance of FPT overiterative and learning-based point set registration methods. Second, wedemonstrate superior performance in rigid and non-rigid registration androbustness to missing data. Last, we highlight the interesting generalizabilityof the ModelNet-trained FPT by registering reconstructed freehand ultrasoundscans of the spine and generic spine models without additional training,whereby the average difference to the ground truth curvatures is 1.3 degrees,across 13 patients.

Learning Generalized Non-Rigid Multimodal Biomedical Image Registration from Generic Point Set Data