Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

Convolutional neural networks to predict brain tumor grades and Alzheimer’s disease with MR spectroscopic imaging data

Purpose

To evaluate the value of convolutional neural network (CNN) in the diagnosis of human brain tumor or Alzheimer’s disease by MR spectroscopic imaging (MRSI) and to compare its Matthews correlation coefficient (MCC) score against that of other machine learning methods and previous evaluation of the same data. We address two challenges: 1) limited number of cases in MRSI datasets and 2) interpretability of results in the form of relevant spectral regions.

Methods

A shallow CNN with only one hidden layer and an ad-hoc loss function was constructed involving two branches for processing spectral and image features of a brain voxel respectively. Each branch consists of a single convolutional hidden layer. The output of the two convolutional layers is merged and fed to a classification layer that outputs class predictions for the given brain voxel.

Results

Our CNN method separated glioma grades 3 and 4 and identified Alzheimer’s disease patients using MRSI and complementary MRI data with high MCC score (Area Under the Curve were 0.87 and 0.91 respectively). The results demonstrated superior effectiveness over other popular methods as Partial Least Squares or Support Vector Machines. Also, our method automatically identified the spectral regions most important in the diagnosis process and we show that these are in good agreement with existing biomarkers from the literature.

Conclusion

Shallow CNNs models integrating image and spectral features improved quantitative and exploration and diagnosis of brain diseases for research and clinical purposes. Software is available at https://bitbucket.org/TeslaH2O/cnn_mrsi.

Heat Modulation of Intrinsic MR Contrasts for Tumor Characterization

(1) Background: The longitudinal relaxation time (T1), transverse relaxation time (T2), water proton chemical shift (CS), and apparent diffusion coefficient (ADC) are MR quantities that change with temperature. In this work, we investigate heat-induced intrinsic MR contrast types to add salient information to conventional MR imaging to improve tumor characterization. (2) Methods: Imaging tests were performed in vivo using different rat tumor models. The rats were cooled/heated to steady-state temperatures from 26–36 °C and quantitative measurements of T1, T2, and ADC were obtained. Temperature maps were measured using the proton resonance frequency shift (PRFS) method during the heating and cooling cycles. (3) Results: All tissue samples show repeatable relaxation parameter measurement over a range of 26–36 °C. Most notably, we observed a more than 3.3% change in T1/°C in breast adenocarcinoma tumors compared to a 1% change in benign breast fibroadenoma lesions. In addition, we note distinct values of T2/°C change for rat prostate carcinoma cells compared to benign tissue. (4) Conclusion: These findings suggest the possibility of improving MR imaging visualization and characterization of tissue with heat-induced contrast types. Specifically, these results suggest that the temporal thermal responses of heat-sensitive MR imaging contrast mechanisms in different tissue types contain information for improved (i) characterization of tumor/tissue boundaries for diagnostic and therapy purposes, and (ii) characterization of salient behavior of tissues, e.g., malignant versus benign tumors.

Context aware deep learning for brain tumor segmentation, subtype classification, and survival prediction using radiology images

A brain tumor is an uncontrolled growth of cancerous cells in the brain. Accurate segmentation and classification of tumors are critical for subsequent prognosis and treatment planning. This work proposes context aware deep learning for brain tumor segmentation, subtype classification, and overall survival prediction using structural multimodal magnetic resonance images (mMRI). We first propose a 3D context aware deep learning, that considers uncertainty of tumor location in the radiology mMRI image sub-regions, to obtain tumor segmentation. We then apply a regular 3D convolutional neural network (CNN) on the tumor segments to achieve tumor subtype classification. Finally, we perform survival prediction using a hybrid method of deep learning and machine learning. To evaluate the performance, we apply the proposed methods to the Multimodal Brain Tumor Segmentation Challenge 2019 (BraTS 2019) dataset for tumor segmentation and overall survival prediction, and to the dataset of the Computational Precision Medicine Radiology-Pathology (CPM-RadPath) Challenge on Brain Tumor Classification 2019 for tumor classification. We also perform an extensive performance evaluation based on popular evaluation metrics, such as Dice score coefficient, Hausdorff distance at percentile 95 (HD95), classification accuracy, and mean square error. The results suggest that the proposed method offers robust tumor segmentation and survival prediction, respectively. Furthermore, the tumor classification results in this work is ranked at second place in the testing phase of the 2019 CPM-RadPath global challenge.

Optimization of Brain Tumor MR Image Classification Accuracy Using Optimal Threshold, PCA and Training ANFIS with Different Repetitions

BACKGROUND

One of the leading causes of death is brain tumors. Accurate tumor classification leads to appropriate decision making and providing the most efficient treatment to the patients. This study aims to optimize brain tumor MR images classification accuracy using optimal threshold, PCA and training Adaptive Neuro Fuzzy Inference System (ANFIS) with different repetitions.

MATERIAL AND METHODS

The procedure used in this study consists of five steps: (1) T1, T2 weighted images collection, (2) tumor separation with different threshold levels, (3) feature extraction, (4) presence and absence of feature reduction applying principal component analysis (PCA) and (5) ANFIS classification with 0, 20 and 200 training repetitions.

RESULTS

ANFIS accuracy was 40%, 80% and 97% for all features and 97%, 98.5% and 100% for the 6 selected features by PCA in 0, 20 and 200 training repetitions, respectively.

CONCLUSION

The findings of the present study demonstrated that accuracy can be raised up to 100% by using an optimized threshold method, PCA and increasing training repetitions.

Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: concepts, workflow, and use-cases

BACKGROUND

With a wide array of multi-modal, multi-protocol, and multi-scale biomedical data being routinely acquired for disease characterization, there is a pressing need for quantitative tools to combine these varied channels of information. The goal of these integrated predictors is to combine these varied sources of information, while improving on the predictive ability of any individual modality. A number of application-specific data fusion methods have been previously proposed in the literature which have attempted to reconcile the differences in dimensionalities and length scales across different modalities. Our objective in this paper was to help identify metholodological choices that need to be made in order to build a data fusion technique, as it is not always clear which strategy is optimal for a particular problem. As a comprehensive review of all possible data fusion methods was outside the scope of this paper, we have focused on fusion approaches that employ dimensionality reduction (DR).

METHODS

In this work, we quantitatively evaluate 4 non-overlapping existing instantiations of DR-based data fusion, within 3 different biomedical applications comprising over 100 studies. These instantiations utilized different knowledge representation and knowledge fusion methods, allowing us to examine the interplay of these modules in the context of data fusion. The use cases considered in this work involve the integration of (a) radiomics features from T2w MRI with peak area features from MR spectroscopy for identification of prostate cancer in vivo, (b) histomorphometric features (quantitative features extracted from histopathology) with protein mass spectrometry features for predicting 5 year biochemical recurrence in prostate cancer patients, and (c) volumetric measurements on T1w MRI with protein expression features to discriminate between patients with and without Alzheimers' Disease.

RESULTS AND CONCLUSIONS

Our preliminary results in these specific use cases indicated that the use of kernel representations in conjunction with DR-based fusion may be most effective, as a weighted multi-kernel-based DR approach resulted in the highest area under the ROC curve of over 0.8. By contrast non-optimized DR-based representation and fusion methods yielded the worst predictive performance across all 3 applications. Our results suggest that when the individual modalities demonstrate relatively poor discriminability, many of the data fusion methods may not yield accurate, discriminatory representations either. In summary, to outperform the predictive ability of individual modalities, methodological choices for data fusion must explicitly account for the sparsity of and noise in the feature space.

Accurate grading of brain gliomas by soft independent modeling of class analogy based on non-negative matrix factorization of proton magnetic resonance spectra

Hydrogen magnetic resonance spectroscopy ((1) H-MRS) is a non-invasive technique which provides a 'frequency-signal intensity' spectrum of biochemical compounds of tissues in the body. Although this method is currently used in human brain studies, accurate classification of in-vivo (1) H-MRS is a challenging task in the diagnosis of brain tumors. Problems such as overlapping metabolite peaks, incomplete information on background component and low signal-to-noise ratio disturb classification results of this spectroscopic method. This study presents an alternative approach to the soft independent modeling of class analogy (SIMCA) technique, using non-negative matrix factorization (NMF) for dimensionality reduction. In the adopted strategy, the performance of SIMCA was improved by application of a robust algorithm for classification in the presence of noisy measurements. Total of 219 spectra from two databases were taken by water-suppressed short echo-time (1) H-MRS, acquired from different subjects with different stages of glial brain tumors (Grade II (26 cases), grade III (24 cases), grade IV (41 cases), as well as 25 healthy cases). The SIMCA was performed using two approaches: (i) principal component analysis (PCA) and (ii) non-negative matrix factorization (NMF), as a modified approach. Square prediction error was considered to assess the class membership of the external validation set. Finally, several figures of merit such as the correct classification rate (CCR), sensitivity and specificity were calculated. Results of SIMCA based on NMF showed significant improvement in percentage of correctly classified samples, 91.4% versus 83.5% for PCA-based model in an independent test set.

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.

Multidimensional texture characterization: on analysis for brain tumor tissues using MRS and MRI

This paper investigates the efficacy of automated pattern recognition methods on magnetic resonance data with the objective of assisting radiologists in the clinical diagnosis of brain tissue tumors. In this paper, the sciences of magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) are combined to improve the accuracy of the classifier, based on the multidimensional co-occurrence matrices to assess the detection of pathological tissues (tumor and edema), normal tissues (white matter - WM and gray matter - GM), and fluid (cerebrospinal fluid - CSF). The results show the ability of the classifier with iterative training to automatically and simultaneously recover tissue-specific spectral and structural patterns and achieve segmentation of tumor and edema and grading of high and low glioma tumor. Here, extreme learning machine - improved particle swarm optimization (ELM-IPSO) neural network classifier is trained with the feature descriptions in brain magnetic resonance (MR) spectra. This has the characteristics of varying the normal spectral pattern associated with tumor patterns along with imaging features. Validation was performed considering 35 clinical studies. The volumetric features extracted from the vectors of this matrix articulate some important elementary structures, which along with spectroscopic metabolite ratios discriminate the tumor grades and tissue classes. The quantitative 3D analysis reveals significant improvement in terms of global accuracy rate for automatic classification in brain tissues and discriminating pathological tumor tissue from structural healthy brain tissue.

Manifold Learning in MR spectroscopy using nonlinear dimensionality reduction and unsupervised clustering

PURPOSE

To investigate whether nonlinear dimensionality reduction improves unsupervised classification of (1) H MRS brain tumor data compared with a linear method.

METHODS

In vivo single-voxel (1) H magnetic resonance spectroscopy (55 patients) and (1) H magnetic resonance spectroscopy imaging (MRSI) (29 patients) data were acquired from histopathologically diagnosed gliomas. Data reduction using Laplacian eigenmaps (LE) or independent component analysis (ICA) was followed by k-means clustering or agglomerative hierarchical clustering (AHC) for unsupervised learning to assess tumor grade and for tissue type segmentation of MRSI data.

RESULTS

An accuracy of 93% in classification of glioma grade II and grade IV, with 100% accuracy in distinguishing tumor and normal spectra, was obtained by LE with unsupervised clustering, but not with the combination of k-means and ICA. With (1) H MRSI data, LE provided a more linear distribution of data for cluster analysis and better cluster stability than ICA. LE combined with k-means or AHC provided 91% accuracy for classifying tumor grade and 100% accuracy for identifying normal tissue voxels. Color-coded visualization of normal brain, tumor core, and infiltration regions was achieved with LE combined with AHC.

CONCLUSION

The LE method is promising for unsupervised clustering to separate brain and tumor tissue with automated color-coding for visualization of (1) H MRSI data after cluster analysis.

Extracting MRS discriminant functional features of brain tumors

The current challenge in automatic brain tumor classification based on MRS is the improvement of the robustness of the classification models that explicitly account for the probable breach of the independent and identically distributed conditions in the MRS data points. To contribute to this purpose, a new algorithm for the extraction of discriminant MRS features of brain tumors based on a functional approach is presented. Functional data analysis based on region segmentation (RSFDA) is based on the functional data analysis formalism using nonuniformly distributed B splines according to spectral regions that are highly correlated. An exhaustive characterization of the method is presented in this work using controlled and real scenarios. The performance of RSFDA was compared with other widely used feature extraction methods. In all simulated conditions, RSFDA was proven to be stable with respect to the number of variables selected and with respect to the classification performance against noise and baseline artifacts. Furthermore, with real multicenter datasets classification, RSFDA and peak integration (PI) obtained better performance than the other feature extraction methods used for comparison. Other advantages of the method proposed are its usefulness in selecting the optimal number of features for classification and its simplified functional representation of the spectra, which contributes to highlight the discriminative regions of the MR spectrum for each classification task.

Accurate classification of childhood brain tumours by in vivo ¹H MRS - a multi-centre study

AIMS

To evaluate the accuracy of single-voxel Magnetic Resonance Spectroscopy ((1)H MRS) as a non-invasive diagnostic aid for paediatric brain tumours in a multi-national study. Our hypotheses are (1) that automated classification based on (1)H MRS provides an accurate non-invasive diagnosis in multi-centre datasets and (2) using a protocol which increases the metabolite information improves the diagnostic accuracy.

METHODS

Seventy-eight patients under 16 years old with histologically proven brain tumours from 10 international centres were investigated. Discrimination of 29 medulloblastomas, 11 ependymomas and 38 pilocytic astrocytomas (PILOAs) was evaluated. Single-voxel MRS was undertaken prior to diagnosis (1.5 T Point-Resolved Spectroscopy (PRESS), Proton Brain Exam (PROBE) or Stimulated Echo Acquisition Mode (STEAM), echo time (TE) 20-32 ms and 135-136 ms). MRS data were processed using two strategies, determination of metabolite concentrations using TARQUIN software and automatic feature extraction with Peak Integration (PI). Linear Discriminant Analysis (LDA) was applied to this data to produce diagnostic classifiers. An evaluation of the diagnostic accuracy was performed based on resampling to measure the Balanced Accuracy Rate (BAR).

RESULTS

The accuracy of the diagnostic classifiers for discriminating the three tumour types was found to be high (BAR 0.98) when a combination of TE was used. The combination of both TEs significantly improved the classification performance (p<0.01, Tukey's test) compared with the use of one TE alone. Other tumour types were classified accurately as glial or primitive neuroectodermal (BAR 1.00).

CONCLUSION

(1)H MRS has excellent accuracy for the non-invasive diagnosis of common childhood brain tumours particularly if the metabolite information is maximised and should become part of routine clinical assessment for these children.

Multimodal wavelet embedding representation for data combination (MaWERiC): integrating magnetic resonance imaging and spectroscopy for prostate cancer detection

Recently, both Magnetic Resonance (MR) Imaging (MRI) and Spectroscopy (MRS) have emerged as promising tools for detection of prostate cancer (CaP). However, due to the inherent dimensionality differences in MR imaging and spectral information, quantitative integration of T(2) weighted MRI (T(2)w MRI) and MRS for improved CaP detection has been a major challenge. In this paper, we present a novel computerized decision support system called multimodal wavelet embedding representation for data combination (MaWERiC) that employs, (i) wavelet theory to extract 171 Haar wavelet features from MRS and 54 Gabor features from T(2)w MRI, (ii) dimensionality reduction to individually project wavelet features from MRS and T(2)w MRI into a common reduced Eigen vector space, and (iii), a random forest classifier for automated prostate cancer detection on a per voxel basis from combined 1.5 T in vivo MRI and MRS. A total of 36 1.5 T endorectal in vivo T(2)w MRI and MRS patient studies were evaluated per voxel by MaWERiC using a three-fold cross validation approach over 25 iterations. Ground truth for evaluation of results was obtained by an expert radiologist annotations of prostate cancer on a per voxel basis who compared each MRI section with corresponding ex vivo wholemount histology sections with the disease extent mapped out on histology. Results suggest that MaWERiC based MRS T(2)w meta-classifier (mean AUC, μ = 0.89 ± 0.02) significantly outperformed (i) a T(2)w MRI (using wavelet texture features) classifier (μ = 0.55 ± 0.02), (ii) a MRS (using metabolite ratios) classifier (μ = 0.77 ± 0.03), (iii) a decision fusion classifier obtained by combining individual T(2)w MRI and MRS classifier outputs (μ = 0.85 ± 0.03), and (iv) a data combination method involving a combination of metabolic MRS and MR signal intensity features (μ = 0.66 ± 0.02).

A hybrid method of application of independent component analysis to in vivo 1H MR spectra of childhood brain tumours

Independent component analysis (ICA) can automatically extract individual metabolite, macromolecular and lipid (MMLip) components from a series of in vivo MR spectra. The traditional feature extraction (FE)-based ICA approach is limited, in that a large sample size is required and a combination of metabolite and MMLip components can appear in the same independent component. The alternative ICA approach, based on blind source separation (BSS), is weak when dealing with overlapping peaks. Combining the advantages of both BSS and FE methods may lead to better results. Thus, we propose an ICA approach involving a hybrid of the BSS and FE techniques for the automated decomposition of a series of MR spectra. Experiments were performed on synthesised and patient in vivo childhood brain tumour MR spectra datasets. The hybrid ICA method showed an improvement in the decomposition ability compared with BSS-ICA or FE-ICA, with an increased correlation between the independent components and simulated metabolite and MMLip signals. Furthermore, we were able to automatically extract metabolites from the patient MR spectra dataset that were not in commonly used basis sets (e.g. guanidinoacetate).

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.

Manual and semi-automatic quantification of in vivo ¹H-MRS data for the classification of human primary brain tumors

In vivo proton magnetic resonance spectroscopy (¹H-MRS) is a technique capable of assessing biochemical content and pathways in normal and pathological tissue. In the brain, ¹H-MRS complements the information given by magnetic resonance images. The main goal of the present study was to assess the accuracy of ¹H-MRS for the classification of brain tumors in a pilot study comparing results obtained by manual and semi-automatic quantification of metabolites. In vivo single-voxel ¹H-MRS was performed in 24 control subjects and 26 patients with brain neoplasms that included meningiomas, high-grade neuroglial tumors and pilocytic astrocytomas. Seven metabolite groups (lactate, lipids, N-acetyl-aspartate, glutamate and glutamine group, total creatine, total choline, myo-inositol) were evaluated in all spectra by two methods: a manual one consisting of integration of manually defined peak areas, and the advanced method for accurate, robust and efficient spectral fitting (AMARES), a semi-automatic quantification method implemented in the jMRUI software. Statistical methods included discriminant analysis and the leave-one-out cross-validation method. Both manual and semi-automatic analyses detected differences in metabolite content between tumor groups and controls (P < 0.005). The classification accuracy obtained with the manual method was 75% for high-grade neuroglial tumors, 55% for meningiomas and 56% for pilocytic astrocytomas, while for the semi-automatic method it was 78, 70, and 98%, respectively. Both methods classified all control subjects correctly. The study demonstrated that ¹H-MRS accurately differentiated normal from tumoral brain tissue and confirmed the superiority of the semi-automatic quantification method.

Computer-aided prognosis: predicting patient and disease outcome via quantitative fusion of multi-scale, multi-modal data

Computer-aided prognosis (CAP) is a new and exciting complement to the field of computer-aided diagnosis (CAD) and involves developing and applying computerized image analysis and multi-modal data fusion algorithms to digitized patient data (e.g. imaging, tissue, genomic) for helping physicians predict disease outcome and patient survival. While a number of data channels, ranging from the macro (e.g. MRI) to the nano-scales (proteins, genes) are now being routinely acquired for disease characterization, one of the challenges in predicting patient outcome and treatment response has been in our inability to quantitatively fuse these disparate, heterogeneous data sources. At the Laboratory for Computational Imaging and Bioinformatics (LCIB)(1) at Rutgers University, our team has been developing computerized algorithms for high dimensional data and image analysis for predicting disease outcome from multiple modalities including MRI, digital pathology, and protein expression. Additionally, we have been developing novel data fusion algorithms based on non-linear dimensionality reduction methods (such as Graph Embedding) to quantitatively integrate information from multiple data sources and modalities with the overarching goal of optimizing meta-classifiers for making prognostic predictions. In this paper, we briefly describe 4 representative and ongoing CAP projects at LCIB. These projects include (1) an Image-based Risk Score (IbRiS) algorithm for predicting outcome of Estrogen receptor positive breast cancer patients based on quantitative image analysis of digitized breast cancer biopsy specimens alone, (2) segmenting and determining extent of lymphocytic infiltration (identified as a possible prognostic marker for outcome in human epidermal growth factor amplified breast cancers) from digitized histopathology, (3) distinguishing patients with different Gleason grades of prostate cancer (grade being known to be correlated to outcome) from digitized needle biopsy specimens, and (4) integrating protein expression measurements obtained from mass spectrometry with quantitative image features derived from digitized histopathology for distinguishing between prostate cancer patients at low and high risk of disease recurrence following radical prostatectomy.

Visualization and recovery of the (bio)chemical interesting variables in data analysis with support vector machine classification

Support vector machines (SVMs) have become a popular technique in the chemometrics and bioinformatics field, and other fields, for the classification of complex data sets. Especially because SVMs are able to model nonlinear relationships, the usage of this technique has increased substantially. This modeling is obtained by mapping the data in a higher-dimensional feature space. The disadvantage of such a transformation is, however, that information about the contribution of the original variables in the classification is lost. In this paper we introduce an innovative method which can retrieve the information about the variables of complex data sets. We apply the proposed method to several benchmark data sets and a metabolomics data set to illustrate that we can determine the contribution of the original variables in SVM classifications. The corresponding visualization of the contribution of the variables can assist in a better understanding of the underlying chemical or biological process.

Combined use of neuroradiology and 1H-MR spectroscopy may provide an intervention limiting diagnosis of glioblastoma multiforme

PURPOSE

To evaluate the accuracy of (1)H-MR spectroscopy ((1)H-MRS) as an intervention limiting diagnostic tool for glioblastoma multiforme. GBM is the most common and aggressive primary brain tumor, with mean survival under a year. Oncological practice currently requires histopathological diagnosis before radiotherapy.

MATERIALS AND METHODS

Eighty-nine patients had clinical computed tomography (CT) and MR imaging and 1.5T SV SE (1)H-MRS with PRESS localization for neuroradiological diagnosis and tumor classification with spectroscopic and automated pattern recognition analysis (TE 30 ms, TR 2000 ms, spectral width 2500 Hz and 2048 data points, 128-256 signal averages were acquired, depending on voxel size (8 cm(3) to 4 cm(3)). Eighteen patients from a cohort of 89 underwent stereotactic biopsy.

RESULTS

The 18 stereotactic biopsies revealed 14 GBM, 2 grade II astrocytomas, 1 lymphoma, and 1 anaplastic astrocytoma. All 14 biopsied GBMs were diagnosed as GBM by a protocol combining an individual radiologist and an automated spectral pattern recognition program.

CONCLUSION

In patients undergoing stereotactic biopsy combined neuroradiological and spectroscopic evaluation diagnoses GBM with accuracy that could replace the need for biopsy. We do not advocate the replacement of biopsy in all patients; instead our data suggest a specific intervention limiting role for the use of (1)H-MRS in brain tumor diagnosis.

Applications of chemical shift imaging to marine sciences

The successful applications of magnetic resonance imaging (MRI) in medicine are mostly due to the non-invasive and non-destructive nature of MRI techniques. Longitudinal studies of humans and animals are easily accomplished, taking advantage of the fact that MRI does not use harmful radiation that would be needed for plain film radiographic, computerized tomography (CT) or positron emission (PET) scans. Routine anatomic and functional studies using the strong signal from the most abundant magnetic nucleus, the proton, can also provide metabolic information when combined with in vivo magnetic resonance spectroscopy (MRS). MRS can be performed using either protons or hetero-nuclei (meaning any magnetic nuclei other than protons or ¹H) including carbon (¹³C) or phosphorus (³¹P). In vivo MR spectra can be obtained from single region of interest (ROI or voxel) or multiple ROIs simultaneously using the technique typically called chemical shift imaging (CSI). Here we report applications of CSI to marine samples and describe a technique to study in vivo glycine metabolism in oysters using ¹³C MRS 12 h after immersion in a sea water chamber dosed with [2-¹³C]-glycine. This is the first report of ¹³C CSI in a marine organism.

A hierarchical spectral clustering and nonlinear dimensionality reduction scheme for detection of prostate cancer from magnetic resonance spectroscopy (MRS)

Magnetic resonance spectroscopy (MRS) has been shown to have great clinical potential as a supplement to magnetic resonance imaging in the detection of prostate cancer (CaP). MRS provides functional information in the form of changes in the relative concentration of specific metabolites including choline, creatine, and citrate which can be used to identify potential areas of CaP. With a view to assisting radiologists in interpretation and analysis of MRS data, some researchers have begun to develop computer-aided detection (CAD) schemes for CaP identification from spectroscopy. Most of these schemes have been centered on identifying and integrating the area under metabolite peaks which is then used to compute relative metabolite ratios. However, manual identification of metabolite peaks on the MR spectra, and especially via CAD, is a challenging problem due to low signal-to-noise ratio, baseline irregularity, peak overlap, and peak distortion. In this article the authors present a novel CAD scheme that integrates nonlinear dimensionality reduction (NLDR) with an unsupervised hierarchical clustering algorithm to automatically identify suspicious regions on the prostate using MRS and hence avoids the need to explicitly identify metabolite peaks. The methodology comprises two stages. In stage 1, a hierarchical spectral clustering algorithm is used to distinguish between extracapsular and prostatic spectra in order to localize the region of interest (ROI) corresponding to the prostate. Once the prostate ROI is localized, in stage 2, a NLDR scheme, in conjunction with a replicated clustering algorithm, is used to automatically discriminate between three classes of spectra (normal appearing, suspicious appearing, and indeterminate). The methodology was quantitatively and qualitatively evaluated on a total of 18 1.5 T in vivo prostate T2-weighted (w) and MRS studies obtained from the multisite, multi-institutional American College of Radiology (ACRIN) trial. In the absence of the precise ground truth for CaP extent on the MR imaging for most of the ACRIN studies, probabilistic quantitative metrics were defined based on partial knowledge on the quadrant location and size of the tumor. The scheme, when evaluated against this partial ground truth, was found to have a CaP detection sensitivity of 89.33% and specificity of 79.79%. The results obtained from randomized threefold and fivefold cross validation suggest that the NLDR based clustering scheme has a higher CaP detection accuracy compared to such commonly used MRS analysis schemes as z score and PCA. In addition, the scheme was found to be robust to changes in system parameters. For 6 of the 18 studies an expert radiologist laboriously labeled each of the individual spectra according to a five point scale, with 1/2 representing spectra that the expert considered normal and 3/4/5 being spectra the expert deemed suspicious. When evaluated on these expert annotated datasets, the CAD system yielded an average sensitivity (cluster corresponding to suspicious spectra being identified as the CaP class) and specificity of 81.39% and 64.71%, respectively.

Nosologic imaging of the brain: segmentation and classification using MRI and MRSI

A new technique is presented to create nosologic images of the brain based on magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging (MRSI). A nosologic image summarizes the presence of different tissues and lesions in a single image by color coding each voxel or pixel according to the histopathological class it is assigned to. The proposed technique applies advanced methods from image processing as well as pattern recognition to segment and classify brain tumors. First, a registered brain atlas and a subject-specific abnormal tissue prior, obtained from MRSI data, are used for the segmentation. Next, the detected abnormal tissue is classified based on supervised pattern recognition methods. Class probabilities are also calculated for the segmented abnormal region. Compared to previous approaches, the new framework is more flexible and able to better exploit spatial information leading to improved nosologic images. The combined scheme offers a new way to produce high-resolution nosologic images, representing tumor heterogeneity and class probabilities, which may help clinicians in decision making.

Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy

JUSTIFICATION

Automatic brain tumor classification by MRS has been under development for more than a decade. Nonetheless, to our knowledge, there are no published evaluations of predictive models with unseen cases that are subsequently acquired in different centers. The multicenter eTUMOUR project (2004-2009), which builds upon previous expertise from the INTERPRET project (2000-2002) has allowed such an evaluation to take place.

MATERIALS AND METHODS

A total of 253 pairwise classifiers for glioblastoma, meningioma, metastasis, and low-grade glial diagnosis were inferred based on 211 SV short TE INTERPRET MR spectra obtained at 1.5 T (PRESS or STEAM, 20-32 ms) and automatically pre-processed. Afterwards, the classifiers were tested with 97 spectra, which were subsequently compiled during eTUMOUR.

RESULTS

In our results based on subsequently acquired spectra, accuracies of around 90% were achieved for most of the pairwise discrimination problems. The exception was for the glioblastoma versus metastasis discrimination, which was below 78%. A more clear definition of metastases may be obtained by other approaches, such as MRSI + MRI.

CONCLUSIONS

The prediction of the tumor type of in-vivo MRS is possible using classifiers developed from previously acquired data, in different hospitals with different instrumentation under the same acquisition protocols. This methodology may find application for assisting in the diagnosis of new brain tumor cases and for the quality control of multicenter MRS databases.

The effect of combining two echo times in automatic brain tumor classification by MRS

(1)H MRS is becoming an accurate, non-invasive technique for initial examination of brain masses. We investigated if the combination of single-voxel (1)H MRS at 1.5 T at two different (TEs), short TE (PRESS or STEAM, 20-32 ms) and long TE (PRESS, 135-136 ms), improves the classification of brain tumors over using only one echo TE. A clinically validated dataset of 50 low-grade meningiomas, 105 aggressive tumors (glioblastoma and metastasis), and 30 low-grade glial tumors (astrocytomas grade II, oligodendrogliomas and oligoastrocytomas) was used to fit predictive models based on the combination of features from short-TEs and long-TE spectra. A new approach that combines the two consecutively was used to produce a single data vector from which relevant features of the two TE spectra could be extracted by means of three algorithms: stepwise, reliefF, and principal components analysis. Least squares support vector machines and linear discriminant analysis were applied to fit the pairwise and multiclass classifiers, respectively. Significant differences in performance were found when short-TE, long-TE or both spectra combined were used as input. In our dataset, to discriminate meningiomas, the combination of the two TE acquisitions produced optimal performance. To discriminate aggressive tumors from low-grade glial tumours, the use of short-TE acquisition alone was preferable. The classifier development strategy used here lends itself to automated learning and test performance processes, which may be of use for future web-based multicentric classifier development studies.

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.

Quantification and classification of high-resolution magic angle spinning data for brain tumor diagnosis

The goal of this work is to propose a complete protocol (preprocessing, processing and classification) for classifying brain tumors with proton high-resolution magic-angle spinning ((1)H HR-MAS) data. The different steps of the procedure are detailed and discussed. Feature extraction techniques such as peak integration, including also the automated quantitation method AQSES, were combined with linear (LDA) and non-linear (least-squares support vector machine or LS-SVM) classifiers. Classification accuracy was assessed using a stratified random sampling scheme. The results suggest that LS-SVM performs better than LDA while AQSES performs better than the standard peak integration feature extraction method.

PDA-based system with teleradiology and image analysis capabilities

The aim of the present study was to design and implement a Personal Digital Assistant (PDA)-based teleradiology system incorporating image processing and analysis facilities for use in emergency situations within a hospital environment. The system comprised a DICOM-server, connected to an MRI unit, 3 wireless access points, and 3 PDAs (HP iPaq rx3715). PDA application software was developed in MS Embedded Visual C++ 4.0. Each PDA can receive, load, process and analyze hi-quality static MR images. Image processing includes gray-scale manipulation and spatial filtering techniques while image analysis incorporates a probabilistic neural network (PNN) classifier, which was optimally designed employing a suitable combination of textural features and was evaluated using the leave-one-out method. The PNN is capable of discriminating between three major types of human brain tumors with accuracy of 86.66%. The developed application may be useful as a mobile medical teleconsultation tool.

A hierarchical unsupervised spectral clustering scheme for detection of prostate cancer from magnetic resonance spectroscopy (MRS)

Magnetic Resonance Spectroscopy (MRS) along with MRI has emerged as a promising tool in diagnosis and potentially screening for prostate cancer. Surprisingly little work, however, has been done in the area of automated quantitative analysis of MRS data for identifying likely cancerous areas in the prostate. In this paper we present a novel approach that integrates a manifold learning scheme (spectral clustering) with an unsupervised hierarchical clustering algorithm to identify spectra corresponding to cancer on prostate MRS. Ground truth location for cancer on prostate was determined from the sextant location and maximum size of cancer available from the ACRIN database, from where a total of 14 MRS studies were obtained. The high dimensional information in the MR spectra is non linearly transformed to a low dimensional embedding space and via repeated clustering of the voxels in this space, non informative spectra are eliminated and only informative spectra retained. Our scheme successfully identified MRS cancer voxels with sensitivity of 77.8%, false positive rate of 28.92%, and false negative rate of 20.88% on a total of 14 prostate MRS studies. Qualitative results seem to suggest that our method has higher specificity compared to a popular scheme, z-score, routinely used for analysis of MRS data.

Linear discriminant analysis of brain tumour (1)H MR spectra: a comparison of classification using whole spectra versus metabolite quantification

(1)H MRS is an attractive choice for non-invasively diagnosing brain tumours. Many studies have been performed to create an objective decision support system, but there is not yet a consensus as to the best techniques of MRS acquisition or data processing to be used for optimum classification. In this study, we investigate whether LCModel analysis of short-TE (30 ms), single-voxel tumour spectra provide a better input for classification than the use of the original spectra. A total of 145 histologically diagnosed brain tumour spectra were acquired [14 astrocytoma grade II (AS2), 15 astrocytoma grade III (AS3), 42 glioblastoma (GBM), 41 metastases (MET) and 33 meningioma (MNG)], and linear discriminant analyses (LDA) were performed on the LCModel analysis of the spectra and the original spectra. The results consistently suggest improvement in classification when the LCModel concentrations are used. LDA of AS2, MNG and high-grade tumours (HG, comprising GBM and MET) correctly classified 94% using the LCModel dataset compared with 93% using the spectral dataset. The inclusion of AS3 reduced the accuracy to 82% and 78% for LCModel analysis and the original spectra, respectively, and further separating HG into GBM and MET gave 70% compared with 60%. Generally MNG spectra have profiles that are visually distinct from those of the other tumour types, but the classification accuracy was typically about 80%, with MNG with substantial lipid/macromolecule signals being classified as HG. Omission of the lipid/macromolecule concentrations in the LCModel dataset provided an improvement in classification of MNG (91% compared with 76%). In conclusion, there appears to be an advantage to performing pattern recognition on the quantitative analysis of tumour spectra rather than using the whole spectra. However, the results suggest that a two-step LDA process may help in classifying the five tumour groups to provide optimum classification of MNG with high lipid/macromolecule contributions which maybe misclassified as HG.

Generating prior probabilities for classifiers of brain tumours using belief networks

Background

Numerous methods for classifying brain tumours based on magnetic resonance spectra and imaging have been presented in the last 15 years. Generally, these methods use supervised machine learning to develop a classifier from a database of cases for which the diagnosis is already known. However, little has been published on developing classifiers based on mixed modalities, e.g. combining imaging information with spectroscopy. In this work a method of generating probabilities of tumour class from anatomical location is presented.

Methods

The method of "belief networks" is introduced as a means of generating probabilities that a tumour is any given type. The belief networks are constructed using a database of paediatric tumour cases consisting of data collected over five decades; the problems associated with using this data are discussed. To verify the usefulness of the networks, an application of the method is presented in which prior probabilities were generated and combined with a classification of tumours based solely on MRS data.

Results

Belief networks were constructed from a database of over 1300 cases. These can be used to generate a probability that a tumour is any given type. Networks are presented for astrocytoma grades I and II, astrocytoma grades III and IV, ependymoma, pineoblastoma, primitive neuroectodermal tumour (PNET), germinoma, medulloblastoma, craniopharyngioma and a group representing rare tumours, "other". Using the network to generate prior probabilities for classification improves the accuracy when compared with generating prior probabilities based on class prevalence.

Conclusion

Bayesian belief networks are a simple way of using discrete clinical information to generate probabilities usable in classification. The belief network method can be robust to incomplete datasets. Inclusion of a priori knowledge is an effective way of improving classification of brain tumours by non-invasive methods.

Visualisation and interpretation of Support Vector Regression models

This paper introduces a technique to visualise the information content of the kernel matrix and a way to interpret the ingredients of the Support Vector Regression (SVR) model. Recently, the use of Support Vector Machines (SVM) for solving classification (SVC) and regression (SVR) problems has increased substantially in the field of chemistry and chemometrics. This is mainly due to its high generalisation performance and its ability to model non-linear relationships in a unique and global manner. Modeling of non-linear relationships will be enabled by applying a kernel function. The kernel function transforms the input data, usually non-linearly related to the associated output property, into a high dimensional feature space where the non-linear relationship can be represented in a linear form. Usually, SVMs are applied as a black box technique. Hence, the model cannot be interpreted like, e.g., Partial Least Squares (PLS). For example, the PLS scores and loadings make it possible to visualise and understand the driving force behind the optimal PLS machinery. In this study, we have investigated the possibilities to visualise and interpret the SVM model. Here, we exclusively have focused on Support Vector Regression to demonstrate these visualisation and interpretation techniques. Our observations show that we are now able to turn a SVR black box model into a transparent and interpretable regression modeling technique.

Automated estimation of tumor probability in prostate magnetic resonance spectroscopic imaging: pattern recognition vs quantification

Despite its diagnostic value and technological availability, (1)H NMR spectroscopic imaging (MRSI) has not found its way into clinical routine yet. Prerequisite for the clinical application is an automated and reliable method for the diagnostic evaluation of MRS images. In the present paper, different approaches to the estimation of tumor probability from MRSI in the prostate are assessed. Two approaches to feature extraction are compared: quantification (VARPRO, AMARES, QUEST) and subspace methods on spectral patterns (principal components, independent components, nonnegative matrix factorization, partial least squares). Linear as well as nonlinear classifiers (support vector machines, Gaussian processes, random forests) are applied and discussed. Quantification-based approaches are much more sensitive to the choice and parameterization of the quantification algorithm than to the choice of the classifier. Furthermore, linear methods based on magnitude spectra easily achieve equal performance and also allow for biochemical interpretation in combination with subspace methods. Nonlinear methods operating directly on magnitude spectra achieve the best results but are less transparent than the linear methods.

Fast nosologic imaging of the brain

Magnetic resonance spectroscopic imaging (MRSI) provides information about the spatial metabolic heterogeneity of an organ in the human body. In this way, MRSI can be used to detect tissue regions with abnormal metabolism, e.g. tumor tissue. The main drawback of MRSI in clinical practice is that the analysis of the data requires a lot of expertise from the radiologists. In this article, we present an automatic method that assigns each voxel of a spectroscopic image of the brain to a histopathological class. The method is based on Canonical Correlation Analysis (CCA), which has recently been shown to be a robust technique for tissue typing. In CCA, the spectral as well as the spatial information about the voxel is used to assign it to a class. This has advantages over other methods that only use spectral information since histopathological classes are normally covering neighbouring voxels. In this paper, a new CCA-based method is introduced in which MRSI and MR imaging information is integrated. The performance of tissue typing is compared for CCA applied to the whole MR spectra and to sets of features obtained from the spectra. Tests on simulated and in vivo MRSI data show that the new method is very accurate in terms of classification and segmentation. The results also show the advantage of combining spectroscopic and imaging data.

Optimal classification of long echo time in vivo magnetic resonance spectra in the detection of recurrent brain tumors

We describe the optimal high-level postprocessing of single-voxel (1)H magnetic resonance spectra and assess the benefits and limitations of automated methods as diagnostic aids in the detection of recurrent brain tumor. In a previous clinical study, 90 long-echo-time single-voxel spectra were obtained from 52 patients and classified during follow-up (30/28/32 normal/non-progressive tumor/tumor). Based on these data, a large number of evaluation strategies, including both standard resonance line quantification and algorithms from pattern recognition and machine learning, were compared in a quantitative evaluation. Results from linear and non-linear feature extraction, including ICA, PCA and wavelet transformations, and also the data from resonance line quantification were combined systematically with different classifiers such as LDA, chemometric methods (PLS, PCR), support vector machines and ensemble methods. Classification accuracy was assessed using a leave-one-out cross-validation scheme and the area under the curve (AUC) of the receiver operator characteristic (ROC). A regularized linear regression on spectra with binned channels reached 91% classification accuracy compared with 83% from quantification. Interpreting the loadings of these regressions, we find that lipid and lactate signals are too unreliable to be used in a simple machine rule. Choline and NAA are the main source of relevant information. Overall, we find that fully automated pattern recognition algorithms perform as well as, or slightly better than, a manually controlled and optimized resonance line quantification.

Contrast/Noise ratio on conventional MRI and choline/creatine ratio on proton MRI spectroscopy accurately discriminate low-grade from high-grade cerebral gliomas

RATIONALE AND OBJECTIVES

Histopathology is the gold standard to establish the grade of brain tumors but biopsy and/or surgery are not always possible. The aim of this study is to determine whether histological grade of tumors may be predicted by means of conventional gadolinium-enhanced MRI and proton magnetic resonance spectroscopy (MRS).

MATERIALS AND METHODS

In this study, we included 35 consecutive patients with single brain tumors and final histopathological verification: 12 had low-grade glioma, 16 had high-grade glioma, and 7 had single metastasis. Initially, we carried out T1 and T2 MRI paying attention to the following features: border definition, mass effect, heterogeneity of signal, perilesional edeme, hemorrhage, necrosis, and corpus callosum invasion. Gadolinium-enhancement was evaluated with the contrast-to-noise ratio (CNR). Next, single-voxel proton MRS was carried out to measure the absolute values of metabolites (N-acetyl-aspartate, creatine, choline, and myo-inositol) and their ratios in the area of maximum contrast enhancement.

RESULTS

We found that gadolinium-enhancement measured with the CNR (CNR > 35.86) predicted malignancy at 82.6% sensitivity and 91.7% specificity (area under the curve, 0.88; 95% confidence interval [CI], 0.73-0.97). With regard to MRS a choline/creatine ratio higher than 1.56 predicted malignancy at 88.9% sensitivity and 91.7% specificity (area under the curve, 0.94; 95% CI, 0.78-0.99). When we combined the CNR value, the choline/creatine ratio, and the presence of lactates in a model of discriminant analysis the predictive power improved significantly with an area under the curve of 0.99% (95% CI, 0.87-1). However, the used techniques were unable to distinguish metastases from high-grade gliomas accurately.

CONCLUSIONS

The intensity of contrast enhancement measured with the CNR, the choline/creatine ratio, and the presence of lactate were the most powerful variables to predict malignancy in brain tumors. The CNR is a simple, objective, and useful tool in the initial assessment of gliomas and metastases.

Advanced neuroimaging of pediatric brain tumors: MR diffusion, MR perfusion, and MR spectroscopy

This article highlights the MR imaging techniques of MR perfusion, MR diffusion, and MR spectroscopy in the evaluation of the child with a pediatric brain tumor. These techniques are complementary to conventional MR imaging in providing tumor physiologic information useful for diagnosis and therapy.

Noninvasive diagnostic assessment of brain tumors using combined in vivo MR imaging and spectroscopy

To determine the potential value of multimodal MRI for the presurgical management of patients with brain tumors, we performed combined magnetic resonance imaging (MRI) and proton MR spectroscopy (MRS) in 164 patients who presented with tumors of various histological subtypes confirmed by surgical biopsy. Univariate statistical analysis of metabolic ratios carried out on the first 121 patients demonstrated significant differences in between-group comparisons, but failed to provide sufficiently robust classification of individual cases. However, a multivariate statistical approach correctly classified the tumors using linear discriminant analysis (LDA) of combined MRI and MRS data. After initial separation of contrast-enhancing and non-contrast-enhancing lesions, 91% of the former and 87% of the latter were correctly classified. The results were stable when this diagnostic strategy was tested on the additional 43 patients included for validation after the initial statistical analysis, with over 90% of correct classification. Combined MRI and MRS had superior diagnostic value compared to MRS alone, especially in the contrast-enhancing group. This study shows the clinical value of a multivariate statistical analysis based on multimodal MRI and MRS for the noninvasive evaluation of intracranial tumors.

Brain tumor evaluation and segmentation by in vivo proton spectroscopy and relaxometry

A new methodology has been developed for the evaluation and segmentation of brain tumors using information obtained by different magnetic resonance techniques such as in vivo proton magnetic resonance spectroscopy (1HMRS) and relaxometry. In vivo 1HMRS may be used as a preoperative technique that allows noninvasive monitoring of metabolites to identify the different tissue types present in the lesion (active tumor, necrotic tissue, edema, and normal or non-affected tissue). Spatial resolution for treatment consideration may be improved by using 1HMRS combined or fused with images obtained by relaxometry which exhibit excellent spatial resolution. Some segmentation schemes are presented and discussed. The results show that segmentation performed in this way efficiently determines the spatial localization of the tumor both qualitatively and quantitatively. It provides appropriate information for therapy planning and application of therapies such as radiosurgery or radiotherapy and future control of patient evolution.