Carles Majós

Brain tumor classification based on long echo proton MRS signals

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

Proton MR Spectroscopy Improves Discrimination between Tumor and Pseudotumoral Lesion in Solid Brain Masses

BACKGROUND AND PURPOSE: Differentiating between tumors and pseudotumoral lesions by conventional MR imaging may be a challenging question. This study aims to evaluate the potential usefulness and the added value that single-voxel proton MR spectroscopy could provide on this discrimination. MATERIALS AND METHODS: A total of 84 solid brain lesions were retrospectively included in the study (68 glial tumors and 16 pseudotumoral lesions). Single-voxel spectra at TE 30 ms (short TE) and 136 ms (long TE) were available in all cases. Two groups were defined: “training-set” (56 cases) and “test-set” (28 cases). Tumors and pseudotumors were compared in the training-set with the Mann-Whitney U test. Ratios between resonances were defined as classifiers for new cases, and thresholds were selected with receiver operating characteristic (ROC) curves. The added value of spectroscopy was evaluated by 5 neuroradiologists and assessed with the Wilcoxon signed-rank test. RESULTS: Differences between tumors and pseudotumors were found in myo-inositol (mIns); P < .01) at short TE, and N-acetylaspartate (NAA; P < .001), glutamine (Glx; P < .01), and choline (CHO; P < .05) at long TE. Classifiers suggested tumor when mIns/NAA ratio was more than 0.9 at short TE and also when CHO/NAA ratio was more than 1.9 at long TE. Classifier accuracy was tested in the test-set with the following results: short TE, 82% (23/28); long TE, 79% (22/28). The neuroradiologists’ confidence rating of the test-cases on a 5-point scale (0–4) improved between 5% (from 2.86–3) and 27% (from 2.25–2.86) with spectroscopy (mean, 17%; P < .01). CONCLUSIONS: The proposed ratios of mIns/NAA at short TE and CHO/NAA at long TE provide valuable information to discriminate between brain tumor and pseudotumor by improving neuroradiologists’ accuracy and confidence.

The INTERPRET Decision-Support System version 3.0 for evaluation of Magnetic Resonance Spectroscopy data from human brain tumours and other abnormal brain masses

BackgroundProton Magnetic Resonance (MR) Spectroscopy (MRS) is a widely available technique for those clinical centres equipped with MR scanners. Unlike the rest of MR-based techniques, MRS yields not images but spectra of metabolites in the tissues. In pathological situations, the MRS profile changes and this has been particularly described for brain tumours. However, radiologists are frequently not familiar to the interpretation of MRS data and for this reason, the usefulness of decision-support systems (DSS) in MRS data analysis has been explored.ResultsThis work presents the INTERPRET DSS version 3.0, analysing the improvements made from its first release in 2002. Version 3.0 is aimed to be a program that 1st, can be easily used with any new case from any MR scanner manufacturer and 2nd, improves the initial analysis capabilities of the first version. The main improvements are an embedded database, user accounts, more diagnostic discrimination capabilities and the possibility to analyse data acquired under additional data acquisition conditions. Other improvements include a customisable graphical user interface (GUI). Most diagnostic problems included have been addressed through a pattern-recognition based approach, in which classifiers based on linear discriminant analysis (LDA) were trained and tested.ConclusionsThe INTERPRET DSS 3.0 allows radiologists, medical physicists, biochemists or, generally speaking, any person with a minimum knowledge of what an MR spectrum is, to enter their own SV raw data, acquired at 1.5 T, and to analyse them. The system is expected to help in the categorisation of MR Spectra from abnormal brain masses.

Rhombencephalitis: a series of 97 patients.

The term rhombencephalitis refers to inflammatory diseases affecting the hindbrain (brainstem and cerebellum). Rhombencephalitis has a wide variety of etiologies, some of them potentially severe and life threatening without proper early treatment. In this retrospective observational study, we reviewed the records of consecutively hospitalized patients at University Hospital of Bellvitge (Barcelona, Spain) from January 1990 to December 2008. Rhombencephalitis was defined as a brainstem and/or cerebellar condition demonstrated clinically or by neuroimaging, with pleocytosis (>4 cells/mm3) in cerebrospinal fluid. Ninety-seven patients (48 female; mean age, 37 yr; range, 14-79 yr) fulfilled these criteria. We reviewed their clinical, cerebrospinal fluid, and radiologic characteristics. The mean follow-up was 5 years (range, 0-20 yr). The etiologies of rhombencephalitis were as follows: unknown cause (n = 31), multiple sclerosis (n = 28), Behçet disease (n = 10), Listeria monocytogenes infection (n = 9), paraneoplastic syndrome (n = 6) (3 cases associated with anti-Yo antibodies and 3 with anti-Tr antibodies), Epstein-Barr virus (n = 4), tuberculosis (n = 2), pneumococcal infection (n = 2), systemic lupus erythematosus (n = 1), lymphoma (n = 1), Brucella species infection (n = 1), JC virus (n = 1), and relapsing polychondritis (n = 1). Certain clinical, cerebrospinal fluid, and radiologic characteristics that are commonly seen in some of these etiologies can guide us in the first approach to the etiologic diagnosis of rhombencephalitis. Abbreviations: CSF = cerebrospinal fluid, EBV = Epstein-Barr virus, MS = multiple sclerosis, PCR = polymerase chain reaction, RE = rhombencephalitis.

Imaging of giant pituitary adenomas

Abstract We present five proven giant pituitary adenomas studied by CT and MRI, and review the clinical and imaging findings. Our aim was to examine the radiologic appearances and to search for criteria useful in distinguishing these tumors from other sellar and suprasellar tumours, mainly craniopharyngioma. The main differences from small adenomas were high prevalence of macrocysts, a more invasive behaviour and a clinical picture dominated by mass effect rather than endocrine disturbance. Factors supporting the diagnosis of pituitary adenoma in a giant intra- and suprasellar mass include: infrasellar extension, absence of calcification and presence of low-signal cysts on T1-weighted images.

Orbital lymphoma: imaging features and differential diagnosis

PurposePatterns of orbital lymphoma at diagnosis and follow-up are described. We also discuss differential diagnosis of orbital masses.Materials and methodsThis pictorial review contains 19 cases of orbital lymphoma before and after treatment. Superior-lateral quadrant and extra-conal location were observed predominantly. Effective response after treatment was presented on follow-up imaging, although few local relapses were found. Further follow-up showed no changes of residual images.DiscussionLocation of orbital masses can help in the differential diagnosis. Moreover, imaging features of lymphoma at diagnosis can be useful in planning surgical biopsy. Pattern of follow-up described may be relevant on monitoring imaging.Teaching points• Orbital lymphoma involves mainly superior-lateral quadrant and the orbital structures inside.• Location of retrobulbar mass-like lesions are useful information in the differential diagnosis.• Satisfactory response is detected after treatment, however relapse is noted, so follow-up is needed.

Intraventricular ganglioglioma: case report.

Abstract We report a case of ganglioglioma located in the body and frontal horn of the right lateral ventricle. The lesion was found in a 71-year-old man who suffered from recurrent episodes of right hemicranial headache. CT and MRI showed a heterogeneous intraventricular tumour with multiple microcysts that suggested a diagnosis of subependymoma or central neurocytoma, but the pathological findings were consistent with ganglioglioma. Although the most frequent intracranial location of ganglioglioma is the temporal lobe, any location in the central nervous system may be seen. Nevertheless an exclusively intraventricular location is exceptional. To our knowledge this is the first complete radiological report of a purely intraventricular ganglioglioma.

Central neurocytoma arising in the third ventricle

Abstract A central neurocytoma confined to the third ventricle and presenting clinically as subarachnoid haemorrhage is reported.

Intraventricular mass lesions of the brain.

Intraventricular tumours represent a diverse group of lesions, some of them infrequent, with a wide variety of radiological features. Determination of their precise aetiology or origin can be difficult. Nevertheless, considering patient’s age, location within the ventricles, and some specific radiological features, the radiologist should be able to narrow down the differential diagnosis. This paper reviews the characteristic radiological appearances of the diverse intraventricular lesions emphasising its differential diagnosis.

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

This article investigates methods for the accurate and robust differentiation of metastases from glioblastomas on the basis of single‐voxel 1H MRS information. Single‐voxel 1H 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 1H MRS. Copyright