Decision Making in Surveillance of High-Grade Gliomas Using Perfusion MRI as Adjunct to Conventional MRI and Artificial Intelligence.

Copyright © 2019 by American Society of Clinical Oncology
Journal of Clinical Oncology. 2019 May;37(15)_suppl doi: 10.1200/JCO.2019.37.15_suppl.2054

Abstract

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.
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.
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).
CONCLUSIONS:
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.

Multi-Parametric MRI as Supplement to mRANO Criteria for Response Assessment to MDNA55 in Adults with Recurrent or Progressive Glioblastoma.

Copyright © 2019 by American Society of Clinical Oncology
Journal of Clinical Oncology. 2019 May;37(15)_suppl doi: 10.1200/JCO.2019.37.15_suppl.e13559

Abstract

BACKGROUND:
Modified response assessment in neuro-oncology (mRANO) criteria are widely used in GBM but seem insufficient to capture Pseudoprogression (PsP), which occurs due to extensive inflammatory infiltration, increased vascular permeability, tumor necrosis and edema. mRANO criteria recommend volumetric response evaluation using contrast-enhanced T1 subtraction maps for identifying PsP. Our approach incorporates multi-parametric MRI biomarkers to unravel the true PsP from recurrence or distinguish Pseudo Response (PsR) – following anti-VEGF agents – from delayed (immuno)response.
METHODS:
Multiple time-points MRI (18-24h after convection-enhance delivery of the anti-IL4-R agent MDNA55, then at 30-day intervals) was utilized to determine response. Multi-parametric MRI biomarkers analyzed included (1) 3D-FLAIR-T2-based tumor volume assessment reflecting edema, necrosis and tumor infiltration; (2) 3D-gadolinium-enhanced-based tumor volume estimation reflecting active tumor infiltration, neo-angiogenesis and disrupted blood brain barrier; (3) Dynamic susceptibility contrast-based relative cerebral blood volume (rCBV) measurements for estimation of the vascular tumour properties; and (4) Diffusion weighted imaging – Apparent diffusion coefficient measurements that assess interstitial edema, tumor cellularity and ischemic injury.
RESULTS:
We demonstrate similar imaging phenotypes on conventional FLAIR-T2- and enhanced T1- MR images among different disease states (PsP vs true progression, PsR vs and immuno-response) and describe the perfusion and diffusion MRI biomarkers that improve response staging including PsP masking true progression, PsP masking clinical response, early progression with delayed response, and differentiation between true and PsR. The results are compared with the mRANO-based assessments for concurrence.
CONCLUSIONS:
Incorporating multi-parametric MRI measurements to determine the complex underlying tissue processes enables a better assessment of PsP, PsR and delayed tumour response, and can supplement mRANO-based response assessments in GBM patients undergoing novel immunotherapies.