FDDM: Frequency-Decomposed Diffusion Model for Rectum Cancer Dose Prediction in Radiotherapy

TL;DR

This paper introduces FDDM, a novel frequency-decomposed diffusion model that enhances high-frequency detail prediction in radiotherapy dose maps, improving accuracy over traditional CNN-based methods.

Contribution

The paper presents a new diffusion model that refines high-frequency components of dose maps via wavelet decomposition, reducing over-smoothing issues in radiotherapy planning.

Findings

FDDM outperforms CNN-based methods in dose prediction accuracy.

High-frequency refinement improves detail preservation in dose maps.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Accurate dose distribution prediction is crucial in the radiotherapy planning. Although previous methods based on convolutional neural network have shown promising performance, they have the problem of over-smoothing, leading to prediction without important high-frequency details. Recently, diffusion model has achieved great success in computer vision, which excels in generating images with more high-frequency details, yet suffers from time-consuming and extensive computational resource consumption. To alleviate these problems, we propose Frequency-Decomposed Diffusion Model (FDDM) that refines the high-frequency subbands of the dose map. To be specific, we design a Coarse Dose Prediction Module (CDPM) to first predict a coarse dose map and then utilize discrete wavelet transform to decompose the coarse dose map into a low-frequency subband and three high-frequency subbands. There is a notable difference between the coarse predicted results and ground truth in high-frequency subbands. Therefore, we design a diffusion-based module called High-Frequency Refinement Module (HFRM) that performs diffusion operation in the high-frequency components of the dose map instead of the original dose map. Extensive experiments on an in-house dataset verify the effectiveness of our approach.