Multiple Survival Outcome Prediction of Glioblastoma Patients Based on Multiparametric MRI

Performance of 18 F-FAPI PET/CT in assessing glioblastoma before radiotherapy: a pilot study

BACKGROUND

We aimed to determine the performance of ¹⁸ F-FAPI PET/CT used for preprocedural assessment of glioblastoma before radiotherapy.

METHODS

Twelve glioblastoma patients having undergone incomplete surgical resection or biopsy were examined with ¹⁸ F-FAPI PET/CT and MRI scanning before radiotherapy. All patients had confirmed tumor residues according to findings of histopathological and/or long-term clinical and radiological follow-ups. Lesion characterization data, including SUV_max and tumor-to-background ratio (TBR) on PET/CT were attained. PET/CT and MRI findings were compared in terms of number of lesions. The correlation between immunohistochemistry, molecular expression, and PET/CT parameters was also evaluated.

RESULTS

¹⁸ F-FAPI PET/CT detected 16 FAPI-avid out of 23 lesions in 12 patients described on MRI. MRI was statistically different from ¹⁸ F-FAPI PET/CT for lesion detection according to the exact McNemar statistical test (P = 0.0156). The SUV_max and TBR of the glioblastomas was 7.08 ± 3.55 and 19.95 ± 13.22, respectively. The sensitivity and positive predictive value (PPV) of ¹⁸ F-FAPI PET were 69.6% and 100%, respectively. Neither the Ki-67 index nor the molecular expression was correlated with the FAPI-PET/CT parameters.

CONCLUSION

¹⁸ F-FAPI PET/CT detects glioblastomas at a lower rate than MRI. However, the 100% PPV of the examination may make it useful for differentiating controversial lesions detected on MRI. The ¹⁸ F-FAPI-avid lesions are displayed more clearly probably due to a higher TBR. ¹⁸ F-FAPI PET/CT imaging might find application in glioblastoma biopsy and radiotherapy planning.

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.

Radiogenomics to characterize the immune-related prognostic signature associated with biological functions in glioblastoma

OBJECTIVES

The tumor microenvironment and immune cell infiltration (ICI) associated with glioblastoma (GBM) play a vital role in cancer development, progression, and prognosis. This study aimed to establish an ICI-related prognostic biomarker and explore the associations between ICI signatures and radiomic features in patients with GBM.

METHODS

The gene expression and survival data of patients with GBM were obtained from three databases. Based on the ICI pattern, an individualized ICI score for each GBM patient was developed in the discovery set (n = 400) and independently verified in the validation set (n = 374). A total of 5915 radiomic features were extracted from the intratumoral and peritumoral regions. Recursive feature elimination and support vector machine methods were performed to select the key features and generate a model predictive of low- or high- ICI scores. The prognostic value of the identified radio genomic model was examined in an independent dataset (n = 149) using imaging and survival data.

RESULTS

We found that higher ICI scores often indicated worse patient prognosis (multivariable hazard ratio: 0.48 and 0.63 in discovery and validation set, respectively) and higher expression levels of immune checkpoint-related genes. A model that combined 11 radiomic features could well distinguish tumors with different ICI scores (AUC = 0.96, accuracy = 94%). This model was proven to be helpful for noninvasive prognostic stratification in an independent validation cohort.

CONCLUSIONS

ICI scores may serve as an effective prognostic biomarker to characterize potential biological processes in patients with GBM. This ICI signature can be evaluated noninvasively through radiogenomic analysis.

KEY POINTS

• Immune cell infiltration (ICI) scores can serve as an effective prognostic biomarker in patients with glioblastoma. • The ICI signature can be evaluated noninvasively through radiomic features derived from the intratumoral and peritumoral regions. • The prognostic value of the radiogenomic model can be verified by independent survival and MRI data.