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

Accurate organ at risk (OAR) segmentation is critical to reduce theradiotherapy post-treatment complications. Consensus guidelines recommend a setof more than 40 OARs in the head and neck (H&N) region, however, due to thepredictable prohibitive labor-cost of this task, most institutions choose asubstantially simplified protocol by delineating a smaller subset of OARs andneglecting the dose distributions associated with other OARs. In this work wepropose a novel, automated and highly effective stratified OAR segmentation(SOARS) system using deep learning to precisely delineate a comprehensive setof 42 H&N OARs. SOARS stratifies 42 OARs into anchor, mid-level, and small &hard subcategories, with specifically derived neural network architectures foreach category by neural architecture search (NAS) principles. We built SOARSmodels using 176 training patients in an internal institution and independentlyevaluated on 1327 external patients across six different institutions. Itconsistently outperformed other state-of-the-art methods by at least 3-5% inDice score for each institutional evaluation (up to 36% relative errorreduction in other metrics). More importantly, extensive multi-user studiesevidently demonstrated that 98% of the SOARS predictions need only very minoror no revisions for direct clinical acceptance (saving 90% radiationoncologists workload), and their segmentation and dosimetric accuracy arewithin or smaller than the inter-user variation. These findings confirmed thestrong clinical applicability of SOARS for the OAR delineation process in H&Ncancer radiotherapy workflows, with improved efficiency, comprehensiveness, andquality.

Comprehensive and Clinically Accurate Head and Neck Organs at Risk Delineation via Stratified Deep Learning: A Large-scale Multi-Institutional Study