Radiomics signature for temporal evolution and recurrence patterns of glioblastoma using multimodal magnetic resonance imaging

• Published in: NMR in biomedicine Vol. 35; no. 3; pp. e4647 - n/a
• Main Authors: Chougule, Tanay, Gupta, Rakesh K., Saini, Jitender, Agrawal, Shaleen, Gupta, Mamta, Vakharia, Nirvi, Singh, Anup, Patir, Rana, Vaishya, Sandeep, Ingalhalikar, Madhura
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.03.2022
• Subjects: Adult; Aged; Biological products; Biomarkers; Brain Neoplasms - diagnostic imaging; Diffusion coefficient; Female; Glioblastoma; Glioblastoma - diagnostic imaging; glioblastoma | MRI | radionics | recurrence | temporal evolution; Humans; Learning algorithms; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; Multimodal Imaging - methods; Neoplasm Recurrence, Local - diagnostic imaging; Radiation; Radiomics; Retrospective Studies; Young Adult; glioblastoma | MRI | radionics | recurrence | temporal evolution
• ISSN: 0952-3480; 1099-1492; 1099-1492
• DOI: 10.1002/nbm.4647

Glioblastoma is a highly infiltrative neoplasm with a high propensity of recurrence. The location of recurrence usually cannot be anticipated and depends on various factors, including the surgical resection margins. Currently, radiation planning utilizes the hyperintense signal from T2‐FLAIR MRI and is delivered to a limited area defined by standardized guidelines. To this end, noninvasive early prediction and delineation of recurrence can aid in tailored targeted therapy, which may potentially delay the relapse, consequently improving overall survival. In this work, we hypothesize that radiomics‐based phenotypic quantifiers may support the detection of recurrence before it is visualized on multimodal MRI. We employ retrospective longitudinal data from 29 subjects with a varying number of time points (three to 13) that includes glioblastoma recurrence. Voxelwise textural and intensity features are computed from multimodal MRI (T1‐contrast enhanced [T1CE], FLAIR, and apparent diffusion coefficient), primarily to gain insights into longitudinal radiomic changes from preoperative MRI to recurrence and subsequently to predict the region of relapse from 143 ± 42 days before recurrence using machine learning. T1CE MRI first‐order and gray‐level co‐occurrence matrix features are crucial in detecting local recurrence, while multimodal gray‐level difference matrix and first‐order features are highly predictive of the distant relapse, with a voxelwise test accuracy of 80.1% for distant recurrence and 71.4% for local recurrence. In summary, our work exemplifies a step forward in predicting glioblastoma recurrence using radiomics‐based phenotypic changes that may potentially serve as MR‐based biomarkers for customized therapeutic intervention. Our work outlines phenotypic voxelwise quantitative radiomics, which have a unique capability to illustrate early microstructural and tissue‐level alterations. These textural maps employed in a multivariate machine‐learning framework predict an accurate region of glioblastoma recurrence prior to its visual appearance in images. Moreover, we also illustrate the temporal course of radiomic changes leading to glioblastoma relapse. Such early detection of glioblastoma recurrence can support treatment plans at a personalized level, and aid strategizing radiation therapies to include potential recurrence regions.