Department of Radiation Oncology, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, the Netherlands.
Department of Radiation Oncology, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, the Netherlands.
Phys Med. 2020 Mar;71:124-131. doi: 10.1016/j.ejmp.2020.02.020. Epub 2020 Mar 2.
EPID dosimetry in the Unity MR-Linac system allows for reconstruction of absolute dose distributions within the patient geometry. Dose reconstruction is accurate for the parts of the beam arriving at the EPID through the MRI central unattenuated region, free of gradient coils, resulting in a maximum field size of ~10 × 22 cm at isocentre. The purpose of this study is to develop a Deep Learning-based method to improve the accuracy of 2D EPID reconstructed dose distributions outside this central region, accounting for the effects of the extra attenuation and scatter.
A U-Net was trained to correct EPID dose images calculated at the isocenter inside a cylindrical phantom using the corresponding TPS dose images as ground truth for training. The model was evaluated using a 5-fold cross validation procedure. The clinical validity of the U-Net corrected dose images (the so-called DEEPID dose images) was assessed with in vivo verification data of 45 large rectum IMRT fields. The sensitivity of DEEPID to leaf bank position errors (±1.5 mm) and ±5% MU delivery errors was also tested.
Compared to the TPS, in vivo 2D DEEPID dose images showed an average γ-pass rate of 90.2% (72.6%-99.4%) outside the central unattenuated region. Without DEEPID correction, this number was 44.5% (4.0%-78.4%). DEEPID correctly detected the introduced delivery errors.
DEEPID allows for accurate dose reconstruction using the entire EPID image, thus enabling dosimetric verification for field sizes up to ~19 × 22 cm at isocentre. The method can be used to detect clinically relevant errors.
Unity MR-Linac 系统中的 EPID 剂量学允许在患者体内重建绝对剂量分布。剂量重建对于通过 MRI 中心未衰减区域、无梯度线圈到达 EPID 的光束部分是准确的，从而在等中心处产生最大光束尺寸约为 10×22cm。本研究的目的是开发一种基于深度学习的方法，以提高超出该中心区域的 2D EPID 重建剂量分布的准确性，同时考虑额外衰减和散射的影响。
使用 U-Net 对在圆柱形体模等中心处使用 TPS 剂量图像作为训练的ground truth 计算的 EPID 剂量图像进行校正。使用 5 折交叉验证程序评估模型。使用 45 个大直肠调强放疗场的体内验证数据评估 U-Net 校正的剂量图像（所谓的 DEEPID 剂量图像）的临床有效性。还测试了 DEEPID 对叶片位置误差（±1.5mm）和±5%MU 传递误差的敏感性。
与 TPS 相比，在体内 2D DEEPID 剂量图像在中心未衰减区域外显示平均γ通过率为 90.2%（72.6%-99.4%）。没有 DEEPID 校正，这个数字是 44.5%（4.0%-78.4%）。DEEPID 正确检测到引入的传递误差。
DEEPID 允许使用整个 EPID 图像进行准确的剂量重建，从而能够在等中心处对最大约 19×22cm 的射野进行剂量验证。该方法可用于检测临床相关误差。
