Abstract #0623

Radiomic Texture Features from MR Perfusion images Predicts Pseudoprogression from True Progression in Glioblastoma Patients: A Multi-Institutional Study

Aikaterini Kotrotsou¹, Nabil A Elshafeey¹, Srishti Abrol ¹, Dunia Giniebra Camejo², Islam Hassan¹, Ahmed Hassan¹, Kamel El Salek¹, Ahmed T Shaaban¹, Samuel Bergamaschi³, Fanny E Moron⁴, Meng Law³, Pascal O Zinn⁵, and Rivka R Colen^1,2

¹Diagnostic Radiology, MD Anderson Cancer Center, Houston, TX, United States, ²Cancer Systems Imaging, MD Anderson Cancer Center, Houston, TX, United States, ³Neuroradiology, University of Southern California Keck Medical Center, Los Angeles, CA, United States, ⁴Neuroradiology, Baylor College of Medicine, Houston, TX, United States, ⁵Neurosurgery, Baylor College of Medicine, Houston, TX, United States

Response assessment criteria, such as RANO, struggle to distinguish between true progression and pseudoprogression. In this work we evaluated the performance of radiomic texture features extracted from MR perfusion images (Dynamic contrast enhancement (DCE) and Dynamic susceptibility contrast (DSC)) in discriminating true progression from pseudoprogression. Using a large multi-institutional cohort, we demonstrated that changes in texture features of perfusion maps (DCE and DSC) can be effective predictors of progressive disease. We present a noninvasive, complimentary method that is directly applicable in clinical setting and can assist physicians in diagnosis and therapy planning.

This abstract and the presentation materials are available to members only; a login is required.

Join Here