Brain Tumor Characterization Using Multibiometric Evaluation of MRI

Fractal dimension: analyzing its potential as a neuroimaging biomarker for brain tumor diagnosis using machine learning

Purpose: The main purpose of this study was to comprehensively investigate the potential of fractal dimension (FD) measures in discriminating brain gliomas into low-grade glioma (LGG) and high-grade glioma (HGG) by examining tumor constituents and non-tumorous gray matter (GM) and white matter (WM) regions. Methods: Retrospective magnetic resonance imaging (MRI) data of 42 glioma patients (LGG, n = 27 and HGG, n = 15) were used in this study. Using MRI, we calculated different FD measures based on the general structure, boundary, and skeleton aspects of the tumorous and non-tumorous brain GM and WM regions. Texture features, namely, angular second moment, contrast, inverse difference moment, correlation, and entropy, were also measured in the tumorous and non-tumorous regions. The efficacy of FD features was assessed by comparing them with texture features. Statistical inference and machine learning approaches were used on the aforementioned measures to distinguish LGG and HGG patients. Results: FD measures from tumorous and non-tumorous regions were able to distinguish LGG and HGG patients. Among the 15 different FD measures, the general structure FD values of enhanced tumor regions yielded high accuracy (93%), sensitivity (97%), specificity (98%), and area under the receiver operating characteristic curve (AUC) score (98%). Non-tumorous GM skeleton FD values also yielded good accuracy (83.3%), sensitivity (100%), specificity (60%), and AUC score (80%) in classifying the tumor grades. These measures were also found to be significantly (p < 0.05) different between LGG and HGG patients. On the other hand, among the 25 texture features, enhanced tumor region features, namely, contrast, correlation, and entropy, revealed significant differences between LGG and HGG. In machine learning, the enhanced tumor region texture features yielded high accuracy, sensitivity, specificity, and AUC score. Conclusion: A comparison between texture and FD features revealed that FD analysis on different aspects of the tumorous and non-tumorous components not only distinguished LGG and HGG patients with high statistical significance and classification accuracy but also provided better insights into glioma grade classification. Therefore, FD features can serve as potential neuroimaging biomarkers for glioma.

Arterial input functions in dynamic susceptibility contrast MRI (DSC-MRI) in longitudinal evaluation of brain metastases

BACKGROUND

Dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) could be helpful to separate true disease progression from pseudo-progression in brain metastases when assessing the need for retreatment. However, the selection of arterial input functions (AIFs) is not standardized for analysis, limiting its use for this application.

PURPOSE

To compare population-based AIFs, AIFs specific to each patient, and AIFs specific to every visit in the longitudinal follow-up of brain metastases.

MATERIAL AND METHODS

Longitudinal data were collected from eight patients before treatment (6 of 8 patients) and after treatment (6-17 visits). Imaging was performed using a 1.5-T MRI system. Lesions were segmented by subtracting precontrast images from postcontrast images. Cerebral blood volume (rCBV) and cerebral blood flow (rCBF) were computed, and Pearson's product moment correlation coefficients were calculated to evaluate similarity of DSC parameters dependent on various AIF choices across time. AIF shape characteristics were compared. Parameter differences between white matter (WM) and gray matter (GM) were obtained to determine which AIF choice maximizes tissue differentiation.

RESULTS

Although DSC parameters follow similar patterns in time, the various AIF selections cause large parameter variations with relative standard deviations of up to ±60%. AIFs sampled in one patient across sessions more similar in shape than AIFs sampled across patients. Estimates of rCBV based on scan-specific AIFs differentiated better between perfusion in WM and GM than patient-specific or population-based AIFs (P ≤ 0.02).

CONCLUSION

Results indicate that scan-specific AIFs are the best choice for DSC-MRI parameter estimations in the longitudinal follow-up of brain metastases.

Applications of Artificial Intelligence Based on Medical Imaging in Glioma: Current State and Future Challenges

Glioma is one of the most fatal primary brain tumors, and it is well-known for its difficulty in diagnosis and management. Medical imaging techniques such as magnetic resonance imaging (MRI), positron emission tomography (PET), and spectral imaging can efficiently aid physicians in diagnosing, treating, and evaluating patients with gliomas. With the increasing clinical records and digital images, the application of artificial intelligence (AI) based on medical imaging has reduced the burden on physicians treating gliomas even further. This review will classify AI technologies and procedures used in medical imaging analysis. Additionally, we will discuss the applications of AI in glioma, including tumor segmentation and classification, prediction of genetic markers, and prediction of treatment response and prognosis, using MRI, PET, and spectral imaging. Despite the benefits of AI in clinical applications, several issues such as data management, incomprehension, safety, clinical efficacy evaluation, and ethical or legal considerations, remain to be solved. In the future, doctors and researchers should collaborate to solve these issues, with a particular emphasis on interdisciplinary teamwork.

Automated brain tumour identification using magnetic resonance imaging: a systematic review and meta-analysis

Background

Automated brain tumor identification facilitates diagnosis and treatment planning. We evaluate the performance of traditional machine learning (TML) and deep learning (DL) in brain tumor detection and segmentation, using MRI.

Methods

A systematic literature search from January 2000 to May 8, 2021 was conducted. Study quality was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Detection meta-analysis was performed using a unified hierarchical model. Segmentation studies were evaluated using a random effects model. Sensitivity analysis was performed for externally validated studies.

Results

Of 224 studies included in the systematic review, 46 segmentation and 38 detection studies were eligible for meta-analysis. In detection, DL achieved a lower false positive rate compared to TML; 0.018 (95% CI, 0.011 to 0.028) and 0.048 (0.032 to 0.072) (P < .001), respectively. In segmentation, DL had a higher dice similarity coefficient (DSC), particularly for tumor core (TC); 0.80 (0.77 to 0.83) and 0.63 (0.56 to 0.71) (P < .001), persisting on sensitivity analysis. Both manual and automated whole tumor (WT) segmentation had “good” (DSC ≥ 0.70) performance. Manual TC segmentation was superior to automated; 0.78 (0.69 to 0.86) and 0.64 (0.53 to 0.74) (P = .014), respectively. Only 30% of studies reported external validation.

Conclusions

The comparable performance of automated to manual WT segmentation supports its integration into clinical practice. However, manual outperformance for sub-compartmental segmentation highlights the need for further development of automated methods in this area. Compared to TML, DL provided superior performance for detection and sub-compartmental segmentation. Improvements in the quality and design of studies, including external validation, are required for the interpretability and generalizability of automated models.

Performance of machine learning algorithms for glioma segmentation of brain MRI: a systematic literature review and meta-analysis

OBJECTIVES

Different machine learning algorithms (MLAs) for automated segmentation of gliomas have been reported in the literature. Automated segmentation of different tumor characteristics can be of added value for the diagnostic work-up and treatment planning. The purpose of this study was to provide an overview and meta-analysis of different MLA methods.

METHODS

A systematic literature review and meta-analysis was performed on the eligible studies describing the segmentation of gliomas. Meta-analysis of the performance was conducted on the reported dice similarity coefficient (DSC) score of both the aggregated results as two subgroups (i.e., high-grade and low-grade gliomas). This study was registered in PROSPERO prior to initiation (CRD42020191033).

RESULTS

After the literature search (n = 734), 42 studies were included in the systematic literature review. Ten studies were eligible for inclusion in the meta-analysis. Overall, the MLAs from the included studies showed an overall DSC score of 0.84 (95% CI: 0.82-0.86). In addition, a DSC score of 0.83 (95% CI: 0.80-0.87) and 0.82 (95% CI: 0.78-0.87) was observed for the automated glioma segmentation of the high-grade and low-grade gliomas, respectively. However, heterogeneity was considerably high between included studies, and publication bias was observed.

CONCLUSION

MLAs facilitating automated segmentation of gliomas show good accuracy, which is promising for future implementation in neuroradiology. However, before actual implementation, a few hurdles are yet to be overcome. It is crucial that quality guidelines are followed when reporting on MLAs, which includes validation on an external test set.

KEY POINTS

• MLAs from the included studies showed an overall DSC score of 0.84 (95% CI: 0.82-0.86), indicating a good performance. • MLA performance was comparable when comparing the segmentation results of the high-grade gliomas and the low-grade gliomas. • For future studies using MLAs, it is crucial that quality guidelines are followed when reporting on MLAs, which includes validation on an external test set.

Cerebral and tumoral blood flow in adult gliomas: a systematic review of results from magnetic resonance imaging

Objective:

Blood flow is the rate of blood movement and relevant to numerous processes, though understudied in gliomas. The aim of this review was to pool blood flow metrics obtained from MRI modalities in adult supratentorial gliomas.

Methods:

MEDLINE, EMBASE and the Cochrane database were queried 01/01/2000–31/12/2019. Studies measuring blood flow in adult Grade II–IV supratentorial gliomas using dynamic susceptibility contrast (DSC) MRI, dynamic contrast enhanced MRI (DCE-MRI) or arterial spin labelling (ASL) were included. Absolute and relative cerebral blood flow (CBF), peritumoral blood flow and tumoral blood flow (TBF) were reported.

Results:

34 studies were included with 1415 patients and 1460 scans. The mean age was 52.4 ± 7.3 years. Most patients had glioblastoma (n = 880, 64.6%). The most common imaging modality was ASL (n = 765, 52.4%) followed by DSC (n = 538, 36.8%). Most studies were performed pre-operatively (n = 1268, 86.8%). With increasing glioma grade (II vs IV), TBF increased (70.8 vs 145.5 ml/100 g/min, p < 0.001) and CBF decreased (85.3 vs 49.6 ml/100 g/min, p < 0.001). In Grade IV gliomas, following treatment, CBF increased in ipsilateral (24.9 ± 1.2 vs 26.1 ± 0.0 ml/100 g/min, p < 0.001) and contralateral white matter (25.6 ± 0.2 vs 26.0± 0.0 ml/100 g/min, p < 0.001).

Conclusion:

Our findings demonstrate that increased mass effect from high-grade gliomas impairs blood flow within the surrounding brain that can improve with surgery.

Advances in knowledge:

This systematic review demonstrates how mass effect from brain tumours impairs blood flow in the surrounding brain parenchyma that can improve with treatment.

Texture analysis of apparent diffusion coefficient (ADC) map for glioma grading: Analysis of whole tumoral and peri-tumoral tissue

PURPOSE

To prospectively investigate the capabilities of texture analysis (TA) based on apparent diffusion coefficient (ADC) map of the entire tumor volume and the whole volume of peri-tumoral edema, in discriminating between high-grade glioma (HGG) and low-grade glioma (LGG).

MATERIALS AND METHODS

A total of 33 patients with histopathological proven glioma were prospectively included. There were 20 men and 13 women with a mean age of 54.5±14.7 (standard deviation [SD]) years (range: 34-75years). TA parameters of whole tumor and peri-tumoral edema were extracted from the ADC map obtained with diffusion-weighted spin-echo echo-planar magnetic resonance imaging at 1.5-T. TA variables of HGG were compared to those of LGG. The optimum cut-off values of TA variables and their corresponding sensitivity, specificity and accuracy for differentiating between LGG and HGG were calculated using receiver operating characteristic curve analysis.

RESULTS

Mean and median tumoral ADC of HGG were significantly lower than those of LGG, at 1.23×10^-3 mm²/s and 1.21×10^-3 mm²/s cut-off values, yielding 70% sensitivity each (95% CI: 59-82% and 61-80%, respectively), 80% (95% CI: 79-98%) and 90% (95% CI: 82-97%) specificity, and 73% (95% CI: 66-91%) and 76% (95% CI: 72-90%) accuracy, respectively. Significant differences in tumoral and peri-tumoral kurtosis were found between HGG and LGG at 1.60 and 0.314 cut-off values yielding sensitivities of 74% (95% CI: 58-83%) and 70% (95% CI: 59-84%), specificities of 90% (95% CI: 80-95%) and 70% (95% CI: 64-83%) and accuracies of 79% (95% CI: 69-89%) and 70% (95% CI: 64-77%), respectively.

CONCLUSION

Measurements of whole tumoral and peri-tumoral TA, based on ADC maps, provide useful information that helps distinguish between HGG and LGG.

Main genetic differences in high-grade gliomas may present different MR imaging and MR spectroscopy correlates

OBJECTIVE

To assess whether the main genetic differences observed in high-grade gliomas (HGG) will present different MR imaging and MR spectroscopy correlates that could be used to better characterize lesions in the clinical setting.

METHODS

Seventy-nine patients with histologically confirmed HGG were recruited. Immunohistochemistry analyses for isocitrate dehydrogenase gene 1 (IDH1), alpha thalassemia mental retardation X-linked gene (ATRX), Ki-67, and p53 protein expression were performed. Tumour radiological features were examined on MR images. Metabolic profile and infiltrative pattern were assessed with MR spectroscopy. MR features were analysed to identify imaging-molecular associations. The Kaplan-Meier method and the Cox regression model were used to identify survival prognostic factors.

RESULTS

In total, 17.7% of the lesions were IDH1-mutated, 8.9% presented ATRX-mutated, 70.9% presented p53 unexpressed, and 22.8% had Ki-67 > 5%. IDH1 wild-type tumours had higher levels of mobile lipids (p = 0.001). The tumour-infiltrative pattern was higher in HGG with unexpressed p53 (p = 0.009). Mutated ATRX tumours presented higher levels of glutamate and glutamine (Glx) (p = 0.001). An association was observed between Glx tumour levels (p = 0.038) and Ki-67 expression (p = 0.008) with the infiltrative pattern. Survival analyses identified IDH1 status, age, and tumour choline levels as independent predictors of prognostic significance.

CONCLUSIONS

Our results suggest that IDH1-wt tumours are more necrotic than IDH1-mut. And that the presence of an infiltrative pattern in HGG is associated with loss of p53 expression, Ki-67 index, and Glx levels. Finally, tumour choline levels could be used as a predictive factor in survival in addition to the IDH1 status to provide a more accurate prediction of survival in HGG patients.

KEY POINTS

• IDH1-wt tumours present higher levels of mobile lipids than IDH1-mut. • Mutated ATRX tumours exhibit higher levels of glutamate and glutamine. • Loss of p53 expression, Ki-67 expression, and glutamate and glutamine levels may contribute to the presence of an infiltrative pattern in HGG.

Multivoxel 1H-MR Spectroscopy Biometrics for Preoprerative Differentiation Between Brain Tumors

We investigated multivoxel proton magnetic resonance spectroscopy (¹H-MRS) biometrics for preoperative differentiation and prognosis of patients with brain metastases (MET), low-grade glioma (LGG) and high-grade glioma (HGG). In total, 33 patients (HGG, 14; LGG, 9; and 10 MET) were included. ¹H-MRS imaging (MRSI) data were assessed and neurochemical profiles for metabolites N-acetyl aspartate (NAA) + NAAG(NAA), Cr + PCr(total creatine, tCr), Glu + Gln(Glx), lactate (Lac), myo-inositol(Ins), GPC + PCho(total choline, tCho), and total lipids, and macromolecule (tMM) signals were estimated. Metabolites were reported as absolute concentrations or ratios to tCho or tCr levels. Voxels of interest in an MRSI matrix were labeled according to tissue. Logistic regression, receiver operating characteristic, and Kaplan-Meier survival analysis was performed. Across HGG, LGG, and MET, average Ins/tCho was shown to be prognostic for overall survival (OS): low values (≤1.29) in affected hemisphere predicting worse OS than high values (>1.29), (log rank < 0.007). Lip/tCho and Ins/tCho combined showed 100% sensitivity and specificity for both HGG/LGG (P < .001) and LGG/MET (P < .001) measured in nonenhancing/contrast-enhancing lesional tissue. Combining tCr/tCho in perilesional edema with tCho/tCr and NAA/tCho from ipsilateral normal- appearing tissue yielded 100% sensitivity and 81.8% specificity (P < .002) for HGG/MET. Best single biomarker: Ins/tCho for HGG/LGG and total lipid/tCho for LGG/MET showed 100% sensitivity and 75% and 100% specificity, respectively. HGG/MET; NAA/tCho showed 75% sensitivity and 84.6% specificity. Multivoxel 1H-MRSI provides prognostic information for OS for HGG/LGG/MET and a multibiometric approach for differentiation may equal or outperform single biometrics.