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

This work aims to study the generalizability of a pre-developed deep learning(DL) dose prediction model for volumetric modulated arc therapy (VMAT) forprostate cancer and to adapt the model to three different internal treatmentplanning styles and one external institution planning style. We built thesource model with planning data from 108 patients previously treated with VMATfor prostate cancer. For the transfer learning, we selected patient casesplanned with three different styles from the same institution and one stylefrom a different institution to adapt the source model to four target models.We compared the dose distributions predicted by the source model and the targetmodels with the clinical dose predictions and quantified the improvement in theprediction quality for the target models over the source model using the Dicesimilarity coefficients (DSC) of 10% to 100% isodose volumes and thedose-volume-histogram (DVH) parameters of the planning target volume and theorgans-at-risk. The source model accurately predicts dose distributions forplans generated in the same source style but performs sub-optimally for thethree internal and one external target styles, with the mean DSC rangingbetween 0.81-0.94 and 0.82-0.91 for the internal and the external styles,respectively. With transfer learning, the target model predictions improved themean DSC to 0.88-0.95 and 0.92-0.96 for the internal and the external styles,respectively. Target model predictions significantly improved the accuracy ofthe DVH parameter predictions to within 1.6%. We demonstrated modelgeneralizability for DL-based dose prediction and the feasibility of usingtransfer learning to solve this problem. With 14-29 cases per style, wesuccessfully adapted the source model into several different practice styles.This indicates a realistic way to widespread clinical implementation ofDL-based dose prediction.

Dose Prediction with Deep Learning for Prostate Cancer Radiation Therapy: Model Adaptation to Different Treatment Planning Practices