Breto Adrian L, Cullison Kaylie, Zacharaki Evangelia I, Wallaengen Veronica, Maziero Danilo, Jones Kolton, Valderrama Alessandro, de la Fuente Macarena I, Meshman Jessica, Azzam Gregory A, Ford John C, Stoyanova Radka, Mellon Eric A
Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, Miller School of Medicine, University of Miami, Miami, FL 33136, USA.
Department of Radiation Medicine & Applied Sciences, UC San Diego Health, La Jolla, CA 92093, USA.
Cancers (Basel). 2023 Oct 31;15(21):5241. doi: 10.3390/cancers15215241.
Glioblastoma changes during chemoradiotherapy are inferred from high-field MRI before and after treatment but are rarely investigated during radiotherapy. The purpose of this study was to develop a deep learning network to automatically segment glioblastoma tumors on daily treatment set-up scans from the first glioblastoma patients treated on MRI-linac. Glioblastoma patients were prospectively imaged daily during chemoradiotherapy on 0.35T MRI-linac. Tumor and edema (tumor lesion) and resection cavity kinetics throughout the treatment were manually segmented on these daily MRI. Utilizing a convolutional neural network, an automatic segmentation deep learning network was built. A nine-fold cross-validation schema was used to train the network using 80:10:10 for training, validation, and testing. Thirty-six glioblastoma patients were imaged pre-treatment and 30 times during radiotherapy ( = 31 volumes, total of 930 MRIs). The average tumor lesion and resection cavity volumes were 94.56 ± 64.68 cc and 72.44 ± 35.08 cc, respectively. The average Dice similarity coefficient between manual and auto-segmentation for tumor lesion and resection cavity across all patients was 0.67 and 0.84, respectively. This is the first brain lesion segmentation network developed for MRI-linac. The network performed comparably to the only other published network for auto-segmentation of post-operative glioblastoma lesions. Segmented volumes can be utilized for adaptive radiotherapy and propagated across multiple MRI contrasts to create a prognostic model for glioblastoma based on multiparametric MRI.
胶质母细胞瘤在放化疗期间的变化可通过治疗前后的高场强磁共振成像（MRI）推断得出，但在放疗期间却很少被研究。本研究的目的是开发一种深度学习网络，用于在MRI直线加速器治疗的首批胶质母细胞瘤患者的每日治疗摆位扫描中自动分割胶质母细胞瘤肿瘤。胶质母细胞瘤患者在0.35T MRI直线加速器上进行放化疗期间每天进行前瞻性成像。在这些每日的MRI图像上手动分割整个治疗过程中的肿瘤、水肿（肿瘤病变）和切除腔的动力学变化。利用卷积神经网络构建了一个自动分割深度学习网络。采用九折交叉验证方案，以80:10:10的比例用于训练、验证和测试来训练网络。36例胶质母细胞瘤患者在治疗前进行了成像，并在放疗期间成像30次（共31个容积，总计930幅MRI图像）。肿瘤病变和切除腔的平均体积分别为94.56±64.68立方厘米和72.44±35.08立方厘米。所有患者肿瘤病变和切除腔手动分割与自动分割之间的平均骰子相似系数分别为0.67和0.84。这是首个为MRI直线加速器开发的脑病变分割网络。该网络的表现与另一篇已发表的用于术后胶质母细胞瘤病变自动分割的网络相当。分割后的体积可用于自适应放疗，并在多个MRI对比中进行传播，以基于多参数MRI创建胶质母细胞瘤的预后模型。
