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

Purpose: To develop a machine learning-based, 3D dose prediction methodologyfor Gamma Knife (GK) radiosurgery. The methodology accounts for cases involvingtargets of any number, size, and shape. Methods: Data from 322 GK treatmentplans was modified by isolating and cropping the contoured MRI and clinicaldose distributions based on tumor location, then scaling the resulting tumorspaces to a standard size. An accompanying 3D tensor was created for eachinstance to account for tumor size. The modified dataset for 272 patients wasused to train both a generative adversarial network (GAN-GK) and a 3D U-Netmodel (U-Net-GK). Unmodified data was used to train equivalent baseline models.All models were used to predict the dose distribution of 50 out-of-samplepatients. Prediction accuracy was evaluated using gamma, with criteria of4%/2mm, 3%/3mm, 3%/1mm and 1%/1mm. Prediction quality was assessed usingcoverage, selectivity, and conformity indices. Results: The predictionsresulting from GAN-GK and U-Net-GK were similar to their clinical counterparts,with average gamma (4%/2mm) passing rates of 84.9 and 83.1, respectively. Incontrast, the gamma passing rate of baseline models were significantly worsethan their respective GK-specific models (p < 0.001) at all criterion levels.The quality of GK-specific predictions was also similar to that of clinicalplans. Conclusion: Deep learning models can use GK-specific data modificationto predict 3D dose distributions for GKRS plans with a large range in size,shape, or number of targets. Standard deep learning models applied tounmodified GK data generated poorer predictions.

3D dose prediction for Gamma Knife radiosurgery using deep learning and data modification