DECISION MAKING IN SURVEILLANCE OF HIGH-GRADE GLIOMAS USING PERFUSION MRI AS ADJUNCT TO CONVENTIONAL MRI AND ARTIFICIAL INTELLIGENCE. Sotirios Bisdas 1 , Loizos Shakallis 2 , Andy McEvoy 2 ,, Anna oMiserocchi 2 George Samanduras 2 , Sebastian Brandner 3 , Jeremy Rees 3 , Naomi Fersht 4 , Jorge M Cardoso 5 , Jasmina Panovska-Griffiths 6 , Carole Sudre 7 , Faiq Shaikh 8 , Diana Roettger 8 ; Department of Neuroradiology, University College London Hospitals, London, United Kingdom 1 ; Department of Neurosurgery, University College London Hospitals, London 2 , United Kingdom 2 ; Department of Neurology, University College London Hospitals, London, United Kingdom 3 ; Department of Radiation Oncology, University College London Hospitals, London, United Kingdom 4 ; Imaging and Biomedical Engineering, King's College London, London, United Kingdom 5 ; Department of Applied Health Research, University College London, London, United Kingdom 6 ; Imaging and Biomedical Engineering, King’s College London, London, United Kingdom 7 ; Image Analysis Group, London, United Kingdom 8 . BACKGROUND: Surveillance of High-Grade Gliomas (HGGs) remains a major challenge in clinical neurooncology. Histopathological validation is not an option during the course of disease and imaging surveillance suffers from ambiguous features of both disease progression and treatment related changes. This study aimed to differentiate between Pseudoprogression (PsP) and Progressive Disease (PD) using an artificial intelligence (support vector machine - SVM) classification algorithm. RESULTS: Our results indicate that the addition of multiple time point perfusion MRI combined with structural (conventional with gadolinium-enhanced sequences) MRI features results in optimal classification performance (median error rate: 0.016, lowest value dispersion). Subtracted feature datasets improved classification performance, more prominently when the final and first perfusion studies were included in the analysis. On the contrary, in the single time point group analysis, structural feature-based classification performed best (median error rate: 0.012) (Figures 1-3). CONCLUSION: Validation of our results with a larger patient cohort may have significant clinical importance in optimising imaging surveillance and clinical decision making for patients with HGG. REFERENCES: 1. Ammirati, M., et al. (1987). "Effect of the extent of surgical resection on survival and quality of life in patients with supratentorial glioblastomas and anaplastic astrocytomas." Neurosurgery 21(2): 201-206. 2. Ananthnarayan, S., et al. (2008). "Time course of imaging changes of GBM during extended bevacizumab treatment." Journal of neuro-oncology 88(3): 339-347. 3. Artzi, M., et al. (2016). "Differentiation between treatment-related changes and progressive disease in patients with high grade brain tumors using support vector machine classification based on DCE MRI." Journal of neuro-oncology 127(3): 515-524. METHODS: Two groups of patients with histologically proven HGGs were analysed, a group with a single time point DSC perfusion MRI (45 patients) and a group with multiple time point DSC perfusion MRI (19 patients). Both groups included conventional MRI studies prior and after each perfusion MRI. This study design aimed to replicate decision making in clinical practice including multiple previous studies for each patient. SVM training was performed with all available MRI studies for each group and classification was based on different feature datasets from a single or multiple (subtracted features) time points. Classification accuracy comparisons were performed by calculating prediction error rates for different feature datasets and different time point analyses.