Towards a method for automated classification of 1H MRS spectra from brain tumours

TensorFit: A torch-based tool for ultrafast metabolite fitting of large MRSI data sets

PURPOSE

To introduce a tool (TensorFit) for ultrafast and robust metabolite fitting of MRSI data based on Torch's auto-differentiation and optimization framework.

METHODS

TensorFit was implemented in Python based on Torch's auto-differentiation to fit individual metabolites in MRS spectra. The underlying time domain and/or frequency domain fitting model is based on a linear combination of metabolite spectroscopic response. The computational time efficiency and accuracy of TensorFit were tested on simulated and in vivo MRS data and compared against TDFDFit and QUEST.

RESULTS

TensorFit demonstrates a significant improvement in computation speed, achieving a 165-times acceleration compared with TDFDFit and 115 times against QUEST. TensorFit showed smaller percentual errors on simulated data compared with TDFDFit and QUEST. When tested on in vivo data, it performed similarly to TDFDFit with a 2% better fit in terms of mean squared error while obtaining a 169-fold speedup.

CONCLUSION

TensorFit enables fast and robust metabolite fitting in large MRSI data sets compared with conventional metabolite fitting methods. This tool could boost the clinical applicability of large 3D MRSI by enabling the fitting of large MRSI data sets within computation times acceptable in a clinical environment.

Using Single-Voxel Magnetic Resonance Spectroscopy Data Acquired at 1.5T to Classify Multivoxel Data at 3T: A Proof-of-Concept Study

In vivo magnetic resonance spectroscopy (MRS) has two modalities, single-voxel (SV) and multivoxel (MV), in which one or more contiguous grids of SVs are acquired.

PURPOSE

To test whether MV grids can be classified with models trained with SV.

METHODS

Retrospective study. Training dataset: Multicenter multiformat SV INTERPRET, 1.5T. Testing dataset: MV eTumour, 3T. Two classification tasks were completed: 3-class (meningioma vs. aggressive vs. normal) and 4-class (meningioma vs. low-grade glioma vs. aggressive vs. normal). Five different methods were tested for feature selection. The classification was implemented using linear discriminant analysis (LDA), random forest, and support vector machines. The evaluation was completed with balanced error rate (BER) and area under the curve (AUC) on both sets. The accuracy in class prediction was calculated by developing a solid tumor index (STI) and segmentation accuracy with the Dice score.

RESULTS

The best method was sequential forward feature selection combined with LDA, with AUCs = 0.95 (meningioma), 0.89 (aggressive), 0.82 (low-grade glioma), and 0.82 (normal). STI was 66% (4-class task) and 71% (3-class task) because two cases failed completely and two more had suboptimal STI as defined by us.

DISCUSSION

The reasons for failure in the classification of the MV test set were related to the presence of artifacts.

Metabolomics and Heart Diseases: From Basic to Clinical Approach

BACKGROUND

The field of metabolomics has been steadily increasing in size for the last 15 years. Advances in analytical and statistical methods have allowed metabolomics to flourish in various areas of medicine. Cardiovascular diseases are some of the main research targets in metabolomics, due to their social and medical relevance, and also to the important role metabolic alterations play in their pathogenesis and evolution. Metabolomics has been applied to the full spectrum of cardiovascular diseases: from patient risk stratification to myocardial infarction and heart failure. However - despite the many proof-ofconcept studies describing the applicability of metabolomics in the diagnosis, prognosis and treatment evaluation in cardiovascular diseases - it is not yet used in routine clinical practice. Recently, large phenome centers have been established in clinical environments, and it is expected that they will provide definitive proof of the applicability of metabolomics in clinical practice. But there is also room for small and medium size centers to work on uncommon pathologies or to resolve specific but relevant clinical questions.

OBJECTIVES

In this review, we will introduce metabolomics, cover the metabolomic work done so far in the area of cardiovascular diseases.

CONCLUSION

The cardiovascular field has been at the forefront of metabolomics application and it should lead the transfer to the clinic in the not so distant future.

Metabolomic signature of brain cancer

Despite advances in surgery and adjuvant therapy, brain tumors represent one of the leading causes of cancer-related mortality and morbidity in both adults and children. Gliomas constitute about 60% of all cerebral tumors, showing varying degrees of malignancy. They are difficult to treat due to dismal prognosis and limited therapeutics. Metabolomics is the untargeted and targeted analyses of endogenous and exogenous small molecules, which charact erizes the phenotype of an individual. This emerging "omics" science provides functional readouts of cellular activity that contribute greatly to the understanding of cancer biology including brain tumor biology. Metabolites are highly informative as a direct signature of biochemical activity; therefore, metabolite profiling has become a promising approach for clinical diagnostics and prognostics. The metabolic alterations are well-recognized as one of the key hallmarks in monitoring disease progression, therapy, and revealing new molecular targets for effective therapeutic intervention. Taking advantage of the latest high-throughput analytical technologies, that is, nuclear magnetic resonance (NMR) spectroscopy and mass spectrometry (MS), metabolomics is now a promising field for precision medicine and drug discovery. In the present report, we review the application of metabolomics and in vivo metabolic profiling in the context of adult gliomas and paediatric brain tumors. Analytical platforms such as high-resolution (HR) NMR, in vivo magnetic resonance spectroscopic imaging and high- and low-resolution MS are discussed. Moreover, the relevance of metabolic studies in the development of new therapeutic strategies for treatment of gliomas are reviewed.

Accurate classification of brain gliomas by discriminate dictionary learning based on projective dictionary pair learning of proton magnetic resonance spectra

Proton magnetic resonance spectroscopy is a powerful noninvasive technique that complements the structural images of cMRI, which aids biomedical and clinical researches, by identifying and visualizing the compositions of various metabolites within the tissues of interest. However, accurate classification of proton magnetic resonance spectroscopy is still a challenging issue in clinics due to low signal-to-noise ratio, overlapping peaks of metabolites, and the presence of background macromolecules. This paper evaluates the performance of a discriminate dictionary learning classifiers based on projective dictionary pair learning method for brain gliomas proton magnetic resonance spectroscopy spectra classification task, and the result were compared with the sub-dictionary learning methods. The proton magnetic resonance spectroscopy data contain a total of 150 spectra (74 healthy, 23 grade II, 23 grade III, and 30 grade IV) from two databases. The datasets from both databases were first coupled together, followed by column normalization. The Kennard-Stone algorithm was used to split the datasets into its training and test sets. Performance comparison based on the overall accuracy, sensitivity, specificity, and precision was conducted. Based on the overall accuracy of our classification scheme, the dictionary pair learning method was found to outperform the sub-dictionary learning methods 97.78% compared with 68.89%, respectively. Copyright © 2016 John Wiley & Sons, Ltd.

Brain metabolic pattern analysis using a magnetic resonance spectra classification software in experimental stroke

Background

Magnetic resonance spectroscopy (MRS) provides non-invasive information about the metabolic pattern of the brain parenchyma in vivo. The SpectraClassifier software performs MRS pattern-recognition by determining the spectral features (metabolites) which can be used objectively to classify spectra. Our aim was to develop an Infarct Evolution Classifier and a Brain Regions Classifier in a rat model of focal ischemic stroke using SpectraClassifier.

Results

A total of 164 single-voxel proton spectra obtained with a 7 Tesla magnet at an echo time of 12 ms from non-infarcted parenchyma, subventricular zones and infarcted parenchyma were analyzed with SpectraClassifier (http://gabrmn.uab.es/?q=sc). The spectra corresponded to Sprague-Dawley rats (healthy rats, n = 7) and stroke rats at day 1 post-stroke (acute phase, n = 6 rats) and at days 7 ± 1 post-stroke (subacute phase, n = 14). In the Infarct Evolution Classifier, spectral features contributed by lactate + mobile lipids (1.33 ppm), total creatine (3.05 ppm) and mobile lipids (0.85 ppm) distinguished among non-infarcted parenchyma (100% sensitivity and 100% specificity), acute phase of infarct (100% sensitivity and 95% specificity) and subacute phase of infarct (78% sensitivity and 100% specificity). In the Brain Regions Classifier, spectral features contributed by myoinositol (3.62 ppm) and total creatine (3.04/3.05 ppm) distinguished among infarcted parenchyma (100% sensitivity and 98% specificity), non-infarcted parenchyma (84% sensitivity and 84% specificity) and subventricular zones (76% sensitivity and 93% specificity).

Conclusion

SpectraClassifier identified candidate biomarkers for infarct evolution (mobile lipids accumulation) and different brain regions (myoinositol content).

Electronic supplementary material

The online version of this article (doi:10.1186/s12868-016-0328-x) contains supplementary material, which is available to authorized users.

A joint analysis of transcriptomic and metabolomic data uncovers enhanced enzyme-metabolite coupling in breast cancer

Disrupted regulation of cellular processes is considered one of the hallmarks of cancer. We analyze metabolomic and transcriptomic profiles jointly collected from breast cancer and hepatocellular carcinoma patients to explore the associations between the expression of metabolic enzymes and the levels of the metabolites participating in the reactions they catalyze. Surprisingly, both breast cancer and hepatocellular tumors exhibit an increase in their gene-metabolites associations compared to noncancerous adjacent tissues. Following, we build predictors of metabolite levels from the expression of the enzyme genes catalyzing them. Applying these predictors to a large cohort of breast cancer samples we find that depleted levels of key cancer-related metabolites including glucose, glycine, serine and acetate are significantly associated with improved patient survival. Thus, we show that the levels of a wide range of metabolites in breast cancer can be successfully predicted from the transcriptome, going beyond the limited set of those measured.

Classification of brain tumours from MR spectra: the INTERPRET collaboration and its outcomes

The INTERPRET project was a multicentre European collaboration, carried out from 2000 to 2002, which developed a decision-support system (DSS) for helping neuroradiologists with no experience of MRS to utilize spectroscopic data for the diagnosis and grading of human brain tumours. INTERPRET gathered a large collection of MR spectra of brain tumours and pseudo-tumoural lesions from seven centres. Consensus acquisition protocols, a standard processing pipeline and strict methods for quality control of the aquired data were put in place. Particular emphasis was placed on ensuring the diagnostic certainty of each case, for which all cases were evaluated by a clinical data validation committee. One outcome of the project is a database of 304 fully validated spectra from brain tumours, pseudotumoural lesions and normal brains, along with their associated images and clinical data, which remains available to the scientific and medical community. The second is the INTERPRET DSS, which has continued to be developed and clinically evaluated since the project ended. We also review here the results of the post-INTERPRET period. We evaluate the results of the studies with the INTERPRET database by other consortia or research groups. A summary of the clinical evaluations that have been performed on the post-INTERPRET DSS versions is also presented. Several have shown that diagnostic certainty can be improved for certain tumour types when the INTERPRET DSS is used in conjunction with conventional radiological image interpretation. About 30 papers concerned with the INTERPRET single-voxel dataset have so far been published. We discuss stengths and weaknesses of the DSS and the lessons learned. Finally we speculate on how the INTERPRET concept might be carried into the future.

Modeling cancer metabolism on a genome scale

Cancer cells have fundamentally altered cellular metabolism that is associated with their tumorigenicity and malignancy. In addition to the widely studied Warburg effect, several new key metabolic alterations in cancer have been established over the last decade, leading to the recognition that altered tumor metabolism is one of the hallmarks of cancer. Deciphering the full scope and functional implications of the dysregulated metabolism in cancer requires both the advancement of a variety of omics measurements and the advancement of computational approaches for the analysis and contextualization of the accumulated data. Encouragingly, while the metabolic network is highly interconnected and complex, it is at the same time probably the best characterized cellular network. Following, this review discusses the challenges that genome-scale modeling of cancer metabolism has been facing. We survey several recent studies demonstrating the first strides that have been done, testifying to the value of this approach in portraying a network-level view of the cancer metabolism and in identifying novel drug targets and biomarkers. Finally, we outline a few new steps that may further advance this field.

2D-1H proton magnetic resonance spectroscopic imaging study on brain metabolite alterations in patients with diabetic hypertension

The aim of the present study was to investigate the possible metabolic alterations in the frontal cortex and parietal white matter in patients with diabetic hypertension (DHT) using proton magnetic resonance (MR) spectroscopic imaging. A total of 33 DHT patients and 30 healthy control subjects aged between 45 and 75 were included in the present study. All subjects were right‑handed. The spectroscopy data were collected using a GE Healthcare 1.5T MR scanner. The multi‑voxels were located in the semioval center (repetition time/echo time=1,500 ms/35 ms). The area of interest was 8x10x2 cm in volume and contained the two sides of the frontal cortex and the parietal white matter. The spectra data were processed using SAGE software. The ratios of brain metabolite concentrations, particularly for N‑acetylaspartate (NAA)/creatine (Cr) and Choline (Cho)/Cr were calculated and analyzed. Statistical analyses were performed using SPSS 17.0. The NAA/Cr ratio of the bilateral prefrontal cortex of the DHT group was significantly lower than that of the control group (left t=‑7.854, P=0.000 and right t=‑5.787, P=0.000), The Cho/Cr ratio was also much lower than the control group (left t=2.422, P=0.024 and right t=2.920, P=0.007). NAA/Cr ratio of the left parietal white matter of the DHT group was extremely lower than that of the control group (t=‑4.199, P=0.000). Therefore, DHT may result in metabolic disorders in the frontal cortex and parietal white matter but the metabolic alterations are different in various regions of the brain. The alteration in cerebral metabolism is associated with diabetes and hypertension. The ratios of NAA/Cr and Cho/Cr are potential metabolic markers for the brain damage induced by DHT.

Molecular imaging coupled to pattern recognition distinguishes response to temozolomide in preclinical glioblastoma

Non-invasive monitoring of response to treatment of glioblastoma (GB) is nowadays carried out using MRI. MRS and MR spectroscopic imaging (MRSI) constitute promising tools for this undertaking. A temozolomide (TMZ) protocol was optimized for GL261 GB. Sixty-three mice were studied by MRI/MRS/MRSI. The spectroscopic information was used for the classification of control brain and untreated and responding GB, and validated against post-mortem immunostainings in selected animals. A classification system was developed, based on the MRSI-sampled metabolome of normal brain parenchyma, untreated and responding GB, with a 93% accuracy. Classification of an independent test set yielded a balanced error rate of 6% or less. Classifications correlated well both with tumor volume changes detected by MRI after two TMZ cycles and with the histopathological data: a significant decrease (p < 0.05) in the proliferation and mitotic rates and a 4.6-fold increase in the apoptotic rate. A surrogate response biomarker based on the linear combination of 12 spectral features has been found in the MRS/MRSI pattern of treated tumors, allowing the non-invasive classification of growing and responding GL261 GB. The methodology described can be applied to preclinical treatment efficacy studies to test new antitumoral drugs, and begets translational potential for early response detection in clinical studies.

MRS-based Metabolomics in Cancer Research

Metabolomics is a relatively new technique that is gaining importance very rapidly. MRS-based metabolomics, in particular, is becoming a useful tool in the study of body fluids, tissue biopsies and whole organisms. Advances in analytical techniques and data analysis methods have opened a new opportunity for such technology to contribute in the field of diagnostics. In the MRS approach to the diagnosis of disease, it is important that the analysis utilizes all the essential information in the spectra, is robust, and is non-subjective. Although some of the data analytic methods widely used in chemical and biological sciences are sketched, a more extensive discussion is given of a 5-stage Statistical Classification Strategy. This proposes powerful feature selection methods, based on, for example, genetic algorithms and novel projection techniques. The applications of MRS-based metabolomics in breast cancer, prostate cancer, colorectal cancer, pancreatic cancer, hepatobiliary cancers, gastric cancer, and brain cancer have been reviewed. While the majority of these applications relate to body fluids and tissue biopsies, some in vivo applications have also been included. It should be emphasized that the number of subjects studied must be sufficiently large to ensure a robust diagnostic classification. Before MRS-based metabolomics can become a widely used clinical tool, however, certain challenges need to be overcome. These include manufacturing user-friendly commercial instruments with all the essential features, and educating physicians and medical technologists in the acquisition, analysis, and interpretation of metabolomics data.

A novel semi-supervised methodology for extracting tumor type-specific MRS sources in human brain data

Background

The clinical investigation of human brain tumors often starts with a non-invasive imaging study, providing information about the tumor extent and location, but little insight into the biochemistry of the analyzed tissue. Magnetic Resonance Spectroscopy can complement imaging by supplying a metabolic fingerprint of the tissue. This study analyzes single-voxel magnetic resonance spectra, which represent signal information in the frequency domain. Given that a single voxel may contain a heterogeneous mix of tissues, signal source identification is a relevant challenge for the problem of tumor type classification from the spectroscopic signal.

Methodology/Principal Findings

Non-negative matrix factorization techniques have recently shown their potential for the identification of meaningful sources from brain tissue spectroscopy data. In this study, we use a convex variant of these methods that is capable of handling negatively-valued data and generating sources that can be interpreted as tumor class prototypes. A novel approach to convex non-negative matrix factorization is proposed, in which prior knowledge about class information is utilized in model optimization. Class-specific information is integrated into this semi-supervised process by setting the metric of a latent variable space where the matrix factorization is carried out. The reported experimental study comprises 196 cases from different tumor types drawn from two international, multi-center databases. The results indicate that the proposed approach outperforms a purely unsupervised process by achieving near perfect correlation of the extracted sources with the mean spectra of the tumor types. It also improves tissue type classification.

Conclusions/Significance

We show that source extraction by unsupervised matrix factorization benefits from the integration of the available class information, so operating in a semi-supervised learning manner, for discriminative source identification and brain tumor labeling from single-voxel spectroscopy data. We are confident that the proposed methodology has wider applicability for biomedical signal processing.

Lipid and macromolecules quantitation in differentiating glioblastoma from solitary metastasis: a short-echo time single-voxel magnetic resonance spectroscopy study at 3 T

OBJECTIVE

The differentiation between solitary metastasis (MET) and glioblastoma (GBM) is difficult using only magnetic resonance imaging techniques. Magnetic resonance spectroscopy (MRS) lipid signal indicates cellular necrosis both in GBMs and METs. The purpose of this prospective study was to determine whether a class of lipids and/or macromolecules (MMs), able to efficiently discriminate between these two types of lesions, exists.

METHODS

Forty-one patients with solitary brain tumor (23 GBMs and 18 METs) underwent magnetic resonance imaging and single-voxel MRS. Short-echo time point resolved spectroscopy sequence acquisition with water suppression technique was used. Spectra were analyzed using LCModel. Absolute quantification was performed with "water-scaling" procedure. The analysis was focused on sums of lipid and macromolecular (LM) components at 0.9 and 1.3 ppm.

RESULTS

The LM13 absolute concentration was statistically different (P < 0.0001) between GBMs and METs. With a cutoff of 81 mM in LM13 absolute concentration, METs and GBMs can be distinguished with a 78% of specificity and an 81% of sensitivity. The presence of the MM12 peak, related to the fucose II complex, in tumors harboring a K-ras gene mutation has been investigated.

CONCLUSIONS

We exploited the performance of a clinically easily implementable method, such as short-echo time single-voxel MRS, for the differentiation between brain metastasis and primary brain tumors. The study showed that MRS absolute lipid and macromolecular signals could be helpful in differentiating GBM from metastasis. LM13 class was found to be a discriminant parameter with an accuracy of 85%. Detection of the MM12-fucose peak may also have a role in understanding molecular biology of brain metastasis and should be further investigated to address specific metabolic phenotypes.

Non-negative matrix factorisation methods for the spectral decomposition of MRS data from human brain tumours

BACKGROUND

In-vivo single voxel proton magnetic resonance spectroscopy (SV 1H-MRS), coupled with supervised pattern recognition (PR) methods, has been widely used in clinical studies of discrimination of brain tumour types and follow-up of patients bearing abnormal brain masses. SV 1H-MRS provides useful biochemical information about the metabolic state of tumours and can be performed at short (< 45 ms) or long (> 45 ms) echo time (TE), each with particular advantages. Short-TE spectra are more adequate for detecting lipids, while the long-TE provides a much flatter signal baseline in between peaks but also negative signals for metabolites such as lactate. Both, lipids and lactate, are respectively indicative of specific metabolic processes taking place. Ideally, the information provided by both TE should be of use for clinical purposes. In this study, we characterise the performance of a range of Non-negative Matrix Factorisation (NMF) methods in two respects: first, to derive sources correlated with the mean spectra of known tissue types (tumours and normal tissue); second, taking the best performing NMF method for source separation, we compare its accuracy for class assignment when using the mixing matrix directly as a basis for classification, as against using the method for dimensionality reduction (DR). For this, we used SV 1H-MRS data with positive and negative peaks, from a widely tested SV 1H-MRS human brain tumour database.

RESULTS

The results reported in this paper reveal the advantage of using a recently described variant of NMF, namely Convex-NMF, as an unsupervised method of source extraction from SV1H-MRS. Most of the sources extracted in our experiments closely correspond to the mean spectra of some of the analysed tumour types. This similarity allows accurate diagnostic predictions to be made both in fully unsupervised mode and using Convex-NMF as a DR step previous to standard supervised classification. The obtained results are comparable to, or more accurate than those obtained with supervised techniques.

CONCLUSIONS

The unsupervised properties of Convex-NMF place this approach one step ahead of classical label-requiring supervised methods for the discrimination of brain tumour types, as it accounts for their increasingly recognised molecular subtype heterogeneity. The application of Convex-NMF in computer assisted decision support systems is expected to facilitate further improvements in the uptake of MRS-derived information by clinicians.

Identifying malignant transformations in recurrent low grade gliomas using high resolution magic angle spinning spectroscopy

OBJECTIVE

The objective of this study was to determine whether metabolic parameters derived from ex vivo analysis of tissue samples are predictive of biologic characteristics of recurrent low grade gliomas (LGGs). This was achieved by exploring the use of multivariate pattern recognition methods to generate statistical models of the metabolic characteristics of recurrent LGGs that correlate with aggressive biology and poor clinical outcome.

METHODS

Statistical models were constructed to distinguish between patients with recurrent gliomas that had undergone malignant transformation to a higher grade and those that remained grade 2. The pattern recognition methods explored in this paper include three filter-based feature selection methods (chi-square, gain ratio, and two-way conditional probability), a genetic search wrapper-based feature subset selection algorithm, and five classification algorithms (linear discriminant analysis, logistic regression, functional trees, support vector machines, and decision stump logit boost). The accuracy of each pattern recognition framework was evaluated using leave-one-out cross-validation and bootstrapping.

MATERIALS

The population studied included fifty-three patients with recurrent grade 2 gliomas. Among these patients, seven had tumors that transformed to grade 4, twenty-four had tumors that transformed to grade 3, and twenty-two had tumors that remained grade 2. Image-guided tissue samples were obtained from these patients using surgical navigation software. Part of each tissue sample was examined by a pathologist for histological features and for consistency with the tumor grade diagnosis. The other part of the tissue sample was analyzed with ex vivo nuclear magnetic resonance (NMR) spectroscopy.

RESULTS

Distinguishing between recurrent low grade gliomas that transformed to a higher grade and those that remained grade 2 was achieved with 96% accuracy, using areas of the ex vivo NMR spectrum corresponding to myoinositol, 2-hydroxyglutarate, hypo-taurine, choline, glycerophosphocholine, phosphocholine, glutathione, and lipid. Logistic regression and decision stump boosting models were able to distinguish between recurrent gliomas that transformed to a higher grade and those that did not with 100% training accuracy (95% confidence interval [93-100%]), 96% leave-one-out cross-validation accuracy (95% confidence interval [87-100%]), and 96% bootstrapping accuracy (95% confidence interval [95-97%]). Linear discriminant analysis, functional trees, and support vector machines were able to achieve leave-one-out cross-validation accuracy above 90% and bootstrapping accuracy above 85%. The three feature ranking methods were comparable in performance.

CONCLUSIONS

This study demonstrates the feasibility of using quantitative pattern recognition methods for the analysis of metabolic data from brain tissue obtained during the surgical resection of gliomas. All pattern recognition techniques provided good diagnostic accuracies, though logistic regression and decision stump boosting slightly outperform the other classifiers. These methods identified biomarkers that can be used to detect malignant transformations in individual low grade gliomas, and can lead to a timely change in treatment for each patient.

Improving the classification of brain tumors in mice with perturbation enhanced (PE)-MRSI

Classifiers based on statistical pattern recognition analysis of MRSI data are becoming important tools for the non-invasive diagnosis of human brain tumors. Here we investigate the potential interest of perturbation-enhanced MRSI (PE-MRSI), in this case acute hyperglycemia, for improving the discrimination between mouse brain MRS patterns of glioblastoma multiforme (GBM), oligodendroglioma (ODG), and non-tumor brain parenchyma (NT). Six GBM-bearing mice and three ODG-bearing mice were scanned at 7 Tesla by PRESS-MRSI with 12 and 136 ms echo-time, during euglycemia (Eug) and also during induced acute hyperglycemia (Hyp), generating altogether four datasets per animal (echo time + glycemic condition): 12Eug, 136Eug, 12Hyp, and 136Hyp. For classifier development all spectral vectors (spv) selected from the MRSI matrix were unit length normalized (UL2) and used either as a training set (76 GBM spv, four mice; 70 ODG spv, two mice; 54 NT spv) or as an independent testing set (61 GBM spv, two mice; 31 ODG, one mouse; 23 NT spv). All Fisher's LDA classifiers obtained were evaluated as far as their descriptive performance-correctly classified cases of the training set (bootstrapping)-and predictive accuracy-balanced error rate of independent testing set classification. MRSI-based classifiers at 12Hyp were consistently more efficient in separating GBM, ODG, and NT regions, with overall accuracies always >80% and up to 95-96%; remaining classifiers were within the 48-85% range. This was also confirmed by user-independent selection of training and testing sets, using leave-one-out (LOO). This highlights the potential interest of perturbation-enhanced MRSI protocols for improving the non-invasive characterization of preclinical brain tumors.

Bioinformatics tools for cancer metabolomics

It is well known that significant metabolic change take place as cells are transformed from normal to malignant. This review focuses on the use of different bioinformatics tools in cancer metabolomics studies. The article begins by describing different metabolomics technologies and data generation techniques. Overview of the data pre-processing techniques is provided and multivariate data analysis techniques are discussed and illustrated with case studies, including principal component analysis, clustering techniques, self-organizing maps, partial least squares, and discriminant function analysis. Also included is a discussion of available software packages.

Clinical pitfalls related to short and long echo times in cerebral MR spectroscopy

MR-spectroscopy (MRS) is a multiparameter diagnostic tool and modification of each parameter results in spectrum morphology changes. In particular, changing the echo time (TE) represents a useful tool to highlight different diagnostic elements, but also has significant impact on the spectrum morphology. Diagnostic errors can result if the role of TE is not properly considered. This article reviews the four most common TE-related pitfalls of MRS interpretation. Clinical practical methods to avoid such pitfalls are also suggested.

Imaging of brain tumors: MR spectroscopy and metabolic imaging

The utility of magnetic resonance spectroscopy (MRS) in diagnosis and evaluation of treatment response to human brain tumors has been widely documented. The role of MRS in tumor classification, tumors versus nonneoplastic lesions, prediction of survival, treatment planning, monitoring of therapy, and post-therapy evaluation is discussed. This article delineates the need for standardization and further study in order for MRS to become widely used as a routine clinical tool.

Proton MR spectroscopy provides relevant prognostic information in high-grade astrocytomas

BACKGROUND AND PURPOSE

There is a large range of survival times in patients with HGA that can only be partially explained by histologic grade and clinical aspects. This study aims to retrospectively assess the predictive value of single-voxel (1)H-MRS regarding survival in HGA.

MATERIALS AND METHODS

Pretreatment (1)H-MRS in 187 patients with HGA produced 180 spectra at STE (30 ms) and 182 at LTE (136 ms). Patients were dichotomized into 2 groups according to survival better or worse than the median. The spectra of the 2 groups were compared using the Mann-Whitney U test. The points on the spectrum with the most significant differences were selected for discriminating patients with good and poor prognosis. Thresholds were defined with ROC curves, and survival was analyzed by using the Kaplan-Meier method and the Cox proportional hazards model.

RESULTS

Four points on the spectrum showed the most significant differences: 0.98 and 3.67 ppm at STE; and 0.98 and 1.25 ppm at LTE (P between <.001 and .011). These points were useful for stratifying 2 prognostic groups (P between <.001 and .003, Kaplan-Meier). The Cox forward stepwise model selected 3 spectroscopic variables: the intensity values of the points 3.67 ppm at STE (hazard ratio, 2.132; 95% CI, 1.504-3.023), 0.98 ppm at LTE (hazard ratio, 0.499; 95% CI, 0.339-0.736), and 1.25 ppm at LTE (hazard ratio, 0.574; 95% CI, 0.368-0.897).

CONCLUSIONS

(1)H-MRS is of value in predicting the length of survival in patients with HGA and could be used to stratify prognostic groups.

Detection of metabolite changes in C6 glioma cells cultured with antimitotic oleyl glycoside by 1H MAS NMR

The synthetic glycoside, oleyl N-acetyl-alpha-D-glucosaminide (1), was previously shown to exhibit antimitotic activity on rat (C6) and human (U-373) glioma lines. To obtain information about its mechanism of action, metabolite changes in C6 glioma cells were analyzed after treatment with 1 using high-resolution magic angle spinning (1)H NMR. Compound 1 caused either a decrease or an increase in the intensity of the signal assigned to coenzyme A (CoA) metabolites depending on the concentration used. The data obtained from the (1)H NMR spectra of cells cultured with 1, combined with those obtained after treatment with oleic acid (an inhibitor of acetyl-CoA carboxylase) and phenyl butyrate (a known antineoplastic agent), suggest that 1 may be altering the metabolism of fatty acids and induce apoptosis of C6 glioma cells. These results point to NMR spectroscopy as an efficient technique for monitoring the response of the cells to therapeutic agents.

Short-term temperature effect on the HRMAS spectra of human brain tumor biopsies and their pattern recognition analysis

OBJECT

To investigate the effect of temperature (0 versus 37 degrees C) in the high-resolution magic angle spinning spectroscopy (HRMAS) pattern of human brain tumor biopsies and its influence in recognition-based tumor type prediction. This proof-of-principle study addressed the bilateral discrimination between meningioma (MM) and glioblastoma multiforme (GBM) cases.

MATERIALS AND METHODS

Forty-three tumor biopsy samples were collected (20 MM and 23 GBM), kept frozen and later analyzed at 0 degrees C and 37 degrees C by HRMAS. Post-HRMAS histopathology was used to validate the tumor type. Time-course experiments (100 min) at both temperatures were carried out to monitor HRMAS pattern changes. Principal component analysis and linear discriminant analysis were used for classifier development with a training set of 20 biopsies.

RESULTS

Temperature-dependent, spectral pattern changes mostly affected mobile lipids and choline-containing compounds resonances and were essentially reversible. Incubation of 3 MM and 3 GBM at 37 degrees C during 100 minutes produced irreversible pattern changes below 13% in a few resonances. Classification performance of an independent test set of 7 biopsies was 100% for the pulse-and-acquire, CPMG at echo times (TE) of 30 ms and 144 ms and Hahn Echo at TE 30 ms at 0 degrees C and 37 degrees C. The performance for Hahn Echo spectra at 136 ms was 83.3% at 0 degrees C and 100% at 37 degrees C.

CONCLUSION

The spectral pattern of mobile lipids changes reversibly with temperature. HRMAS demonstrated potential for automated brain tumor biopsy classification. No advantage was obtained when acquiring spectra at 37 degrees C with respect to 0 degrees C in most of the conditions used for the discrimination addressed.

Short echo time MR spectroscopy of brain tumors: grading of cerebral gliomas by correlation analysis of normalized spectral amplitudes

PURPOSE

To process single voxel spectra of low- and high-grade gliomas. To propose correlation analysis of the scatter plots of normalized spectral amplitudes as a pattern recognition tool for the classification (grading) of brain tumors. To propose a spectrum processing approach that improves the differentiation of proton spectra with dominating macromolecule and lipid peaks.

MATERIALS AND METHODS

LCModel was used to process spectra. Mean metabolite concentrations and mean normalized spectra were obtained for normal white matter and for gliomas. The mean spectra of macromolecules and lipids (ML) in the range 1.4-0.9 ppm, and mean difference spectra (DS) without ML and lactate were computed. Correlation analysis of the scatter plot of the patient and mean normalized spectral amplitudes and dispersion of the scatter plot points were used for classification and grading of tumors.

RESULTS

It was found advantageous to perform the classifications using DS spectra. The shape of ML spectrum and concentration of tCr seem to be a good markers for glioma grade.

CONCLUSION

Combining a qualitative comparison of the patient and mean DS spectra of the tumors using correlation analysis of normalized spectra amplitudes with a quantitative comparison of metabolite concentrations is a powerful tool in studying brain lesions.

SpectraClassifier 1.0: a user friendly, automated MRS-based classifier-development system

BACKGROUND

SpectraClassifier (SC) is a Java solution for designing and implementing Magnetic Resonance Spectroscopy (MRS)-based classifiers. The main goal of SC is to allow users with minimum background knowledge of multivariate statistics to perform a fully automated pattern recognition analysis. SC incorporates feature selection (greedy stepwise approach, either forward or backward), and feature extraction (PCA). Fisher Linear Discriminant Analysis is the method of choice for classification. Classifier evaluation is performed through various methods: display of the confusion matrix of the training and testing datasets; K-fold cross-validation, leave-one-out and bootstrapping as well as Receiver Operating Characteristic (ROC) curves.

RESULTS

SC is composed of the following modules: Classifier design, Data exploration, Data visualisation, Classifier evaluation, Reports, and Classifier history. It is able to read low resolution in-vivo MRS (single-voxel and multi-voxel) and high resolution tissue MRS (HRMAS), processed with existing tools (jMRUI, INTERPRET, 3DiCSI or TopSpin). In addition, to facilitate exchanging data between applications, a standard format capable of storing all the information needed for a dataset was developed. Each functionality of SC has been specifically validated with real data with the purpose of bug-testing and methods validation. Data from the INTERPRET project was used.

CONCLUSIONS

SC is a user-friendly software designed to fulfil the needs of potential users in the MRS community. It accepts all kinds of pre-processed MRS data types and classifies them semi-automatically, allowing spectroscopists to concentrate on interpretation of results with the use of its visualisation tools.

Proton MR spectroscopy improves discrimination between tumor and pseudotumoral lesion in solid brain masses

BACKGROUND AND PURPOSE

Differentiating between tumors and pseudotumoral lesions by conventional MR imaging may be a challenging question. This study aims to evaluate the potential usefulness and the added value that single-voxel proton MR spectroscopy could provide on this discrimination.

MATERIALS AND METHODS

A total of 84 solid brain lesions were retrospectively included in the study (68 glial tumors and 16 pseudotumoral lesions). Single-voxel spectra at TE 30 ms (short TE) and 136 ms (long TE) were available in all cases. Two groups were defined: "training-set" (56 cases) and "test-set" (28 cases). Tumors and pseudotumors were compared in the training-set with the Mann-Whitney U test. Ratios between resonances were defined as classifiers for new cases, and thresholds were selected with receiver operating characteristic (ROC) curves. The added value of spectroscopy was evaluated by 5 neuroradiologists and assessed with the Wilcoxon signed-rank test.

RESULTS

Differences between tumors and pseudotumors were found in myo-inositol (mIns); P < .01) at short TE, and N-acetylaspartate (NAA; P < .001), glutamine (Glx; P < .01), and choline (CHO; P < .05) at long TE. Classifiers suggested tumor when mIns/NAA ratio was more than 0.9 at short TE and also when CHO/NAA ratio was more than 1.9 at long TE. Classifier accuracy was tested in the test-set with the following results: short TE, 82% (23/28); long TE, 79% (22/28). The neuroradiologists' confidence rating of the test-cases on a 5-point scale (0-4) improved between 5% (from 2.86-3) and 27% (from 2.25-2.86) with spectroscopy (mean, 17%; P < .01).

CONCLUSIONS

The proposed ratios of mIns/NAA at short TE and CHO/NAA at long TE provide valuable information to discriminate between brain tumor and pseudotumor by improving neuroradiologists' accuracy and confidence.

Supervised pattern recognition for the prediction of contrast-enhancement appearance in brain tumors from multivariate magnetic resonance imaging and spectroscopy

OBJECTIVE

The purpose of this study was to develop a pattern classification algorithm for use in predicting the location of new contrast-enhancement in brain tumor patients using data obtained via multivariate magnetic resonance (MR) imaging from a prior scan. We also explore the use of feature selection or weighting in improving the accuracy of the pattern classifier.

METHODS AND MATERIALS

Contrast-enhanced MR images, perfusion images, diffusion images, and proton spectroscopic imaging data were obtained from 26 patients with glioblastoma multiforme brain tumors, divided into a design set and an unseen test set for verification of results. A k-NN algorithm was implemented to classify unknown data based on a set of training data with ground truth derived from post-treatment contrast-enhanced images; the quality of the k-NN results was evaluated using a leave-one-out cross-validation method. A genetic algorithm was implemented to select optimal features and feature weights for the k-NN algorithm. The binary representation of the weights was varied from 1 to 4 bits. Each individual parameter was thresholded as a simple classification technique, and the results compared with the k-NN.

RESULTS

The feature selection k-NN was able to achieve a sensitivity of 0.78+/-0.18 and specificity of 0.79+/-0.06 on the holdout test data using only 7 of the 38 original features. Similar results were obtained with non-binary weights, but using a larger number of features. Overfitting was also observed in the higher bit representations. The best single-variable classifier, based on a choline-to-NAA abnormality index computed from spectroscopic data, achieved a sensitivity of 0.79+/-0.20 and specificity of 0.71+/-0.11. The k-NN results had lower variation across patients than the single-variable classifiers.

CONCLUSIONS

We have demonstrated that the optimized k-NN rule could be used for quantitative analysis of multivariate images, and be applied to a specific clinical research question. Selecting features was found to be useful in improving the accuracy of feature weighting algorithms and improving the comprehensibility of the results. We believe that in addition to lending insight into parameter relevance, such algorithms may be useful in aiding radiological interpretation of complex multimodality datasets.

Metabolic fingerprinting as a diagnostic tool

Within the framework of systems biology, functional analyses at all 'omic levels have seen an intense level of activity during the first decade of the twenty-first century. These include genomics, transcriptomics, proteomics, metabolomics and lipidomics. It could be said that metabolomics offers some unique advantages over the other 'omics disciplines and one of the core approaches of metabolomics for disease diagnostics is metabolic fingerprinting. This review provides an overview of the main metabolic fingerprinting approaches used for disease diagnostics and includes: infrared and Raman spectroscopy, Nuclear magnetic resonance (NMR) spectroscopy, followed by an introduction to a wide range of novel mass spectrometry-based methods, which are currently under intense investigation and developmental activity in laboratories worldwide. It is hoped that this review will act as a springboard for researchers and clinicians across a wide range of disciplines in this exciting era of multidisciplinary and novel approaches to disease diagnostics.

Perturbation of mouse glioma MRS pattern by induced acute hyperglycemia

(1)H MRS is evolving into an invaluable tool for brain tumor classification in humans based on pattern recognition analysis, but there is still room for improvement. Here we propose a new approach: to challenge tumor metabolism in vivo by a defined perturbation, and study the induced changes in MRS pattern. For this we recorded single voxel (1)H MR spectra from mice bearing a stereotactically induced GL261 grade IV brain glioma during a period of induced acute hyperglycemia. A total of 29 C57BL/6 mice were used. Single voxel spectra were acquired at 7 T with point resolved spectroscopy and TE of 12, 30 and 136 ms. Tumors were induced by stereotactic injection of 10(5) GL261cells in 17 mice. Hyperglycemia (up to 338 +/- 36 mg/dL glucose in the blood) was induced by intraperitoneal bolus injection. Maximal increases in glucose resonances of up to 2.4-fold were recorded from tumors in vivo. Our observations are in agreement with extracellular accumulation of glucose, which may suggest that glucose transport and/or metabolism are working close to their maximum capacity in GL261 tumors. The significant and specific MRS pattern changes observed when comparing euglycemia and hyperglycemia may be of use for future pattern-recognition studies of animal and human brain tumors by enhancing MRS-based discrimination between tumor types and grades.

Monovoxel 1H Magnetic Resonance Spectroscopy in the Progression of Gliomas

AIM

Can monovoxel magnetic resonance spectroscopy (MRS) reliably follow tumour progression in low-grade glioma?

MATERIALS AND METHODS

21 patients with low-grade glioma underwent at least 3 MRS.

RESULTS

For progression from a grade II to grade III tumour, a sensitivity of 57.1% and specificity of 60% were observed, with a positive predictive value (PPV) of 48.8% and a negative predictive value (NPV) of 54.5%. For progression under treatment, we obtained a sensitivity of 57.1% by N-acetylaspartate (NAA)/choline (Cho) and myoinositol/creatine (Cr) and a specificity of 100% by Cho/Cr and lipids, with a PPV of 80% and a NPV of 63.6%.

CONCLUSION

We found that NAA/Cho is the best marker of tumour progression before therapy, with a sensitivity of 53.9%. For the therapeutic response, sensitivity was only 28.2%.

A metabolomics perspective of human brain tumours

During the past decade or so, a wealth of information about metabolites in various human brain tumour preparations (cultured cells, tissue specimens, tumours in vivo) has been accumulated by global profiling tools. Such holistic approaches to cellular biochemistry have been termed metabolomics. Inherent and specific metabolic profiles of major brain tumour cell types, as determined by proton nuclear magnetic resonance spectroscopy ((1)H MRS), have also been used to define metabolite phenotypes in tumours in vivo. This minireview examines the recent advances in the field of human brain tumour metabolomics research, including advances in MRS and mass spectrometry technologies, and data analysis.

A possible cellular explanation for the NMR-visible mobile lipid (ML) changes in cultured C6 glioma cells with growth

The NMR-visible mobile lipid (ML) signals of C6 glioma cells have been monitored at 9.4 and 11.7 T (single pulse and 136 ms echo time) from cell pellets by (1)H NMR spectroscopy. A reproducible behavior with growth has been found. ML signals increase from log phase (4 days of culture) to postconfluence (7 days of culture). This ML behavior is paralleled by the percentage of cells containing epifluorescence detectable Nile Red stained cytosolic droplets (range 23%-60% of cells). The number of positive cells increases after seeding (days 0-1), decreases at log phase (days 2-4), increases again at confluence (day 5) and even further at post-confluence (day 7). C6 cells proliferation arrest induced by growth factors deprivation induces an even higher accumulation of cytosolic droplets (up to 100% of cells) and a large ML increase (up to 21-fold with respect to 4-day log phase cells). When neutral lipid content is quantified by thin-layer chromatography (TLC) on total lipid extracts of C6 cells, no statistically significant change can be detected (in microg/10(8) cells) with growth or growth arrest in major neutral lipid containing species (triacylglycerol, TAG, diacylglycerol, DAG, cholesteryl esters, ChoEst) except for DAG, which decreased in post-confluent, 7-day cells. The apparent discrepancy between NMR, optical microscopy and TLC results can be reconciled if possible biophysical changes in the neutral lipid pool with growth are taken into account. A cellular explanation for the observed results is proposed: the TAG-droplet-size-change hypothesis.

Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra

A computer-based decision support system to assist radiologists in diagnosing and grading brain tumours has been developed by the multi-centre INTERPRET project. Spectra from a database of 1H single-voxel spectra of different types of brain tumours, acquired in vivo from 334 patients at four different centres, are clustered according to their pathology, using automated pattern recognition techniques and the results are presented as a two-dimensional scatterplot using an intuitive graphical user interface (GUI). Formal quality control procedures were performed to standardize the performance of the instruments and check each spectrum, and teams of expert neuroradiologists, neurosurgeons, neurologists and neuropathologists clinically validated each case. The prototype decision support system (DSS) successfully classified 89% of the cases in an independent test set of 91 cases of the most frequent tumour types (meningiomas, low-grade gliomas and high-grade malignant tumours--glioblastomas and metastases). It also helps to resolve diagnostic difficulty in borderline cases. When the prototype was tested by radiologists and other clinicians it was favourably received. Results of the preliminary clinical analysis of the added value of using the DSS for brain tumour diagnosis with MRS showed a small but significant improvement over MRI used alone. In the comparison of individual pathologies, PNETs were significantly better diagnosed with the DSS than with MRI alone.

The Cinderella story of metabolic profiling: does metabolomics get to go to the functional genomics ball?

To date most global approaches to functional genomics have centred on genomics, transcriptomics and proteomics. However, since a number of high-profile publications, interest in metabolomics, the global profiling of metabolites in a cell, tissue or organism, has been rapidly increasing. A range of analytical techniques, including 1H NMR spectroscopy, gas chromatography-mass spectrometry (GC-MS), liquid chromatography-mass spectrometry (LC-MS), Fourier Transform mass spectrometry (FT-MS), high performance liquid chromatography (HPLC) and electrochemical array (EC-array), are required in order to maximize the number of metabolites that can be identified in a matrix. Applications have included phenotyping of yeast, mice and plants, understanding drug toxicity in pharmaceutical drug safety assessment, monitoring tumour treatment regimes and disease diagnosis in human populations. These successes are likely to be built on as other analytical and bioinformatic approaches are developed to fully exploit the information obtained in metabolic profiles. To assist in this process, databases of metabolomic data will be necessary to allow the passage of information between laboratories. In this prospective review, the capabilities of metabolomics in the field of medicine will be assessed in an attempt to predict the impact this 'Cinderella approach' will have at the 'functional genomic ball'.

Distinction of brain tissue, low grade and high grade glioma with time-resolved fluorescence spectroscopy

Neuropathology frozen section diagnoses are difficult in part because of the small tissue samples and the paucity of adjunctive rapid intraoperative stains. This study aims to explore the use of time-resolved laser-induced fluorescence spectroscopy as a rapid adjunctive tool for the diagnosis of glioma specimens and for distinction of glioma from normal tissues intraoperatively. Ten low grade gliomas, 15 high grade gliomas without necrosis, 6 high grade gliomas with necrosis and/or radiation effect, and 14 histologically uninvolved "normal" brain specimens are spectroscopicaly analyzed and contrasted. Tissue autofluorescence was induced with a pulsed Nitrogen laser (337 nm, 1.2 ns) and the transient intensity decay profiles were recorded in the 370-500 nm spectral range with a fast digitized (0.2 ns time resolution). Spectral intensities and time-dependent parameters derived from the time-resolved spectra of each site were used for tissue characterization. A linear discriminant analysis diagnostic algorithm was used for tissue classification. Both low and high grade gliomas can be distinguished from histologically uninvolved cerebral cortex and white matter with high accuracy (above 90%). In addition, the presence or absence of treatment effect and/or necrosis can be identified in high grade gliomas. Taking advantage of tissue autofluorescence, this technique facilitates a direct and rapid investigation of surgically obtained tissue.

A multi-centre, web-accessible and quality control-checked database of in vivo MR spectra of brain tumour patients

OBJECTIVE

To describe an Internet-accessible database that contains validated in vivo MR spectra and clinical data of brain tumour patients.

MATERIALS AND METHODS

All data from patients entering the INTERPRET project (International Network for Pattern Recognition of Tumours Using Magnetic Resonance, <http://azizu.uab.es/INTERPRET>) were stored in a web-accessible database (iDB) and selected using its query functionality. Criteria for selection were that the case had a single voxel (SV) short-echo (20-32 ms) 1.5 T spectrum acquired from a nodular region of the tumour, that the voxel had been positioned in the same region as where subsequent biopsy was obtained, that the short-echo spectrum had not been discarded because of acquisition artefacts or other reasons, and that a histopathological diagnosis was agreed among a committee of neuropathologists. When the spectra were obtained from normal volunteers or were of abscesses or clinically proven metastases, biopsy was not required.

RESULTS

A subset of 304 cases (22 normal volunteers and 282 tumour patients) was obtained. These cases were migrated to another similar database (validated-DB).

CONCLUSION

The validated-DB complies with ethics regulations and represents the population studied. It is accessible by neuroradiologists willing to use information provided by MRS to help in the non-invasive diagnosis of brain tumours.

Diagnosis of meningioma by time-resolved fluorescence spectroscopy

We investigate the use of time-resolved laser-induced fluorescence spectroscopy (TR-LIFS) as an adjunctive tool for the intraoperative rapid evaluation of tumor specimens and delineation of tumor from surrounding normal tissue. Tissue autofluorescence is induced with a pulsed nitrogen laser (337 nm, 1.2 ns) and the intensity decay profiles are recorded in the 370 to 500 nm spectral range with a fast digitizer (0.2 ns resolution). Experiments are conducted on excised specimens (meningioma, dura mater, cerebral cortex) from 26 patients (97 sites). Spectral intensities and time-dependent parameters derived from the time-resolved spectra of each site are used for tissue characterization. A linear discriminant analysis algorithm is used for tissue classification. Our results reveal that meningioma is characterized by unique fluorescence characteristics that enable discrimination of tumor from normal tissue with high sensitivity (>89%) and specificity (100%). The accuracy of classification is found to increase (92.8% cases in the training set and 91.8% in the cross-validated set correctly classified) when parameters from both the spectral and the time domain are used for discrimination. Our findings establish the feasibility of using TR-LIFS as a tool for the identification of meningiomas and enables further development of real-time diagnostic tools for analyzing surgical tissue specimens of meningioma or other brain tumors.

Metabolic differences between primary and recurrent human brain tumors: a 1H NMR spectroscopic investigation

High-resolution proton magnetic resonance spectroscopy was performed on tissue specimens from 33 patients with astrocytic tumors (22 astrocytomas, 11 glioblastomas) and 13 patients with meningiomas. For all patients, samples of primary tumors and their first recurrences were examined. Increased anaplasia, with respect to malignant transformation, resulting in a higher malignancy grade, was present in 11 recurrences of 22 astrocytoma patients. Spectroscopic features of tumor types, as determined on samples of the primary occurrences, were in good agreement with previous studies. Compared with the respective primary astrocytomas, characteristic features of glioblastomas were significantly increased concentrations of alanine (Ala) (p = 0.005), increased metabolite ratios of glycine (Gly)/total creatine (tCr) (p = 0.0001) and glutamate (Glu)/glutamine (Gln) (p = 0.004). Meningiomas showed increased Ala (p = 0.02) and metabolite ratios [Gly, total choline (tCho), Ala] over tCr (p = 0.001) relative to astrocytomas, and N-acetylaspartate and myo-inositol were absent. Metabolic changes of an evolving tumor were observed in recurrent astrocytomas: owing to their consecutive assessments, more indicators of malignant degeneration were detected in astrocytoma recurrences (e.g. Gly, p = 0.029; tCho, p = 0.034; Glu, p = 0.015; tCho/tCr, p = 0.001) in contrast to the comparison of primary astrocytomas with primary glioblastomas. The present investigation demonstrated a correlation of the tCho-signal with tumor progression. Significantly elevated concentrations of Ala (p = 0.037) and Glu (p = 0.003) and metabolite ratio tCho/tCr (p = 0.005) were even found in recurrent low-grade astrocytomas with unchanged histopathological grading (n = 11). This may be related to an early stage of malignant transformation, not yet detectable morphologically, and emphasizes the high sensitivity of 1H NMR spectroscopy in elucidating characteristics of brain tumor metabolism.

The use of multivariate MR imaging intensities versus metabolic data from MR spectroscopic imaging for brain tumour classification

This study investigated the value of information from both magnetic resonance imaging and magnetic resonance spectroscopic imaging (MRSI) to automated discrimination of brain tumours. The influence of imaging intensities and metabolic data was tested by comparing the use of MR spectra from MRSI, MR imaging intensities, peak integration values obtained from the MR spectra and a combination of the latter two. Three classification techniques were objectively compared: linear discriminant analysis, least squares support vector machines (LS-SVM) with a linear kernel as linear techniques and LS-SVM with radial basis function kernel as a nonlinear technique. Classifiers were evaluated over 100 stratified random splittings of the dataset into training and test sets. The area under the receiver operating characteristic (ROC) curve (AUC) was used as a global performance measure on test data. In general, all techniques obtained a high performance when using peak integration values with or without MR imaging intensities. For example for low- versus high-grade tumours, low- versus high-grade gliomas and gliomas versus meningiomas, the mean test AUC was higher than 0.91, 0.94, and 0.99, respectively, when both MR imaging intensities and peak integration values were used. The use of metabolic data from MRSI significantly improved automated classification of brain tumour types compared to the use of MR imaging intensities solely.

The development of functional imaging in the diagnosis, management and understanding of childhood brain tumours

Imaging plays a fundamental role in the management of children with brain tumours. A series of new techniques, commonly grouped under the heading functional imaging, promise to give information on the properties and biological characteristics of tissues thereby adding to the structural information available from current imaging. The EPSRC funded a workshop to bring together clinicians from the UK Children's Cancer Study Group and scientific experts in the field to identify clinical problems in childhood brain tumours that may be addressed by functional imaging and to develop a clinical test bed for applying, evaluating and developing this new technology. The presentations and discussion sessions from the workshop are summarised and a review of the current 'state of the art' for this rapidly developing area provided. A key output of the workshop was agreement on a series of hypotheses which can be tested in carefully designed clinical studies.

Brain tumor classification based on long echo proton MRS signals

There has been a growing research interest in brain tumor classification based on proton magnetic resonance spectroscopy (1H MRS) signals. Four research centers within the EU funded INTERPRET project have acquired a significant number of long echo 1H MRS signals for brain tumor classification. In this paper, we present an objective comparison of several classification techniques applied to the discrimination of four types of brain tumors: meningiomas, glioblastomas, astrocytomas grade II and metastases. Linear and non-linear classifiers are compared: linear discriminant analysis (LDA), support vector machines (SVM) and least squares SVM (LS-SVM) with a linear kernel as linear techniques and LS-SVM with a radial basis function (RBF) kernel as a non-linear technique. Kernel-based methods can perform well in processing high dimensional data. This motivates the inclusion of SVM and LS-SVM in this study. The analysis includes optimal input variable selection, (hyper-) parameter estimation, followed by performance evaluation. The classification performance is evaluated over 200 stratified random samplings of the dataset into training and test sets. Receiver operating characteristic (ROC) curve analysis measures the performance of binary classification, while for multiclass classification, we consider the accuracy as performance measure. Based on the complete magnitude spectra, automated binary classifiers are able to reach an area under the ROC curve (AUC) of more than 0.9 except for the hard case glioblastomas versus metastases. Although, based on the available long echo 1H MRS data, we did not find any statistically significant difference between the performances of LDA and the kernel-based methods, the latter have the strength that no dimensionality reduction is required to obtain such a high performance.