Selecting the most relevant brain regions to discriminate Alzheimer's disease patients from healthy controls using multiple kernel learning: A comparison across functional and structural imaging modalities and atlases.

BACKGROUND: Machine learning techniques such as support vector machine (SVM) have been applied recently in order to accurately classify individuals with neuropsychiatric disorders such as Alzheimer's disease (AD) based on neuroimaging data. However, the multivariate nature of the SVM approach often precludes the identification of the brain regions that contribute most to classification accuracy. Multiple kernel learning (MKL) is a sparse machine learning method that allows the identification of the most relevant sources for the classification. By parcelating the brain into regions of interest (ROI) it is possible to use each ROI as a source to MKL (ROI-MKL). METHODS: We applied MKL to multimodal neuroimaging data in order to: 1) compare the diagnostic performance of ROI-MKL and whole-brain SVM in discriminating patients with AD from demographically matched healthy controls and 2) identify the most relevant brain regions to the classification. We used two atlases (AAL and Brodmann's) to parcelate the brain into ROIs and applied ROI-MKL to structural (T1) MRI, 18F-FDG-PET and regional cerebral blood flow SPECT (rCBF-SPECT) data acquired from the same subjects (20 patients with early AD and 18 controls). In ROI-MKL, each ROI received a weight (ROI-weight) that indicated the region's relevance to the classification. For each ROI, we also calculated whether there was a predominance of voxels indicating decreased or increased regional activity (for 18F-FDG-PET and rCBF-SPECT) or volume (for T1-MRI) in AD patients. RESULTS: Compared to whole-brain SVM, the ROI-MKL approach resulted in better accuracies (with either atlas) for classification using 18F-FDG-PET (92.5% accuracy for ROI-MKL versus 84% for whole-brain), but not when using rCBF-SPECT or T1-MRI. Although several cortical and subcortical regions contributed to discrimination, high ROI-weights and predominance of hypometabolism and atrophy were identified specially in medial parietal and temporo-limbic cortical regions. Also, the weight of discrimination due to a pattern of increased voxel-weight values in AD individuals was surprisingly high (ranging from approximately 20% to 40% depending on the imaging modality), located mainly in primary sensorimotor and visual cortices and subcortical nuclei. CONCLUSION: The MKL-ROI approach highlights the high discriminative weight of a subset of brain regions of known relevance to AD, the selection of which contributes to increased classification accuracy when applied to 18F-FDG-PET data. Moreover, the MKL-ROI approach demonstrates that brain regions typically spared in mild stages of AD also contribute substantially in the individual discrimination of AD patients from controls.

Framingham Coronary Heart Disease Risk Score Can be Predicted from Structural Brain Images in Elderly Subjects.

Recent literature has presented evidence that cardiovascular risk factors (CVRF) play an important role on cognitive performance in elderly individuals, both those who are asymptomatic and those who suffer from symptoms of neurodegenerative disorders. Findings from studies applying neuroimaging methods have increasingly reinforced such notion. Studies addressing the impact of CVRF on brain anatomy changes have gained increasing importance, as recent papers have reported gray matter loss predominantly in regions traditionally affected in Alzheimer's disease (AD) and vascular dementia in the presence of a high degree of cardiovascular risk. In the present paper, we explore the association between CVRF and brain changes using pattern recognition techniques applied to structural MRI and the Framingham score (a composite measure of cardiovascular risk largely used in epidemiological studies) in a sample of healthy elderly individuals. We aim to answer the following questions: is it possible to decode (i.e., to learn information regarding cardiovascular risk from structural brain images) enabling individual predictions? Among clinical measures comprising the Framingham score, are there particular risk factors that stand as more predictable from patterns of brain changes? Our main findings are threefold: (i) we verified that structural changes in spatially distributed patterns in the brain enable statistically significant prediction of Framingham scores. This result is still significant when controlling for the presence of the APOE 4 allele (an important genetic risk factor for both AD and cardiovascular disease). (ii) When considering each risk factor singly, we found different levels of correlation between real and predicted factors; however, single factors were not significantly predictable from brain images when considering APOE4 allele presence as covariate. (iii) We found important gender differences, and the possible causes of that finding are discussed.

Measuring abnormal brains: building normative rules in neuroimaging using one-class support vector machines.

Pattern recognition methods have demonstrated to be suitable analyses tools to handle the high dimensionality of neuroimaging data. However, most studies combining neuroimaging with pattern recognition methods focus on two-class classification problems, usually aiming to discriminate patients under a specific condition (e.g., Alzheimer's disease) from healthy controls. In this perspective paper we highlight the potential of the one-class support vector machines (OC-SVM) as an unsupervised or exploratory approach that can be used to create normative rules in a multivariate sense. In contrast with the standard SVM that finds an optimal boundary separating two classes (discriminating boundary), the OC-SVM finds the boundary enclosing a specific class (characteristic boundary). If the OC-SVM is trained with patterns of healthy control subjects, the distance to the boundary can be interpreted as an abnormality score. This score might allow quantification of symptom severity or provide insights about subgroups of patients. We provide an intuitive description of basic concepts in one-class classification, the foundations of OC-SVM, current applications, and discuss how this tool can bring new insights to neuroimaging studies.

Cerebral and corpus callosum atrophy in systemic lupus erythematosus.

OBJECTIVE: To determine cerebral and corpus callosum volumes in patients with systemic lupus erythematosus (SLE), using semiautomatic magnetic resonance imaging (MRI) volumetric measurements, and to determine possible relationships between a reduction in cerebral volume and disease duration, total corticosteroid dose, neuropsychiatric manifestations, and the presence of antiphospholipid antibodies. METHODS: We studied 115 consecutive patients with SLE and 44 healthy volunteers. A complete clinical, laboratory, and neurologic evaluation was performed. MRI scans were obtained through a standardized protocol. Sagittal T1-weighted images were used for semiautomatic volumetric measurements. We compared SLE patients with controls using the 2-sample t-test. Analysis of variance was used to test for differences between groups, followed by Tukey's post hoc test for pairwise comparisons, when necessary. Linear regression was used to analyze the association between cerebral atrophy and disease duration and total corticosteroid dose. RESULTS: Cerebral and corpus callosum volumes were significantly smaller in patients with SLE compared with healthy volunteers (P < 0.001). Reduced cerebral and corpus callosum volumes were related to disease duration (P < 0.001). Patients with a history of central nervous system (CNS) involvement more frequently had a reduction in cerebral and corpus callosum volumes (P < 0.001). Patients with cognitive impairment had significantly reduced corpus callosum and cerebral volumes when compared with SLE patients without cognitive impairment (P = 0.001). Cerebral and corpus callosum volumes were not associated with the total corticosteroid dose or the presence of antiphospholipid antibodies. CONCLUSION: In patients with SLE, a reduction in cerebral and corpus callosum volumes is associated with disease duration, a history of CNS involvement, and cognitive impairment. The total corticosteroid dose and the presence of antiphospholipid antibodies were not associated with more pronounced atrophy.

Um sistema de segmentação interativa do ventrículo esquerdo em seqüências de imagens de ressonância magnética (Cine MR) / A system for interactive segmentation of left ventricle in sequences of magnetic resonance images (Cine MR)

A utilização de imagens de Ressonância Magnética vem ganhando crescente importância na análise do funcionamento cardíaco e detecção de cardiopatias. Contudo, para a obtenção de informações quantitativas utilizadas em determinados diagnósticos é necessária a realização de um processo de segmentação das imagens, visando a extração de estruturas de interesse. A segmentação de forma manual é muitas vezes utilizada para este propósito. No entanto, esta abordagem demanda uma quantidade muito elevada de trabalho repetitivo principalmente considerando-se a técnica cine MR, cujos exames são, em geral, constituídos por centenas de imagens. Este artigo apresenta a descrição de um sistema desenvolvido para a segmentação do ventrículo esquerdo em seqüências de imagens obtidas por cine MR. O método de segmentação utilizado é a transformação Watershed com marcadores no contexto da Morfologia Matemática. Para a avaliação do sistema proposto foram feitos testes sistemáticos de segmentação com um conjunto de 10 exames e a partir destes foram realizadas análises comparativas abordando aspectos como variações intra e inter-operadores, comparação com a segmentação manual, variação volumétrica e coomparações das frações de ejeção. São apresentados neste artigo resultados obtidos nas comparações de alguns exames e uma discussão a respeito dos resultados completos.