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

Organ at risk (OAR) segmentation is a crucial step for treatment planning andoutcome determination in radiotherapy treatments of cancer patients. Severaldeep learning based segmentation algorithms have been developed in recentyears, however, U-Net remains the de facto algorithm designed specifically forbiomedical image segmentation and has spawned many variants with knownweaknesses. In this study, our goal is to present simple architectural changesin U-Net to improve its accuracy and generalization properties. Unlike manyother available studies evaluating their algorithms on single center data, wethoroughly evaluate several variations of U-Net as well as our proposedenhanced architecture on multiple data sets for an extensive and reliable studyof the OAR segmentation problem. Our enhanced segmentation model includes(a)architectural changes in the loss function, (b)optimization framework, and(c)convolution type. Testing on three publicly available multi-objectsegmentation data sets, we achieved an average of 80% dice score compared tothe baseline U-Net performance of 63%.

Enhancing Organ at Risk Segmentation with Improved Deep Neural Networks