Dose-PlanNet: Physics Based Radiotherapy Dose Prediction with Deep Learning

Abstract:Automating prostate radiotherapy treatment planning is dosimetrically complex, particularly for extreme hypofractionated regimens. In this study, we introduce Dose-PlanNet, a physics-guided 3D deep learning architecture designed to predict dose distributions. This model's performance was evaluated on a cohort of patients treated in a prospective trial where two different dose fractionation regimens were employed. Dose-PlanNet achieved comparable target coverage ($D_{95}$), though statistical analysis revealed a marginal reduction in target homogeneity ($p<0.001$) offset. However the model achieved statistically significant improvements in high-dose organ-at-risk sparing ($p<0.001$). When evaluated against strict Prospective Randomized protocol volumetric constraints, automated plans met prespecified clinical acceptance criteria in $11$ out of $14$ Moderate Hypofraction Arm plans and $9$ out of $12$ Stereotactic Body Radiation Therapy Arm plans. This pipeline demonstrates that physics-informed deep learning can accelerate radiotherapy workflows while safely maintaining the stringent dosimetric quality required for high-precision clinical deployment.

The paper consists of 22 pages, 4 figures, 6 tables. The end-to-end pipeline of Dose-PlanNet will soon be made available on the GitHub repository of CHAVI-India (this https URL)

Medical Physics (physics.med-ph); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

arXiv:2608.26901 [physics.med-ph]

(or arXiv:2608.26901v1 [physics.med-ph] for this version)

https://doi.org/10.48550/arXiv.2608.26901 arXiv-issued DOI via DataCite (pending registration)