DiffDP: Radiotherapy Dose Prediction via a Diffusion Model

TL;DR

DiffDP introduces a diffusion-based model for radiotherapy dose prediction, addressing over-smoothing issues in existing deep learning methods by modeling the distribution through a forward and reverse process, incorporating anatomical information for improved accuracy.

Contribution

The paper presents a novel diffusion model for dose prediction in radiotherapy, integrating anatomical features and noise modeling to enhance prediction quality over traditional methods.

Findings

Outperforms existing deep learning models in dose prediction accuracy.

Effectively incorporates anatomical information to respect organ constraints.

Reduces over-smoothing compared to L1/L2 loss-based methods.

Abstract

Currently, deep learning (DL) has achieved the automatic prediction of dose distribution in radiotherapy planning, enhancing its efficiency and quality. However, existing methods suffer from the over-smoothing problem for their commonly used L_1 or L_2 loss with posterior average calculations. To alleviate this limitation, we innovatively introduce a diffusion-based dose prediction (DiffDP) model for predicting the radiotherapy dose distribution of cancer patients. Specifically, the DiffDP model contains a forward process and a reverse process. In the forward process, DiffDP gradually transforms dose distribution maps into Gaussian noise by adding small noise and trains a noise predictor to predict the noise added in each timestep. In the reverse process, it removes the noise from the original Gaussian noise in multiple steps with the well-trained noise predictor and finally outputs the predicted dose distribution map. To ensure the accuracy of the prediction, we further design a structure encoder to extract anatomical information from patient anatomy images and enable the noise predictor to be aware of the dose constraints within several essential organs, i.e., the planning target volume and organs at risk. Extensive experiments on an in-house dataset with 130 rectum cancer patients demonstrate the s