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 and objective: MeshCNN is a recently proposed Deep Learningframework that drew attention due to its direct operation on irregular,non-uniform 3D meshes. On selected benchmarking datasets, it outperformedstate-of-the-art methods within classification and segmentation tasks.Especially, the medical domain provides a large amount of complex 3D surfacemodels that may benefit from processing with MeshCNN. However, severallimitations prevent outstanding performances of MeshCNN on highly diversemedical surface models. Within this work, we propose MedMeshCNN as an expansionfor complex, diverse, and fine-grained medical data. Methods: MedMeshCNNfollows the functionality of MeshCNN with a significantly increased memoryefficiency that allows retaining patient-specific properties during thesegmentation process. Furthermore, it enables the segmentation of pathologicalstructures that often come with highly imbalanced class distributions. Results:We tested the performance of MedMeshCNN on a complex part segmentation task ofintracranial aneurysms and their surrounding vessel structures and reached amean Intersection over Union of 63.24\%. The pathological aneurysm is segmentedwith an Intersection over Union of 71.4\%. Conclusions: These resultsdemonstrate that MedMeshCNN enables the application of MeshCNN on complex,fine-grained medical surface meshes. The imbalanced class distribution derivingfrom the pathological finding is considered by MedMeshCNN and patient-specificproperties are mostly retained during the segmentation process.

MedMeshCNN -- Enabling MeshCNN for Medical Surface Models