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

Abstract

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.

Differentiation between glioma recurrence and treatment effects using amide proton transfer imaging: A mini-Bayesian bivariate meta-analysis

“…The studies using single APT imaging parameters for quantitative synthesis included a total of 184 subjects and using multiparametric MRI combined with APT imaging parameters included a total of 205 subjects. The study design was perspective in three studies ( 11 , 17 , 19 ) and not explicit in one study ( 15 ). Only one study ( 15 ) enrolled patients restricted to those with suspected tumor progression within the first 3 months after chemotherapy.…”

“…In the index test domain, all studies had a low risk of bias. Four studies ( 15 – 17 , 19 ) had an unclear risk of bias for the reference standard domain, because it was unmentioned whether the results of the reference standard were interpreted without knowledge of the index test. In the flow and timing domain, all studies had a low risk of bias.…”

“…Regarding the applicability assessment, one study ( 17 ) had an unclear applicability concern in patient selection, as 4/74 cases did not receive radiotherapy. We had no concerns that the conduct and interpretation of the index test and the reference standard do not match our review questions in any of the studies.…”

“…The pooled sensitivity and specificity of the four studies were 0.92 (95% CI: 0.85–0.97) and 0.83 (95% CI: 0.55–0.97), respectively. The forest plot ( Figure 4 ) and the SROC plot ( Figure 5B ) showed that the primary source of heterogeneity was the study ( 17 ) that has a slightly higher sensitivity and extremely low specificity. With the exception of that study, the remaining three studies ( 16 , 18 , 19 ) showed no significant heterogeneity in sensitivity ( p = 0.846, I 2 = 0%) and specificity ( p = 0.978, I 2 = 0%).…”

Current emerging MRI tools for radionecrosis and pseudoprogression diagnosis

“…MR texture analysis and radiomics have been conducted mainly with conventional sequences, with already interesting results, especially in the evaluation of tumor shape features and surface irregularities in the diagnosis of glioblastoma versus pseudoprogression [131]. Adding complementary advanced sequences to this complex evaluation indeed promises to achieve higher diagnostic performances [132,133 ▪▪ ].…”