DiffDP: Radiotherapy Dose Prediction via a Diffusion Model
This work addresses a specific bottleneck in medical imaging for cancer treatment planning, offering an incremental but practical enhancement to existing methods.
The authors tackled the over-smoothing problem in deep learning-based radiotherapy dose prediction by introducing a diffusion model (DiffDP) that incorporates anatomical information, achieving state-of-the-art results with a 3.2% improvement in dose distribution accuracy on a dataset of 130 rectum cancer patients.
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