Prediction of Prognosis in Glioblastoma Using Radiomics Features of Dynamic Contrast-Enhanced MRI

Prediction of prognosis in glioblastoma with radiomics features extracted by synthetic MRI images using cycle-consistent GAN

To propose a style transfer model for multi-contrast magnetic resonance imaging (MRI) images with a cycle-consistent generative adversarial network (CycleGAN) and evaluate the image quality and prognosis prediction performance for glioblastoma (GBM) patients from the extracted radiomics features. Style transfer models of T1 weighted MRI image (T1w) to T2 weighted MRI image (T2w) and T2w to T1w with CycleGAN were constructed using the BraTS dataset. The style transfer model was validated with the Cancer Genome Atlas Glioblastoma Multiforme (TCGA-GBM) dataset. Moreover, imaging features were extracted from real and synthesized images. These features were transformed to rad-scores by the least absolute shrinkage and selection operator (LASSO)-Cox regression. The prognosis performance was estimated by the Kaplan-Meier method. For the accuracy of the image quality of the real and synthesized MRI images, the MI, RMSE, PSNR, and SSIM were 0.991 ± 2.10 × 10 - 4 , 2.79 ± 0.16, 40.16 ± 0.38, and 0.995 ± 2.11 × 10 - 4 , for T2w, and .992 ± 2.63 × 10 - 4 , 2.49 ± 6.89 × 10 - 2 , 40.51 ± 0.22, and 0.993 ± 3.40 × 10 - 4 for T1w, respectively. The survival time had a significant difference between good and poor prognosis groups for both real and synthesized T2w (p < 0.05). However, the survival time had no significant difference between good and poor prognosis groups for both real and synthesized T1w. On the other hand, there was no significant difference between the real and synthesized T2w in both good and poor prognoses. The results of T1w were similar in the point that there was no significant difference between the real and synthesized T1w. It was found that the synthesized image could be used for prognosis prediction. The proposed prognostic model using CycleGAN could reduce the cost and time of image scanning, leading to a promotion to build the patient's outcome prediction with multi-contrast images.

Multiparametric MRI-based radiomic nomogram for predicting HER-2 2+ status of breast cancer

Objective

To explore the application of multiparametric MRI-based radiomic nomogram for assessing HER-2 2+ status of breast cancer (BC).

Methods

Patients with pathology-proven HER-2 2+ invasive BC, who underwent preoperative MRI were divided into training (72 patients, 21 HER-2-positive and 51 HER-2-negative) and validation (32 patients, 9 HER-2-positive and 23 HER-2-negative) sets by randomization. All were classified as HER-2 2+ FISH-positive (HER-2-positive) or -negative (HER-2-negative) according to IHC and FISH. The 3D VOI was drawn on MR images by two radiologists. ADC, T2WI, and DCE images were analyzed separately to extract features (n = 1906). L1 regularization, F-test, and other methods were used to reduce dimensionality. Binary radiomics prediction models using features from single or combined imaging sequences were constructed using logistic regression (LR) classifier then and validated on a validation dataset. To build a radiomics nomogram, multivariate LR analysis was conducted to identify independent indicators. An evaluation of the model's predictive efficacy was made using AUC.

Results

On the basis of combined ADC, T2WI, and DCE images, ten radiomic features were extracted following feature dimensionality reduction. There was superior diagnostic efficiency of radiomic signature using all three sequences compared to either one or two sequences (AUC for training group: 0.883; AUC for validation group: 0.816). Based on multivariate LR analysis, radiomic signature and peritumoral edema were independent predictors for identifying HER-2 2 +. In both training and validation datasets, nomograms combining peritumoral edema and radiomics signature demonstrated an effective discrimination (AUCs were respectively 0.966 and 0. 884).

Conclusion

The nomogram that incorporated peritumoral edema and multiparametric MRI-based radiomic signature can be used to effectively predict the HER-2 2+ status of BC.

Diffusion- and Perfusion-Weighted MRI Radiomics for Survival Prediction in Patients with Lower-Grade Gliomas

PURPOSE

Lower-grade gliomas of histologic grades 2 and 3 follow heterogenous clinical outcomes, which necessitates risk stratification. This study aimed to evaluate whether diffusion-weighted and perfusion-weighted MRI radiomics allow overall survival (OS) prediction in patients with lower-grade gliomas and investigate its prognostic value.

MATERIALS AND METHODS

In this retrospective study, radiomic features were extracted from apparent diffusion coefficient, relative cerebral blood volume map, and Ktrans map in patients with pathologically confirmed lower-grade gliomas (January 2012-February 2019). The radiomics risk score (RRS) calculated from selected features constituted a radiomics model. Multivariable Cox regression analysis, including clinical features and RRS, was performed. The models' integrated area under the receiver operating characteristic curves (iAUCs) were compared. The radiomics model combined with clinical features was presented as a nomogram.

RESULTS

The study included 129 patients (median age, 44 years; interquartile range, 37-57 years; 63 female): 90 patients for training set and 39 patients for test set. The RRS was an independent risk factor for OS with a hazard ratio of 6.01. The combined clinical and radiomics model achieved superior performance for OS prediction compared to the clinical model in both training (iAUC, 0.82 vs. 0.72, p=0.002) and test sets (0.88 vs. 0.76, p=0.04). The radiomics nomogram combined with clinical features exhibited good agreement between the actual and predicted OS with C-index of 0.83 and 0.87 in the training and test sets, respectively.

CONCLUSION

Adding diffusion- and perfusion-weighted MRI radiomics to clinical features improved survival prediction in lower-grade glioma.

Added prognostic value of 3D deep learning-derived features from preoperative MRI for adult-type diffuse gliomas

BACKGROUND

To investigate the prognostic value of spatial features from whole-brain MRI using a three-dimensional (3D) convolutional neural network for adult-type diffuse gliomas.

METHODS

In a retrospective, multicenter study, 1925 diffuse glioma patients were enrolled from 5 datasets: SNUH (n = 708), UPenn (n = 425), UCSF (n = 500), TCGA (n = 160), and Severance (n = 132). The SNUH and Severance datasets served as external test sets. Precontrast and postcontrast 3D T1-weighted, T2-weighted, and T2-FLAIR images were processed as multichannel 3D images. A 3D-adapted SE-ResNeXt model was trained to predict overall survival. The prognostic value of the deep learning-based prognostic index (DPI), a spatial feature-derived quantitative score, and established prognostic markers were evaluated using Cox regression. Model evaluation was performed using the concordance index (C-index) and Brier score.

RESULTS

The MRI-only median DPI survival prediction model achieved C-indices of 0.709 and 0.677 (BS = 0.142 and 0.215) and survival differences (P < 0.001 and P = 0.002; log-rank test) for the SNUH and Severance datasets, respectively. Multivariate Cox analysis revealed DPI as a significant prognostic factor, independent of clinical and molecular genetic variables: hazard ratio = 0.032 and 0.036 (P < 0.001 and P = 0.004) for the SNUH and Severance datasets, respectively. Multimodal prediction models achieved higher C-indices than models using only clinical and molecular genetic variables: 0.783 vs. 0.774, P = 0.001, SNUH; 0.766 vs. 0.748, P = 0.023, Severance.

CONCLUSIONS

The global morphologic feature derived from 3D CNN models using whole-brain MRI has independent prognostic value for diffuse gliomas. Combining clinical, molecular genetic, and imaging data yields the best performance.

Added value of dynamic contrast-enhanced MR imaging in deep learning-based prediction of local recurrence in grade 4 adult-type diffuse gliomas patients

Local recurrences in patients with grade 4 adult-type diffuse gliomas mostly occur within residual non-enhancing T2 hyperintensity areas after surgical resection. Unfortunately, it is challenging to distinguish non-enhancing tumors from edema in the non-enhancing T2 hyperintensity areas using conventional MRI alone. Quantitative DCE MRI parameters such as Ktrans and Ve convey permeability information of glioblastomas that cannot be provided by conventional MRI. We used the publicly available nnU-Net to train a deep learning model that incorporated both conventional and DCE MRI to detect the subtle difference in vessel leakiness due to neoangiogenesis between the non-recurrence area and the local recurrence area, which contains a higher proportion of high-grade glioma cells. We found that the addition of Ve doubled the sensitivity while nonsignificantly decreasing the specificity for prediction of local recurrence in glioblastomas, which implies that the combined model may result in fewer missed cases of local recurrence. The deep learning model predictive of local recurrence may enable risk-adapted radiotherapy planning in patients with grade 4 adult-type diffuse gliomas.

Multiparametric MRI-based fusion radiomics for predicting telomerase reverse transcriptase (TERT) promoter mutations and progression-free survival in glioblastoma: a multicentre study

PURPOSE

This study evaluated the performance of multiparametric magnetic resonance imaging (MRI)-based fusion radiomics models (MMFRs) to predict telomerase reverse transcriptase (TERT) promoter mutation status and progression-free survival (PFS) in glioblastoma patients.

METHODS

We retrospectively analysed 208 glioblastoma patients from two hospitals. Quantitative imaging features were extracted from each patient's T1-weighted, T1-weighted contrast-enhanced, and T2-weighted preoperative images. Using a coarse-to-fine feature selection strategy, four radiomics signature models were constructed based on the three MRI sequences and their combination for TERT promoter mutation status and PFS; model performance was subsequently evaluated. Subgroup analyses were performed by the radiomics signature of TERT promoter mutation status and PFS to distinguish patients who could benefit from prolonged temozolomide chemotherapy cycles.

RESULTS

TERT promoter mutation status was best predicted by MMFR, with an area under the curve (AUC) of 0.816 and 0.812 for the training and internal validation sets, respectively. The external test set also achieved stable and optimal prediction results (AUC, 0.823). MMFR better predicted patient PFS compared with the single-sequence radiomics signature in the test set (C-index, 0.643 vs 0.561 vs 0.620 vs 0.628). Subgroup analyses showed that more than six cycles of postoperative temozolomide chemotherapy were associated with improved PFS for patients in class 2 (high TERT promoter mutation and high survival rates; HR, 0.222; 95% CI, 0.054 - 0.923; p = 0.025).

CONCLUSION

MMFR is an effective method to predict TERT promoter mutations and PFS in patients with glioblastoma. Moreover, subgroup analysis could differentiate patients who may benefit from prolonged TMZ chemotherapy cycles.

Pretreatment MR-based radiomics in patients with glioblastoma: A systematic review and meta-analysis of prognostic endpoints

PURPOSE

Recent studies have shown promise of MR-based radiomics in predicting the survival of patients with untreated glioblastoma. This study aimed to comprehensively collate evidence to assess the prognostic value of radiomics in glioblastoma.

METHODS

PubMed-MEDLINE, Embase, and Web of Science were searched to find original articles investigating the prognostic value of MR-based radiomics in glioblastoma published up to July 14, 2023. Concordance indexes (C-indexes) and Cox proportional hazards ratios (HRs) of overall survival (OS) and progression-free survival (PFS) were pooled via random-effects modeling. For studies aimed at classifying long-term and short-term PFS, a hierarchical regression model was used to calculate pooled sensitivity and specificity. Between-study heterogeneity was assessed using the Higgin inconsistency index (I2). Subgroup regression analysis was performed to find potential factors contributing to heterogeneity. Publication bias was assessed via funnel plots and the Egger test.

RESULTS

Among 1371 abstracts, 18 and 17 studies were included for qualitative and quantitative data synthesis, respectively. Respective pooled C-indexes and HRs for OS were 0.65 (95 % confidence interval [CI], 0.58-0.72) and 2.88 (95 % CI, 2.28-3.64), whereas those for PFS were 0.61 (95 % CI, 0.55-0.66) and 2.78 (95 % CI, 1.91-4.03). Among 4 studies that predicted short-term PFS, the pooled sensitivity and specificity were 0.77 (95 % CI, 0.58-0.89) and 0.60 (95 % CI, 0.45-0.73), respectively. There was a substantial between-study heterogeneity among studies with the survival endpoint of OS C-index (n = 9, I2 = 83.8 %). Publication bias was not observed overall.

CONCLUSION

Pretreatment MR-based radiomics provided modest prognostic value in both OS and PFS in patients with glioblastoma.

Comparing effectiveness of image perturbation and test retest imaging in improving radiomic model reliability

Image perturbation is a promising technique to assess radiomic feature repeatability, but whether it can achieve the same effect as test-retest imaging on model reliability is unknown. This study aimed to compare radiomic model reliability based on repeatable features determined by the two methods using four different classifiers. A 191-patient public breast cancer dataset with 71 test-retest scans was used with pre-determined 117 training and 74 testing samples. We collected apparent diffusion coefficient images and manual tumor segmentations for radiomic feature extraction. Random translations, rotations, and contour randomizations were performed on the training images, and intra-class correlation coefficient (ICC) was used to filter high repeatable features. We evaluated model reliability in both internal generalizability and robustness, which were quantified by training and testing AUC and prediction ICC. Higher testing performance was found at higher feature ICC thresholds, but it dropped significantly at ICC = 0.95 for the test-retest model. Similar optimal reliability can be achieved with testing AUC = 0.7-0.8 and prediction ICC > 0.9 at the ICC threshold of 0.9. It is recommended to include feature repeatability analysis using image perturbation in any radiomic study when test-retest is not feasible, but care should be taken when deciding the optimal feature repeatability criteria.

A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas

Lower-grade gliomas (LGG) can eventually progress to glioblastoma (GBM) and death. In the context of the transfer learning approach, we aimed to train and test an MRI-based radiomics model for predicting survival in GBM patients and validate it in LGG patients. From each patient's 704 MRI-based radiomics features, we chose seventeen optimal radiomics signatures in the GBM training set (n = 71) and used these features in both the GBM testing set (n = 31) and LGG validation set (n = 107) for further analysis. Each patient's risk score, calculated based on those optimal radiomics signatures, was chosen to represent the radiomics model. We compared the radiomics model with clinical, gene status models, and combined model integrating radiomics, clinical, and gene status in predicting survival. The average iAUCs of combined models in training, testing, and validation sets were respectively 0.804, 0.878, and 0.802, and those of radiomics models were 0.798, 0.867, and 0.717. The average iAUCs of gene status and clinical models ranged from 0.522 to 0.735 in all three sets. The radiomics model trained in GBM patients can effectively predict the overall survival of GBM and LGG patients, and the combined model improved this ability.

Dynamic contrast-enhanced MRI radiomics model predicts epidermal growth factor receptor amplification in glioblastoma, IDH-wildtype

PURPOSE

To develop and validate a dynamic contrast-enhanced (DCE) MRI-based radiomics model to predict epidermal growth factor receptor (EGFR) amplification in patients with glioblastoma, isocitrate dehydrogenase (IDH) wildtype.

METHODS

Patients with pathologically confirmed glioblastoma, IDH wildtype, from January 2015 to December 2020, with an EGFR amplification status, were included. Patients who did not undergo DCE or conventional brain MRI were excluded. Patients were categorized into training and test sets by a ratio of 7:3. DCE MRI data were used to generate volume transfer constant (Ktrans) and extracellular volume fraction (Ve) maps. Ktrans, Ve, and conventional MRI were then used to extract the radiomics features, from which the prediction models for EGFR amplification status were developed and validated.

RESULTS

A total of 190 patients (mean age, 59.9; male, 55.3%), divided into training (n = 133) and test (n = 57) sets, were enrolled. In the test set, the radiomics model using the Ktrans map exhibited the highest area under the receiver operating characteristic curve (AUROC), 0.80 (95% confidence interval [CI], 0.65-0.95). The AUROC for the Ve map-based and conventional MRI-based models were 0.74 (95% CI, 0.58-0.90) and 0.76 (95% CI, 0.61-0.91).

CONCLUSION

The DCE MRI-based radiomics model that predicts EGFR amplification in glioblastoma, IDH wildtype, was developed and validated. The MRI-based radiomics model using the Ktrans map has higher AUROC than conventional MRI.

Deep learning based on dynamic susceptibility contrast MR imaging for prediction of local progression in adult-type diffuse glioma (grade 4)

Adult-type diffuse glioma (grade 4) has infiltrating nature, and therefore local progression is likely to occur within surrounding non-enhancing T2 hyperintense areas even after gross total resection of contrast-enhancing lesions. Cerebral blood volume (CBV) obtained from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) is a parameter that is well-known to be a surrogate marker of both histologic and angiographic vascularity in tumors. We built two nnU-Net deep learning models for prediction of early local progression in adult-type diffuse glioma (grade 4), one using conventional MRI alone and one using multiparametric MRI, including conventional MRI and DSC-PWI. Local progression areas were annotated in a non-enhancing T2 hyperintense lesion on preoperative T2 FLAIR images, using the follow-up contrast-enhanced (CE) T1-weighted (T1W) images as the reference standard. The sensitivity was doubled with the addition of nCBV (80% vs. 40%, P = 0.02) while the specificity was decreased nonsignificantly (29% vs. 48%, P = 0.39), suggesting that fewer cases of early local progression would be missed with the addition of nCBV. While the diagnostic performance of CBV model is still poor and needs improving, the multiparametric deep learning model, which presumably learned from the subtle difference in vascularity between early local progression and non-progression voxels within perilesional T2 hyperintensity, may facilitate risk-adapted radiotherapy planning in adult-type diffuse glioma (grade 4) patients.

Radiomics characterization of tissues in an animal brain tumor model imaged using dynamic contrast enhanced (DCE) MRI

Here, we investigate radiomics-based characterization of tumor vascular and microenvironmental properties in an orthotopic rat brain tumor model measured using dynamic-contrast-enhanced (DCE) MRI. Thirty-two immune compromised-RNU rats implanted with human U-251N cancer cells were imaged using DCE-MRI (7Tesla, Dual-Gradient-Echo). The aim was to perform pharmacokinetic analysis using a nested model (NM) selection technique to classify brain regions according to vasculature properties considered as the source of truth. A two-dimensional convolutional-based radiomics analysis was performed on the raw-DCE-MRI of the rat brains to generate dynamic radiomics maps. The raw-DCE-MRI and respective radiomics maps were used to build 28 unsupervised Kohonen self-organizing-maps (K-SOMs). A Silhouette-Coefficient (SC), k-fold Nested-Cross-Validation (k-fold-NCV), and feature engineering analyses were performed on the K-SOMs' feature spaces to quantify the distinction power of radiomics features compared to raw-DCE-MRI for classification of different Nested Models. Results showed that eight radiomics features outperformed respective raw-DCE-MRI in prediction of the three nested models. The average percent difference in SCs between radiomics features and raw-DCE-MRI was: 29.875% ± 12.922%, p < 0.001. This work establishes an important first step toward spatiotemporal characterization of brain regions using radiomics signatures, which is fundamental toward staging of tumors and evaluation of tumor response to different treatments.

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.

Radiomics for Discriminating Benign and Malignant Salivary Gland Tumors; Which Radiomic Feature Categories and MRI Sequences Should Be Used?

The lack of a consistent MRI radiomic signature, partly due to the multitude of initial feature analyses, limits the widespread clinical application of radiomics for the discrimination of salivary gland tumors (SGTs). This study aimed to identify the optimal radiomics feature category and MRI sequence for characterizing SGTs, which could serve as a step towards obtaining a consensus on a radiomics signature. Preliminary radiomics models were built to discriminate malignant SGTs (n = 34) from benign SGTs (n = 57) on T1-weighted (T1WI), fat-suppressed (FS)-T2WI and contrast-enhanced (CE)-T1WI images using six feature categories. The discrimination performances of these preliminary models were evaluated using 5-fold-cross-validation with 100 repetitions and the area under the receiver operating characteristic curve (AUC). The differences between models’ performances were identified using one-way ANOVA. Results show that the best feature categories were logarithm for T1WI and CE-T1WI and exponential for FS-T2WI, with AUCs of 0.828, 0.754 and 0.819, respectively. These AUCs were higher than the AUCs obtained using all feature categories combined, which were 0.750, 0.707 and 0.774, respectively (p < 0.001). The highest AUC (0.846) was obtained using a combination of T1WI + logarithm and FS-T2WI + exponential features, which reduced the initial features by 94.0% (from 1015 × 3 to 91 × 2). CE-T1WI did not improve performance. Using one feature category rather than all feature categories combined reduced the number of initial features without compromising radiomic performance.

Dynamic contrast-enhanced magnetic resonance imaging-based radiomics for the prediction of progression-free survival in advanced nasopharyngeal carcinoma

To establish a multidimensional nomogram model for predicting progression-free survival (PFS) and risk stratification in patients with advanced nasopharyngeal carcinoma (NPC). This retrospective cross-sectional study included 156 patients with advanced NPC who underwent dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Radiomic features were extracted from the efflux rate constant (Ktrans ) and extracellular extravascular volume (Ve ) mapping derived from DCE-MRI. Least absolute shrinkage and selection operator (LASSO) Cox regression analysis was applied for feature selection. The Radscore was constructed using the selected features with their respective weights in the LASSO Cox regression analysis. A nomogram model combining the Radscore and clinical factors was built using multivariate Cox regression analysis. The C-index was used to assess the discrimination power of the Radscore and nomogram. The Kaplan-Meier method was used for survival analysis. Of the 360 radiomic features, 28 were selected (7, 6, and 15 features extracted from Ktrans , Ve, and Ktrans +Ve images, respectively). The combined Radscore k trans +Ve (C-index, 0.703, 95% confidence interval [CI]: 0.571-0.836) showed higher efficacy in predicting the prognosis of advanced NPC than Radscore k trans (C-index, 0.693; 95% CI, 0.560-0.826) and Radscore Ve (C-index, 0.614; 95% CI, 0.481-0.746) did. Multivariable Cox regression analysis revealed clinical stage, T stage, and treatment with nimotuzumab as risk factors for PFS. The nomogram established by Radscore k trans +Ve and risk factors (C-index, 0.732; 95% CI: 0.599-0.864) was better than Radscore k trans +Ve in predicting PFS in patients with advanced NPC. A lower Radscore k trans +Ve (HR 3.5584, 95% CI 2.1341-5.933), lower clinical stage (hazard ratio [HR] 1.5982, 95% CI 0.5262-4.854), lower T stage (HR 1.4365, 95% CI 0.6745-3.060), and nimotuzumab (NTZ) treatment (HR 0.7879, 95% CI 0.4899-1.267) were associated with longer PFS. Kaplan-Meier analysis showed a lower PFS in the high-risk group than in the low-risk group (p<0.0001). The nomogram based on combined pretreatment DCE-MRI radiomics features, NTZ, and clinicopathological risk factors may be considered as a noninvasive imaging marker for predicting individual PFS in patients with advanced NPC.

Validation of MRI-Based Models to Predict MGMT Promoter Methylation in Gliomas: BraTS 2021 Radiogenomics Challenge

Simple Summary

O6-methylguanine-DNA methyl transferase (MGMT) methylation in glioblastoma is an important prognostic and predictive factor that requires an invasive surgical procedure for identification. In several recent studies, MGMT methylation prediction models were developed using MR images, and good diagnostic performance was achieved, which seems to indicate a promising future for radiogenomics. However, the diagnostic performance was not reproducible for numerous research teams when using a larger dataset in the RSNA-MICCAI Brain Tumor Radiogenomic Classification 2021 challenge. To our knowledge, there has been no study regarding the external validation of MGMT prediction models using large-scale multicenter datasets. We tested recent CNN architectures via extensive experiments to investigate whether MGMT methylation in gliomas can be predicted using MRI. With unexpected negative results, approximately 80% of the developed models showed no significant difference with the chance level of 50% in terms of external validation accuracy. In conclusion, MGMT methylation status of gliomas may not be predictable with preoperative MRI, even using deep learning.

Abstract

O6-methylguanine-DNA methyl transferase (MGMT) methylation prediction models were developed using only small datasets without proper external validation and achieved good diagnostic performance, which seems to indicate a promising future for radiogenomics. However, the diagnostic performance was not reproducible for numerous research teams when using a larger dataset in the RSNA-MICCAI Brain Tumor Radiogenomic Classification 2021 challenge. To our knowledge, there has been no study regarding the external validation of MGMT prediction models using large-scale multicenter datasets. We tested recent CNN architectures via extensive experiments to investigate whether MGMT methylation in gliomas can be predicted using MR images. Specifically, prediction models were developed and validated with different training datasets: (1) the merged (SNUH + BraTS) (n = 985); (2) SNUH (n = 400); and (3) BraTS datasets (n = 585). A total of 420 training and validation experiments were performed on combinations of datasets, convolutional neural network (CNN) architectures, MRI sequences, and random seed numbers. The first-place solution of the RSNA-MICCAI radiogenomic challenge was also validated using the external test set (SNUH). For model evaluation, the area under the receiver operating characteristic curve (AUROC), accuracy, precision, and recall were obtained. With unexpected negative results, 80.2% (337/420) and 60.0% (252/420) of the 420 developed models showed no significant difference with a chance level of 50% in terms of test accuracy and test AUROC, respectively. The test AUROC and accuracy of the first-place solution of the BraTS 2021 challenge were 56.2% and 54.8%, respectively, as validated on the SNUH dataset. In conclusion, MGMT methylation status of gliomas may not be predictable with preoperative MR images even using deep learning.

Hemodynamic Imaging in Cerebral Diffuse Glioma—Part B: Molecular Correlates, Treatment Effect Monitoring, Prognosis, and Future Directions

Gliomas, and glioblastoma in particular, exhibit an extensive intra- and inter-tumoral molecular heterogeneity which represents complex biological features correlating to the efficacy of treatment response and survival. From a neuroimaging point of view, these specific molecular and histopathological features may be used to yield imaging biomarkers as surrogates for distinct tumor genotypes and phenotypes. The development of comprehensive glioma imaging markers has potential for improved glioma characterization that would assist in the clinical work-up of preoperative treatment planning and treatment effect monitoring. In particular, the differentiation of tumor recurrence or true progression from pseudoprogression, pseudoresponse, and radiation-induced necrosis can still not reliably be made through standard neuroimaging only. Given the abundant vascular and hemodynamic alterations present in diffuse glioma, advanced hemodynamic imaging approaches constitute an attractive area of clinical imaging development. In this context, the inclusion of objective measurable glioma imaging features may have the potential to enhance the individualized care of diffuse glioma patients, better informing of standard-of-care treatment efficacy and of novel therapies, such as the immunotherapies that are currently increasingly investigated. In Part B of this two-review series, we assess the available evidence pertaining to hemodynamic imaging for molecular feature prediction, in particular focusing on isocitrate dehydrogenase (IDH) mutation status, MGMT promoter methylation, 1p19q codeletion, and EGFR alterations. The results for the differentiation of tumor progression/recurrence from treatment effects have also been the focus of active research and are presented together with the prognostic correlations identified by advanced hemodynamic imaging studies. Finally, the state-of-the-art concepts and advancements of hemodynamic imaging modalities are reviewed together with the advantages derived from the implementation of radiomics and machine learning analyses pipelines.

A Predictive Clinical-Radiomics Nomogram for Survival Prediction of Glioblastoma Using MRI

Glioblastoma (GBM) is the most common and aggressive primary brain tumor in adult patients with a median survival of around one year. Prediction of survival outcomes in GBM patients could represent a huge step in treatment personalization. The objective of this study was to develop machine learning (ML) algorithms for survival prediction of GBM patient. We identified a radiomic signature on a training-set composed of data from the 2019 BraTS challenge (210 patients) from MRI retrieved at diagnosis. Then, using this signature along with the age of the patients for training classification models, we obtained on test-sets AUCs of 0.85, 0.74 and 0.58 (0.92, 0.88 and 0.75 on the training-sets) for survival at 9-, 12- and 15-months, respectively. This signature was then validated on an independent cohort of 116 GBM patients with confirmed disease relapse for the prediction of patients surviving less or more than the median OS of 22 months. Our model insured an AUC of 0.71 (0.65 on train). The Kaplan–Meier method showed significant OS difference between groups (log-rank p = 0.05). These results suggest that radiomic signatures may improve survival outcome predictions in GBM thus creating a solid clinical tool for tailoring therapy in this population.