Classification of brain tumours using short echo time 1H MR spectra

Prediction of individual weight loss using supervised learning: findings from the CALERIETM 2 study

BACKGROUND

Predicting individual weight loss (WL) responses to lifestyle interventions is challenging but might help practitioners and clinicians select the most promising approach for each individual.

OBJECTIVE

The primary aim of this study was to develop machine learning (ML) models to predict individual WL responses using only variables known before starting the intervention. In addition, we used ML to identify pre-intervention variables influencing the individual WL response.

METHODS

We used 12-mo data from the comprehensive assessment of long-term effects of reducing intake of energy (CALERIETM) phase 2 study, which aimed to analyze the long-term effects of caloric restriction on human longevity. On the basis of the data from 130 subjects in the intervention group, we developed classification models to predict binary ("Success" and "No/low success") or multiclass ("High success," "Medium success," and "Low/no success") WL outcomes. Additionally, regression models were developed to predict individual weight change (percent). Models were evaluated on the basis of accuracy, sensitivity, specificity (classification models), and root mean squared error (RMSE; regression models).

RESULTS

Best classification models used 20-40 predictors and achieved 89%-97% accuracy, 91%-100% sensitivity, and 56%-86% specificity for binary classification. For multiclass classification, accuracy (69%) and sensitivity (50%) tended to be lower. The best regression performance was obtained with 36 variables with an RMSE of 2.84%. Among the 21 variables predicting individual weight change most consistently, we identified 2 novel predictors, namely orgasm satisfaction and sexual behavior/experience. Other common predictors have previously been associated with WL (16) or are already used in traditional prediction models (3).

CONCLUSIONS

The prediction models could be implemented by practitioners and clinicians to support the decision of whether lifestyle interventions are sufficient or more aggressive interventions are needed for a given individual, thereby supporting better, faster, data-driven, and unbiased decisions. The CALERIETM phase 2 study was registered at clinicaltrials.gov as NCT00427193.

Advances in Neuro-Oncological Imaging: An Update on Diagnostic Approach to Brain Tumors

This study delineates the pivotal role of imaging within the field of neurology, emphasizing its significance in the diagnosis, prognostication, and evaluation of treatment responses for central nervous system (CNS) tumors. A comprehensive understanding of both the capabilities and limitations inherent in emerging imaging technologies is imperative for delivering a heightened level of personalized care to individuals with neuro-oncological conditions. Ongoing research in neuro-oncological imaging endeavors to rectify some limitations of radiological modalities, aiming to augment accuracy and efficacy in the management of brain tumors. This review is dedicated to the comparison and critical examination of the latest advancements in diverse imaging modalities employed in neuro-oncology. The objective is to investigate their respective impacts on diagnosis, cancer staging, prognosis, and post-treatment monitoring. By providing a comprehensive analysis of these modalities, this review aims to contribute to the collective knowledge in the field, fostering an informed approach to neuro-oncological care. In conclusion, the outlook for neuro-oncological imaging appears promising, and sustained exploration in this domain is anticipated to yield further breakthroughs, ultimately enhancing outcomes for individuals grappling with CNS tumors.

A comparison of non-negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

Magnetic resonance spectroscopy (MRS) is an MR technique that provides information about the biochemistry of tissues in a noninvasive way. MRS has been widely used for the study of brain tumors, both preoperatively and during follow-up. In this study, we investigated the performance of a range of variants of unsupervised matrix factorization methods of the non-negative matrix underapproximation (NMU) family, namely, sparse NMU, global NMU, and recursive NMU, and compared them with convex non-negative matrix factorization (C-NMF), which has previously shown a good performance on brain tumor diagnostic support problems using MRS data. The purpose of the investigation was 2-fold: first, to ascertain the differences among the sources extracted by these methods; and second, to compare the influence of each method in the diagnostic accuracy of the classification of brain tumors, using them as feature extractors. We discovered that, first, NMU variants found meaningful sources in terms of biological interpretability, but representing parts of the spectrum, in contrast to C-NMF; and second, that NMU methods achieved better classification accuracy than C-NMF for the classification tasks when one class was not meningioma.

The role of 3-Tesla magnetic resonance perfusion and spectroscopy in distinguishing glioblastoma from solitary brain metastasis

OBJECTIVES

This study aimed to assess the value of magnetic resonance perfusion (MR perfusion) and magnetic resonance spectroscopy (MR spectroscopy) in 3.0-Tesla magnetic resonanceimaging (MRI) for differential diagnosis of glioblastoma (GBM) and solitary brain metastasis (SBM).

MATERIAL AND METHODS

This retrospective study involved 36 patients, including 24 cases of GBM and 12 of SBM diagnosed using histopathology. All patients underwent a 3.0-Tesla MRI examination with pre-operative MR perfusion and MR spectroscopy. We assessed the differences in age, sex, cerebral blood volume (CBV), relative CBV (rCBV), and the metabolite ratios of choline/N-acetylaspartate (Cho/NAA) and Cho/creatine between the GBM and SBM groups using the Mann-Whitney U-test and Chi-square test. The cutoff value, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value of the significantly different parameters between these two groups were determined using the receiver operating characteristic curve.

RESULTS

In MR perfusion, the CBV of the peritumoral region (pCBV) had the highest preoperative predictive value in discriminating GBM from SBM (cutoff: 1.41; sensitivity: 70.83%; and specificity: 83.33%), followed by the ratio of CBV of the solid tumor component to CBV of normal white matter (rCBVt/n) and the ratio of CBV of the pCBV to CBV of normal white matter (rCBVp/n). In MR spectroscopy, the Cho/NAA ratio of the pCBV (pCho/NAA; cutoff: 1.02; sensitivity: 87.50%; and specificity: 75%) and the Cho/NAA ratio of the solid tumor component (tCho/NAA; cutoff: 2.11; sensitivity: 87.50%; and specificity: 66.67%) were significantly different between groups. Moreover, combining these remarkably different parameters increased their diagnostic utility for distinguishing between GBM and SBM.

CONCLUSION

pCBV, rCBVt/n, rCBVp/n, pCho/NAA, and tCho/NAA are useful indices for differentiating between GBM and SBM. Combining these indices can improve diagnostic performance in distinguishing between these two tumors.

Automated multi-class brain tumor types detection by extracting RICA based features and employing machine learning techniques

Among the other cancer types, the brain tumor is one the leading cause of cancer across globe. If the tumor is properly identified at an earlier stage, then the chances of the survival can be increased. To categorize the brain tumor there are several factors including texture, type and location of brain tumor. We proposed a novel reconstruction independent component analysis (RICA) feature extraction method to detect multi-class brain tumor types (pituitary, meningioma, and glioma). We then employed the robust machine learning techniques as support vector machine (SVM) with quadratic and linear kernels and linear discriminant analysis (LDA). For training and testing of the data validation, a 10-fold cross validation was employed. For the multi-class classification, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy and AUC were, respectively, 97.78%, 100%, 100%, 99.07, 99.34% and 0.9892 to detect pituitary using SVM Cubic followed by meningioma with accuracy (96.96%0, AUC (0.9348) and glioma with accuracy (95.88%), AUC (0.9635). The findings indicates that RICA feature based proposed methodology has more potential to detect the multiclass brain tumor types for improving diagnostic efficiency and can further improve the prediction accuracy to achieve the clinical outcomes.

Supervised machine learning tools: a tutorial for clinicians

In an increasingly data-driven world, artificial intelligence is expected to be a key tool for converting big data into tangible benefits and the healthcare domain is no exception to this. Machine learning aims to identify complex patterns in multi-dimensional data and use these uncovered patterns to classify new unseen cases or make data-driven predictions. In recent years, deep neural networks have shown to be capable of producing results that considerably exceed those of conventional machine learning methods for various classification and regression tasks. In this paper, we provide an accessible tutorial of the most important supervised machine learning concepts and methods, including deep learning, which are potentially the most relevant for the medical domain. We aim to take some of the mystery out of machine learning and depict how machine learning models can be useful for medical applications. Finally, this tutorial provides a few practical suggestions for how to properly design a machine learning model for a generic medical problem.

Intraoperative 3-T Magnetic Resonance Spectroscopy for Detection of Proliferative Remnants of Glioma

BACKGROUND

Few studies have examined the usefulness of intraoperative magnetic resonance spectroscopy (iMRS) for identifying abnormal signals at the resection margin during glioma surgery. The aim of this study was to assess the value of iMRS for detecting proliferative remnants of glioma at the resection margin.

METHODS

Fifteen patients with newly diagnosed glioma underwent single-voxel 3-T iMRS concurrently with intraoperative magnetic resonance imaging-assisted surgery. Volumes of interest (VOIs) were placed at T2-hyperintense or contrast-enhancing lesions at the resection margin. In addition to technical verification, the correlation between the MIB-1 labeling index (a pathologic feature) and metabolites measured using iMRS (N-acetyl-L-aspartate [NAA], choline [Cho], and Cho/NAA ratio) was analyzed.

RESULTS

iMRS was performed for 20 VOIs in 15 patients. Fourteen (70%) of these VOIs were confirmed to be MIB-1-positive. There was a significant positive correlation between the Cho/NAA ratio and MIB-1 index (r = 0.46, P = 0.04). Cho level (P = 0.003) and Cho/NAA ratio (P = 0.002) were significantly higher in VOIs that were MIB-1-positive than in those that were MIB-1-negative. Detection of a Cho level >1.074 mM and a Cho/NAA ratio >0.48 using iMRS resulted in high diagnostic accuracy for MIB-1-positive remnants (Cho level: sensitivity 86%, specificity 100%; Cho/NAA ratio: sensitivity 79%, specificity 100%).

CONCLUSIONS

This study provides evidence that 3-T iMRS can detect proliferative remnants of glioma at the resection margin using the Cho level and Cho/NAA ratio, suggesting that intraoperative magnetic resonance imaging-assisted surgery with iMRS would be practicable in glioma.

The value of magnetic resonance spectroscopy as a supplement to MRI of the brain in a clinical setting

BACKGROUND

There are different opinions of the clinical value of MRS of the brain. In selected materials MRS has demonstrated good results for characterisation of both neoplastic and non-neoplastic lesions. The aim of this study was to evaluate the supplemental value of MR spectroscopy (MRS) in a clinical setting.

MATERIAL AND METHODS

MRI and MRS were re-evaluated in 208 cases with a clinically indicated MRS (cases with uncertain or insufficient information on MRI) and a confirmed diagnosis. Both single voxel spectroscopy (SVS) and chemical shift imaging (CSI) were performed in 105 cases, only SVS or CSI in 54 and 49 cases, respectively. Diagnoses were grouped into categories: non-neoplastic disease, low-grade tumour, and high-grade tumour. The clinical value of MRS was considered very beneficial if it provided the correct category or location when MRI did not, beneficial if it ruled out suspected diseases or was more specific than MRI, inconsequential if it provided the same level of information, or misleading if it provided less or incorrect information.

RESULTS

There were 70 non-neoplastic lesions, 43 low-grade tumours, and 95 high-grade tumours. For MRI, the category was correct in 130 cases (62%), indeterminate in 39 cases (19%), and incorrect in 39 cases (19%). Supplemented with MRS, 134 cases (64%) were correct, 23 cases (11%) indeterminate, and 51 (25%) incorrect. Additional information from MRS was beneficial or very beneficial in 31 cases (15%) and misleading in 36 cases (17%).

CONCLUSION

In most cases MRS did not add to the diagnostic value of MRI. In selected cases, MRS may be a valuable supplement to MRI.

Prospective multicentre evaluation and refinement of an analysis tool for magnetic resonance spectroscopy of childhood cerebellar tumours

BACKGROUND

A tool for diagnosing childhood cerebellar tumours using magnetic resonance (MR) spectroscopy peak height measurement has been developed based on retrospective analysis of single-centre data.

OBJECTIVE

To determine the diagnostic accuracy of the peak height measurement tool in a multicentre prospective study, and optimise it by adding new prospective data to the original dataset.

MATERIALS AND METHODS

Magnetic resonance imaging (MRI) and single-voxel MR spectroscopy were performed on children with cerebellar tumours at three centres. Spectra were processed using standard scanner software and peak heights for N-acetyl aspartate, creatine, total choline and myo-inositol were measured. The original diagnostic tool was used to classify 26 new tumours as pilocytic astrocytoma, medulloblastoma or ependymoma. These spectra were subsequently combined with the original dataset to develop an optimised scheme from 53 tumours in total.

RESULTS

Of the pilocytic astrocytomas, medulloblastomas and ependymomas, 65.4% were correctly assigned using the original tool. An optimized scheme was produced from the combined dataset correctly assigning 90.6%. Rare tumour types showed distinctive MR spectroscopy features.

CONCLUSION

The original diagnostic tool gave modest accuracy when tested prospectively on multicentre data. Increasing the dataset provided a diagnostic tool based on MR spectroscopy peak height measurement with high levels of accuracy for multicentre data.

Differentiating solid, non-macroscopic fat containing, enhancing renal masses using fast Fourier transform analysis of multiphase CT

OBJECTIVE

To test the feasibility of two-dimensional fast Fourier transforms (FFT)-based imaging metrics in differentiating solid, non-macroscopic fat containing, enhancing renal masses using contrast-enhanced CT images. We quantify image-based intratumoral textural variations (indicator of tumor heterogeneity) using frequency-based (FFT) imaging metrics.

METHODS

In this Institutional Review Board approved, Health Insurance Portability and Accountability Act -compliant, retrospective case-control study, we evaluated 156 patients with predominantly solid, non-macroscopic fat containing, enhancing renal masses identified between June 2009 and June 2016. 110 cases (70%) were malignant RCC, including clear cell, papillary and chromophobe subtypes and, 46 cases (30%) were benign renal masses: oncocytoma and lipid-poor angiomyolipoma. Whole lesions were manually segmented using Synapse 3D (Fujifilm, CT) and co-registered from the multiphase CT acquisitions for each tumor. Pathological diagnosis of all tumors was obtained following surgical resection. Matlab function, FFT2 was used to perform the image to frequency transformation.

RESULTS

A Wilcoxon rank sum test showed that FFT-based metrics were significantly (p < 0.005) different between 1. benign vs malignant renal masses, 2. oncocytoma vs clear cell renal cell carcinoma and 3. oncocytoma vs lipid-poor angiomyolipoma. Receiver operator characteristics analysis revealed reasonable discrimination (area under the curve >0.7, p < 0.05) within these three groups of comparisons.

CONCLUSION

In combination with other metrics, FFT-metrics may improve patient management and potentially help differentiate other renal tumors. Advances in knowledge: We report for the first time that FFT-based metrics can differentiate between some solid, non-macroscopic fat containing, enhancing renal masses using their contrast-enhanced CT data.

The role of cerebral blood flow gradient in peritumoral edema for differentiation of glioblastomas from solitary metastatic lesions

OBJECTIVE

Differentiation of glioblastomas from solitary brain metastases using conventional MRI remains an important unsolved problem. In this study, we introduced the conception of the cerebral blood flow (CBF) gradient in peritumoral edema-the difference in CBF values from the proximity of the enhancing tumor to the normal-appearing white matter, and investigated the contribution of perfusion metrics on the discrimination of glioblastoma from a metastatic lesion.

MATERIALS AND METHODS

Fifty-two consecutive patients with glioblastoma or a solitary metastatic lesion underwent three-dimensional arterial spin labeling (3D-ASL) before surgical resection. The CBF values were measured in the peritumoral edema (near: G1; Intermediate: G2; Far: G3). The CBF gradient was calculated as the subtractions CBFG1 -CBFG3, CBFG1 - CBFG2 and CBFG2 - CBFG3. A receiver operating characteristic (ROC) curve analysis was used to seek for the best cutoff value permitting discrimination between these two tumors.

RESULTS

The absolute/related CBF values and the CBF gradient in the peritumoral regions of glioblastomas were significantly higher than those in metastases(P < 0.038). ROC curve analysis reveals, a cutoff value of 1.92 ml/100g for the CBF gradient of CBFG1 -CBFG3 generated the best combination of sensitivity (92.86%) and specificity (100.00%) for distinguishing between a glioblastoma and metastasis.

CONCLUSION

The CBF gradient in peritumoral edema appears to be a more promising ASL perfusion metrics in differentiating high grade glioma from a solitary metastasis.

Brain metastases: neuroimaging

Magnetic resonance imaging (MRI) is the cornerstone for evaluating patients with brain masses such as primary and metastatic tumors. Important challenges in effectively detecting and diagnosing brain metastases and in accurately characterizing their subsequent response to treatment remain. These difficulties include discriminating metastases from potential mimics such as primary brain tumors and infection, detecting small metastases, and differentiating treatment response from tumor recurrence and progression. Optimal patient management could be benefited by improved and well-validated prognostic and predictive imaging markers, as well as early response markers to identify successful treatment prior to changes in tumor size. To address these fundamental needs, newer MRI techniques including diffusion and perfusion imaging, MR spectroscopy, and positron emission tomography (PET) tracers beyond traditionally used 18-fluorodeoxyglucose are the subject of extensive ongoing investigations, with several promising avenues of added value already identified. These newer techniques provide a wealth of physiologic and metabolic information that may supplement standard MR evaluation, by providing the ability to monitor and characterize cellularity, angiogenesis, perfusion, pH, hypoxia, metabolite concentrations, and other critical features of malignancy. This chapter reviews standard and advanced imaging of brain metastases provided by computed tomography, MRI, and amino acid PET, focusing on potential biomarkers that can serve as problem-solving tools in the clinical management of patients with brain metastases.

Multiparametric Imaging Analysis: Magnetic Resonance Spectroscopy

Magnetic resonance spectroscopy (MRS) is a magnetic resonance-based imaging modality that allows noninvasive sampling of metabolic changes in normal and abnormal brain parenchyma. MRS is particularly useful in the differentiation of developmental or non-neoplastic disorders from neoplastic processes. MRS is also useful during routine imaging follow-up after radiation treatment or during antiangiogenic treatment and for predicting outcomes and treatment response. The objective of this article is to provide a concise but thorough review of the basic physical principles, important applications of MRS in brain tumor imaging, and future directions.

Multiclass imbalance learning: Improving classification of pediatric brain tumors from magnetic resonance spectroscopy

Purpose

Classification of pediatric brain tumors from ¹H‐magnetic resonance spectroscopy (MRS) can aid diagnosis and management of brain tumors. However, varied incidence of the different tumor types leads to imbalanced class sizes and introduces difficulties in classifying rare tumor groups. This study assessed different imbalanced multiclass learning techniques and compared the use of complete spectra and quantified metabolite profiles for classification of three main childhood brain tumor types.

Methods

Single‐voxel, Short echo time MRS data were collected from 90 patients with pilocytic astrocytoma (n = 42), medulloblastoma (n = 38), or ependymoma (n = 10). Both spectra and metabolite profiles were used to develop the learning algorithms. The borderline synthetic minority oversampling technique and AdaboostM1 were used to correct for the skewed distribution. Classifiers were trained using five different pattern recognition algorithms.

Results

Use of imbalanced learning techniques improved the balanced accuracy rate (BAR) of all classification methods (average BAR over all classification methods for spectra: oversampled data = 0.81, original = 0.63, P < 0.001; metabolite concentration: oversampled‐data = 0.91, original = 0.75, P < 0.0001). Performance of all classifiers in discriminating ependymomas increased when oversampled data were used compared with original data for both complete spectra (F‐measure P < 0.01) and metabolite profile (F‐measure P < 0.001).

Conclusion

Imbalanced learning techniques improve the classification accuracy of childhood brain tumors from MRS where group sizes differ and facilitate the inclusion of rarer tumor types into clinical decision support systems. Magn Reson Med 77:2114–2124, 2017. © 2016 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Impact of Single or Repeated Dose Intranasal Zinc-free Insulin in Young and Aged F344 Rats on Cognition, Signaling, and Brain Metabolism

Novel therapies have turned to delivering compounds to the brain using nasal sprays, bypassing the blood brain barrier, and enriching treatment options for brain aging and/or Alzheimer's disease. We conducted a series of in vivo experiments to test the impact of intranasal Apidra, a zinc-free insulin formulation, on the brain of young and aged F344 rats. Both single acute and repeated daily doses were compared to test the hypothesis that insulin could improve memory recall in aged memory-deficient animals. We quantified insulin signaling in different brain regions and at different times following delivery. We measured cerebral blood flow (CBF) using MRI and also characterized several brain metabolite levels using MR spectroscopy. We show that neither acute nor chronic Apidra improved memory or recall in young or aged animals. Within 2 hours of a single dose, increased insulin signaling was seen in ventral areas of the aged brains only. Although chronic Apidra was able to offset reduced CBF with aging, it also caused significant reductions in markers of neuronal integrity. Our data suggest that this zinc-free insulin formulation may actually hasten cognitive decline with age when used chronically.

Usefulness of the apparent diffusion coefficient for the evaluation of the white matter to differentiate between glioblastoma and brain metastases

OBJECTIVE

To determine whether there are significant differences in the apparent diffusion coefficient (ADC) between the apparently normal peritumor white matter surrounding glioblastomas and that surrounding brain metastases.

MATERIAL AND METHODS

We retrospectively reviewed 42 patients with histologically confirmed glioblastomas and 42 patients with a single cerebral metastasis. We measured the signal intensity in the apparently normal peritumor white matter and in the abnormal peritumor white matter on the ADC maps. We used mean ADC values in the contralateral occipital white matter as a reference from which to design normalized ADC indices. We compared mean values between the two tumor types. We calculated the area under the receiver operator characteristic curve and estimated the sensitivity and specificity of the measurements taken.

RESULTS

Supratentorial lesions and compromise of the corpus callosum were more common in patients with glioblastoma than in patients with brain metastases. The maximum diameter of the enhanced area after injection of a contrast agent was greater in the glioblastomas (p<0.001). The minimum ADC value measured in the apparently normal peritumor white matter was higher for the glioblastomas than for the metastases (p=0.002). Significant differences in the ADC index were found only for the minimum ADC value in apparently normal peritumor white matter. The sensitivity and specificity were less than 70% for all variables analyzed.

CONCLUSIONS

There are differences in the ADC values of apparently normal peritumor white matter between glioblastomas and cerebral metastases, but the magnitude of these differences is slight and the application of these differences in clinical practice is still limited.

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.

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

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

Morphometric model for discrimination between glioblastoma multiforme and solitary metastasis using three-dimensional shape analysis

PURPOSE

Glioblastoma multiforme (GBM) and brain metastasis (MET) are the most common intra-axial brain neoplasms in adults and often pose a diagnostic dilemma using standard clinical MRI. These tumor types require different oncological and surgical management, which subsequently influence prognosis and clinical outcome.

METHODS

Here, we hypothesize that GBM and MET possess different three-dimensional (3D) morphological attributes based on their physical characteristics. A 3D morphological analysis was applied on the tumor surface defined by our diffusion tensor imaging (DTI) segmentation technique. It segments the DTI data into clusters representing different isotropic and anisotropic water diffusion characteristics, from which a distinct surface boundary between healthy and pathological tissue was identified. Morphometric features of shape index and curvedness were then computed for each tumor surface and used to build a morphometric model of GBM and MET pathology with the goal of developing a tumor classification method based on shape characteristics.

RESULTS

Our 3D morphometric method was applied on 48 untreated brain tumor patients. Cross-validation resulted in a 95.8% accuracy classification with only two shape features needed and that can be objectively derived from quantitative imaging methods.

CONCLUSION

The proposed 3D morphometric analysis framework can be applied to distinguish GBMs from solitary METs. Magn Reson Med 75:2505-2516, 2016. © 2015 Wiley Periodicals, Inc.

Magnetic resonance spectroscopy and imaging on fresh human brain tumor biopsies at microscopic resolution

The metabolic composition and concentration knowledge provided by magnetic resonance spectroscopy (MRS) liquid and high-resolution magic angle spinning spectroscopy (HR-MAS) has a relevant impact in clinical practice during magnetic resonance imaging (MRI) monitoring of human tumors. In addition, the combination of morphological and chemical information by MRI and MRS has been particularly useful for diagnosis and prognosis of tumor evolution. MRI spatial resolution reachable in human beings is limited for safety reasons and the demanding necessary conditions are only applicable on experimental model animals. Nevertheless, MRS and MRI can be performed on human biopsies at high spatial resolution, enough to allow a direct correlation between the chemical information and the histological features observed in such biopsies. Although HR-MAS is nowadays a well-established technique for spectroscopic analysis of tumor biopsies, with this approach just a mean metabolic profile of the whole sample can be obtained and thus the high histological heterogeneity of some important tumors is mostly neglected. The value of metabolic HR-MAS data strongly depends on a wide statistical analysis and usually the microanatomical rationale for the correlation between histology and spectroscopy is lost. We present here a different approach for the combined use of MRI and MRS on fresh human brain tumor biopsies with native contrast. This approach has been designed to achieve high spatial (18 × 18 × 50 μm) and spectral (0.031 μL) resolution in order to obtain as much spatially detailed morphological and metabolical information as possible without any previous treatment that can alter the sample. The preservation of native tissue conditions can provide information that can be translated to in vivo studies and additionally opens the possibility of performing other techniques to obtain complementary information from the same sample.

Discrete Wavelet Transform-Based Whole-Spectral and Subspectral Analysis for Improved Brain Tumor Clustering Using Single Voxel MR Spectroscopy

Many approaches have been considered for automatic grading of brain tumors by means of pattern recognition with magnetic resonance spectroscopy (MRS). Providing an improved technique which can assist clinicians in accurately identifying brain tumor grades is our main objective. The proposed technique, which is based on the discrete wavelet transform (DWT) of whole-spectral or subspectral information of key metabolites, combined with unsupervised learning, inspects the separability of the extracted wavelet features from the MRS signal to aid the clustering. In total, we included 134 short echo time single voxel MRS spectra (SV MRS) in our study that cover normal controls, low grade and high grade tumors. The combination of DWT-based whole-spectral or subspectral analysis and unsupervised clustering achieved an overall clustering accuracy of 94.8% and a balanced error rate of 7.8%. To the best of our knowledge, it is the first study using DWT combined with unsupervised learning to cluster brain SV MRS. Instead of dimensionality reduction on SV MRS or feature selection using model fitting, our study provides an alternative method of extracting features to obtain promising clustering results.

Computer-Aided Detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review

Prostate cancer is the second most diagnosed cancer of men all over the world. In the last few decades, new imaging techniques based on Magnetic Resonance Imaging (MRI) have been developed to improve diagnosis. In practise, diagnosis can be affected by multiple factors such as observer variability and visibility and complexity of the lesions. In this regard, computer-aided detection and computer-aided diagnosis systems have been designed to help radiologists in their clinical practice. Research on computer-aided systems specifically focused for prostate cancer is a young technology and has been part of a dynamic field of research for the last 10 years. This survey aims to provide a comprehensive review of the state-of-the-art in this lapse of time, focusing on the different stages composing the work-flow of a computer-aided system. We also provide a comparison between studies and a discussion about the potential avenues for future research. In addition, this paper presents a new public online dataset which is made available to the research community with the aim of providing a common evaluation framework to overcome some of the current limitations identified in this survey.

Gamma Knife radiosurgery for low-grade tectal gliomas

BACKGROUND

Tectal gliomas are present in a critical location that makes their surgical treatment difficult. Stereotactic radiosurgery presents an attractive noninvasive treatment option. However, tectal gliomas are also commonly associated with aqueductal obstruction and consequently hydrocephalus. This necessitates some form of CSF diversion procedure before radiosurgery. The aim of the study was to assess the efficacy and safety of Gamma Knife radiosurgery for tectal gliomas.

PATIENTS AND METHODS

Between October 2002 and May 2011, 11 patients with tectal gliomas were treated with Gamma Knife radiosurgery. Five patients had pilocytic astrocytomas and six nonpilocytic astrocytomas. Ten patients presented with hydrocephalus and underwent a CSF diversion procedure [7 V-P shunt and 3 endoscopic third ventriculostomy (ETV)]. The tumor volume ranged between 1.2-14.7 cc (median 4.5 cc). The prescription dose was 11-14 Gy (median 12 Gy).

RESULTS

Patients were followed for a median of 40 months (13-114 months). Tumor control after radiosurgery was seen in all cases. In 6/11 cases, the tumors eventually disappeared after treatment. Peritumoral edema developed in 5/11 cases at an onset of 3-6 months after treatment. Transient tumor swelling was observed in four cases. Four patients developed cysts after treatment. One of these cases required aspiration and eventually disappeared, one became smaller spontaneously, and two remained stable.

CONCLUSION

Gamma Knife radiosurgery is an effective and safe technique for treatment of tectal gliomas. Tumor shrinkage or disappearance after Gamma Knife radiosurgery may preclude the need for a shunt later on.

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.

Discrimination between glioblastoma multiforme and solitary metastasis using morphological features derived from the p:q tensor decomposition of diffusion tensor imaging

The management and treatment of high-grade glioblastoma multiforme (GBM) and solitary metastasis (MET) are very different and influence the prognosis and subsequent clinical outcomes. In the case of a solitary MET, diagnosis using conventional radiology can be equivocal. Currently, a definitive diagnosis is based on histopathological analysis on a biopsy sample. Here, we present a computerised decision support framework for discrimination between GBM and solitary MET using MRI, which includes: (i) a semi-automatic segmentation method based on diffusion tensor imaging; (ii) two-dimensional morphological feature extraction and selection; and (iii) a pattern recognition module for automated tumour classification. Ground truth was provided by histopathological analysis from pre-treatment stereotactic biopsy or at surgical resection. Our two-dimensional morphological analysis outperforms previous methods with high cross-validation accuracy of 97.9% and area under the receiver operating characteristic curve of 0.975 using a neural networks-based classifier.

Imaging of brain tumors

Neuroimaging plays a crucial role in diagnosis of brain tumors and in the decision-making process for therapy. Functional imaging techniques can reflect cellular density (diffusion imaging), capillary density (perfusion techniques), and tissue biochemistry (magnetic resonance [MR] spectroscopy). In addition, cortical activation imaging (functional MR imaging) can identify various loci of eloquent cerebral cortical function. Combining these new tools can increase diagnostic specificity and confidence. Familiarity with conventional and advanced imaging findings facilitates accurate diagnosis, differentiation from other processes, and optimal patient treatment. This article is a practical synopsis of pathologic, clinical, and imaging spectra of most common brain tumors.

Gradient of apparent diffusion coefficient values in peritumoral edema helps in differentiation of glioblastoma from solitary metastatic lesions

OBJECTIVE

Glioblastoma and solitary metastatic lesions can be difficult to differentiate with conventional MRI. The use of diffusion-weighted MRI to better characterize peritumoral edema has been explored for this purpose, but the results have been conflicting. The purpose of this study was to test the hypothesis that the gradient of apparent diffusion coefficient (ADC) values in peritumoral edema--that is, the difference in ADC values from the region closest to the enhancing tumor and the one closest to the normal-appearing white matter--may be a marker for differentiating glioblastoma from a metastatic lesion.

MATERIALS AND METHODS

Forty patients, 20 with glioblastoma and 20 with a solitary metastatic lesion, underwent diffusion-weighted brain MRI before surgical resection. The ADC values were retrospectively collected in the peritumoral edema in three positions: near, an intermediate distance from, and far from the core enhancing tumor (G1, G2, and G3). The ADC gradient in the peritumoral edema was calculated as the subtractions ADCG3 - ADCG1, ADCG3 - ADCG2, and ADCG2 - ADCG1. The ADC values in the enhancing tumor, peritumoral edema, ipsilateral normal-appearing white matter, contralateral healthy white matter, and CSF were also collected.

RESULTS

A gradient of ADC values was found in the peritumoral edema of glioblastoma. The ADC values increased from the region close to the enhancing tumor (1.36 ± 0.24 × 10(-3) mm(2)/s) to the area near the normal-appearing white matter (1.57 ± 0.34 × 10(-3) mm(2)/s). In metastatic lesions, however, those values were nearly homogeneous (p = 0.04).

CONCLUSION

The ADC gradient in peritumoral edema appears to be a promising tool for differentiating glioblastoma from a metastatic lesion.

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

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

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.

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.

A dual neural network ensemble approach for multiclass brain tumor classification

The present study is conducted to develop an interactive computer aided diagnosis (CAD) system for assisting radiologists in multiclass classification of brain tumors. In this paper, primary brain tumors such as astrocytoma, glioblastoma multiforme, childhood tumor-medulloblastoma, meningioma and secondary tumor-metastases along with normal regions are classified by a dual level neural network ensemble. Two hundred eighteen texture and intensity features are extracted from 856 segmented regions of interest (SROIs) and are taken as input. PCA is used for reduction of dimensionality of the feature space. The study is performed on a diversified dataset of 428 post contrast T1-weighted magnetic resonance images of 55 patients. Two sets of experiments are performed. In the first experiment, random selection is used which may allow SROIs from the same patient having similar characteristics to appear in both training and testing simultaneously. In the second experiment, not even a single SROI from the same patient is common during training and testing. In the first experiment, it is observed that the dual level neural network ensemble has enhanced the overall accuracy to 95.85% compared with 91.97% of single level artificial neural network. The proposed method delivers high accuracy for each class. The accuracy obtained for each class is: astrocytoma 96.29%, glioblastoma multiforme 96.15%, childhood tumor-medulloblastoma 90%, meningioma 93.00%, secondary tumor-metastases 96.67% and normal regions 97.41%. This study reveals that dual level neural network ensemble provides better results than the single level artificial neural network. In the second experiment, overall classification accuracy of 90.4% was achieved. The generalization ability of this approach can be tested by analyzing larger datasets. The extensive training will also further improve the performance of the proposed dual network ensemble. Quantitative results obtained from the proposed method will assist the radiologist in forming a better decision for classifying brain tumors.

Convex non-negative matrix factorization for brain tumor delimitation from MRSI data

Background

Pattern Recognition techniques can provide invaluable insights in the field of neuro-oncology. This is because the clinical analysis of brain tumors requires the use of non-invasive methods that generate complex data in electronic format. Magnetic Resonance (MR), in the modalities of spectroscopy (MRS) and spectroscopic imaging (MRSI), has been widely applied to this purpose. The heterogeneity of the tissue in the brain volumes analyzed by MR remains a challenge in terms of pathological area delimitation.

Methodology/Principal Findings

A pre-clinical study was carried out using seven brain tumor-bearing mice. Imaging and spectroscopy information was acquired from the brain tissue. A methodology is proposed to extract tissue type-specific sources from these signals by applying Convex Non-negative Matrix Factorization (Convex-NMF). Its suitability for the delimitation of pathological brain area from MRSI is experimentally confirmed by comparing the images obtained with its application to selected target regions, and to the gold standard of registered histopathology data. The former showed good accuracy for the solid tumor region (proliferation index (PI)>30%). The latter yielded (i) high sensitivity and specificity in most cases, (ii) acquisition conditions for safe thresholds in tumor and non-tumor regions (PI>30% for solid tumoral region; ≤5% for non-tumor), and (iii) fairly good results when borderline pixels were considered.

Conclusions/Significance

The unsupervised nature of Convex-NMF, which does not use prior information regarding the tumor area for its delimitation, places this approach one step ahead of classical label-requiring supervised methods for discrimination between tissue types, minimizing the negative effect of using mislabeled voxels. Convex-NMF also relaxes the non-negativity constraints on the observed data, which allows for a natural representation of the MRSI signal. This should help radiologists to accurately tackle one of the main sources of uncertainty in the clinical management of brain tumors, which is the difficulty of appropriately delimiting the pathological area.

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.

Classification of single-voxel 1H spectra of childhood cerebellar tumors using LCModel and whole tissue representations

In this study, mean tumor spectra are used as the basis functions in LCModel to create a direct classification tool for short echo time (1)H magnetic resonance spectroscopy of pediatric brain tumors. LCModel is a widely used analysis tool designed to fit a linear combination of individual metabolite spectra to in vivo spectra. Here, we have used LCModel to fit mean spectra and corresponding variability components of childhood cerebellar tumors, as calculated using principal component analysis, and assessed for classification accuracy. Classification was performed according to the highest estimated tumor proportion. This method was tested in a leave-one-out analysis discriminating between pediatric brain tumor spectra of medulloblastoma vs. pilocytic astrocytoma and medulloblastoma vs. pilocytic astrocytoma vs. ependymoma. Additionally, the effect of accepting different Cramér-Rao Lower Bound cut-off criteria on classification accuracy and estimated tissue proportions was investigated. The best classification results differentiating medulloblastoma vs. pilocytic astrocytoma and medulloblastoma vs. pilocytic astrocytoma vs. ependymoma were 100 and 87.7%, respectively. These results are comparable to a specialized pattern recognition analysis of this data set and give easy to interpret results in the form of estimated tissue proportions. The method requires minimal user input and is easily transferable across sites and to other magnetic resonance spectroscopy classification problems.

Quantitative short echo time 1H MRSI of the peripheral edematous region of human brain tumors in the differentiation between glioblastoma, metastasis, and meningioma

PURPOSE

To assess metabolite levels in peritumoral edematous (PO) and surrounding apparently normal (SAN) brain regions of glioblastoma, metastasis, and meningioma in humans with (1)H-MRSI to find biomarkers that can discriminate between tumors and characterize infiltrative tumor growth.

MATERIALS AND METHODS

Magnetic resonance (MR) spectra (semi-LASER MRSI, 30 msec echo time, 3T) were selected from regions of interest (ROIs) under MRI guidance, and after quality control of MR spectra. Statistical testing between patient groups was performed for mean metabolite ratios of an entire ROI and for the highest value within that ROI.

RESULTS

The highest ratios of the level of choline compounds and the sum of myo-inositol and glycine over N-acetylaspartate and creatine compounds were significantly increased in PO regions of glioblastoma versus that of metastasis and meningioma. In the SAN region of glioblastoma some of these ratios were increased. Differences were less prominent for metabolite levels averaged over entire ROIs.

CONCLUSION

Specific metabolite ratios in PO and SAN regions can be used to discriminate glioblastoma from metastasis and meningioma. An analysis of these ratios averaged over entire ROIs and those with most abnormal values indicates that infiltrative tumor growth in glioblastoma is inhomogeneous and extends into the SAN region.

Robust discrimination of glioblastomas from metastatic brain tumors on the basis of single-voxel (1)H MRS

This article investigates methods for the accurate and robust differentiation of metastases from glioblastomas on the basis of single-voxel (1)H MRS information. Single-voxel (1)H MR spectra from a total of 109 patients (78 glioblastomas and 31 metastases) from the multicenter, international INTERPRET database, plus a test set of 40 patients (30 glioblastomas and 10 metastases) from three different centers in the Barcelona (Spain) metropolitan area, were analyzed using a robust method for feature (spectral frequency) selection coupled with a linear-in-the-parameters single-layer perceptron classifier. For the test set, a parsimonious selection of five frequencies yielded an area under the receiver operating characteristic curve of 0.86, and an area under the convex hull of the receiver operating characteristic curve of 0.91. Moreover, these accurate results for the discrimination between glioblastomas and metastases were obtained using a small number of frequencies that are amenable to metabolic interpretation, which should ease their use as diagnostic markers. Importantly, the prediction can be expressed as a simple formula based on a linear combination of these frequencies. As a result, new cases could be straightforwardly predicted by integrating this formula into a computer-based medical decision support system. This work also shows that the combination of spectra acquired at different TEs (short TE, 20-32 ms; long TE, 135-144 ms) is key to the successful discrimination between glioblastomas and metastases from single-voxel (1)H MRS.

Prospective diagnostic performance evaluation of single-voxel 1H MRS for typing and grading of brain tumours

The purpose of this study was to evaluate whether single-voxel (1)H MRS could add useful information to conventional MRI in the preoperative characterisation of the type and grade of brain tumours. MRI and MRS examinations from a prospective cohort of 40 consecutive patients were analysed double blind by radiologists and spectroscopists before the histological diagnosis was known. The spectroscopists had only the MR spectra, whereas the radiologists had both the MR images and basic clinical details (age, sex and presenting symptoms). Then, the radiologists and spectroscopists exchanged their predictions and re-evaluated their initial opinions, taking into account the new evidence. Spectroscopists used four different systems of analysis for (1)H MRS data, and the efficacy of each of these methods was also evaluated. Information extracted from (1)H MRS significantly improved the radiologists' MRI-based characterisation of grade IV tumours (glioblastomas, metastases, medulloblastomas and lymphomas) in the cohort [area under the curve (AUC) in the MRI re-evaluation 0.93 versus AUC in the MRI evaluation 0.85], and also of the less malignant glial tumours (AUC in the MRI re-evaluation 0.93 versus AUC in the MRI evaluation 0.81). One of the MRS analysis systems used, the INTERPRET (International Network for Pattern Recognition of Tumours Using Magnetic Resonance) decision support system, outperformed the others, as well as being better than the MRI evaluation for the characterisation of grade III astrocytomas. Thus, preoperative MRS data improve the radiologists' performance in diagnosing grade IV tumours and, for those of grade II-III, MRS data help them to recognise the glial lineage. Even in cases in which their diagnoses were not improved, the provision of MRS data to the radiologists had no negative influence on their predictions.

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).