Shiraishi Satomi, Moore Kevin L
Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, California 92093.
Med Phys. 2016 Jan;43(1):378. doi: 10.1118/1.4938583.
To demonstrate knowledge-based 3D dose prediction for external beam radiotherapy.
Using previously treated plans as training data, an artificial neural network (ANN) was trained to predict a dose matrix based on patient-specific geometric and planning parameters, such as the closest distance (r) to planning target volume (PTV) and organ-at-risks (OARs). Twenty-three prostate and 43 stereotactic radiosurgery/radiotherapy (SRS/SRT) cases with at least one nearby OAR were studied. All were planned with volumetric-modulated arc therapy to prescription doses of 81 Gy for prostate and 12-30 Gy for SRS. Using these clinically approved plans, ANNs were trained to predict dose matrix and the predictive accuracy was evaluated using the dose difference between the clinical plan and prediction, δD = Dclin - Dpred. The mean (〈δDr〉), standard deviation (σδDr ), and their interquartile range (IQR) for the training plans were evaluated at a 2-3 mm interval from the PTV boundary (rPTV) to assess prediction bias and precision. Initially, unfiltered models which were trained using all plans in the cohorts were created for each treatment site. The models predict approximately the average quality of OAR sparing. Emphasizing a subset of plans that exhibited superior to the average OAR sparing during training, refined models were created to predict high-quality rectum sparing for prostate and brainstem sparing for SRS. Using the refined model, potentially suboptimal plans were identified where the model predicted further sparing of the OARs was achievable. Replans were performed to test if the OAR sparing could be improved as predicted by the model.
The refined models demonstrated highly accurate dose distribution prediction. For prostate cases, the average prediction bias for all voxels irrespective of organ delineation ranged from -1% to 0% with maximum IQR of 3% over rPTV ∈ [ - 6, 30] mm. The average prediction error was less than 10% for the same rPTV range. For SRS cases, the average prediction bias ranged from -0.7% to 1.5% with maximum IQR of 5% over rPTV ∈ [ - 4, 32] mm. The average prediction error was less than 8%. Four potentially suboptimal plans were identified for each site and subsequent replanning demonstrated improved sparing of rectum and brainstem.
The study demonstrates highly accurate knowledge-based 3D dose predictions for radiotherapy plans.
展示基于知识的外照射放疗三维剂量预测。
以前期治疗计划作为训练数据，训练人工神经网络（ANN），以根据患者特定的几何和计划参数来预测剂量矩阵，如到计划靶体积（PTV）和危及器官（OARs）的最近距离（r）。研究了23例前列腺癌病例和43例立体定向放射外科/放疗（SRS/SRT）病例，这些病例均至少有一个邻近的OAR。所有病例均采用容积调强弧形放疗，前列腺癌的处方剂量为81 Gy，SRS的处方剂量为12 - 30 Gy。利用这些临床批准的计划，训练ANN以预测剂量矩阵，并使用临床计划与预测之间的剂量差异δD = Dclin - Dpred评估预测准确性。在从PTV边界（rPTV）起2 - 3 mm间隔处评估训练计划的平均值（〈δDr〉）、标准差（σδDr）及其四分位间距（IQR），以评估预测偏差和精度。最初，针对每个治疗部位创建使用队列中所有计划训练的未过滤模型。这些模型大致预测了OAR保留的平均质量。在训练过程中强调一组表现优于平均OAR保留的计划，创建了优化模型以预测前列腺癌中高质量的直肠保留和SRS中高质量的脑干保留。使用优化模型，识别出潜在的次优计划，即模型预测可以进一步实现OAR保留的计划。进行重新计划以测试是否可以如模型预测的那样改善OAR保留。
优化模型展示了高度准确的剂量分布预测。对于前列腺癌病例，无论器官轮廓如何，所有体素的平均预测偏差在 - 1%至0%之间，在rPTV ∈ [ - 6, 30] mm范围内最大IQR为3%。在相同的rPTV范围内，平均预测误差小于10%。对于SRS病例，平均预测偏差在 - 0.7%至1.5%之间，在rPTV ∈ [ - 4, 32] mm范围内最大IQR为5%。平均预测误差小于8%。每个部位识别出四个潜在的次优计划，随后的重新计划显示直肠和脑干的保留得到了改善。
该研究展示了针对放疗计划的基于知识的高度准确的三维剂量预测。
