Cao Xiangxu, Zhao Yuqian, Li Shuzhou, Zhang Fan, Yang Zhen, Yang Xiaoyu
School of Automation, Central South University, Changsha, China.
Key Laboratory of Industrial Intelligence and Systems (Central South University), Ministry of Education, Changsha, China.
Med Phys. 2025 Jul;52(7):e17989. doi: 10.1002/mp.17989.
Deep learning has been widely applied to the design of cancer radiotherapy treatment planning for dose distribution prediction. However, the significant variability in tumor size, quantity, and location poses substantial challenges for accurate dose distribution prediction in liver cancer radiotherapy.
Given that the clinical effectiveness and accuracy of the predicted dose distribution directly impact the quality of treatment plans generated by automatic radiotherapy planning methods, this study aims to develop a novel and precise dose prediction method based on diffusion models.
We propose a beam field (BF) guided diffusion model (BeamDiff) consisting of a forward and a reverse process for liver cancer radiotherapy dose distribution prediction. In the forward process, noise is progressively added to the actual dose distribution map until it transforms into a standard Gaussian noise map. In the reverse process, a noise predictor is used to estimate the noise and iteratively generate the desired dose distribution map. To effectively leverage patient-specific clinical features, we design a multi-branch hybrid encoder to extract features from BF and clinical structural information, with their relationships captured by a designed multi-condition aggregation module (MAM). Given that our inputs consist solely of 2D slices, which inherently lack inter-slice dependencies and similarity features, we integrate the multi-head attention (MHA) module into the encoder to re-establish connections between slices. In the decoder, we design an asymmetric fusion module (AFM) to integrate high-level feature maps from the encoder with low-level ones from the decoder, mitigating information loss caused by downsampling while preserving fine details and contextual information.
We evaluate the proposed method on a clinical liver cancer radiotherapy dataset. In terms of prediction accuracy, our model achieves an average Dose score of 1.27 Gy and a DVH score of 0.28 Gy. The mean absolute error (MAE) is 1.97 Gy for the planning target volume (PTV), 2.21 Gy for the liver, 1.14 Gy for the spinal cord, and 1.16 Gy for the stomach. Regarding clinical effectiveness, the predicted results of our method are the closest to meeting clinical requirements across the evaluated metrics.
We develop a method specifically tailored for liver cancer radiotherapy dose prediction. The proposed model demonstrates competitive performance in terms of both prediction accuracy and clinical effectiveness. These results suggest that the method has considerable potential to enhance the efficiency of the radiotherapy workflow.
深度学习已广泛应用于癌症放射治疗计划设计，用于剂量分布预测。然而，肿瘤大小、数量和位置的显著变异性给肝癌放射治疗中准确的剂量分布预测带来了重大挑战。
鉴于预测剂量分布的临床有效性和准确性直接影响自动放射治疗计划方法生成的治疗计划质量，本研究旨在开发一种基于扩散模型的新颖且精确的剂量预测方法。
我们提出一种用于肝癌放射治疗剂量分布预测的束流场（BF）引导扩散模型（BeamDiff），它由一个正向过程和一个反向过程组成。在正向过程中，噪声逐渐添加到实际剂量分布图中，直至其转变为标准高斯噪声图。在反向过程中，使用噪声预测器估计噪声并迭代生成所需的剂量分布图。为了有效利用患者特定的临床特征，我们设计了一个多分支混合编码器，从BF和临床结构信息中提取特征，其关系由设计的多条件聚合模块（MAM）捕获。鉴于我们的输入仅由2D切片组成，其固有地缺乏切片间的依赖性和相似性特征，我们将多头注意力（MHA）模块集成到编码器中，以重新建立切片之间的连接。在解码器中，我们设计了一个不对称融合模块（AFM），将来自编码器的高级特征图与来自解码器的低级特征图进行集成，减轻下采样导致的信息损失，同时保留精细细节和上下文信息。
我们在一个临床肝癌放射治疗数据集上评估了所提出的方法。就预测准确性而言，我们的模型实现了平均剂量得分1.27 Gy和剂量体积直方图（DVH）得分0.28 Gy。计划靶体积（PTV）的平均绝对误差（MAE）为1.97 Gy，肝脏为2.21 Gy，脊髓为1.14 Gy，胃为1.16 Gy。关于临床有效性，在评估指标中，我们方法的预测结果最接近满足临床要求。
我们开发了一种专门针对肝癌放射治疗剂量预测的方法。所提出的模型在预测准确性和临床有效性方面均表现出有竞争力的性能。这些结果表明该方法在提高放射治疗工作流程效率方面具有相当大的潜力。
