Division of Medical Physics, Department of Information Technology and Medical Engineering, Human Health Sciences, Graduate School of Medicine, Kyoto University, 53 Kawahara-Cho, Shogoin, Sakyo-ku, Kyoto, 606-8507, Japan.
Department of Radiation Oncology and Image-Applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
Radiat Oncol. 2022 Feb 23;17(1):42. doi: 10.1186/s13014-022-02012-7.
In infrared reflective (IR) marker-based hybrid real-time tumor tracking (RTTT), the internal target position is predicted with the positions of IR markers attached on the patient's body surface using a prediction model. In this work, we developed two artificial intelligence (AI)-driven prediction models to improve RTTT radiotherapy, namely, a convolutional neural network (CNN) and an adaptive neuro-fuzzy inference system (ANFIS) model. The models aim to improve the accuracy in predicting three-dimensional tumor motion.
From patients whose respiration-induced motion of the tumor, indicated by the fiducial markers, exceeded 8 mm, 1079 logfiles of IR marker-based hybrid RTTT (IR Tracking) with the gimbal-head radiotherapy system were acquired and randomly divided into two datasets. All the included patients were breathing freely with more than four external IR markers. The historical dataset for the CNN model contained 1003 logfiles, while the remaining 76 logfiles complemented the evaluation dataset. The logfiles recorded the external IR marker positions at a frequency of 60 Hz and fiducial markers as surrogates for the detected target positions every 80-640 ms for 20-40 s. For each logfile in the evaluation dataset, the prediction models were trained based on the data in the first three quarters of the recording period. In the last quarter, the performance of the patient-specific prediction models was tested and evaluated. The overall performance of the AI-driven prediction models was ranked by the percentage of predicted target position within 2 mm of the detected target position. Moreover, the performance of the AI-driven models was compared to a regression prediction model currently implemented in gimbal-head radiotherapy systems.
The percentage of the predicted target position within 2 mm of the detected target position was 95.1%, 92.6% and 85.6% for the CNN, ANFIS, and regression model, respectively. In the evaluation dataset, the CNN, ANFIS, and regression model performed best in 43, 28 and 5 logfiles, respectively.
The proposed AI-driven prediction models outperformed the regression prediction model, and the overall performance of the CNN model was slightly better than that of the ANFIS model on the evaluation dataset.
在基于红外反射（IR）标记的混合实时肿瘤跟踪（RTTT）中，使用预测模型，根据附着在患者体表的 IR 标记的位置来预测内部目标位置。在这项工作中，我们开发了两种人工智能（AI）驱动的预测模型，以改善 RTTT 放射治疗，即卷积神经网络（CNN）和自适应神经模糊推理系统（ANFIS）模型。这些模型旨在提高预测三维肿瘤运动的准确性。
从肿瘤的呼吸运动导致的标记物运动超过 8mm 的患者中，获取了 1079 个基于 IR 标记的混合 RTTT（IR Tracking）的日志文件，并随机分为两个数据集。所有纳入的患者均采用自由呼吸方式，使用超过四个外部 IR 标记物。CNN 模型的历史数据集包含 1003 个日志文件，其余 76 个日志文件补充了评估数据集。日志文件以 60Hz 的频率记录外部 IR 标记的位置，每隔 80-640ms 记录作为检测目标位置的替代物的基准标记位置，记录时间为 20-40s。对于评估数据集中的每个日志文件，基于记录周期前三分之一的数据训练患者特异性预测模型。在最后一个季度，测试和评估患者特异性预测模型的性能。通过预测目标位置与检测目标位置之间的距离在 2mm 内的比例来对 AI 驱动的预测模型的整体性能进行排名。此外，还将 AI 驱动的模型的性能与目前在万向头放疗系统中实现的回归预测模型进行了比较。
在检测目标位置的距离在 2mm 内的预测目标位置的比例分别为 95.1%、92.6%和 85.6%，对于 CNN、ANFIS 和回归模型。在评估数据集中，CNN、ANFIS 和回归模型在 43、28 和 5 个日志文件中的性能最好。
与回归预测模型相比，所提出的 AI 驱动的预测模型表现更好，在评估数据集中，CNN 模型的整体性能略优于 ANFIS 模型。
