{"title":"评估基于深度学习的 1.5 T 磁共振引导直线加速器伽马通过率预测系统。","authors":"Ryota Tozuka, Noriyuki Kadoya, Kazuhiro Arai, Kiyokazu Sato, Keiichi Jingu","doi":"10.1007/s12194-024-00800-2","DOIUrl":null,"url":null,"abstract":"<p><p>Measurement-based verification is impossible for the patient-specific quality assurance (QA) of online adaptive magnetic resonance imaging-guided radiotherapy (oMRgRT) because the patient remains on the couch throughout the session. We assessed a deep learning (DL) system for oMRgRT to predict the gamma passing rate (GPR). This study collected 125 verification plans [reference plan (RP), 100; adapted plan (AP), 25] from patients with prostate cancer treated using Elekta Unity. Based on our previous study, we employed a convolutional neural network that predicted the GPRs of nine pairs of gamma criteria from 1%/1 mm to 3%/3 mm. First, we trained and tested the DL model using RPs (n = 75 and n = 25 for training and testing, respectively) for its optimization. Second, we tested the GPR prediction accuracy using APs to determine whether the DL model could be applied to APs. The mean absolute error (MAE) and correlation coefficient (r) of the RPs were 1.22 ± 0.27% and 0.29 ± 0.10 in 3%/2 mm, 1.35 ± 0.16% and 0.37 ± 0.15 in 2%/2 mm, and 3.62 ± 0.55% and 0.32 ± 0.14 in 1%/1 mm, respectively. The MAE and r of the APs were 1.13 ± 0.33% and 0.35 ± 0.22 in 3%/2 mm, 1.68 ± 0.47% and 0.30 ± 0.11 in 2%/2 mm, and 5.08 ± 0.29% and 0.15 ± 0.10 in 1%/1 mm, respectively. The time cost was within 3 s for the prediction. The results suggest the DL-based model has the potential for rapid GPR prediction in Elekta Unity.</p>","PeriodicalId":46252,"journal":{"name":"Radiological Physics and Technology","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Assessment of the deep learning-based gamma passing rate prediction system for 1.5 T magnetic resonance-guided linear accelerator.\",\"authors\":\"Ryota Tozuka, Noriyuki Kadoya, Kazuhiro Arai, Kiyokazu Sato, Keiichi Jingu\",\"doi\":\"10.1007/s12194-024-00800-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Measurement-based verification is impossible for the patient-specific quality assurance (QA) of online adaptive magnetic resonance imaging-guided radiotherapy (oMRgRT) because the patient remains on the couch throughout the session. We assessed a deep learning (DL) system for oMRgRT to predict the gamma passing rate (GPR). This study collected 125 verification plans [reference plan (RP), 100; adapted plan (AP), 25] from patients with prostate cancer treated using Elekta Unity. Based on our previous study, we employed a convolutional neural network that predicted the GPRs of nine pairs of gamma criteria from 1%/1 mm to 3%/3 mm. First, we trained and tested the DL model using RPs (n = 75 and n = 25 for training and testing, respectively) for its optimization. Second, we tested the GPR prediction accuracy using APs to determine whether the DL model could be applied to APs. The mean absolute error (MAE) and correlation coefficient (r) of the RPs were 1.22 ± 0.27% and 0.29 ± 0.10 in 3%/2 mm, 1.35 ± 0.16% and 0.37 ± 0.15 in 2%/2 mm, and 3.62 ± 0.55% and 0.32 ± 0.14 in 1%/1 mm, respectively. The MAE and r of the APs were 1.13 ± 0.33% and 0.35 ± 0.22 in 3%/2 mm, 1.68 ± 0.47% and 0.30 ± 0.11 in 2%/2 mm, and 5.08 ± 0.29% and 0.15 ± 0.10 in 1%/1 mm, respectively. The time cost was within 3 s for the prediction. The results suggest the DL-based model has the potential for rapid GPR prediction in Elekta Unity.</p>\",\"PeriodicalId\":46252,\"journal\":{\"name\":\"Radiological Physics and Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiological Physics and Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s12194-024-00800-2\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/4/30 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiological Physics and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s12194-024-00800-2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/4/30 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
摘要
对于在线自适应磁共振成像引导放射治疗(oMRgRT)的患者特定质量保证(QA)来说,基于测量的验证是不可能的,因为患者在整个治疗过程中一直躺在沙发上。我们对用于 oMRgRT 的深度学习(DL)系统进行了评估,以预测伽马通过率(GPR)。本研究收集了使用 Elekta Unity 治疗的前列腺癌患者的 125 个验证计划(参考计划 (RP) 100 个;调整计划 (AP) 25 个)。在之前研究的基础上,我们采用了一个卷积神经网络来预测从 1%/1 mm 到 3%/3 mm 的九对伽马标准的 GPR。首先,我们使用 RPs(训练和测试分别使用 n = 75 和 n = 25)对 DL 模型进行了优化训练和测试。其次,我们使用 AP 测试了 GPR 预测的准确性,以确定 DL 模型是否适用于 AP。RP 的平均绝对误差(MAE)和相关系数(r)在 3%/2 mm 中分别为 1.22 ± 0.27% 和 0.29 ± 0.10,在 2%/2 mm 中分别为 1.35 ± 0.16% 和 0.37 ± 0.15,在 1%/1 mm 中分别为 3.62 ± 0.55% 和 0.32 ± 0.14。AP 的 MAE 和 r 在 3%/2 mm 中分别为 1.13 ± 0.33% 和 0.35 ± 0.22,在 2%/2 mm 中分别为 1.68 ± 0.47% 和 0.30 ± 0.11,在 1%/1 mm 中分别为 5.08 ± 0.29% 和 0.15 ± 0.10。预测的时间成本在 3 秒以内。结果表明,基于 DL 的模型具有在 Elekta Unity 中进行快速 GPR 预测的潜力。
Assessment of the deep learning-based gamma passing rate prediction system for 1.5 T magnetic resonance-guided linear accelerator.
Measurement-based verification is impossible for the patient-specific quality assurance (QA) of online adaptive magnetic resonance imaging-guided radiotherapy (oMRgRT) because the patient remains on the couch throughout the session. We assessed a deep learning (DL) system for oMRgRT to predict the gamma passing rate (GPR). This study collected 125 verification plans [reference plan (RP), 100; adapted plan (AP), 25] from patients with prostate cancer treated using Elekta Unity. Based on our previous study, we employed a convolutional neural network that predicted the GPRs of nine pairs of gamma criteria from 1%/1 mm to 3%/3 mm. First, we trained and tested the DL model using RPs (n = 75 and n = 25 for training and testing, respectively) for its optimization. Second, we tested the GPR prediction accuracy using APs to determine whether the DL model could be applied to APs. The mean absolute error (MAE) and correlation coefficient (r) of the RPs were 1.22 ± 0.27% and 0.29 ± 0.10 in 3%/2 mm, 1.35 ± 0.16% and 0.37 ± 0.15 in 2%/2 mm, and 3.62 ± 0.55% and 0.32 ± 0.14 in 1%/1 mm, respectively. The MAE and r of the APs were 1.13 ± 0.33% and 0.35 ± 0.22 in 3%/2 mm, 1.68 ± 0.47% and 0.30 ± 0.11 in 2%/2 mm, and 5.08 ± 0.29% and 0.15 ± 0.10 in 1%/1 mm, respectively. The time cost was within 3 s for the prediction. The results suggest the DL-based model has the potential for rapid GPR prediction in Elekta Unity.
期刊介绍:
The purpose of the journal Radiological Physics and Technology is to provide a forum for sharing new knowledge related to research and development in radiological science and technology, including medical physics and radiological technology in diagnostic radiology, nuclear medicine, and radiation therapy among many other radiological disciplines, as well as to contribute to progress and improvement in medical practice and patient health care.