Support vector machine-based classification of neuroimages in Alzheimer's disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals

Objective: To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer's disease (AD). Method: Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. Results: The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. Conclusion: In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.

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.

Support vector machine-based classification of neuroimages in Alzheimer's disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals.

OBJECTIVE: To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer's disease (AD). METHOD: Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. RESULTS: The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. CONCLUSION: In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.

Correlação entre volume tireoidiano determinado pelo método de ultrassonografia versus cintilografia e sua implicação em cálculos dosimétricos na terapia com radioiodo na doença de Graves / Correlation between thyroid volume determined either by ultrasound or by scintigraphy and its implications in dosimetric radioiodine calculations in Graves disease treatment

INTRODUÇÃO: A doença de Graves (DG) é a causa mais comum de hipertireoidismo e, entre as abordagens terapêuticas mais utilizadas para o tratamento do hipertireoidismo por doença de Graves, encontram-se a cirurgia, o uso de drogas antitireoidianas e a radioiodoterapia. No cálculo dosimétrico para determinação da dose de radioiodo a ser utilizada, é possível empregar a ultrassonografia e a cintilografia para avaliar o volume tireoidiano. OBJETIVO: O presente estudo visa correlacionar essas metodologias com ênfase no volume obtido e nas implicações dosimétricas. SUJEITOS E MÉTODOS: Foram incluídos no estudo 103 pacientes com diagnóstico de DG encaminhados para radioiodoterapia. Esses foram submetidos à ultrassonografia da tireoide e à cintilografia tireoidiana, com cálculo de volume pela cintilografia baseado na fórmula de Allen. RESULTADOS E CONCLUSÕES: Observou-se boa correlação entre os dois métodos, porém com massa estimada pela cintilografia sistematicamente maior que a estimada pela ultrassonografia, o que pode acarretar em menor estimativa de dose absorvida quando utilizado o método cintilográfico.

INTRODUCTION: Graves disease (GD) is the most common cause of hiperthyroidism, and the most common treatment options are surgery, antithyroid drugs and radioiodine therapy. In radiodosimetric calculations to determine radioiodine dosage it is possible to use thyroid volume estimatives based on ultrasound or scintigraphy. OBJECTIVE: The present study aimed to correlate these methodologies emphasizing volume estimatives and dosimetric implications. SUBJECTS AND METHODS: Were included 103 patients with GD diagnosis and indication of radioiodine treatment. They were submitted to thyroid ultrasound and thyroid scintigraphy. RESULTS AND CONCLUSIONS: Good correlation between both methods was observed, although scintigraphy systematically obtained greater volumes than ultrasound implying in lower estimatives of absorbed dose when scintigraphy is used.

[Correlation between thyroid volume determined either by ultrasound or by scintigraphy and its implications in dosimetric radioiodine calculations in Graves disease treatment]. / Correlação entre volume tireoidiano determinado pelo método de ultrassonografia versus cintilografia e sua implicação em cálculos dosimétricos na terapia com radioiodo na doença de Graves.

INTRODUCTION: Graves disease (GD) is the most common cause of hiperthyroidism, and the most common treatment options are surgery, antithyroid drugs and radioiodine therapy. In radiodosimetric calculations to determine radioiodine dosage it is possible to use thyroid volume estimatives based on ultrasound or scintigraphy. OBJECTIVE: The present study aimed to correlate these methodologies emphasizing volume estimatives and dosimetric implications. SUBJECTS AND METHODS: Were included 103 patients with GD diagnosis and indication of radioiodine treatment. They were submitted to thyroid ultrasound and thyroid scintigraphy. RESULTS AND CONCLUSIONS: Good correlation between both methods was observed, although scintigraphy systematically obtained greater volumes than ultrasound implying in lower estimatives of absorbed dose when scintigraphy is used.

Baseline hippocampal theta oscillation speeds correlate with rate of operant task acquisition.

Many lines of evidence indicate that theta rhythm, a prominent neural oscillatory mode found in the mammalian hippocampus, plays a key role in the acquisition, processing, and retrieval of memories. However, a predictive neurophysiological feature of the baseline theta rhythm that correlates with the learning rate across different animals has yet to be identified. Here we show that the mean theta rhythm speed observed during baseline periods of immobility has a strong positive correlation with the rate at which rats learn an operant task. This relationship is observed across rats, during both quiet waking (r=0.82; p<0.01) and paradoxical sleep (r=0.83; p<0.01), suggesting that the basal theta frequency relates to basic neurological processes that are important in the acquisition of operant behavior.