Voxel-wise analysis of dynamic (18)F-FET PET: a novel approach for non-invasive glioma characterisation

Enhancing predictability of IDH mutation status in glioma patients at initial diagnosis: a comparative analysis of radiomics from MRI, [18F]FET PET, and TSPO PET

PURPOSE

According to the World Health Organization classification for tumors of the central nervous system, mutation status of the isocitrate dehydrogenase (IDH) genes has become a major diagnostic discriminator for gliomas. Therefore, imaging-based prediction of IDH mutation status is of high interest for individual patient management. We compared and evaluated the diagnostic value of radiomics derived from dual positron emission tomography (PET) and magnetic resonance imaging (MRI) data to predict the IDH mutation status non-invasively.

METHODS

Eighty-seven glioma patients at initial diagnosis who underwent PET targeting the translocator protein (TSPO) using [18F]GE-180, dynamic amino acid PET using [18F]FET, and T1-/T2-weighted MRI scans were examined. In addition to calculating tumor-to-background ratio (TBR) images for all modalities, parametric images quantifying dynamic [18F]FET PET information were generated. Radiomic features were extracted from TBR and parametric images. The area under the receiver operating characteristic curve (AUC) was employed to assess the performance of logistic regression (LR) classifiers. To report robust estimates, nested cross-validation with five folds and 50 repeats was applied.

RESULTS

TBRGE-180 features extracted from TSPO-positive volumes had the highest predictive power among TBR images (AUC 0.88, with age as co-factor 0.94). Dynamic [18F]FET PET reached a similarly high performance (0.94, with age 0.96). The highest LR coefficients in multimodal analyses included TBRGE-180 features, parameters from kinetic and early static [18F]FET PET images, age, and the features from TBRT2 images such as the kurtosis (0.97).

CONCLUSION

The findings suggest that incorporating TBRGE-180 features along with kinetic information from dynamic [18F]FET PET, kurtosis from TBRT2, and age can yield very high predictability of IDH mutation status, thus potentially improving early patient management.

Prediction of Glioma Grade and IDH Status Using 18F-FET PET/CT Dynamic and Multiparametric Texture Analysis

Mutations in isocitrate dehydrogenase (IDH) represent an independent predictor of better survival in patients with gliomas. We aimed to assess grade and IDH mutation status in patients with untreated gliomas, by evaluating the respective value of 18F-FET PET/CT via dynamic and texture analyses. A total of 73 patients (male: 48, median age: 47) who underwent an 18F-FET PET/CT for initial glioma evaluation were retrospectively included. IDH status was available in 61 patients (20 patients with WHO grade 2 gliomas, 41 with grade 3-4 gliomas). Time-activity curve type and 20 parameters obtained from static analysis using LIFEx© v6.30 software were recorded. Respective performance was assessed using receiver operating characteristic curve analysis and stepwise multivariate regression analysis adjusted for patients' age and sex. The time-activity curve type and texture parameters derived from the static parameters showed satisfactory-to-good performance in predicting glioma grade and IDH status. Both time-activity curve type (stepwise OR: 101.6 (95% CI: 5.76-1791), p = 0.002) and NGLDM coarseness (stepwise OR: 2.08 × 1043 (95% CI: 2.76 × 1012-1.57 × 1074), p = 0.006) were independent predictors of glioma grade. No independent predictor of IDH status was found. Dynamic and texture analyses of 18F-FET PET/CT have limited predictive value for IDH status when adjusted for confounding factors. However, they both help predict glioma grade.

Feasibility of radiomic feature harmonization for pooling of [18F]FET or [18F]GE-180 PET images of gliomas

INTRODUCTION

Large datasets are required to ensure reliable non-invasive glioma assessment with radiomics-based machine learning methods. This can often only be achieved by pooling images from different centers. Moreover, trained models should perform with high accuracy when applied to data from different centers. In this study, the impact of reconstruction settings and segmentation methods on radiomic features derived from amino acid and TSPO PET images of glioma patients was examined. Additionally, the ability to model and thus reduce feature differences was investigated.

METHODS

[¹⁸F]FET and [¹⁸F]GE-180 PET data were acquired from 19 glioma patients. For each acquisition, 10 reconstruction settings and 9 segmentation methods were included to emulate multicentric data. Statistical robustness measures were calculated before and after ComBat harmonization. Differences between features due to setting variations were assessed using Friedman test, coefficient of variation (CV) and inter-rater reliability measures, including intraclass and Spearman's rank correlation coefficients and Fleiss' Kappa.

RESULTS

According to Friedman analyses, most features (>60%) showed significant differences. Yet, CV and inter-rater reliability measures indicated higher robustness. ComBat resulted in almost complete harmonization (>87%) according to Friedman test and little to no improvement according to CV and inter-rater reliability measures. [¹⁸F]GE-180 features were more sensitive to reconstruction settings than [¹⁸F]FET features.

CONCLUSIONS

According to Friedman test, feature distributions could be successfully aligned using ComBat. However, depending on settings, changes in patient ranks were observed for some features and could not be eliminated by harmonization. Thus, for clinical utilization it is recommended to exclude affected features.

Combination of pre-treatment dynamic [18F]FET PET radiomics and conventional clinical parameters for the survival stratification in patients with IDH-wildtype glioblastoma

PURPOSE

The aim of this study was to build and evaluate a prediction model which incorporates clinical parameters and radiomic features extracted from static as well as dynamic [18F]FET PET for the survival stratification in patients with newly diagnosed IDH-wildtype glioblastoma.

METHODS

A total of 141 patients with newly diagnosed IDH-wildtype glioblastoma and dynamic [18F]FET PET prior to surgical intervention were included. Patients with a survival time ≤ 12 months were classified as short-term survivors. First order, shape, and texture radiomic features were extracted from pre-treatment static (tumor-to-background ratio; TBR) and dynamic (time-to-peak; TTP) images, respectively, and randomly divided into a training (n = 99) and a testing cohort (n = 42). After feature normalization, recursive feature elimination was applied for feature selection using 5-fold cross-validation on the training cohort, and a machine learning model was constructed to compare radiomic models and combined clinical-radiomic models with selected radiomic features and clinical parameters. The area under the ROC curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were calculated to assess the predictive performance for identifying short-term survivors in both the training and testing cohort.

RESULTS

A combined clinical-radiomic model comprising six clinical parameters and six selected dynamic radiomic features achieved highest predictability of short-term survival with an AUC of 0.74 (95% confidence interval, 0.60-0.88) in the independent testing cohort.

CONCLUSIONS

This study successfully built and evaluated prediction models using [18F]FET PET-based radiomic features and clinical parameters for the individualized assessment of short-term survival in patients with a newly diagnosed IDH-wildtype glioblastoma. The combination of both clinical parameters and dynamic [18F]FET PET-based radiomic features reached highest accuracy in identifying patients at risk. Although the achieved accuracy level remained moderate, our data shows that the integration of dynamic [18F]FET PET radiomic data into clinical prediction models may improve patient stratification beyond established prognostic markers.

18F-FET PET radiomics-based survival prediction in glioblastoma patients receiving radio(chemo)therapy

Background

Quantitative image analysis based on radiomic feature extraction is an emerging field for survival prediction in oncological patients. 18F-Fluorethyltyrosine positron emission tomography (18F-FET PET) provides important diagnostic and grading information for brain tumors, but data on its use in survival prediction is scarce. In this study, we aim at investigating survival prediction based on multiple radiomic features in glioblastoma patients undergoing radio(chemo)therapy.

Methods

A dataset of 37 patients with glioblastoma (WHO grade 4) receiving radio(chemo)therapy was analyzed. Radiomic features were extracted from pre-treatment 18F-FET PET images, following intensity rebinning with a fixed bin width. Principal component analysis (PCA) was applied for variable selection, aiming at the identification of the most relevant features in survival prediction. Random forest classification and prediction algorithms were optimized on an initial set of 25 patients. Testing of the implemented algorithms was carried out in different scenarios, which included additional 12 patients whose images were acquired with a different scanner to check the reproducibility in prediction results.

Results

First order intensity variations and shape features were predominant in the selection of most important radiomic signatures for survival prediction in the available dataset. The major axis length of the 18F-FET-PET volume at tumor to background ratio (TBR) 1.4 and 1.6 correlated significantly with reduced probability of survival. Additional radiomic features were identified as potential survival predictors in the PTV region, showing 76% accuracy in independent testing for both classification and regression.

Conclusions

18F-FET PET prior to radiation provides relevant information for survival prediction in glioblastoma patients. Based on our preliminary analysis, radiomic features in the PTV can be considered a robust dataset for survival prediction.

Can Radiomics Provide Additional Information in [18F]FET-Negative Gliomas?

Simple Summary

Amino acid positron emission tomography (PET) complements standard magnetic resonance imaging (MRI) since it directly visualizes the increased amino acid transport into tumor cells. Amino acid PET using O-(2-[¹⁸F]fluoroethyl)-L-tyrosine ([¹⁸F]FET) has proven to be relevant, for example, for glioma classification, identification of tumor progression or recurrence, or for the delineation of tumor extent. Nevertheless, a relevant proportion of low-grade gliomas (30%) and few high-grade gliomas (5%) were found to show no or even decreased amino acid uptake by conventional visual analysis of PET images. Advanced image analysis with the extraction of radiomic features is known to provide more detailed information on tumor characteristics than conventional analyses. Hence, this study aimed to investigate whether radiomic features derived from dynamic [¹⁸F]FET PET data differ between [¹⁸F]FET-negative glioma and healthy background and thus provide information that cannot be extracted by visual read.

Abstract

The purpose of this study was to evaluate the possibility of extracting relevant information from radiomic features even in apparently [¹⁸F]FET-negative gliomas. A total of 46 patients with a newly diagnosed, histologically verified glioma that was visually classified as [¹⁸F]FET-negative were included. Tumor volumes were defined using routine T2/FLAIR MRI data and applied to extract information from dynamic [¹⁸F]FET PET data, i.e., early and late tumor-to-background (TBR_5–15, TBR_20–40) and time-to-peak (TTP) images. Radiomic features of healthy background were calculated from the tumor volume of interest mirrored in the contralateral hemisphere. The ability to distinguish tumors from healthy tissue was assessed using the Wilcoxon test and logistic regression. A total of 5, 15, and 69% of features derived from TBR_20–40, TBR_5–15, and TTP images, respectively, were significantly different. A high number of significantly different TTP features was even found in isometabolic gliomas (after exclusion of photopenic gliomas) with visually normal [¹⁸F]FET uptake in static images. However, the differences did not reach satisfactory predictability for machine-learning-based identification of tumor tissue. In conclusion, radiomic features derived from dynamic [¹⁸F]FET PET data may extract additional information even in [¹⁸F]FET-negative gliomas, which should be investigated in larger cohorts and correlated with histological and outcome features in future studies.

Differential Spatial Distribution of TSPO or Amino Acid PET Signal and MRI Contrast Enhancement in Gliomas

Simple Summary

Radiotracers targeting the translocator protein (TSPO) have recently gained substantial interest, since TSPO is overexpressed in malignant gliomas, where it correlates inversely with patient’s survival. The high-affinity TSPO PET ligand [¹⁸F]GE180 was found to depict tumor areas with a remarkably high contrast and has been shown to provide non-invasive information on histological tumor grades. Yet, its significance was questioned with the argument, that the high contrast may solely arise from nonspecific accumulation in tissue supplied by leaky vessels. This study aimed to address this question by providing a detailed evaluation of spatial associations between TSPO and amino acid PET with relative contrast enhancement in T1-weighted MRI. The results show that [¹⁸F]GE180 contrast does not reflect a disrupted blood–brain barrier (BBB) only and that multi-modal imaging generates complementary information, which may better depict spatial heterogeneity of tumor biology and may be used to individualize the therapy for each patient.

Abstract

In this study, dual PET and contrast enhanced MRI were combined to investigate their correlation per voxel in patients at initial diagnosis with suspected glioblastoma. Correlation with contrast enhancement (CE) as an indicator of BBB leakage was further used to evaluate whether PET signal is likely caused by BBB disruption alone, or rather attributable to specific binding after BBB passage. PET images with [¹⁸F]GE180 and the amino acid [¹⁸F]FET were acquired and normalized to healthy background (tumor-to-background ratio, TBR). Contrast enhanced images were normalized voxel by voxel with the pre-contrast T1-weighted MRI to generate relative CE values (rCE). Voxel-wise analysis revealed a high PET signal even within the sub-volumes without detectable CE. No to moderate correlation of rCE with TBR voxel-values and a small overlap as well as a larger distance of the hotspots delineated in rCE and TBR-PET images were detected. In contrast, voxel-wise correlation between both PET modalities was strong for most patients and hotspots showed a moderate overlap and distance. The high PET signal in tumor sub-volumes without CE observed in voxel-wise analysis as well as the discordant hotspots emphasize the specificity of the PET signals and the relevance of combined differential information from dual PET and MRI images.

Prediction of TERTp-mutation status in IDH-wildtype high-grade gliomas using pre-treatment dynamic [18F]FET PET radiomics

Purpose

To evaluate radiomic features extracted from standard static images (20–40 min p.i.), early summation images (5–15 min p.i.), and dynamic [¹⁸F]FET PET images for the prediction of TERTp-mutation status in patients with IDH-wildtype high-grade glioma.

Methods

A total of 159 patients (median age 60.2 years, range 19–82 years) with newly diagnosed IDH-wildtype diffuse astrocytic glioma (WHO grade III or IV) and dynamic [¹⁸F]FET PET prior to surgical intervention were enrolled and divided into a training (n = 112) and a testing cohort (n = 47) randomly. First-order, shape, and texture radiomic features were extracted from standard static (20–40 min summation images; TBR_20–40), early static (5–15 min summation images; TBR_5–15), and dynamic (time-to-peak; TTP) images, respectively. Recursive feature elimination was used for feature selection by 10-fold cross-validation in the training cohort after normalization, and logistic regression models were generated using the radiomic features extracted from each image to differentiate TERTp-mutation status. The areas under the ROC curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive value were calculated to illustrate diagnostic power in both the training and testing cohort.

Results

The TTP model comprised nine selected features and achieved highest predictability of TERTp-mutation with an AUC of 0.82 (95% confidence interval 0.71–0.92) and sensitivity of 92.1% in the independent testing cohort. Weak predictive capability was obtained in the TBR_5–15 model, with an AUC of 0.61 (95% CI 0.42–0.80) in the testing cohort, while no predictive power was observed in the TBR_20–40 model.

Conclusions

Radiomics based on TTP images extracted from dynamic [¹⁸F]FET PET can predict the TERTp-mutation status of IDH-wildtype diffuse astrocytic high-grade gliomas with high accuracy preoperatively.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05526-6.

Repeatability of image features extracted from FET PET in application to post-surgical glioblastoma assessment

Positron emission tomography (PET) imaging using the amino acid tracer O-[2-(¹⁸F)fluoroethyl]-L-tyrosine (FET) has gained increased popularity within the past decade in the management of glioblastoma (GBM). Radiomics features extracted from FET PET images may be sensitive to variations when imaging at multiple time points. It is therefore necessary to assess feature robustness to test-retest imaging. Eight patients with histologically confirmed GBM that had undergone post-surgical test-retest FET PET imaging were recruited. In total, 1578 radiomic features were extracted from biological tumour volumes (BTVs) delineated using a semi-automatic contouring method. Feature repeatability was assessed using the intraclass correlation coefficient (ICC). The effect of both bin width and filter choice on feature repeatability was also investigated. 59/106 (55.7%) features from the original image and 843/1472 (57.3%) features from filtered images had an ICC ≥ 0.85. Shape and first order features were most stable. Choice of bin width showed minimal impact on features defined as stable. The Laplacian of Gaussian (LoG, σ = 5 mm) and Wavelet filters (HLL and LHL) significantly improved feature repeatability (p ≪ 0.0001, p = 0.003, p = 0.002, respectively). Correlation of textural features with tumour volume was reported for transparency. FET PET radiomic features extracted from post-surgical images of GBM patients that are robust to test-retest imaging were identified. An investigation with a larger dataset is warranted to validate the findings in this study.

A Linearized Fit Model for Robust Shape Parameterization of FET-PET TACs

The kinetic analysis of [Formula: see text]-FET time-activity curves (TAC) can provide valuable diagnostic information in glioma patients. The analysis is most often limited to the average TAC over a large tissue volume and is normally assessed by visual inspection or by evaluating the time-to-peak and linear slope during the late uptake phase. Here, we derived and validated a linearized model for TACs of [Formula: see text]-FET in dynamic PET scans. Emphasis was put on the robustness of the numerical parameters and how reliably automatic voxel-wise analysis of TAC kinetics was possible. The diagnostic performance of the extracted shape parameters for the discrimination between isocitrate dehydrogenase (IDH) wildtype (wt) and IDH-mutant (mut) glioma was assessed by receiver-operating characteristic in a group of 33 adult glioma patients. A high agreement between the adjusted model and measured TACs could be obtained and relative, estimated parameter uncertainties were small. The best differentiation between IDH-wt and IDH-mut gliomas was achieved with the linearized model fitted to the averaged TAC values from dynamic FET PET data in the time interval 4-50 min p.i.. When limiting the acquisition time to 20-40 min p.i., classification accuracy was only slightly lower (-3%) and was comparable to classification based on linear fits in this time interval. Voxel-wise fitting was possible within a computation time ≈ 1 min per image slice. Parameter uncertainties smaller than 80% for all fits with the linearized model were achieved. The agreement of best-fit parameters when comparing voxel-wise fits and fits of averaged TACs was very high (p < 0.001).

Voxelwise Principal Component Analysis of Dynamic [S-Methyl-11C]Methionine PET Data in Glioma Patients

Recent works have demonstrated the added value of dynamic amino acid positron emission tomography (PET) for glioma grading and genotyping, biopsy targeting, and recurrence diagnosis. However, most of these studies are based on hand-crafted qualitative or semi-quantitative features extracted from the mean time activity curve within predefined volumes. Voxelwise dynamic PET data analysis could instead provide a better insight into intra-tumor heterogeneity of gliomas. In this work, we investigate the ability of principal component analysis (PCA) to extract relevant quantitative features from a large number of motion-corrected [S-methyl-¹¹C]methionine ([¹¹C]MET) PET frames. We first demonstrate the robustness of our methodology to noise by means of numerical simulations. We then build a PCA model from dynamic [¹¹C]MET acquisitions of 20 glioma patients. In a distinct cohort of 13 glioma patients, we compare the parametric maps derived from our PCA model to these provided by the classical one-compartment pharmacokinetic model (1TCM). We show that our PCA model outperforms the 1TCM to distinguish characteristic dynamic uptake behaviors within the tumor while being less computationally expensive and not requiring arterial sampling. Such methodology could be valuable to assess the tumor aggressiveness locally with applications for treatment planning and response evaluation. This work further supports the added value of dynamic over static [¹¹C]MET PET in gliomas.

A Critical Review of PET Tracers Used for Brain Tumor Imaging

The brain is a common site for metastases as well as primary tumors. Although evaluation of these malignancies with contrast-enhanced MR imaging defines current clinical practice, ¹⁸F-fluorodeoxyglucose (FDG)-PET has shown considerable utility in this area. In addition, many other tracers targeting various aspects of tumor biology have been developed and tested. This article discusses recent developments in PET imaging and the anticipated role of FDG and other tracers in the assessment of brain tumors.

Artificial Intelligence and Machine Learning in Nuclear Medicine: Future Perspectives

Artificial intelligence and machine learning based approaches are increasingly finding their way into various areas of nuclear medicine imaging. With the technical development of new methods and the expansion to new fields of application, this trend is likely to become even more pronounced in future. Possible means of application range from automated image reading and classification to correlation with clinical outcomes and to technological applications in image processing and reconstruction. In the context of tumor imaging, that is, predominantly FDG or PSMA PET imaging but also bone scintigraphy, artificial intelligence approaches can be used to quantify the whole-body tumor volume, for the segmentation and classification of pathological foci or to facilitate the diagnosis of micro-metastases. More advanced applications aim at the correlation of image features that are derived by artificial intelligence with clinical endpoints, for example, whole-body tumor volume with overall survival. In nuclear medicine imaging of benign diseases, artificial intelligence methods are predominantly used for automated and/or facilitated image classification and clinical decision making. Automated feature selection, segmentation and classification of myocardial perfusion scintigraphy can help in identifying patients that would benefit from intervention and to forecast clinical prognosis. Automated reporting of neurodegenerative diseases such as Alzheimer's disease might be extended to early diagnosis-being of special interest, if targeted treatment options might become available. Technological approaches include artificial intelligence-based attenuation correction of PET images, image reconstruction or anatomical landmarking. Attenuation correction is of special interest for avoiding the need of a coregistered CT scan, in the process of image reconstruction artefacts might be reduced, or ultra low-dose PET images might be denoised. The development of accurate ultra low-dose PET imaging might broaden the method's applicability, for example, toward oncologic PET screening. Most artificial intelligence approaches in nuclear medicine imaging are still in early stages of development, further improvements are necessary for broad clinical applications. In this review, we describe the current trends in the context fields of body oncology, cardiac imaging, and neuroimaging while an additional section puts emphasis on technological trends. Our aim is not only to describe currently available methods, but also to place a special focus on the description of possible future developments.

An update on PET-based molecular imaging in neuro-oncology: challenges and implementation for a precision medicine approach in cancer care

PET imaging using novel radiotracers show promises for tumor grading and molecular characterization through visualizing molecular and functional properties of the tumors. Application of PET tracers in brain neoplasm depends on both type of the neoplasm and the research or clinical significance required to be addressed. In clinical neuro-oncology, ¹⁸F-FDG is used mainly to differentiate tumor recurrence from radiation-induced necrosis, and novel PET agents show attractive imaging properties. Novel PET tracers can offer biologic information not visible via contrast-enhanced MRI or ¹⁸F-FDG PET. This review aims to provide an update on the complementary role of PET imaging in neuro-oncology both in research and clinical settings along with presenting interesting cases in this context.

18F-Fluoroethyl-tyrosine uptake is correlated with amino acid transport and neovascularization in treatment-naive glioblastomas

PURPOSE

To investigate the in vivo correlation between ¹⁸F-fluoroethyl-tyrosine (¹⁸F-FET) uptake and amino acid transporter expression and vascularization in treatment-naive glioblastomas.

METHODS

A total of 43 stereotactic biopsies were obtained from 13 patients with suspected glioblastoma prior to therapy. All patients underwent a dynamic ¹⁸F-FET PET/MRI scan before biopsy. Immunohistochemistry was performed using antibodies against SLC7A5 (amino acid transporter), MIB-1 (Ki67, proliferation), CD31 (vascularization) and CA-IX (hypoxia). The intensity of staining was correlated with ¹⁸F-FET uptake and the dynamic ¹⁸F-FET uptake slope at the biopsy target point.

RESULTS

In all patients, the final diagnosis was IDH-wildtype glioblastoma, WHO grade IV. Static ¹⁸F-FET uptake was significantly correlated with SLC7A5 staining (r = 0.494, p = 0.001). While the dynamic ¹⁸F-FET uptake slope did not show a significant correlation with amino acid transporter expression, it was significantly correlated with the number of CD31-positive vessels (r = -0.350, p = 0.031), which is line with earlier results linking ¹⁸F-FET kinetics with vascularization and perfusion. Besides, static ¹⁸F-FET uptake also showed correlations with CA-IX staining (r = 0.394, p = 0.009) and CD31 positivity (r = 0.410, p = 0.006). While the correlation between static ¹⁸F-FET uptake and SLC7A5 staining was confirmed as significant in multivariate analysis, this was not the case for the correlation with CD31 positivity, most likely because of the lower effect size and the relatively low number of samples. No significant correlation between ¹⁸F-FET uptake and Ki67 proliferation index was observed in our cohort.

CONCLUSION

Our results support the findings of preclinical studies suggesting that specific ¹⁸F-FET uptake in glioblastomas is mediated by amino acid transporters. As proposed previously, dynamic ¹⁸F-FET parameters might be more influenced by perfusion and therefore related to properties of the tumour neovascularization.