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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The treatment planning process for patients with head and neck (H&N) canceris regarded as one of the most complicated due to large target volume, multipleprescription dose levels, and many radiation-sensitive critical structures nearthe target. Treatment planning for this site requires a high level of humanexpertise and a tremendous amount of effort to produce personalized highquality plans, taking as long as a week, which deteriorates the chances oftumor control and patient survival. To solve this problem, we propose toinvestigate a deep learning-based dose prediction model, Hierarchically DenselyConnected U-net, based on two highly popular network architectures: U-net andDenseNet. We find that this new architecture is able to accurately andefficiently predict the dose distribution, outperforming the other two models,the Standard U-net and DenseNet, in homogeneity, dose conformity, and dosecoverage on the test data. Averaging across all organs at risk, our proposedmodel is capable of predicting the organ-at-risk max dose within 6.3% and meandose within 5.1% of the prescription dose on the test data. The other models,the Standard U-net and DenseNet, performed worse, having an averagedorgan-at-risk max dose prediction error of 8.2% and 9.3%, respectively, andaveraged mean dose prediction error of 6.4% and 6.8%, respectively. Inaddition, our proposed model used 12 times less trainable parameters than theStandard U-net, and predicted the patient dose 4 times faster than DenseNet.

physics in medicine and biology/physics in medicine and biology

Three-Dimensional Radiotherapy Dose Prediction on Head and Neck Cancer  Patients with a Hierarchically Densely Connected U-net Deep Learning  Architecture