Clinical DVH metrics as a loss function for 3D dose prediction in head and neck radiotherapy
Authors:
Open Access
- 13 August 2026
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 21 (11) , 2363-2373
Abstract
Purpose: Deep learning-based three-dimensional (3D) dose prediction is widely used in automated radiotherapy workflows. However, most existing models are trained with voxel-wise regression losses, which are poorly aligned with clinical plan evaluation criteria based on dose–volume histogram (DVH) metrics. This study aims to develop a clinically guided loss formulation that directly optimizes clinically used DVH metrics while remaining computationally efficient for head and neck (H&N) dose prediction. Methods: We propose a clinical DVH metric loss (CDM loss) that incorporates differentiable D-metrics and surrogate V-metrics , together with a lossless bit-mask region-of-interest (ROI) encoding to improve training efficiency. The method was evaluated on 174 H&N patients using a temporal split (137 training, 37 testing). Results: Compared with MAE- and DVH curve-based losses, CDM loss substantially improved target coverage and satisfied all clinical constraints. Using a standard 3D U-Net, the PTV Score was reduced from 1.544 (MAE) to 0.491 (MAE + CDM), while OAR sparing remained comparable. Bit-mask encoding reduced training time by 82.2% and lowered GPU memory usage. Conclusion: Directly optimizing clinically used DVH metrics enables 3D dose predictions that are better aligned with clinical treatment planning criteria than conventional voxel-wise or DVH curve-based supervision. The proposed CDM loss, combined with efficient ROI bit-mask encoding, provides a practical and scalable framework for H&N dose prediction.Keywords
All Related Versions
Funding Information
- China Scholarship Council (202207720085)
This publication has 14 references indexed in Scilit:
- Beam-wise dose composition learning for head and neck cancer dose prediction in radiotherapyMedical Image Analysis, 2023
- MedNeXt: Transformer-Driven Scaling of ConvNets for Medical Image Segmentation2023
- Deep Learning-Based Head and Neck Radiotherapy Planning Dose Prediction via Beam-Wise Dose Decomposition2022
- Domain knowledge driven 3D dose prediction using moment-based loss functionPhysics in Medicine & Biology, 2022
- Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images2022
- OpenKBP: The open‐access knowledge‐based planning grand challenge and datasetMedical Physics, 2021
- Technical Note: A cascade 3D U‐Net for dose prediction in radiotherapyMedical Physics, 2021
- Development and evaluation of radiotherapy deep learning dose prediction models for breast cancerPhysics and Imaging in Radiation Oncology, 2021
- Incorporating human and learned domain knowledge into training deep neural networks: A differentiable dose‐volume histogram and adversarial inspired framework for generating Pareto optimal dose distributions in radiation therapyMedical Physics, 2019
- Interobserver variability in radiation therapy plan output: Results of a single-institution studyPractical Radiation Oncology, 2016