Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre, Maastricht, The Netherlands.
Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre, Maastricht, The Netherlands.
Radiother Oncol. 2020 Dec;153:243-249. doi: 10.1016/j.radonc.2020.09.048. Epub 2020 Oct 2.
BACKGROUND/PURPOSE: Electronic portal imaging device (EPID) dosimetry aims to detect treatment errors, potentially leading to treatment adaptation. Clinically used threshold classification methods for detecting errors lead to loss of information (from multi-dimensional EPID data to a few numbers) and cannot be used for identifying causes of errors. Advanced classification methods, such as deep learning, can use all available information. In this study, convolutional neural networks (CNNs) were trained to detect and identify error type and magnitude of simulated treatment errors in lung cancer patients. The purpose of this simulation study is to provide a proof-of-concept of CNNs for error identification using EPID dosimetry in an in vivo scenario.
Clinically realistic ranges of anatomical changes, positioning errors and mechanical errors were simulated for lung cancer patients. Predicted portal dose images (PDIs) containing errors were compared to error-free PDIs using the widely used gamma analysis. CNNs were trained to classify errors using 2D gamma maps. Three classification levels were assessed: Level 1 (main error type, e.g., anatomical change), Level 2 (error subtype, e.g., tumor regression) and Level 3 (error magnitude, e.g., >50% tumor regression).
CNNs showed good performance for all classification levels (training/test accuracy 99.5%/96.1%, 92.5%/86.8%, 82.0%/72.9%). For Level 3, overfitting became more apparent.
This simulation study indicates that deep learning is a promising powerful tool for identifying types and magnitude of treatment errors with EPID dosimetry, providing additional information not currently available from EPID dosimetry. This is a first step towards rapid, automated models for identification of treatment errors using EPID dosimetry.
背景/目的：电子射野影像装置（EPID）剂量测定旨在检测治疗误差，从而可能导致治疗适应。临床上用于检测误差的阈值分类方法会导致信息丢失（从多维 EPID 数据到少数数字），并且无法用于识别误差的原因。先进的分类方法，如深度学习，可以使用所有可用的信息。在这项研究中，训练卷积神经网络（CNN）以检测和识别模拟肺癌患者治疗误差的类型和幅度。本模拟研究的目的是提供使用 EPID 剂量测定在体内情况下识别误差的 CNN 的概念验证。
模拟了肺癌患者的解剖变化、定位误差和机械误差的临床现实范围。使用广泛使用的伽马分析比较了包含误差的预测门户剂量图像（PDI）和无误差的 PDI。使用二维伽马图对 CNN 进行训练以进行错误分类。评估了三个分类级别：级别 1（主要错误类型，例如解剖变化）、级别 2（错误子类型，例如肿瘤消退）和级别 3（错误幅度，例如 >50%肿瘤消退）。
CNN 在所有分类级别上均表现出良好的性能（训练/测试准确性为 99.5%/96.1%、92.5%/86.8%、82.0%/72.9%）。对于级别 3，过拟合变得更加明显。
这项模拟研究表明，深度学习是一种很有前途的强大工具，可用于通过 EPID 剂量测定识别治疗误差的类型和幅度，提供了 EPID 剂量测定目前无法提供的附加信息。这是使用 EPID 剂量测定快速、自动识别治疗误差的模型的第一步。
