Spectroscopic evaluation of glioma grading at 3T: the combined role of short and long TE

Grading of Gliomas by Contrast-Enhanced CT Radiomics Features

Background

Gliomas, as Central Nervous System (CNS) tumors, are greatly common with 80% of malignancy. Treatment methods for gliomas, such as surgery, radiation therapy, and chemotherapy depend on the grade, size, location, and the patient's age.

Objective

This study aimed to quantify glioma based on the radiomics analysis and classify its grade into High-grade Glioma (HGG) or Low-grade Glioma (LGG) by various machine-learning methods using contrast-enhanced brain Computerized Tomography (CT) scans.

Material and Methods

This retrospective study involved acquiring and segmenting data, selecting and extracting features, classifying, analyzing, and evaluating classifiers. The study included a total of 62 patients (31 with LGG and 31 with HGG). The tumors were segmented by an experienced CT-scan technologist with 3D slicer software. A total of 14 shape features, 18 histogram-based features, and 75 texture-based features were computed. The Area Under the Curve (AUC) and Receiver Operating Characteristic Curve (ROC) were used to evaluate and compare classification models.

Results

A total of 13 out of 107 features were selected to differentiate between LGGs and HGGs and to perform various classifier algorithms with different cross-validations. The best classifier algorithm was linear-discriminant with 93.5% accuracy, 96.77% sensitivity, 90.3% specificity, and 0.98% AUC in the differentiation of LGGs and HGGs.

Conclusion

The proposed method can identify LGG and HGG with 93.5% accuracy, 96.77% sensitivity, 90.3% specificity, and 0.98% AUC, leading to the best treatment for glioma patients by using CT scans based on radiomics analysis.

Magnetic Resonance Spectroscopy of Intra-axial Gliomas With Histopathological Correlation in a Tertiary Care Center of Eastern Nepal

Background and objective Magnetic resonance spectroscopy (MRS) is a magnetic resonance imaging technique used to identify in vivo metabolites non-invasively within the tissue of interest. It plays an important role in diagnosing brain lesions, particularly tumors and infections. There are certain metabolites whose levels are increased or decreased in brain tumors, the ratios of which can also be used to grade the tumors as high- or low-grade. This study aimed to assess the spectrum of different metabolites in intraaxial gliomas using magnetic resonance spectroscopy and to assess the usefulness of their ratios for grading gliomas into high-grade and low-grade. Methods This descriptive cross-sectional study was performed in the radiology department of Nobel Medical College and Teaching Hospital, Biratnagar, Nepal over one year (September 2019 to September 2020). Thirty-five patients diagnosed as having intra-axial tumors were enrolled. After taking informed consent the examination findings were recorded in structured proforma. Siemens' 3 Tesla open magnet MAGNETOM Skyra (Siemens Healthineers AG, Munich, Germany) MR scanner was used to evaluate each patient. Data was analyzed using the software Statistical Package for Social Sciences (SPSS), version 26.0 (IBM Corp., Armonk, NY). Results Out of 35 patients scanned, 18 had high-grade glioma and 17 had low-grade glioma. High-grade glioma had a choline/creatine (Cho/Cr) ratio of 2.44 ± 0.78 and a choline/N-acetyl-aspartate (Cho/NAA) ratio of 2.05 ± 0.84. Low-grade glioma had a Cho/Cr ratio of 1.48 ± 0.50 and a Cho/NAA ratio of 1.41 ± 0.19. Fourteen out of eighteen high-grade gliomas had raised lipid/lactate peaks. The sensitivity, specificity, positive and negative predictive values (PPV and NPV), and accuracy for diagnosing high-grade glioma with a Cho/Cr ratio cut-off of 1.5 was 83.3 %, 82.4%, 83.3%,82.4 %, and 82.85% respectively. Conclusion MRS metabolite ratios can be used to diagnose and grade gliomas. Cho/Cr, Cho/NAA, and the presence or absence of lipid/lactate peak can significantly improve the sensitivity, specificity, predictive values, and accuracy of preoperative glioma grading when used in conjunction with conventional MRI.

MRI findings of primary intracranial sarcomas in children

BACKGROUND

Primary intracranial sarcoma is a very rare high-grade tumor. Scant reports exist on this malignancy in children, which limit the information about its imaging characteristics.

OBJECTIVE

We aimed to describe the main characteristics of primary intracranial sarcoma on MRI.

MATERIALS AND METHODS

In this cross-sectional descriptive observational study, we reviewed 18 patients (aged 1-18 years) with primary intracranial sarcomas diagnosed between 2015 and 2021.

RESULTS

The main findings were contrast enhancement (100%), diffusion restriction (78%), hemorrhage (89%), meningeal extension (67%), necrosis (67%), and supratentorial location (72%).

CONCLUSION

Primary intracranial sarcoma are typically supratentorial in location. MRI findings of primary intracranial sarcoma are similar to other intracranial malignancies.

Application of 7T MRS to High-Grade Gliomas

MRS, including single-voxel spectroscopy and MR spectroscopic imaging, captures metabolites in high-grade gliomas. Emerging evidence indicates that 7T MRS may be more sensitive to aberrant metabolic activity than lower-field strength MRS. However, the literature on the use of 7T MRS to visualize high-grade gliomas has not been summarized. We aimed to identify metabolic information provided by 7T MRS, optimal spectroscopic sequences, and areas for improvement in and new applications for 7T MRS. Literature was found on PubMed using "high-grade glioma," "malignant glioma," "glioblastoma," "anaplastic astrocytoma," "7T," "MR spectroscopy," and "MR spectroscopic imaging." 7T MRS offers higher SNR, modestly improved spatial resolution, and better resolution of overlapping resonances. 7T MRS also yields reduced Cramér-Rao lower bound values. These features help to quantify D-2-hydroxyglutarate in isocitrate dehydrogenase 1 and 2 gliomas and to isolate variable glutamate, increased glutamine, and increased glycine with higher sensitivity and specificity. 7T MRS may better characterize tumor infiltration and treatment effect in high-grade gliomas, though further study is necessary. 7T MRS will benefit from increased sample size; reductions in field inhomogeneity, specific absorption rate, and acquisition time; and advanced editing techniques. These findings suggest that 7T MRS may advance understanding of high-grade glioma metabolism, with reduced Cramér-Rao lower bound values and better measurement of smaller metabolite signals. Nevertheless, 7T is not widely used clinically, and technical improvements are necessary. 7T MRS isolates metabolites that may be valuable therapeutic targets in high-grade gliomas, potentially resulting in wider ranging neuro-oncologic applications.

Diagnostic Accuracy of Magnetic Resonance Spectroscopy in Predicting the Grade of Glioma Keeping Histopathology as the Gold Standard

Background

Gliomas are the most prevalent intrinsic tumors of the central nervous system and are categorized from grade I to grade IV. Magnetic resonance imaging (MRI) provides exact diagnosis, prognosis, and assessment of tumor response to current chemotherapy/immunotherapy and radiation therapy. With histopathology serving as the gold standard, we aimed to assess the diagnostic accuracy of magnetic resonance spectroscopy (MRS) in predicting glioma grade.

Methodology

This cross-sectional study was conducted in the Department of Radiology, KRL Hospital, Islamabad, from December 15, 2019, to September 30, 2021. After providing written consent, 80 patients with untreated gliomas were included in this study. The voxel of interest was identified using MRI brain conventional contrast-enhanced sequences to assess the grade of the gliomas and link it to the histology report. Following this identification, tissue metabolites were calculated using MRS.

Results

The patients’ age ranged from 13 to 80 years, with a mean age of 49.5 years. Male patients comprised 57.5% of the total study population, while female patients comprised 42.5%. Overall, 23.75% of patients had low-grade tumors, while 76.25% had high-grade tumors. Low-grade tumors had a choline (Cho)/creatine (Cr) metabolite ratio of 1.7421, whereas high-grade tumors had an average Cho/Cr metabolite ratio of 2.5575. N-acetyl aspartate (NAA)/Cr ratio was 1.6368 in low grade and 0.6734 in high-grade tumors. Sensitivity of 77% and specificity of 84.2% were noted, with 78.75% diagnostic accuracy for the Cho/Cr ratio.

Conclusions

Multivoxel MRS has been shown to reliably predict the grade of gliomas despite its non-invasive nature and lack of procedural challenges. When used together Cho/Cr and NAA/Cr ratios and histopathology can accurately determine tumor grade and can be used as a supplementary non-invasive technique.

Accuracy of Magnetic Resonance Spectroscopy in Discrimination of Neoplastic and Non-Neoplastic Brain Lesions

Background

Differentiation of brain lesions by conventional MRI alone is not enough. The introduction of sophisticated imaging methods, such as MR Spectroscopy (MRS), will contribute to accurate differentiation.

Objective

To determine the diagnostic accuracy of MRS in differentiating neoplasm and non-neoplastic brain lesion.

Methodology

This is a cross-sectional descriptive study conducted at Khartoum State from the period of 2015 to 2017. Thirty cases with brain lesions were included in the study investigated with MRS (Single-voxel spectroscopy) and conventional MRI. A comparison of MRS findings and histopathologic analysis was performed. The ratios of Cho/Cr and Cho/NAA were analyzed and compared between neoplastic and non-neoplastic brain masses. Data were analyzed using SPSS version 23.

Results

Out of the 30 patients affected with brain lesions, there were 16 females and 14 males with a mean age of 44 +- 18 years. The ratios of Cho/Cr and Cho/NAA were higher in gliomas, astrocytoma, and meningioma than non-neoplastic lesions. Kappa statistical value (K) showed a good agreement between MRS and histopathological analysis (K= 0.60). The diagnostic accuracy of MRS was 100%, with 82.60% sensitivity, 85.71% specificity, 95% PPV, and 60% NPV.

Conclusion

MRS has high diagnostic accuracy in differentiating neoplasm from non-neoplastic brain tumors. The elevation ratios of Choline-to- N-acetyl aspartate and choline-to- creatine can help neurosurgeons and clinicians differentiate benign from malignant masses.

Minor stroke with bilateral acute infarctions and combined vascular anomalies: A complex case report

We report the case of a patient with bilateral acute ischemic lesions (AIS) in middle cerebral artery (MCA) territory associated with an extremely rare combination of anomalies of the aortic arch and the left internal carotid artery (ICA). The diagnosis deposed for bilateral minor embolic stroke of undetermined source (ESUS), inpatient with patent foramen ovale (PFO) and positive antiphospholipid (aPL) test. To our knowledge, this is the first description of a patient with this rare combination of vascular anomalies.

Differentiating High-Grade Gliomas from Brain Metastases at Magnetic Resonance: The Role of Texture Analysis of the Peritumoral Zone

High-grade gliomas (HGGs) and solitary brain metastases (BMs) have similar imaging appearances, which often leads to misclassification. In HGGs, the surrounding tissues show malignant invasion, while BMs tend to displace the adjacent area. The surrounding edema produced by the two cannot be differentiated by conventional magnetic resonance (MRI) examinations. Forty-two patients with pathology-proven brain tumors who underwent conventional pretreatment MRIs were retrospectively included (HGGs, n = 16; BMs, n = 26). Texture analysis of the peritumoral zone was performed on the T2-weighted sequence using dedicated software. The most discriminative texture features were selected using the Fisher and the probability of classification error and average correlation coefficients. The ability of texture parameters to distinguish between HGGs and BMs was evaluated through univariate, receiver operating, and multivariate analyses. The first percentile and wavelet energy texture parameters were independent predictors of HGGs (75–87.5% sensitivity, 53.85–88.46% specificity). The prediction model consisting of all parameters that showed statistically significant results at the univariate analysis was able to identify HGGs with 100% sensitivity and 66.7% specificity. Texture analysis can provide a quantitative description of the peritumoral zone encountered in solitary brain tumors, that can provide adequate differentiation between HGGs and BMs.

CT-2A neurospheres-derived high-grade glioma in mice: a new model to address tumor stem cells and immunosuppression

Recently, several promising treatments for high-grade gliomas (HGGs) failed to provide significant benefit when translated from the preclinical setting to patients. Improving the animal models is fundamental to overcoming this translational gap. To address this need, we developed and comprehensively characterized a new in vivo model based on the orthotopic implantation of CT-2A cells cultured in neurospheres (NS/CT-2A). Murine CT-2A methylcholanthrene-induced HGG cells (C57BL/6 background) were cultured in monolayers (ML) or NS and orthotopically inoculated in syngeneic animals. ML/CT-2A and NS/CT-2A tumors' characterization included the analysis of tumor growth, immune microenvironment, glioma stem cells (GSCs), vascularization and metabolites. The immuno-modulating properties of NS/CT-2A and ML/CT-2A cells on splenocytes were tested in vitro. Mice harboring NS/CT-2A tumors had a shorter survival than those harboring ML/CT-2A tumors (P=0.0033). Compared to standard ML/CT-2A tumors, NS/CT-2A tumors showed more abundant GSCs (P=0.0002 and 0.0770 for Nestin and CD133, respectively) and regulatory T cells (Tregs, P=0.0074), and a strong tendency towards an increased vascularization (P=0.0503). There were no significant differences in metabolites' composition between NS/ and ML/CT-2A tumors. In vitro, NS were able to drive splenocytes towards a more immunosuppressive status by reducing CD8⁺ T cells (P=0.0354) and by promoting Tregs (P=0.0082), macrophages (MF, P=0.0019) and their M2 subset (P=0.0536). Compared to standard ML/CT-2A tumors, NS/CT-2A tumors show a more aggressive phenotype with increased immunosuppression and GSCs proliferation. Because of these specific features, the NS/CT-2A model represents a clinically relevant platform in the search for new HGG treatments aimed at reducing immunosuppression and eliminating GSCs.

Summary: The NS/CT-2A tumor model represents a valuable research platform for the study of innovative treatments aimed at eliminating GSCs and reversing the tumor-induced immunosuppression in HGGs.

Lack of choline elevation on proton magnetic resonance spectroscopy in grade I-III gliomas

Elevated levels of choline are generally emphasized as marker of increased cellularity and cell membrane turnover in gliomas. In this study, we investigated the incidence rate of lack of choline/creatine and choline/water elevation in a population of grade I-III gliomas. A cohort of 41 patients with histopathologically confirmed gliomas underwent multi-voxel proton magnetic resonance spectroscopy on a 3 T magnetic resonance system prior to treatment. Peak areas for choline and myoinositol were measured from all voxels that exhibited hyperintensity on fluid-attenuated inversion recovery images and were normalized to creatine and unsuppressed water from each voxel. The average metabolite/creatine and metabolite/water ratios from these voxels were then computed. Similarly, average metabolite ratios were computed from normal brain parenchyma. Gliomas were considered for lack of choline elevation when choline/creatine and choline/water ratios from neoplastic regions were less than those from normal brain parenchyma regions. Six of 41 (14.6%) grade I-III gliomas showed lack of elevation for choline/creatine and choline/water ratios compared to normal brain parenchyma. Four of these six gliomas also demonstrated elevated levels of myoinositol/creatine ratio. All other gliomas (n = 35) had elevated choline levels from neoplastic regions relative to normal parenchyma. The sensitivity of choline/creatine or choline/water in determining a grade I-III glioma was 85.4%. These findings suggest that a lack of choline/creatine or choline/water elevation may be seen in some gliomas and low choline levels should not prevent us from considering the possibility of a grade I-III glioma.

Predictive value of 1H MR spectroscopy and 18F-FDG PET/CT for local control of advanced oropharyngeal and hypopharyngeal squamous cell carcinoma receiving chemoradiotherapy: a prospective study

Purpose

To determine whether pretreatment in vivo 1H magnetic resonance (MR) spectroscopy at 3 Tesla (T) and 18F-FDG PET/CT can offer predictive power regarding the local control of oropharyngeal or hypopharyngeal squamous cell carcinoma (OHSCC) patients.

Materials and Methods

¹H MR spectroscopy was performed in addition to conventional MR imaging before definitive chemoradiotherapy in 58 patients with advanced OHSCC. The relationship of local control with the ¹H MR spectroscopy and ¹⁸F-FDG PET/CT parameters was analyzed.

Results

With a median follow-up of 17.6 months, 13 (22.4%) patients exhibited local failure; whereas the remaining 45 achieved local control. Kaplan-Meier analysis identified age > 60 years, creatine level on MRS ≦ 6.02 mM, glutamine and glutamate (Glx) level on MRS > 3.31 mM, and total lesion glycolysis (TLG) on ¹⁸F-FDG PET/CT > 217.18 g/mL × mL as significant adverse predictors for 2-year local control. Multivariate Cox regression analysis showed that age (p=0.017), Glx level on MRS (p=0.021), and TLG on ¹⁸F-FDG PET/CT (p=0.028) retained their independent prognostic significance. A scoring system was constructed based on the sum of these three factors. We found that patients with scores of 2-3 had significantly poorer local control rates than patients with scores of 0-1 (33.3% versus 86.8%, p=0.003).

Conclusion

We conclude that Glx on ¹H MR spectroscopy at 3 T was the independent prognostic factor for local control of OHSCC patients treated with chemoradiotherapy, and its combination with age and TLG may help identify a subgroup of patients at high risk for developing local failure.

Role of Multivoxel Intermediate TE 2D CSI MR Spectroscopy and 2D Echoplanar Diffusion Imaging in Grading of Primary Glial Brain Tumours

INTRODUCTION

Preoperative tumour grading is imperative owing to difference in invasive, aggressive tendencies of different grades of glial tumours implying varied prognosis, therapeutic options. Histopathological examination has inherent sampling errors. Magnetic Resonance Spectroscopy (MRS) and Diffusion Weighted Imaging (DWI) can provide non invasive information about internal mileu hence, aiding in tumour grading by adding to information provided by conventional MRI sequences.

AIM

To evaluate the role of multivoxel intermediate TE 2D CSI MRS and 2D echoplanar diffusion imaging in grading of primary glial brain tumours.

MATERIAL AND METHODS

A prospective study was conducted in Department of Radiology, Teerthanker Mahaveer Medical College and Research Centre, Uttar Pradesh, India, from April 2015 to August 2016 after obtaining necessary approvals from Institutional Ethical Committee and written informed consent from all participants on histopathological proven cases of glial brain tumours that underwent multivoxel MRS using intermediate TE 2D chemical shift imaging and DWI using 2D echoplanar imaging. Tumour grade calculated on MRI using MRS and DWI was compared with histopathological grading. Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity, specificity and accuracy were calculated for each parameter and statistical significance was evaluated using two tailed Pearson test.

RESULTS

Choline: N Acetyl aspartate (Cho: NAA) and Choline: creatinine (Cho: Cr) ratios from MRS as well as Apparent Diffusion Coffecient (ADC) values from DWI were significantly higher with increasing severity of tumour grade. Accuracy of 58.6% was obtained with DWI while it was 83% with MRS. MRS and DWI used together provided 88.4% accuracy. All parameters evaluated showed statistical significance.

CONCLUSION

Both DWI as well as MRS were found to have statistically significant roles in grading of glial brain tumours. MRS was found to be more useful than DWI.

Novel application of chemical shift gradient echo in- and opposed-phase sequences in 3 T MRI for the detection of H-MRS visible lipids and grading of glioma

Objectives

We evaluated the feasibility of using chemical shift gradient-echo (GE) in- and opposed-phase (IOP) imaging to grade glioma.

Methods

A phantom study was performed to investigate the correlation of ¹H MRS-visible lipids with the signal loss ratio (SLR) obtained using IOP imaging. A cross-sectional study approved by the institutional review board was carried out in 22 patients with different glioma grades. The patients underwent scanning using IOP imaging and single-voxel spectroscopy (SVS) using 3T MRI. The brain spectra acquisitions from solid and cystic components were obtained and correlated with the SLR for different grades.

Results

The phantom study showed a positive linear correlation between lipid quantification at 0.9 parts per million (ppm) and 1.3 ppm with SLR (r = 0.79–0.99, p < 0.05). In the clinical study, we found that SLR at the solid portions was the best measure for differentiating glioma grades using optimal cut-points of 0.064 and 0.086 with classification probabilities for grade II (S_II = 1), grade III (S_III = 0.50) and grade IV (S_IV = 0.89).

Conclusions

The results underscore the lipid quantification differences in grades of glioma and provide a more comprehensive characterization by using SLR in chemical shift GE IOP imaging. SLR in IOP sequence demonstrates good performance in glioma grading.

Key Points

• Strong correlation was seen between lipid concentration and SLR obtained using IOP

• IOP sequence demonstrates significant differences in signal loss within the glioma grades

• SLR at solid tumour portions was the best measure for differentiation

• This sequence is applicable in a research capacity for glioma staging armamentarium

Multimodality Brain Tumor Imaging: MR Imaging, PET, and PET/MR Imaging

Standard MR imaging and CT are routinely used for anatomic diagnosis in brain tumors. Pretherapy planning and posttreatment response assessments rely heavily on gadolinium-enhanced MR imaging. Advanced MR imaging techniques and PET imaging offer physiologic, metabolic, or functional information about tumor biology that goes beyond the diagnostic yield of standard anatomic imaging. With the advent of combined PET/MR imaging scanners, we are entering an era wherein the relationships among different elements of tumor metabolism can be simultaneously explored through multimodality MR imaging and PET imaging. The purpose of this review is to provide a practical and clinically relevant overview of current anatomic and physiologic imaging of brain tumors as a foundation for further investigations, with a primary focus on MR imaging and PET techniques that have demonstrated utility in the current care of brain tumor patients.

Inhibition of Pediatric Glioblastoma Tumor Growth by the Anti-Cancer Agent OKN-007 in Orthotopic Mouse Xenografts

Pediatric glioblastomas (pGBM), although rare, are one of the leading causes of cancer-related deaths in children, with tumors essentially refractory to existing treatments. Here, we describe the use of conventional and advanced in vivo magnetic resonance imaging (MRI) techniques to assess a novel orthotopic xenograft pGBM mouse (IC-3752GBM patient-derived culture) model, and to monitor the effects of the anti-cancer agent OKN-007 as an inhibitor of pGBM tumor growth. Immunohistochemistry support data is also presented for cell proliferation and tumor growth signaling. OKN-007 was found to significantly decrease tumor volumes (p<0.05) and increase animal survival (p<0.05) in all OKN-007-treated mice compared to untreated animals. In a responsive cohort of treated animals, OKN-007 was able to significantly decrease tumor volumes (p<0.0001), increase survival (p<0.001), and increase diffusion (p<0.01) and perfusion rates (p<0.05). OKN-007 also significantly reduced lipid tumor metabolism in responsive animals [(Lip1.3 and Lip0.9)-to-creatine ratio (p<0.05)], as well as significantly decrease tumor cell proliferation (p<0.05) and microvessel density (p<0.05). Furthermore, in relationship to the PDGFRα pathway, OKN-007 was able to significantly decrease SULF2 (p<0.05) and PDGFR-α (platelet-derived growth factor receptor-α) (p<0.05) immunoexpression, and significantly increase decorin expression (p<0.05) in responsive mice. This study indicates that OKN-007 may be an effective anti-cancer agent for some patients with pGBMs by inhibiting cell proliferation and angiogenesis, possibly via the PDGFRα pathway, and could be considered as an additional therapy for pediatric brain tumor patients.

Fast spectroscopic multiple analysis (FASMA) for brain tumor classification: a clinical decision support system utilizing multi-parametric 3T MR data

INTRODUCTION

A clinical decision support system (CDSS) for brain tumor classification can be used to assist in the diagnosis and grading of brain tumors. A Fast Spectroscopic Multiple Analysis (FASMA) system that uses combinations of multiparametric MRI data sets was developed as a CDSS for brain tumor classification.

METHODS

MRI metabolic ratios and spectra, from long and short TE, respectively, as well as diffusion and perfusion data were acquired from the intratumoral and peritumoral area of 126 patients with untreated intracranial tumors. These data were categorized based on the pathology, and different machine learning methods were evaluated regarding their classification performance for glioma grading and differentiation of infiltrating versus non-infiltrating lesions. Additional databases were embedded to the system, including updated literature values of the related MR parameters and typical tumor characteristics (imaging and histological), for further comparisons. Custom Graphical User Interface (GUI) layouts were developed to facilitate classification of the unknown cases based on the user's available MR data.

RESULTS

The highest classification performance was achieved with a support vector machine (SVM) using the combination of all MR features. FASMA correctly classified 89 and 79% in the intratumoral and peritumoral area, respectively, for cases from an independent test set. FASMA produced the correct diagnosis, even in the misclassified cases, since discrimination between infiltrative versus non-infiltrative cases was possible.

CONCLUSIONS

FASMA is a prototype CDSS, which integrates complex quantitative MR data for brain tumor characterization. FASMA was developed as a diagnostic assistant that provides fast analysis, representation and classification for a set of MR parameters. This software may serve as a teaching tool on advanced MRI techniques, as it incorporates additional information regarding typical tumor characteristics derived from the literature.

Clinical decision support systems for brain tumor characterization using advanced magnetic resonance imaging techniques

In recent years, advanced magnetic resonance imaging (MRI) techniques, such as magnetic resonance spectroscopy, diffusion weighted imaging, diffusion tensor imaging and perfusion weighted imaging have been used in order to resolve demanding diagnostic problems such as brain tumor characterization and grading, as these techniques offer a more detailed and non-invasive evaluation of the area under study. In the last decade a great effort has been made to import and utilize intelligent systems in the so-called clinical decision support systems (CDSS) for automatic processing, classification, evaluation and representation of MRI data in order for advanced MRI techniques to become a part of the clinical routine, since the amount of data from the aforementioned techniques has gradually increased. Hence, the purpose of the current review article is two-fold. The first is to review and evaluate the progress that has been made towards the utilization of CDSS based on data from advanced MRI techniques. The second is to analyze and propose the future work that has to be done, based on the existing problems and challenges, especially taking into account the new imaging techniques and parameters that can be introduced into intelligent systems to significantly improve their diagnostic specificity and clinical application.

Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion data

PURPOSE

Differentiation of glioblastomas from metastases is clinical important, but may be difficult even for expert observers. To investigate the contribution of machine learning algorithms in the differentiation of glioblastomas multiforme (GB) from metastases, we developed and tested a pattern recognition system based on 3T magnetic resonance (MR) data.

MATERIALS AND METHODS

Single and multi-voxel proton magnetic resonance spectroscopy (1H-MRS) and dynamic susceptibility contrast (DSC) MRI scans were performed on 49 patients with solitary brain tumors (35 glioblastoma multiforme and 14 metastases). Metabolic (NAA/Cr, Cho/Cr, (Lip [Formula: see text] Lac)/Cr) and perfusion (rCBV) parameters were measured in both intratumoral and peritumoral regions. The statistical significance of these parameters was evaluated. For the classification procedure, three datasets were created to find the optimum combination of parameters that provides maximum differentiation. Three machine learning methods were utilized: Naïve-Bayes, Support Vector Machine (SVM) and [Formula: see text]-nearest neighbor (KNN). The discrimination ability of each classifier was evaluated with quantitative performance metrics.

RESULTS

Glioblastoma and metastases were differentiable only in the peritumoral region of these lesions ([Formula: see text]). SVM achieved the highest overall performance (accuracy 98%) for both the intratumoral and peritumoral areas. Naïve-Bayes and KNN presented greater variations in performance. The proper selection of datasets plays a very significant role as they are closely correlated to the underlying pathophysiology.

CONCLUSION

The application of pattern recognition techniques using 3T MR-based perfusion and metabolic features may provide incremental diagnostic value in the differentiation of common intraaxial brain tumors, such as glioblastoma versus metastasis.