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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Radiation therapy serves as an effective and standard method for cancertreatment. Excellent radiation therapy plans always rely on high-quality dosedistribution maps obtained through repeated trial and error by experiencedexperts. However, due to individual differences and complex clinicalsituations, even seasoned expert teams may need help to achieve the besttreatment plan every time quickly. Many automatic dose distribution predictionmethods have been proposed recently to accelerate the radiation therapyplanning process and have achieved good results. However, these results sufferfrom over-smoothing issues, with the obtained dose distribution maps needingmore high-frequency details, limiting their clinical application. To addressthese limitations, we propose a dose prediction diffusion model based onSwinTransformer and a projector, SP-DiffDose. To capture the direct correlationbetween anatomical structure and dose distribution maps, SP-DiffDose uses astructural encoder to extract features from anatomical images, then employs aconditional diffusion process to blend noise and anatomical images at multiplescales and gradually map them to dose distribution maps. To enhance the doseprediction distribution for organs at risk, SP-DiffDose utilizesSwinTransformer in the deeper layers of the network to capture features atdifferent scales in the image. To learn good representations from the fusedfeatures, SP-DiffDose passes the fused features through a designed projector,improving dose prediction accuracy. Finally, we evaluate SP-DiffDose on aninternal dataset. The results show that SP-DiffDose outperforms existingmethods on multiple evaluation metrics, demonstrating the superiority andgeneralizability of our method.

SP-DiffDose: A Conditional Diffusion Model for Radiation Dose Prediction  Based on Multi-Scale Fusion of Anatomical Structures, Guided by  SwinTransformer and Projector