# 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

arXiv: https://arxiv.org/abs/1908.05874 · HTML: https://mlsanity.com/paper/1908.05874/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [Domain Knowledge Driven 3D Dose Prediction Using Moment-Based Loss Function](https://mlsanity.com/paper/2207.03414/) (2022)
- [LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction](https://mlsanity.com/paper/2106.06733/) (2021)
- [DeepDoseNet: A Deep Learning model for 3D Dose Prediction in Radiation Therapy](https://mlsanity.com/paper/2111.00077/) (2021)
- [Probabilistic feature extraction, dose statistic prediction and dose mimicking for automated radiation therapy treatment planning](https://mlsanity.com/paper/2102.12569/) (2021)
- [Swin UNETR++: Advancing Transformer-Based Dense Dose Prediction Towards Fully Automated Radiation Oncology Treatments](https://mlsanity.com/paper/2311.06572/) (2023)
- [Knowledge-Informed Machine Learning for Cancer Diagnosis and Prognosis: A review](https://mlsanity.com/paper/2401.06406/) (2024)
- [Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study](https://mlsanity.com/paper/2605.09622/) (2026)
- [Deep Learning 3D Dose Prediction for Conventional Lung IMRT Using Consistent/Unbiased Automated Plans](https://mlsanity.com/paper/2106.03705/) (2021)
- [Virtual Dosimetrists: A Radiotherapy Training "Flight Simulator"](https://mlsanity.com/paper/2505.09796/) (2025)
- [Clinical DVH metrics as a loss function for 3D dose prediction in head and neck radiotherapy](https://mlsanity.com/paper/2603.29670/) (2026)

## Abstract (arXiv)

We propose a novel domain specific loss, which is a differentiable loss function based on the dose volume histogram, and combine it with an adversarial loss for the training of deep neural networks to generate Pareto optimal dose distributions. The mean squared error (MSE) loss, dose volume histogram (DVH) loss, and adversarial (ADV) loss were used to train 4 instances of the neural network model: 1) MSE, 2) MSE+ADV, 3) MSE+DVH, and 4) MSE+DVH+ADV. 70 prostate patients were acquired, and the dose influence arrays were calculated for each patient. 1200 Pareto surface plans per patient were generated by pseudo-randomizing the tradeoff weights (84,000 plans total). We divided the data into 54 training, 6 validation, and 10 testing patients. Each model was trained for 100,000 iterations, with a batch size of 2. The prediction time of each model is 0.052 seconds. Quantitatively, the MSE+DVH+ADV model had the lowest prediction error of 0.038 (conformation), 0.026 (homogeneity), 0.298 (R50), 1.65% (D95), 2.14% (D98), 2.43% (D99). The MSE model had the worst prediction error of 0.134 (conformation), 0.041 (homogeneity), 0.520 (R50), 3.91% (D95), 4.33% (D98), 4.60% (D99). For both the mean dose PTV error and the max dose PTV, Body, Bladder and rectum error, the MSE+DVH+ADV outperformed all other models. All model's predictions have an average mean and max dose error less than 2.8% and 4.2%, respectively. Expert human domain specific knowledge can be the largest driver in the performance improvement, and adversarial learning can be used to further capture nuanced features. The real-time prediction capabilities allow for a physician to quickly navigate the tradeoff space, and produce a dose distribution as a tangible endpoint for the dosimetrist to use for planning. This can considerably reduce the treatment planning time, allowing for clinicians to focus their efforts on challenging cases.