100 Toward the Co-clinical Glioblastoma Treatment Paradigm—Radiomic Machine Learning Identifies Glioblastoma Gene Expression in Patients and Corresponding Xenograft Tumor Models. Issue Volume 65:Issue CN(2018)Supplement 1 (16th August 2018)

• Record Type: Journal Article
• Authors: Zinn, Pascal O; Singh, Sanjay K; Kotrotsou, Aikaterini; Hassan, Islam; Luedi, Markus M; Thomas, Ginu; Elshafeey, Nabil; Mosley, Jennifer; Elakkad, Ahmed; Idris, Tagwa; Gumin, Joy; Fuller, Gregory N; de Groot, John; Baladandayuthapani, Veera; Sulman, Erik P; Kumar, Ashok M; Sawaya, Raymond; Lang, Frederick F; Piwnica-Worms, David; Colen, Rivka R
• Is Part Of: Neurosurgery. Volume 65:Issue CN(2018)Supplement 1
• Page Start: 80
• Page End: 80
• Publication Date: 2018-08-16
• Subjects: Nervous system -- Surgery -- Periodicals; 617.48005
• DOI: 10.1093/neuros/nyy303.100
• Languages: English
• ISSNs: 0148-396X

Abstract

Abstract: INTRODUCTION: Radiomics is extraction of multidimensional imaging features which when correlated with genomics is termed radiogenomics. The radiogenomic relationship has never been biologically validated. Towards creating a co-clinical glioblastoma treatment paradigm, we sought to establish causality between differential gene expression status and MRI-extracted radiomic-texture features in glioblastoma. METHODS: Radiogenomic predictions and validation were done using orthotopic xenograft models (n = 40) and the Cancer Genome Atlas glioblastoma patient cohort with matched imaging (n = 94). Tumor phenotypes were segmented and radiomic features extracted using machine learning algorithms. Patients and animals were dichotomized based on Periostin (POSTN) expression levels. RNA and protein levels confirmed RNAi-mediated POSTN knockdown. Total RNAs of tumor cells isolated from mouse brains (knockdown and control) was used for microarray-based expression profiling. Radiomic features were then utilized to predict POSTN expression status in patient and mouse, and interspecies. RESULTS: Our robust machine learning based analytical pipeline consists of segmentation, radiomic texture extraction, feature normalization and selection, and predictive-model generation. POSTN expression status was not associated with qualitative or volumetric MRI parameters. However, radiomic features significantly predicted POSTN expression status in both patients (AUC 100%, sensitivity/specificity: 100%/100%) and animal model (AUC 95.24%, sensitivity/specificity: 100%/88.88%). Furthermore, texture features in xenografts were significantly associated with humans with similar POSTN expression levels (AUC 74.36%, sensitivity/specificity: 74.42%/87.17%; P -value .0279). CONCLUSION: We established a high degree of causality between radiomic texture features and POSTN expression levels in a preclinical model with clinical validation. Our biologically validated machine learning-based radiomic pipeline also showed potential application in human-mouse matched co-clinical trials and opens an avenue for the personalized co-clinical glioblastoma treatment paradigm.