Fully automated analysis combining [18F]-FET-PET and multiparametric MRI including DSC perfusion and APTw imaging: a promising tool for objective evaluation of glioma progression.

PURPOSE: To evaluate diagnostic accuracy of fully automated analysis of multimodal imaging data using [18F]-FET-PET and MRI (including amide proton transfer-weighted (APTw) imaging and dynamic-susceptibility-contrast (DSC) perfusion) in differentiation of tumor progression from treatment-related changes in patients with glioma. MATERIAL AND METHODS: At suspected tumor progression, MRI and [18F]-FET-PET data as part of a retrospective analysis of an observational cohort of 66 patients/74 scans (51 glioblastoma and 23 lower-grade-glioma, 8 patients included at two different time points) were automatically segmented into necrosis, FLAIR-hyperintense, and contrast-enhancing areas using an ensemble of deep learning algorithms. In parallel, previous MR exam was processed in a similar way to subtract preexisting tumor areas and focus on progressive tumor only. Within these progressive areas, intensity statistics were automatically extracted from [18F]-FET-PET, APTw, and DSC-derived cerebral-blood-volume (CBV) maps and used to train a Random Forest classifier with threefold cross-validation. To evaluate contribution of the imaging modalities to the classifier's performance, impurity-based importance measures were collected. Classifier performance was compared with radiology reports and interdisciplinary tumor board assessments. RESULTS: In 57/74 cases (77%), tumor progression was confirmed histopathologically (39 cases) or via follow-up imaging (18 cases), while remaining 17 cases were diagnosed as treatment-related changes. The classification accuracy of the Random Forest classifier was 0.86, 95% CI 0.77-0.93 (sensitivity 0.91, 95% CI 0.81-0.97; specificity 0.71, 95% CI 0.44-0.9), significantly above the no-information rate of 0.77 (p = 0.03), and higher compared to an accuracy of 0.82 for MRI (95% CI 0.72-0.9), 0.81 for [18F]-FET-PET (95% CI 0.7-0.89), and 0.81 for expert consensus (95% CI 0.7-0.89), although these differences were not statistically significant (p > 0.1 for all comparisons, McNemar test). [18F]-FET-PET hot-spot volume was single-most important variable, with relevant contribution from all imaging modalities. CONCLUSION: Automated, joint image analysis of [18F]-FET-PET and advanced MR imaging techniques APTw and DSC perfusion is a promising tool for objective response assessment in gliomas.

Methylation subgroup and molecular heterogeneity is a hallmark of glioblastoma: implications for biopsy targeting, classification and therapy.

BACKGROUND: Intratumoral heterogeneity at the cellular and molecular level is a hallmark of glioblastoma (GB) that contributes to treatment resistance and poor clinical outcome. Little is known regarding epigenetic heterogeneity and intratumoral phylogeny and their implication for molecular classification and targeted therapies. PATIENTS AND METHODS: Multiple tissue biopsies (238 in total) were sampled from 56 newly-diagnosed, treatment-naive GB patients from a prospective in-house cohort and publicly available data and profiled for DNA methylation using the Illumina MethylationEPIC array. Methylation-based classification using the glioma classifier developed by Ceccarelli et al. and estimation of the MGMT promoter methylation status via the MGMT-STP27 model were carried out. In addition, copy number variations (CNVs) and phylogeny were analyzed. RESULTS: Almost half of the patients (22/56, 39%) harbored tumors composed of heterogeneous methylation subtypes. We found two predominant subtype combinations: classic-/mesenchymal-like, and mesenchymal-/pilocytic astrocytoma-like. Nine patients (16%) had tumors composed of subvolumes with and without MGMT promoter methylation, whereas 20 patients (36%) were homogeneously methylated, and 27 patients (48%) were homogeneously unmethylated. CNV analysis revealed high variations in many genes, including CDKN2A/B, EGFR, and PTEN. Phylogenetic analysis correspondingly showed a general pattern of CDKN2A/B loss and gain of EGFR, PDGFRA, and CDK4 during early stages of tumor development. CONCLUSIONS: (Epi)genetic intratumoral heterogeneity is a hallmark of GB, both at DNA methylation and CNV level. This intratumoral heterogeneity is of utmost importance for molecular classification as well as for defining therapeutic targets in this disease, as single biopsies might underestimate the true molecular diversity in a tumor.

Optimal classification of long echo time in vivo magnetic resonance spectra in the detection of recurrent brain tumors.

We describe the optimal high-level postprocessing of single-voxel (1)H magnetic resonance spectra and assess the benefits and limitations of automated methods as diagnostic aids in the detection of recurrent brain tumor. In a previous clinical study, 90 long-echo-time single-voxel spectra were obtained from 52 patients and classified during follow-up (30/28/32 normal/non-progressive tumor/tumor). Based on these data, a large number of evaluation strategies, including both standard resonance line quantification and algorithms from pattern recognition and machine learning, were compared in a quantitative evaluation. Results from linear and non-linear feature extraction, including ICA, PCA and wavelet transformations, and also the data from resonance line quantification were combined systematically with different classifiers such as LDA, chemometric methods (PLS, PCR), support vector machines and ensemble methods. Classification accuracy was assessed using a leave-one-out cross-validation scheme and the area under the curve (AUC) of the receiver operator characteristic (ROC). A regularized linear regression on spectra with binned channels reached 91% classification accuracy compared with 83% from quantification. Interpreting the loadings of these regressions, we find that lipid and lactate signals are too unreliable to be used in a simple machine rule. Choline and NAA are the main source of relevant information. Overall, we find that fully automated pattern recognition algorithms perform as well as, or slightly better than, a manually controlled and optimized resonance line quantification.