A radiomics-based comparative study on arterial spin labeling and dynamic susceptibility contrast perfusion-weighted imaging in gliomas

The Value of Cerebral Blood Volume Derived from Dynamic Susceptibility Contrast Perfusion MRI in Predicting IDH Mutation Status of Brain Gliomas-A Systematic Review and Meta-Analysis

Background: Dynamic susceptibility contrast perfusion MRI (DSC-MRI) is a promising non-invasive examination to predict histological and molecular characteristics of brain gliomas. However, the diagnostic accuracy of relative cerebral blood volume (rCBV) is heterogeneously reported in the literature. This systematic review and meta-analysis aims to assess the diagnostic accuracy of mean rCBV derived from DSC-MRI in differentiating Isocitrate Dehydrogenase (IDH)-mutant from IDH-wildtype gliomas. Methods: A comprehensive literature search was conducted in PubMed, Web of Science, and EMBASE up to January 2025, following PRISMA guidelines. Eligible studies reported mean CBV values in treatment-naïve gliomas with histologically confirmed IDH status. Pooled estimates of standardized mean differences (SMDs), diagnostic odds ratios (DOR), and area under the receiver-operating characteristic curve (AUC) were computed using a random-effects model. Heterogeneity was assessed via I2 statistic. Meta-regression analyses were also performed. Results: An analysis of 18 studies (n = 1733) showed that mean rCBV is significantly lower in IDH-mutant gliomas (SMD = -0.86; p < 0.0001). The pooled AUC was 0.80 (95% CI, 0.75-0.90), with moderate sensitivity and specificity. Meta-regression revealed no significant influence of DSC-MRI acquisition parameters, although a flip angle showed a trend toward significance (p = 0.055). Conclusions: Mean rCBV is a reliable imaging biomarker for IDH mutation status in gliomas, demonstrating good diagnostic performance. However, heterogeneity in acquisition parameters and post-processing methods limits generalizability of results. Future research should focus on standardizing DSC-MRI protocols.

Evaluation of an Image-based Classification Model to Identify Glioma Subtypes Using Arterial Spin Labeling Perfusion MRI On the Publicly Available UCSF Glioma Dataset

PURPOSE

Glioma is a complex cancer comprising various subtypes and mutations, which may have different metabolic characteristics that can potentially be investigated and identified using perfusion imaging. Therefore, the aim of this work was to use radiomics and machine learning analysis of arterial spin labeling MRI data to automatically differentiate glioma subtypes and mutations.

METHODS

A total of 495 Arterial Spin Labeling (ASL) perfusion imaging datasets from the UCSF Glioma database were used in this study. These datasets were segmented to delineate the tumor volume and classified according to tumor grade, pathological diagnosis, and IDH status. Perfusion image data was obtained from a 3T MRI scanner using pseudo-continuous ASL. High level texture features were extracted for each ASL dataset using PyRadiomics after tumor volume segmentation and then analyzed using a machine learning framework consisting of ReliefF feature ranking and logistic model tree classification algorithms.

RESULTS

The results of the evaluation revealed balanced accuracies for the three endpoints ranging from 55.76% (SD = 4.28, 95% CI: 53.90-57.65) for the tumor grade using 25.4 ± 37.21 features, 62.53% (SD = 2.86, 95% CI: 61.27-63.78) for the mutation status with 23.3 ± 29.17 picked features, and 80.97% (SD = 1.83, 95% CI: 80.17-81.78) for the pathological diagnosis which used 47.3 ± 32.72 selected features.

CONCLUSIONS

Radiomics and machine learning analysis of ASL perfusion data in glioma patients hold potential for aiding in the diagnosis and treatment of glioma, mainly for discerning glioblastoma from astrocytoma, while performance for tumor grading and mutation status appears limited.

Differentiation Between High-Grade Glioma and Brain Metastasis Using Cerebral Perfusion-Related Parameters (Cerebral Blood Volume and Cerebral Blood Flow): A Systematic Review and Meta-Analysis of Perfusion-weighted MRI Techniques

BACKGROUND

Distinguishing high-grade gliomas (HGGs) from brain metastases (BMs) using perfusion-weighted imaging (PWI) remains challenging. PWI offers quantitative measurements of cerebral blood flow (CBF) and cerebral blood volume (CBV), but optimal PWI parameters for differentiation are unclear.

PURPOSE

To compare CBF and CBV derived from PWIs in HGGs and BMs, and to identify the most effective PWI parameters and techniques for differentiation.

STUDY TYPE

Systematic review and meta-analysis.

POPULATION

Twenty-four studies compared CBF and CBV between HGGs (n = 704) and BMs (n = 488).

FIELD STRENGTH/SEQUENCE

Arterial spin labeling (ASL), dynamic susceptibility contrast (DSC), dynamic contrast-enhanced (DCE), and dynamic susceptibility contrast-enhanced (DSCE) sequences at 1.5 T and 3.0 T.

ASSESSMENT

Following the PRISMA guidelines, four major databases were searched from 2000 to 2024 for studies evaluating CBF or CBV using PWI in HGGs and BMs.

STATISTICAL TESTS

Standardized mean difference (SMD) with 95% CIs was used. Risk of bias (ROB) and publication bias were assessed, and I2 statistic was used to assess statistical heterogeneity. A P-value<0.05 was considered significant.

RESULTS

HGGs showed a significant modest increase in CBF (SMD = 0.37, 95% CI: 0.05-0.69) and CBV (SMD = 0.26, 95% CI: 0.01-0.51) compared with BMs. Subgroup analysis based on region, sequence, ROB, and field strength for CBF (HGGs: 375 and BMs: 222) and CBV (HGGs: 493 and BMs: 378) values were conducted. ASL showed a considerable moderate increase (50% overlapping CI) in CBF for HGGs compared with BMs. However, no significant difference was found between ASL and DSC (P = 0.08).

DATA CONCLUSION

ASL-derived CBF may be more useful than DSC-derived CBF in differentiating HGGs from BMs. This suggests that ASL may be used as an alternative to DSC when contrast medium is contraindicated or when intravenous injection is not feasible.

LEVEL OF EVIDENCE: 1

TECHNICAL EFFICACY

Stage 2.

Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors

OBJECTIVES

The objective is to develop and validate intratumoral and peritumoral ultrasomics models utilizing endoscopic ultrasonography (EUS) to predict pathological grading in pancreatic neuroendocrine tumors (PNETs).

METHODS

Eighty-one patients, including 51 with grade 1 PNETs and 30 with grade 2/3 PNETs, were included in this retrospective study after confirmation through pathological examination. The patients were randomly allocated to the training or test group in a 6:4 ratio. Univariate and multivariate logistic regression were used for screening clinical and ultrasonic characteristics. Ultrasomics is ultrasound-based radiomics. Ultrasomics features were extracted from both the intratumoral and peritumoral regions of conventional EUS images. Subsequently, the dimensionality of these radiomics features was reduced using the least absolute shrinkage and selection operator (LASSO) algorithm. A machine learning algorithm, namely multilayer perception (MLP), was employed to construct prediction models using only the nonzero coefficient features and retained clinical features, respectively.

RESULTS

One hundred seven ultrasomics features based on EUS were extracted, and only features with nonzero coefficients were ultimately retained. Among all the models, the combined ultrasomics model achieved the greatest performance, with an AUC of 0.858 (95% CI, 0.7512 - 0.9642) in the training group and 0.842 (95% CI, 0.7061 - 0.9785) in the test group. A calibration curve and a decision curve analysis (DCA) also demonstrated its accuracy and utility.

CONCLUSIONS

The integrated model using EUS ultrasomics features from intratumoral and peritumoral tumors accurately predicts PNETs' pathological grades pre-surgery, aiding personalized treatment planning.

TRIAL REGISTRATION

ChiCTR2400091906.

Breast MRI radiomics and machine learning-based predictions of response to neoadjuvant chemotherapy - How are they affected by variations in tumor delineation?

Manual delineation of volumes of interest (VOIs) by experts is considered the gold-standard method in radiomics analysis. However, it suffers from inter- and intra-operator variability. A quantitative assessment of the impact of variations in these delineations on the performance of the radiomics predictors is required to develop robust radiomics based prediction models. In this study, we developed radiomics models for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with two different breast cancer subtypes based on contrast-enhanced magnetic resonance imaging acquired prior to treatment (baseline MRI scans). Different mathematical operations such as erosion, smoothing, dilation, randomization, and ellipse fitting were applied to the original VOIs delineated by experts to simulate variations of segmentation masks. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. Using manual tumor VOIs and radiomics features extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 was achieved for human epidermal growth receptor 2 positive and triple-negative breast cancer, respectively. For smoothing and erosion, VOIs yielded the highest number of robust features and the best prediction performance, while ellipse fitting and dilation lead to the lowest robustness and prediction performance for both breast cancer subtypes. At most 28% of the selected features were similar to manual VOIs when different VOI delineation data were used. Differences in VOI delineation affect different steps of radiomics analysis, and their quantification is therefore important for development of standardized radiomics research.

The Current Diagnostic Performance of MRI-Based Radiomics for Glioma Grading: A Meta-Analysis

BACKGROUND

Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma.

METHODS

A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis.

RESULTS

In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ2 test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used.

CONCLUSIONS

Our findings confirm that present radiomics' diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task.

Comparison of ASL and DSC perfusion methods in the evaluation of response to treatment in patients with a history of treatment for malignant brain tumor

OBJECTIVE

Perfusion MRI is of great benefit in the post-treatment evaluation of brain tumors. Interestingly, dynamic susceptibility contrast-enhanced (DSC) perfusion has taken its place in routine examination for this purpose. The use of arterial spin labeling (ASL), a perfusion technique that does not require exogenous contrast material injection, has gained popularity in recent years. The aim of the study was to compare two different perfusion techniques, ASL and DSC, using qualitative and quantitative measurements and to investigate the diagnostic effectiveness of both. The fact that the number of patients is higher than in studies conducted with 3D pseudo-continious ASL (pCASL), the study group is heterogeneous as it consists of patients with both metastases and glial tumors, the use of 3D Turbo Gradient Spin Echo (TGSE), and the inclusion of visual (qualitative) assessment make our study unique.

METHODS

Ninety patients, who were treated for malignant brain tumor, were enrolled in the retrospective study. DSC Cerebral Blood Volume (CBV), Cerebral Blood Flow (CBF) and ASL CBF maps of each case were obtained. In qualitative analysis, the lesions of the cases were visually classified as treatment-related changes (TRC) and relapse/residual mass (RRT). In the quantitative analysis, three regions of interest (ROI) measurements were taken from each case. The average of these measurements was compared with the ROI taken from the contralateral white matter and normalized values (n) were obtained. These normalized values were compared across events.

RESULTS

Uncorrected DSC normalized CBV (nCBV), DSC normalized CBF (nCBF) and ASL nCBF values of RRT cases were higher than those of TRC cases (p < 0.001). DSC nCBV values were correlated with DSC nCBF (r: 0.94, p < 0.001) and correlated with ASL nCBF (r: 0.75, p < 0.001). Similarly, ASL nCBF was positively correlated with DSC nCBF (r: 0.79 p < 0.01). When the ROC curve parameters were evaluated, the cut-off values were determined as 1.211 for DSC nCBV (AUC: 0.95, 93% sensitivity, 82% specificity), 0.896 for DSC nCBF (AUC; 0.95, 93% sensitivity, 82% specificity), and 0.829 for ASL nCBF (AUC: 0.84, 78% sensitivity, 75% specificity). For qualitative evaluation (visual evaluation), inter-observer agreement was found to be good for ASL CBF (0.714), good for DSC CBF (0.790), and excellent for DSC CBV (0.822). Intra-observer agreement was also evaluated. For the first observer, good agreement was found in ASL CBF (0.626, 70% sensitive, 93% specific), in DSC CBF (0.713, 76% sensitive, 95% specific), and in DSC CBV (0.755, 87% sensitive - 88% specific). In the second observer, moderate agreement was found in ASL CBF (0.584, 61% sensitive, 97% specific) and DSC CBF (0.649, 65% sensitive, 100% specific), and excellent agreement in DSC CBV (0.800, 89% sensitive, 90% specific).

CONCLUSION

It was observed that uncorrected DSC nCBV, DSC nCBF and ASL nCBF values were well correlated with each other. In qualitative evaluation, inter-observer and intra-observer agreement was higher in DSC CBV than DSC CBF and ASL CBF. In addition, DSC CBV is found more sensitive, ASL CBF and DSC CBF are found more specific for both observers. From a diagnostic perspective, all three parameters DSC CBV, DSC CBF and ASL CBF can be used, but it was observed that the highest rate belonged to DSC CBV.

Brain Tumor Imaging without Gadolinium-based Contrast Agents: Feasible or Fantasy?

Gadolinium-based contrast agents (GBCAs) form the cornerstone of current primary brain tumor MRI protocols at all stages of the patient journey. Though an imperfect measure of tumor grade, GBCAs are repeatedly used for diagnosis and monitoring. In practice, however, radiologists will encounter situations where GBCA injection is not needed or of doubtful benefit. Reducing GBCA administration could improve the patient burden of (repeated) imaging (especially in vulnerable patient groups, such as children), minimize risks of putative side effects, and benefit costs, logistics, and the environmental footprint. On the basis of the current literature, imaging strategies to reduce GBCA exposure for pediatric and adult patients with primary brain tumors will be reviewed. Early postoperative MRI and fixed-interval imaging of gliomas are examples of GBCA exposure with uncertain survival benefits. Half-dose GBCAs for gliomas and T2-weighted imaging alone for meningiomas are among options to reduce GBCA use. While most imaging guidelines recommend using GBCAs at all stages of diagnosis and treatment, non-contrast-enhanced sequences, such as the arterial spin labeling, have shown a great potential. Artificial intelligence methods to generate synthetic postcontrast images from decreased-dose or non-GBCA scans have shown promise to replace GBCA-dependent approaches. This review is focused on pediatric and adult gliomas and meningiomas. Special attention is paid to the quality and real-life applicability of the reviewed literature.

Advanced MR Techniques for Preoperative Glioma Characterization: Part 2

Preoperative clinical MRI protocols for gliomas, brain tumors with dismal outcomes due to their infiltrative properties, still rely on conventional structural MRI, which does not deliver information on tumor genotype and is limited in the delineation of diffuse gliomas. The GliMR COST action wants to raise awareness about the state of the art of advanced MRI techniques in gliomas and their possible clinical translation. This review describes current methods, limits, and applications of advanced MRI for the preoperative assessment of glioma, summarizing the level of clinical validation of different techniques. In this second part, we review magnetic resonance spectroscopy (MRS), chemical exchange saturation transfer (CEST), susceptibility-weighted imaging (SWI), MRI-PET, MR elastography (MRE), and MR-based radiomics applications. The first part of this review addresses dynamic susceptibility contrast (DSC) and dynamic contrast-enhanced (DCE) MRI, arterial spin labeling (ASL), diffusion-weighted MRI, vessel imaging, and magnetic resonance fingerprinting (MRF). EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Diagnostic performance of perfusion-weighted imaging combined with serum MMP-2 and -9 levels in tumor recurrence after postoperative concomitant chemoradiotherapy of glioblastoma

OBJECTIVE

To evaluate diagnostic accuracy of dynamic susceptibility contrast- perfusion weighted imaging (DSC-PWI) combined with serum MMP-2 and -9 levels in differentiating recurrent glioblastoma (GBM).

METHODS

We enrolled a total of 220 GBM patients, including recurrent cases (n = 150) and non-recurrent cases (n = 70) after postoperative concomitant chemoradiotherapy. All patients performed preoperative and follow-up DSC-PWI, and two parameters [normalized cerebral blood volume (nCBV) and cerebral blood flow (nCBF)] were obtained. Preoperative serum levels of MMP-2 and MMP-9 were detected using ELISA. The diagnostic performance was evaluated by analyzing receiver operating characteristic (ROC) and area under the curve (AUC).

RESULTS

At baseline, the recurrence patients had higher nCBF and nCBV than the non-recurrence patients, accompanying by the increased MMP-2 and MMP-9 levels in serum. Serum MMP-2 level were positively associated with MMP-9 in recurrent patients. In patients classified as recurrence, both MMP-9 and MMP-2 in serum had a significant correlation with nCBV and nCBF. A sensitivity and specificity of nCBF for recurrence vs. non-recurrence were 94.29% and 63.33%, respectively. nCBV also could provide high discrimination between recurrence and non-recurrence patients (sensitivity: 84.29%, specificity: 62.67%, AUC: 0.821). In ROC analyses, both MMP-2 and MMP-9 distinguished recurrence from non-recurrence with AUC values of 0.883 and 0.900, respectively. Finally, the combination of DSC-PWI parameters (nCBF and nCBV) and serum MMP-2 and -9 levels showed much better discrimination capacity between recurrence and non-recurrence patients with a sensitivity of 92.86%, specificity of 79.33% and AUC of 0.899.

CONCLUSION

The combination of DSC-PWI parameters together with serum MMP-2 and -9 levels offered an attractive approach to noninvasively distinguish recurrence after postoperative radiotherapy of GBM.

MRI phenotypes of glioblastomas early after treatment are suggestive of overall patient survival

Background

Distinguishing true tumor progression (TP) from treatment-induced abnormalities (eg, pseudo-progression (PP) after radiotherapy) on conventional MRI scans remains challenging in patients with a glioblastoma. We aimed to establish brain MRI phenotypes of glioblastomas early after treatment by combined analysis of structural and perfusion tumor characteristics and assessed the relation with recurrence rate and overall survival time.

Methods

Structural and perfusion MR images of 67 patients at 3 months post-radiotherapy were visually scored by a neuroradiologist. In total 23 parameters were predefined and used for hierarchical clustering analysis. Progression status was assessed based on the clinical course of each patient 9 months after radiotherapy (or latest available). Multivariable Cox regression models were used to determine the association between the phenotypes, recurrence rate, and overall survival.

Results

We established 4 subgroups with significantly different tumor MRI characteristics, representing distinct MRI phenotypes of glioblastomas: TP and PP rates did not differ significantly between subgroups. Regression analysis showed that patients in subgroup 1 (characterized by having mostly small and ellipsoid nodular enhancing lesions with some hyper-perfusion) had a significant association with increased mortality at 9 months (HR: 2.6 (CI: 1.1-6.3); P = .03) with a median survival time of 13 months (compared to 22 months of subgroup 2).

Conclusions

Our study suggests that distinct MRI phenotypes of glioblastomas at 3 months post-radiotherapy can be indicative of overall survival, but does not aid in differentiating TP from PP. The early prognostic information our method provides might in the future be informative for prognostication of glioblastoma patients.

Diffusion-weighted imaging and arterial spin labeling radiomics features may improve differentiation between radiation-induced brain injury and glioma recurrence

OBJECTIVES

To determine whether radiomics features derived from diffusion-weighted imaging (DWI) and arterial spin labeling (ASL) can improve the differentiation between radiation-induced brain injury (RIBI) and tumor recurrence (TR) in glioma patients.

METHODS

A total of 4199 radiomics features were extracted from conventional MRI, apparent diffusion coefficient (ADC), and cerebral blood flow (CBF) maps, obtained from 96 pathologically confirmed WHO grade 2~4 gliomas with enhancement after standard treatment. The intraclass correlation coefficient (ICC) was used to test segmentation stability between two doctors. Radiomics features were selected using the Mann-Whitney U test, LASSO regression, and RFE algorithms. Four machine learning classifiers were adopted to establish radiomics models. The diagnostic performance of multiparameter, conventional, and single-parameter MRI radiomics models was compared using the area under the curve (AUC). The models were evaluated in the subsequent independent validation set (n = 30).

RESULTS

Eight important radiomics features (3 from conventional MRI, 1 from ADC, and 4 from CBF) were selected. Support vector machine (SVM) was chosen as the optimal classifier. The diagnostic performance of the multiparameter MRI radiomics model (AUC 0.96) was higher than that of the conventional MRI (AUC 0.88), ADC (AUC 0.91), and CBF (AUC 0.95) radiomics models. For subgroup analysis, the multiparameter MRI radiomics model showed similar performance, with AUCs of 0.98 in WHO grade 2~3 and 0.96 in WHO grade 4.

CONCLUSION

The incorporation of noninvasive DWI and ASL into the MRI radiomics model improved the diagnostic performance in differentiating RIBI from TR; ASL, especially, played a significant role.

KEY POINTS

• The multiparameter MRI radiomics model was superior to the conventional MRI radiomics model in differentiating glioma recurrence from radiation-induced brain injury. • Diffusion and perfusion MRI could improve the ability of the radiomics model in predicting the progression in patients with glioma. • Arterial spin labeling played an important role in predicting glioma progression using radiomics models.

Differentiating Glioblastoma Multiforme from Brain Metastases Using Multidimensional Radiomics Features Derived from MRI and Multiple Machine Learning Models

Due to different treatment strategies, it is extremely important to differentiate between glioblastoma multiforme (GBM) and brain metastases (MET). It often proves difficult to distinguish between GBM and MET using MRI due to their similar appearance on the imaging modalities. Surgical methods are still necessary for definitive diagnosis, despite the importance of magnetic resonance imaging in detecting, characterizing, and monitoring brain tumors. We introduced an accurate, convenient, and user-friendly method to differentiate between GBM and MET through routine MRI sequence and radiomics analyses. We collected 91 patients from one institution, including 50 with GBM and 41 with MET, which were proven pathologically. The tumors separately were segmented on all MRI images (T1-weighted imaging (T1WI), contrast-enhanced T1-weighted imaging (T1C), T2-weighted imaging (T2WI), and fluid-attenuated inversion recovery (FLAIR)) to form the volume of interest (VOI). Eight ML models and feature reduction strategies were evaluated using routine MRI sequences (T1W, T2W, T1-CE, and FLAIR) in two methods with (second model) and without wavelet transform (first model) radiomics. The optimal model was selected based on each model’s accuracy, AUC-roc, and F1-score values. In this study, we have achieved the result of 0.98, 0.99, and 0.98 percent for accuracy, AUC-roc, and F1-score, respectively, which have yielded a better result than the first model. In most investigated models, there were significant improvements in the multidimensional wavelets model compared to the non-multidimensional wavelets model. Multidimensional discrete wavelet transform can analyze hidden features of the MRI from a different perspective and generate accurate features which are highly correlated with the model accuracy.

RP-Rs-fMRIomics as a Novel Imaging Analysis Strategy to Empower Diagnosis of Brain Gliomas

Rs-fMRI can provide rich information about functional processes in the brain with a large array of imaging parameters and is also suitable for investigating the biological processes in cerebral gliomas. We aimed to propose an imaging analysis method of RP-Rs-fMRIomics by adopting omics analysis on rs-fMRI with exhaustive regional parameters and subsequently estimating its feasibility on the prediction diagnosis of gliomas. In this retrospective study, preoperative rs-fMRI data were acquired from patients confirmed with diffuse gliomas (n = 176). A total of 420 features were extracted through measuring 14 regional parameters of rs-fMRI as much as available currently in 10 specific narrow frequency bins and three parts of gliomas. With a randomly split training and testing dataset (ratio 7:3), four classifiers were implemented to construct and optimize RP-Rs-fMRIomics models for predicting glioma grade, IDH status and Karnofsky Performance Status scores. The RP-Rs-fMRIomics models (AUROC 0.988, 0.905, 0.801) were superior to the corresponding traditional single rs-fMRI index (AUROC 0.803, 0.731, 0.632) in predicting glioma grade, IDH and survival. The RP-Rs-fMRIomics analysis, featuring high interpretability, was competitive for prediction of glioma grading, IDH genotype and prognosis. The method expanded the clinical application of rs-fMRI and also contributed a new imaging analysis for brain tumor research.

Automatic discrimination of Yamamoto-Kohama classification by machine learning approach for invasive pattern of oral squamous cell carcinoma using digital microscopic images: a retrospective study

OBJECTIVE

The Yamamoto-Kohama criteria are clinically useful for determining the mode of tumor invasion, especially in Japan. However, this evaluation method is based on subjective visual findings and has led to significant differences in determinations between evaluators and facilities. In this retrospective study, we aimed to develop an automatic method of determining the mode of invasion based on the processing of digital medical images.

STUDY DESIGN

Using 101 digitized photographic images of anonymized stained specimen slides, we created a classifier that allowed clinicians to introduce feature values and subjected the cases to machine learning using a random forest approach. We then compared the Yamamoto-Kohama grades (1, 2, 3, 4C, 4D) determined by a human oral and maxillofacial surgeon with those determined using the machine learning approach.

RESULTS

The input of multiple test images into the newly created classifier yielded an overall F-measure value of 87% (grade 1, 93%; grade 2, 67%; grade 3, 89%; grade 4C, 83%; grade 4D, 94%). These results suggest that the output of the classifier was very similar to the judgments of the clinician.

CONCLUSIONS

This system may be valuable for diagnostic support to provide an accurate determination of the mode of invasion.

A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion

Background

To explore the effectiveness of radiomics features based on routine CT to reflect the difference of cerebral hemispheric perfusion.

Methods

We retrospectively recruited 52 patients with severe stenosis or occlusion in the unilateral middle cerebral artery (MCA), and brain CT perfusion showed an MCA area with deficit perfusion. Radiomics features were extracted from the stenosis side and contralateral of the MCA area based on precontrast CT. Two different region of interest drawing methods were applied. Then the patients were randomly grouped into training and testing sets by the ratio of 8:2. In the training set, ANOVA and the Elastic Net Regression with fivefold cross-validation were conducted to filter and choose the optimized features. Moreover, different machine learning models were built. In the testing set, the area under the receiver operating characteristic (AUC) curve, calibration, and clinical utility were applied to evaluate the predictive performance of the models.

Results

The logistic regression (LR) for the triangle-contour method and artificial neural network (ANN) for the semiautomatic-contour method were chosen as radiomics models for their good prediction efficacy in the training phase (AUC = 0.869, 0.873) and the validation phase (AUC = 0.793, 0.799). The radiomics algorithms of the triangle-contour and semiautomatic-contour method were implemented in the whole training set (AUC = 0.870, 0.867) and were evaluated in the testing set (AUC = 0.760, 0.802). According to the optimal cutoff value, these two methods can classify the vascular stenosis side class and normal side class.

Conclusion

Radiomic predictive feature based on precontrast CT image could reflect the difference of cerebral hemispheric perfusion to some extent.

Hemodynamic Imaging in Cerebral Diffuse Glioma-Part A: Concept, Differential Diagnosis and Tumor Grading

Diffuse gliomas are the most common primary malignant intracranial neoplasms. Aside from the challenges pertaining to their treatment-glioblastomas, in particular, have a dismal prognosis and are currently incurable-their pre-operative assessment using standard neuroimaging has several drawbacks, including broad differentials diagnosis, imprecise characterization of tumor subtype and definition of its infiltration in the surrounding brain parenchyma for accurate resection planning. As the pathophysiological alterations of tumor tissue are tightly linked to an aberrant vascularization, advanced hemodynamic imaging, in addition to other innovative approaches, has attracted considerable interest as a means to improve diffuse glioma characterization. In the present part A of our two-review series, the fundamental concepts, techniques and parameters of hemodynamic imaging are discussed in conjunction with their potential role in the differential diagnosis and grading of diffuse gliomas. In particular, recent evidence on dynamic susceptibility contrast, dynamic contrast-enhanced and arterial spin labeling magnetic resonance imaging are reviewed together with perfusion-computed tomography. While these techniques have provided encouraging results in terms of their sensitivity and specificity, the limitations deriving from a lack of standardized acquisition and processing have prevented their widespread clinical adoption, with current efforts aimed at overcoming the existing barriers.

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.

3D pCASL-perfusion in preoperative assessment of brain gliomas in large cohort of patients

The aim of the study was to evaluate the role of pseudocontinuous arterial spin labeling perfusion (pCASL-perfusion) in preoperative assessment of cerebral glioma grades. The study group consisted of 253 patients, aged 7-78 years with supratentorial gliomas (65 low-grade gliomas (LGG), 188 high-grade gliomas (HGG)). We used 3D pCASL-perfusion for each patient in order to calculate the tumor blood flow (TBF). We obtained maximal tumor blood flow (maxTBF) in small regions of interest (30 ± 10 mm²) and then normalized absolute maximum tumor blood flow (nTBF) to that of the contralateral normal-appearing white matter of the centrum semiovale. MaxTBF and nTBF values significantly differed between HGG and LGG groups (p < 0.001), as well as between patient groups separated by the grades (grade II vs. grade III) (p < 0.001). Moreover, we performed ROC-analysis which demonstrated high sensitivity and specificity in differentiating between HGG and LGG. We found significant differences for maxTBF and nTBF between grade III and IV gliomas, however, ROC-analysis showed low sensitivity and specificity. We did not observe a significant difference in TBF for astrocytomas and oligodendrogliomas. Our study demonstrates that 3D pCASL-perfusion as an effective diagnostic tool for preoperative differentiation of glioma grades.

Radiomics-Based Machine Learning Classification for Glioma Grading Using Diffusion- and Perfusion-Weighted Magnetic Resonance Imaging

OBJECTIVE

The aim of this study was to evaluate various radiomics-based machine learning classification models using the apparent diffusion coefficient (ADC) and cerebral blood flow (CBF) maps for differentiating between low-grade gliomas (LGGs) and high-grade gliomas (HGGs).

METHODS

Fifty-two glioma patients, including 18 LGGs (grade II) and 34 HGGs (grade III/IV), were examined using a 3.0-T magnetic resonance scanner. The ADC and CBF maps were obtained from diffusion-weighted imaging and pseudo-continuous arterial spin labeling perfusion-weighted imaging, respectively. A total of 91 radiomic features were extracted from each of the tumor volume on the ADC and CBF maps. We constructed 4 types of machine learning classifiers based on (1) least absolute shrinkage and selection operator regularized logistic regression (LASSO-LR), (2) random forest (RF), (3) support vector machine (SVM) with the radial basis function kernel (SVM-RBF), and (4) SVM with the linear kernel (SVM-L). A training set with 36 gliomas (70%) was used to select the important radiomic features and train each model using 5-fold cross-validation. The remaining 16 gliomas (30%) were used as a test set. Receiver operating characteristic analysis was performed to evaluate the model performance.

RESULTS

A radiomic feature, ADC first-order-based skewness, was selected as an important variable in all classification models. According to the receiver operating characteristic analysis, the areas under the curve of the LASSO-LR, RF, SVM-RBF, and SVM-L models for the training set were 0.965, 1.000, 0.979, and 0.969, respectively. For the test set, the areas under the curve of the LASSO-LR, RF, SVM-RBF, and SVM-L models were 0.883, 0.917, 0.717, and 0.917, respectively. All classification models showed sufficient diagnostic performance on the test set.

CONCLUSIONS

Radiomics-based machine learning classifiers using the quantitative ADC and CBF maps are useful for differentiating HGGs from LGGs.

Current Status and Quality of Machine Learning-Based Radiomics Studies for Glioma Grading: A Systematic Review

INTRODUCTION

Radiomics now has significant momentum in the era of precision medicine. Glioma is one of the pathologies that has been extensively evaluated by radiomics. However, this technique has not been incorporated into clinical practice. In this systematic review, we selected and reviewed the published studies about glioma grading by radiomics to evaluate this technique's feasibility and its challenges.

MATERIAL AND METHODS

Using seven different search strings, we considered all published English manuscripts from 2015 to September 2020 in PubMed, Embase, and Scopus databases. After implementing the exclusion and inclusion criteria, the final papers were selected for the methodological quality assessment based on our in-house Modified Radiomics Standard Scoring (RQS) containing 43 items (minimum score of 0, maximum score of 44). Finally, we offered our opinion about the challenges and weaknesses of the selected papers.

RESULTS

By our search, 1,177 manuscripts were found (485 in PubMed, 343 in Embase, and 349 in Scopus). After the implementation of inclusion and exclusion criteria, 18 papers remained for the final analysis by RQS. The total RQS score ranged from 26 (59% of maximum possible score) to 43 (97% of maximum possible score) with a mean of 33.5 (76% of maximum possible score).

CONCLUSION

The current studies are promising but very heterogeneous in design with high variation in the radiomics software, the number of extracted features, the number of selected features, and machine learning models. All of the studies were retrospective in design; many are based on small datasets and/or suffer from class imbalance and lack of external validation data-sets.

Diagnostic Accuracy of Machine Learning-Based Radiomics in Grading Gliomas: Systematic Review and Meta-Analysis

Purpose

This study aimed to estimate the diagnostic accuracy of machine learning- (ML-) based radiomics in differentiating high-grade gliomas (HGG) from low-grade gliomas (LGG) and to identify potential covariates that could affect the diagnostic accuracy of ML-based radiomic analysis in classifying gliomas.

Method

A primary literature search of the PubMed database was conducted to find all related literatures in English between January 1, 2009, and May 1, 2020, with combining synonyms for “machine learning,” “glioma,” and “radiomics.” Five retrospective designed original articles including LGG and HGG subjects were chosen. Pooled sensitivity, specificity, their 95% confidence interval, area under curve (AUC), and hierarchical summary receiver-operating characteristic (HSROC) models were obtained.

Result

The pooled sensitivity when diagnosing HGG was higher (96% (95% CI: 0.93, 0.98)) than the specificity when diagnosing LGG (90% (95% CI 0.85, 0.93)). Heterogeneity was observed in both sensitivity and specificity. Metaregression confirmed the heterogeneity in sample sizes (p=0.05), imaging sequence types (p=0.02), and data sources (p=0.01), but not for the inclusion of the testing set (p=0.19), feature extraction number (p=0.36), and selection of feature number (p=0.18). The results of subgroup analysis indicate that sample sizes of more than 100 and feature selection numbers less than the total sample size positively affected the diagnostic performance in differentiating HGG from LGG.

Conclusion

This study demonstrates the excellent diagnostic performance of ML-based radiomics in differentiating HGG from LGG.

Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases

We sought to evaluate the utility of radiomics for Amide Proton Transfer weighted (APTw) imaging by assessing its value in differentiating brain metastases from high- and low grade glial brain tumors. We retrospectively identified 48 treatment-naïve patients (10 WHO grade 2, 1 WHO grade 3, 10 WHO grade 4 primary glial brain tumors and 27 metastases) with either primary glial brain tumors or metastases who had undergone APTw MR imaging. After image analysis with radiomics feature extraction and post-processing, machine learning algorithms (multilayer perceptron machine learning algorithm; random forest classifier) with stratified tenfold cross validation were trained on features and were used to differentiate the brain neoplasms. The multilayer perceptron achieved an AUC of 0.836 (receiver operating characteristic curve) in differentiating primary glial brain tumors from metastases. The random forest classifier achieved an AUC of 0.868 in differentiating WHO grade 4 from WHO grade 2/3 primary glial brain tumors. For the differentiation of WHO grade 4 tumors from grade 2/3 tumors and metastases an average AUC of 0.797 was achieved. Our results indicate that the use of radiomics for APTw imaging is feasible and the differentiation of primary glial brain tumors from metastases is achievable with a high degree of accuracy.

Machine Learning in Meningioma MRI: Past to Present. A Narrative Review

Meningioma is one of the most frequent primary central nervous system tumors. While magnetic resonance imaging (MRI), is the standard radiologic technique for provisional diagnosis and surveillance of meningioma, it nevertheless lacks the prima facie capacity in determining meningioma biological aggressiveness, growth, and recurrence potential. An increasing body of evidence highlights the potential of machine learning and radiomics in improving the consistency and productivity and in providing novel diagnostic, treatment, and prognostic modalities in neuroncology imaging. The aim of the present article is to review the evolution and progress of approaches utilizing machine learning in meningioma MRI-based sementation, diagnosis, grading, and prognosis. We provide a historical perspective on original research on meningioma spanning over two decades and highlight recent studies indicating the feasibility of pertinent approaches, including deep learning in addressing several clinically challenging aspects. We indicate the limitations of previous research designs and resources and propose future directions by highlighting areas of research that remain largely unexplored. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 2.

Hyperpolarized 129Xe Time-of-Flight MR Imaging of Perfusion and Brain Function

Perfusion measurements can provide vital information about the homeostasis of an organ and can therefore be used as biomarkers to diagnose a variety of cardiovascular, renal, and neurological diseases. Currently, the most common techniques to measure perfusion are ¹⁵O positron emission tomography (PET), xenon-enhanced computed tomography (CT), single photon emission computed tomography (SPECT), dynamic contrast enhanced (DCE) MRI, and arterial spin labeling (ASL) MRI. Here, we show how regional perfusion can be quantitively measured with magnetic resonance imaging (MRI) using time-resolved depolarization of hyperpolarized (HP) xenon-129 (¹²⁹Xe), and the application of this approach to detect changes in cerebral blood flow (CBF) due to a hemodynamic response in response to brain stimuli. The investigated HP ¹²⁹Xe Time-of-Flight (TOF) technique produced perfusion images with an average signal-to-noise ratio (SNR) of 10.35. Furthermore, to our knowledge, the first hemodynamic response (HDR) map was acquired in healthy volunteers using the HP ¹²⁹Xe TOF imaging. Responses to visual and motor stimuli were observed. The acquired HP TOF HDR maps correlated well with traditional proton blood oxygenation level-dependent functional MRI. Overall, this study expands the field of HP MRI with a novel dynamic imaging technique suitable for rapid and quantitative perfusion imaging.

Association of dynamic susceptibility magnetic resonance imaging at initial tumor diagnosis with the prognosis of different molecular glioma subtypes

Purpose

The updated 2016 CNS World Health Organization classification differentiates three main groups of diffuse glioma according to their molecular characteristics: astrocytic tumors with and without isocitrate dehydrogenase (IDH) mutation and 1p/19q co-deleted oligodendrogliomas. The present study aimed to determine whether dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) is an independent prognostic marker within the molecular subgroups of diffuse glioma.

Methods

Fifty-six patients with treatment-naive gliomas and advanced preoperative MRI examination were assessed retrospectively. The mean and maximal normalized cerebral blood volume values from DSC-MRI within the tumors were measured. Optimal cutoff values for the 1-year progression-free survival (PFS) were defined, and Kaplan-Meier analyses were performed separately for the three glioma subgroups.

Results

IDH wild-type astrocytic tumors had a higher mean and maximal perfusion than IDH-mutant astrocytic tumors and oligodendrogliomas. Patients with IDH wild-type astrocytic tumors and a low mean or maximal perfusion had a significantly shorter PFS than patients of the same group with high perfusion (p = 0.0159/0.0112). Furthermore, they had a significantly higher risk for early progression (hazard ratio = 5.6/5.1). This finding was independent of the methylation status of O6-methylguanin-DNA-methyltransferase and variations of the therapy. Within the groups of IDH-mutant astrocytic tumors and oligodendrogliomas, the PFS of low and highly perfused tumors did not differ.

Conclusion

High perfusion upon initial diagnosis is not compellingly associated with worse short-term prognosis within the different molecular subgroups of diffuse glioma. Particularly, the overall highly perfused group of IDH wild-type astrocytic tumors contains tumors with low perfusion but unfavorable prognosis.