# Clinical DVH metrics as a loss function for 3D dose prediction in head and neck radiotherapy

arXiv: https://arxiv.org/abs/2603.29670 · HTML: https://mlsanity.com/paper/2603.29670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation](https://mlsanity.com/paper/2303.09975/) (2023)
- [OpenKBP: The open-access knowledge-based planning grand challenge](https://mlsanity.com/paper/2011.14076/) (2020)
- [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 therapy](https://mlsanity.com/paper/1908.05874/) (2019)
- [Domain Knowledge Driven 3D Dose Prediction Using Moment-Based Loss Function](https://mlsanity.com/paper/2207.03414/) (2022)
- [Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks](https://mlsanity.com/paper/2011.11559/) (2020)
- [LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction](https://mlsanity.com/paper/2106.06733/) (2021)
- [A Cascade Transformer-based Model for 3D Dose Distribution Prediction in Head and Neck Cancer Radiotherapy](https://mlsanity.com/paper/2307.12005/) (2023)

## Abstract (arXiv)

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 textitD-metrics and surrogate textitV-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 83% 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.