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

Modern deep unsupervised learning methods have shown great promise fordetecting diseases across a variety of medical imaging modalities. Whileprevious generative modeling approaches successfully perform anomaly detectionby learning the distribution of healthy 2D image slices, they process suchslices independently and ignore the fact that they are correlated, all beingsampled from a 3D volume. We show that incorporating the 3D context andprocessing whole-body MRI volumes is beneficial to distinguishing anomaliesfrom their benign counterparts. In our work, we introduce a multi-channelsliding window generative model to perform lesion detection in whole-body MRI(wbMRI). Our experiments demonstrate that our proposed method significantlyoutperforms processing individual images in isolation and our ablations clearlyshow the importance of 3D reasoning. Moreover, our work also shows that it isbeneficial to include additional patient-specific features to further improveanomaly detection in pediatric scans.

3D Reasoning for Unsupervised Anomaly Detection in Pediatric WbMRI