# Three-Dimensional Radiotherapy Dose Prediction on Head and Neck Cancer Patients with a Hierarchically Densely Connected U-net Deep Learning Architecture

arXiv: https://arxiv.org/abs/1805.10397 · HTML: https://mlsanity.com/paper/1805.10397/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2018.

## Built on by (most cited first, 18 of 18)

- [MD-Dose: A diffusion model based on the Mamba for radiation dose prediction](https://mlsanity.com/paper/2403.08479/) (2024)
- [DoseDiff: Distance-aware Diffusion Model for Dose Prediction in Radiotherapy](https://mlsanity.com/paper/2306.16324/) (2023)
- [OpenKBP-Opt: An international and reproducible evaluation of 76 knowledge-based planning pipelines](https://mlsanity.com/paper/2202.08303/) (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)
- [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)
- [Deep Evidential Learning for Radiotherapy Dose Prediction](https://mlsanity.com/paper/2404.17126/) (2024)
- [Learning the Physics of Particle Transport via Transformers](https://mlsanity.com/paper/2109.03951/) (2021)
- [Noisy probing dose facilitated dose prediction for pencil beam scanning proton therapy: physics enhances generalizability](https://mlsanity.com/paper/2312.00975/) (2023)
- [Zero-Shot Large Language Model Agents for Fully Automated Radiotherapy Treatment Planning](https://mlsanity.com/paper/2510.11754/) (2025)
- [Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study](https://mlsanity.com/paper/2605.09622/) (2026)
- [Site-Agnostic 3D Dose Distribution Prediction with Deep Learning Neural Networks](https://mlsanity.com/paper/2106.07825/) (2021)
- [Polymerized Feature-based Domain Adaptation for Cervical Cancer Dose Map Prediction](https://mlsanity.com/paper/2308.10142/) (2023)
- [Can input reconstruction be used to directly estimate uncertainty of a regression U-Net model? -- Application to proton therapy dose prediction for head and neck cancer patients](https://mlsanity.com/paper/2310.19686/) (2023)
- [ARANet: Attention-based Residual Adversarial Network with Deep Supervision for Radiotherapy Dose Prediction of Cervical Cancer](https://mlsanity.com/paper/2408.13981/) (2024)
- [A Fast and Generic Energy-Shifting Transformer for Hybrid Monte Carlo Radiotherapy Calculation](https://mlsanity.com/paper/2604.09157/) (2026)
- [DoseBridge: Denoising Diffusion Bridge Model for Dose Prediction in Lung Intensity-Modulated Proton Therapy](https://mlsanity.com/paper/2608.10173/) (2026)

## Abstract (arXiv)

The treatment planning process for patients with head and neck (H&N) cancer is regarded as one of the most complicated due to large target volume, multiple prescription dose levels, and many radiation-sensitive critical structures near the target. Treatment planning for this site requires a high level of human expertise and a tremendous amount of effort to produce personalized high quality plans, taking as long as a week, which deteriorates the chances of tumor control and patient survival. To solve this problem, we propose to investigate a deep learning-based dose prediction model, Hierarchically Densely Connected U-net, based on two highly popular network architectures: U-net and DenseNet. We find that this new architecture is able to accurately and efficiently predict the dose distribution, outperforming the other two models, the Standard U-net and DenseNet, in homogeneity, dose conformity, and dose coverage on the test data. Averaging across all organs at risk, our proposed model is capable of predicting the organ-at-risk max dose within 6.3% and mean dose within 5.1% of the prescription dose on the test data. The other models, the Standard U-net and DenseNet, performed worse, having an averaged organ-at-risk max dose prediction error of 8.2% and 9.3%, respectively, and averaged mean dose prediction error of 6.4% and 6.8%, respectively. In addition, our proposed model used 12 times less trainable parameters than the Standard U-net, and predicted the patient dose 4 times faster than DenseNet.