使用深度学习和数据修改进行伽玛刀放射外科的3D剂量预测
3D dose prediction for Gamma Knife radiosurgery using deep learning and data modification
摘要：
目的：为伽玛刀（GK）放射外科开发一种基于机器学习的3D剂量预测方法。该方法考虑了涉及任何数量、大小和形状的目标的情况。研究方法：通过基于肿瘤位置隔离和裁剪轮廓MRI和临床剂量分布，然后将所得肿瘤空间缩放至标准尺寸，修改了来自322 GK治疗计划的数据。为每个实例创建伴随的3D张量以说明肿瘤大小。使用272名患者的修改后的数据集来训练生成对抗网络（GAN-GK）和3D U-Net模型（U-Net-GK）。未修改的数据用于训练等效基线模型。所有模型均用于预测50例样本外患者的剂量分布。预测精度用伽马进行评价，标准为4%/2 mm、3%/3 mm、3%/1 mm和1%/1 mm。预测质量进行了评估，使用覆盖率，选择性和一致性指数。结果如下：GAN-GK和U-Net-GK的预测结果与临床结果相似，平均伽马（4%/2 mm）通过率分别为84.9和83.1。相比之下，在所有标准水平下，基线模型的伽马通过率均显著差于其各自的GK特异性模型（p < 0.001）。GK特异性预测的质量也与临床计划相似。结论：深度学习模型可以使用GK特定的数据修改来预测具有大范围大小，形状或目标数量的GKRS计划的3D剂量分布。应用于未经修改的GK数据的标准深度学习模型产生了较差的预测。
英文摘要：
Purpose: To develop a machine learning-based, 3D dose prediction methodology for Gamma Knife (GK) radiosurgery. The methodology accounts for cases involving targets of any number, size, and shape. Methods: Data from 322 GK treatment plans was modified by isolating and cropping the contoured MRI and clinical dose distributions based on tumor location, then scaling the resulting tumor spaces to a standard size. An accompanying 3D tensor was created for each instance to account for tumor size. The modified dataset for 272 patients was used to train both a generative adversarial network (GAN-GK) and a 3D U-Net model (U-Net-GK). Unmodified data was used to train equivalent baseline models. All models were used to predict the dose distribution of 50 out-of-sample patients. Prediction accuracy was evaluated using gamma, with criteria of 4%/2mm, 3%/3mm, 3%/1mm and 1%/1mm. Prediction quality was assessed using coverage, selectivity, and conformity indices. Results: The predictions resulting from GAN-GK and U-Net-GK were similar to their clinical counterparts, with average gamma (4%/2mm) passing rates of 84.9 and 83.1, respectively. In contrast, the gamma passing rate of baseline models were significantly worse than their respective GK-specific models (p < 0.001) at all criterion levels. The quality of GK-specific predictions was also similar to that of clinical plans. Conclusion: Deep learning models can use GK-specific data modification to predict 3D dose distributions for GKRS plans with a large range in size, shape, or number of targets. Standard deep learning models applied to unmodified GK data generated poorer predictions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
