RESUMO
Parkinson's disease (PD) is a chronic, progressive neurodegenerative disease and represents the most common disease of this type, after Alzheimer's dementia. It is characterized by motor and nonmotor features and by a long prodromal stage that lasts many years. Genetic research has shown that PD is a complex and multisystem disorder. To capture the molecular complexity of this disease we used a complex network approach. We maximized the information entropy of the gene co-expression matrix betweenness to obtain a gene adjacency matrix; then we used a fast greedy algorithm to detect communities. Finally we applied principal component analysis on the detected gene communities, with the ultimate purpose of discriminating between PD patients and healthy controls by means of a random forests classifier. We used a publicly available substantia nigra microarray dataset, GSE20163, from NCBI GEO database, containing gene expression profiles for 10 PD patients and 18 normal controls. With this methodology we identified two gene communities that discriminated between the two groups with mean accuracy of 0.88 ± 0.03 and 0.84 ± 0.03, respectively, and validated our results on an independent microarray experiment. The two gene communities presented a considerable reduction in size, over 100 times, compared to the initial network and were stable within a range of tested parameters. Further research focusing on the restricted number of genes belonging to the selected communities may reveal essential mechanisms responsible for PD at a network level and could contribute to the discovery of new biomarkers for PD.
Assuntos
Biologia Computacional/métodos , Expressão Gênica , Marcadores Genéticos , Doença de Parkinson/genética , Substância Negra/metabolismo , Algoritmos , Entropia , Humanos , Substância Negra/patologia , Substância Negra/fisiopatologiaRESUMO
In this study we present a novel fully automated Hippocampal Unified Multi-Atlas-Networks (HUMAN) algorithm for the segmentation of the hippocampus in structural magnetic resonance imaging. In multi-atlas approaches atlas selection is of crucial importance for the accuracy of the segmentation. Here we present an optimized method based on the definition of a small peri-hippocampal region to target the atlas learning with linear and non-linear embedded manifolds. All atlases were co-registered to a data driven template resulting in a computationally efficient method that requires only one test registration. The optimal atlases identified were used to train dedicated artificial neural networks whose labels were then propagated and fused to obtain the final segmentation. To quantify data heterogeneity and protocol inherent effects, HUMAN was tested on two independent data sets provided by the Alzheimer's Disease Neuroimaging Initiative and the Open Access Series of Imaging Studies. HUMAN is accurate and achieves state-of-the-art performance (Dice[Formula: see text] and Dice[Formula: see text]). It is also a robust method that remains stable when applied to the whole hippocampus or to sub-regions (patches). HUMAN also compares favorably with a basic multi-atlas approach and a benchmark segmentation tool such as FreeSurfer.
Assuntos
Algoritmos , Doença de Alzheimer/patologia , Hipocampo/patologia , Interpretação de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Neuroimagem/métodos , Humanos , Redes Neurais de Computação , Reconhecimento Automatizado de PadrãoRESUMO
The hippocampus has a key role in a number of neurodegenerative diseases, such as Alzheimer's Disease. Here we present a novel method for the automated segmentation of the hippocampus from structural magnetic resonance images (MRI), based on a combination of multiple classifiers. The method is validated on a cohort of 50 T1 MRI scans, comprehending healthy control, mild cognitive impairment, and Alzheimer's Disease subjects. The preliminary release of the EADC-ADNI Harmonized Protocol training labels is used as gold standard. The fully automated pipeline consists of a registration using an affine transformation, the extraction of a local bounding box, and the classification of each voxel in two classes (background and hippocampus). The classification is performed slice-by-slice along each of the three orthogonal directions of the 3D-MRI using a Random Forest (RF) classifier, followed by a fusion of the three full segmentations. Dice coefficients obtained by multiple RF (0.87 ± 0.03) are larger than those obtained by a single monolithic RF applied to the entire bounding box, and are comparable to state-of-the-art. A test on an external cohort of 50 T1 MRI scans shows that the presented method is robust and reliable. Additionally, a comparison of local changes in the morphology of the hippocampi between the three subject groups is performed. Our work showed that a multiple classification approach can be implemented for the segmentation for the measurement of volume and shape changes of the hippocampus with diagnostic purposes.
Assuntos
Algoritmos , Hipocampo , Imageamento Tridimensional/métodos , Imageamento por Ressonância MagnéticaRESUMO
The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a primary role in the pathogenesis of other neurological and psychiatric diseases. This study presents a fully automated pattern recognition system for an accurate and reproducible segmentation of the hippocampus in structural Magnetic Resonance Imaging (MRI). The method was validated on a mixed cohort of 56 T1-weighted structural brain images, and consists of three processing levels: (a) Linear registration: all brain images were registered to a standard template and an automated method was applied to capture the global shape of the hippocampus. (b) Feature extraction: all voxels included in the previously selected volume were characterized by 315 features computed from local information. (c) Voxel classification: a Random Forest algorithm was used to classify voxels as belonging or not belonging to the hippocampus. In order to improve the classification performance, an adaptive learning method based on the use of the Pearson's correlation coefficient was developed. The segmentation results (Dice similarity index = 0.81 ± 0.03) compare well with other state-of-the art approaches. A validation study was conducted on an independent dataset of 100 T1-weighted brain images, achieving significantly better results than those obtained with FreeSurfer.