A Deep Learning Approach for Automatic Segmentation during Daily MRI-Linac Radiotherapy of Glioblastoma

• Published in: Cancers Vol. 15; no. 21; p. 5241
• Main Authors: 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
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 31.10.2023
• Subjects: auto-segmentation; Biopsy; Brain cancer; Brain damage; Brain research; Chemoradiotherapy; Deep learning; Edema; Glioblastoma; Glioblastoma multiforme; Image processing; Lesions; Magnetic resonance imaging; MRI; MRI-linac; Neural networks; Patients; Radiation; Radiation therapy; Radiotherapy; Segmentation; Software; Tumors; United States > US; MRI-linac; auto-segmentation; deep learning; glioblastoma; MRI; radiation therapy
• ISSN: 2072-6694; 2072-6694
• 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.