A5004256128- Advanced MRI Techniques and Applications
- Brain Tumor Detection and Classification
- Glioma Diagnosis and Treatment
- Gene expression and cancer classification
- Blind Source Separation Techniques
- MRI in cancer diagnosis
- Metabolomics and Mass Spectrometry Studies
- Neural Networks and Applications
- Advanced NMR Techniques and Applications
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Bioinformatics and Genomic Networks
- Advanced Neuroimaging Techniques and Applications
- Mathematical Biology Tumor Growth
- Cell Image Analysis Techniques
- Lanthanide and Transition Metal Complexes
- Fractal and DNA sequence analysis
- Machine Learning in Bioinformatics
- Spectroscopy Techniques in Biomedical and Chemical Research
- Machine Learning and ELM
- Electron Spin Resonance Studies
- Traditional Chinese Medicine Studies
- Spectroscopy and Chemometric Analyses
- Sparse and Compressive Sensing Techniques
- Atomic and Subatomic Physics Research
Centro de Investigación Biomédica en Red
2015-2024
Universitat Autònoma de Barcelona
2012-2024
Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine
2011-2023
Instituto de Salud Carlos III
2023
Bellvitge University Hospital
2008
Duran i Reynals Hospital
2006
Simón Bolívar University
2006
Abstract A computer‐based decision support system to assist radiologists in diagnosing and grading brain tumours has been developed by the multi‐centre INTERPRET project. Spectra from a database of 1 H single‐voxel spectra different types tumours, acquired vivo 334 patients at four centres, are clustered according their pathology, using automated pattern recognition techniques results presented as two‐dimensional scatterplot an intuitive graphical user interface (GUI). Formal quality control...
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 subsequently acquired in different centers. The multicenter eTUMOUR project (2004-2009), which builds upon previous expertise from the INTERPRET (2000-2002) allowed such an evaluation take place.A total 253 pairwise classifiers glioblastoma, meningioma, metastasis, and low-grade glial...
<b>BACKGROUND AND PURPOSE:</b> Differentiating between tumors and pseudotumoral lesions by conventional MR imaging may be a challenging question. This study aims to evaluate the potential usefulness added value that single-voxel proton spectroscopy could provide on this discrimination. <b>MATERIALS METHODS:</b> A total of 84 solid brain were retrospectively included in (68 glial 16 lesions). Single-voxel spectra at TE 30 ms (short TE) 136 (long available all cases. Two groups defined:...
The purpose of this study was to evaluate whether single‐voxel 1 H MRS could add useful information conventional MRI in the preoperative characterisation type and grade brain tumours. examinations from a prospective cohort 40 consecutive patients were analysed double blind by radiologists spectroscopists before histological diagnosis known. had only MR spectra, whereas both images basic clinical details (age, sex presenting symptoms). Then, exchanged their predictions re‐evaluated initial...
Background Pattern Recognition techniques can provide invaluable insights in the field of neuro-oncology. This is because clinical analysis brain tumors requires use non-invasive methods that generate complex data electronic format. Magnetic Resonance (MR), modalities spectroscopy (MRS) and spectroscopic imaging (MRSI), has been widely applied to this purpose. The heterogeneity tissue volumes analyzed by MR remains a challenge terms pathological area delimitation. Methodology/Principal...
Object The aim of this study was to estimate the accuracy routine magnetic resonance (MR) imaging studies in classification brain tumors terms both cell type and grade malignancy. Methods authors retrospectively assessed correlation between neuroimaging classifications histopathological diagnoses by using multicenter database records from 393 patients with tumors. An ontology devised establish diagnostic agreement. Each tumor category compared corresponding dichotomization. Sensitivity,...
Abstract Background Proton 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 metabolites in tissues. In pathological situations, profile changes and this has been particularly described brain tumours. However, radiologists are frequently familiar to interpretation data reason, usefulness decision-support systems (DSS) analysis explored....
Abstract This paper reports on quality assessment of MRS in the European Union‐funded multicentre project INTERPRET (International Network for Pattern Recognition Tumours Using Magnetic Resonance; http://azizu.uab.es/INTERPRET ), which has developed brain tumour classification software using vivo proton MR spectra. The consisted both system assurance (SQA) and control (QC) spectral data acquired from patients healthy volunteers. performance spectrometers at all participating centres was...
Abstract 1 H MRS is becoming an accurate, non‐invasive technique for initial examination of brain masses. We investigated if the combination single‐voxel at 1.5 T two different ( TE s), short (PRESS or STEAM, 20–32 ms) and long (PRESS, 135–136 ms), improves classification tumors over using only one echo . A clinically validated dataset 50 low‐grade meningiomas, 105 aggressive (glioblastoma metastasis), 30 glial (astrocytomas grade II, oligodendrogliomas oligoastrocytomas) was used to fit...
Abstract Background In-vivo single voxel proton magnetic resonance spectroscopy (SV 1 H-MRS), coupled with supervised pattern recognition (PR) methods, has been widely used in clinical studies of discrimination brain tumour types and follow-up patients bearing abnormal masses. SV H-MRS provides useful biochemical information about the metabolic state tumours can be performed at short (< 45 ms) or long (> echo time (TE), each particular advantages. Short-TE spectra are more adequate for...
There is a large range of survival times in patients with HGA that can only be partially explained by histologic grade and clinical aspects. This study aims to retrospectively assess the predictive value single-voxel (1)H-MRS regarding HGA.Pretreatment 187 produced 180 spectra at STE (30 ms) 182 LTE (136 ms). Patients were dichotomized into 2 groups according better or worse than median. The compared using Mann-Whitney U test. points on spectrum most significant differences selected for...
SpectraClassifier (SC) is a Java solution for designing and implementing Magnetic Resonance Spectroscopy (MRS)-based classifiers. The main goal of SC to allow users with minimum background knowledge multivariate statistics perform fully automated pattern recognition analysis. incorporates feature selection (greedy stepwise approach, either forward or backward), extraction (PCA). Fisher Linear Discriminant Analysis the method choice classification. Classifier evaluation performed through...
This article investigates methods for the accurate and robust differentiation of metastases from glioblastomas on basis single‐voxel 1 H MRS information. Single‐voxel MR spectra a total 109 patients (78 31 metastases) multicenter, international INTERPRET database, plus test set 40 (30 10 three different centers in Barcelona (Spain) metropolitan area, were analyzed using method feature (spectral frequency) selection coupled with linear‐in‐the‐parameters single‐layer perceptron classifier. For...
Non‐invasive monitoring of response to treatment glioblastoma (GB) is nowadays carried out using MRI. MRS and MR spectroscopic imaging (MRSI) constitute promising tools for this undertaking. A temozolomide (TMZ) protocol was optimized GL261 GB. Sixty‐three mice were studied by MRI/MRS/MRSI. The information used the classification control brain untreated responding GB, validated against post‐mortem immunostainings in selected animals. system developed, based on MRSI‐sampled metabolome normal...
Glioblastoma (GBM) causes poor survival in patients even when applying aggressive treatment. Temozolomide (TMZ) is the standard chemotherapeutic choice for GBM treatment, but resistance always ensues. In previous years, efforts have focused on new therapeutic regimens with conventional drugs to activate immune responses that may enhance tumor regression and prevent regrowth, example “metronomic” approaches. metronomic scheduling studies, cyclophosphamide (CPA) GL261 growing subcutaneously...
Characterization of glioblastoma (GB) response to treatment is a key factor for improving patients' survival and prognosis. MRI magnetic resonance spectroscopic imaging (MRSI) provide morphologic metabolic profiles GB but usually fail produce unequivocal biomarkers response. The purpose this work proof concept the ability semi-supervised signal source extraction methodology images with robust recognition temozolomide (TMZ) in preclinical model. A total 38 female C57BL/6 mice were used study....
Abstract Glioblastomas (GB) are brain tumours with poor prognosis even after aggressive therapy. Improvements in both therapeutic and follow‐up strategies urgently needed. In previous work we described an oscillatory pattern of response to Temozolomide (TMZ) using a standard administration protocol, detected through MRSI‐based machine learning approaches. the present work, have introduced Immune‐Enhancing Metronomic Schedule (IMS) every 6‐d TMZ at 60 mg/kg investigated consistence such...
MRI and MRS are established methodologies for evaluating intracranial lesions. One MR spectral feature suggested in vivo grading of astrocytic tumours is the apparent myo-Inositol (mI) intensity (ca 3.55ppm) at short echo times, although glycine (gly) may also contribute to this resonance. The purpose study was quantitatively evaluate mI + gly contribution recorded pattern correlate it with vitro data obtained from perchloric acid extraction tumour biopsies.Patient spectra (n = 95) 1.5T...