基于知识的串联卵型近距离放射治疗三维剂量预测
Knowledge-Based Three-Dimensional Dose Prediction for Tandem-And-Ovoid Brachytherapy
摘要：
目的：利用卷积神经网络开发一个基于知识的体素剂量预测系统，用于使用串联卵形（T&O）施源器的高剂量率近距离放射治疗宫颈癌。研究方法：使用3D U-NET输出剂量预测，使用器官风险（OAR），高风险临床靶体积（HRCTV）和可能的源位置。使用了包括397例（273例培训：62例验证：62例测试）、HRCTV和OAR（膀胱/直肠/乙状结肠）的先前T&O治疗样本。将结构和剂量内插到1x1x2.5mm3剂量平面，具有两个输入通道（源位置、体素识别）和一个剂量输出通道。我们评估了剂量差异（ΔD）（xyz）=D_（实际）（x，y，z）-D_（预测）（x，y，z），并在所有队列中计算了临床相关剂量范围（处方的20-130%）、平均值和标准差的相似系数。我们还研究了用于T&O计划质量评估的离散DVH指标：HRCTVD_90%（最热90%体积剂量）和OARD_2cc，其中Δ Dx = Dx，实际值-Dx，预测值。临床指标的Pearson相关系数、标准差和平均量化模型性能。结果如下：所有体素的平均值（ΔD）和标准差的训练（测试）范围的20-130%剂量范围的体素剂量差异准确度为[-0.3%+/-2.0%至+1.0%+/-12.0%]（[-0.1%+/-4%至+4.0%+/-26%]）。20-130%剂量的体素骰子相似性系数范围为[0.96，0.91]（[0.94，0.87]）。在训练（测试）集中DVH度量预测为HRCTV（ΔD_90）=-0.19+/-0.55Gy（-0.09+/-0.67 Gy），膀胱（ΔD_2cc）=-0.06+/-0.54 Gy直肠（ΔD）2cc =-0.03+/-0.36 Gy（-0.04+/-0.46 Gy），乙状结肠（Δ D2cc）=-0.01+/-0.34 Gy（0.00+/-0.44 Gy）。结论：T&O近距离放射治疗的3D基于知识的剂量预测提供了准确的体素水平和DVH度量估计。
英文摘要：
Purpose: To develop a knowledge-based voxel-wise dose prediction system using a convolution neural network for high-dose-rate brachytherapy cervical cancer treatments with a tandem-and-ovoid (T&O) applicator. Methods: A 3D U-NET was utilized to output dose predictions using organ-at-risk (OAR), high-risk clinical target volume (HRCTV), and possible source locations. A sample of previous T&O treatments comprising 397 cases (273 training:62 validation:62 test), HRCTV and OARs (bladder/rectum/sigmoid) was used. Structures and dose were interpolated to 1x1x2.5mm3 dose planes with two input channels (source positions, voxel identification) and one output channel for dose. We evaluated dose difference (ΔD)(xyz)=D_(actual)(x,y,z)-D_(predicted)(x,y,z) and dice similarity coefficients in all cohorts across the clinically-relevant dose range (20-130% of prescription), mean and standard deviation. We also examined discrete DVH metrics used for T&O plan quality assessment: HRCTV D_90%(dose to hottest 90% volume) and OAR D_2cc, with ΔD_x=D_(x,actual)-D_(x,predicted). Pearson correlation coefficient, standard deviation, and mean quantified model performance on the clinical metrics. Results: Voxel-wise dose difference accuracy for 20-130% dose range for training(test) ranges for mean (ΔD) and standard deviation for all voxels was [-0.3%+/-2.0% to +1.0%+/-12.0%] ([-0.1%+/-4% to +4.0%+/-26%]). Voxel-wise dice similarity coefficients for 20-130% dose ranged from [0.96, 0.91]([0.94, 0.87]). DVH metric prediction in the training (test) set were HRCTV(ΔD_90)=-0.19+/-0.55 Gy (-0.09+/-0.67 Gy), bladder(ΔD_2cc)=-0.06+/-0.54 Gy (-0.17+/-0.67 Gy), rectum(ΔD)_2cc=-0.03+/-0.36 Gy (-0.04+/-0.46 Gy), and sigmoid(ΔD_2cc)=-0.01+/-0.34 Gy (0.00+/-0.44 Gy). Conclusion: 3D knowledge-based dose predictions for T&O brachytherapy provide accurate voxel-level and DVH metric estimates.
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。
