Deep learning dose prediction for IMRT of esophageal cancer: The effect of data quality and quantity on model performance
Deep learning dose prediction for IMRT of esophageal cancer: The effect of data quality and quantity on model performance
复制标题
DOI：
10.1016/j.ejmp.2021.02.026
复制
发表时间：
2021-03-10
影响因子：
3.4
通讯作者：
Sterpin, Edmond
中科院分区：
文献类型：
--
作者：
Barragan-Montero, Ana M.;Thomas, Melissa;Sterpin, Edmond
用途：为了研究数据质量和数量对深度学习（DL）模型性能的影响，用于食管癌调强放射治疗（IMRT）的剂量预测。材料和方法：使用两个数据库：一个变量数据库（VarDB），包含回顾性提取的56个临床病例，包括描绘和计划中的用户依赖性变化，不同的机器和射束配置;和一个同质化数据库（HomDB），创建该数据库是为了通过使用固定的类解决方案方案重新勾画轮廓和重新规划所有患者来减少这种可变性。实验1分析了用户依赖性变异性，使用相同机器和射束设置计划的26名患者（E26-VarDB与E26-HomDB）。实验2增加了两个数据库的10名患者（E16，E26，E36，E46和E56）的训练集。模型评价指标是所选剂量体积指标的平均绝对误差（MAE）和所有身体体素的全局MAE。结果：对于实验1，与E26-VarDB相比，E26-HomDB降低了所考虑剂量体积指标的MAE（例如，D95-PTV降低0.2戈伊，Dmean-心脏降低1.2戈伊，V5-肺降低3.3%）。对于实验2，增加数据库大小略微提高了HomDB模型的性能（例如，与E26-HomDB相比，E56-HomDB的总体MAE降低0.13戈伊），但增加了VarDB模型的误差（例如，与E26-VarDB相比，E56-VarDB的总体MAE增加0.20戈伊）。如果使用同质训练数据，小型数据库可能足以获得良好的DL预测性能。数据可变性降低了DL模型的性能，这在增加训练集时进一步明显。
Purpose: To investigate the effect of data quality and quantity on the performance of deep learning (DL) models, for dose prediction of intensity-modulated radiotherapy (IMRT) of esophageal cancer.Material and methods: Two databases were used: a variable database (VarDB) with 56 clinical cases extracted retrospectively, including user-dependent variability in delineation and planning, different machines and beam configurations; and a homogenized database (HomDB), created to reduce this variability by re-contouring and replanning all patients with a fixed class-solution protocol. Experiment 1 analysed the user-dependent variability, using 26 patients planned with the same machine and beam setup (E26-VarDB versus E26-HomDB). Experiment 2 increased the training set by groups of 10 patients (E16, E26, E36, E46, and E56) for both databases. Model evaluation metrics were the mean absolute error (MAE) for selected dose-volume metrics and the global MAE for all body voxels.Results: For Experiment 1, E26-HomDB reduced the MAE for the considered dose-volume metrics compared to E26-VarDB (e.g. reduction of 0.2 Gy for D95-PTV, 1.2 Gy for Dmean-heart or 3.3% for V5-lungs). For Experiment 2, increasing the database size slightly improved performance for HomDB models (e.g. decrease in global MAE of 0.13 Gy for E56-HomDB versus E26-HomDB), but increased the error for the VarDB models (e.g. increase in global MAE of 0.20 Gy for E56-VarDB versus E26-VarDB).Conclusion: A small database may suffice to obtain good DL prediction performance, provided that homogenous training data is used. Data variability reduces the performance of DL models, which is further pronounced when increasing the training set.