Marianna La Rocca

A Multiplex Network Model to Characterize Brain Atrophy in Structural MRI

We developed a multiplex network approach for the description and recognition of structural brain changes in the context of the early diagnosis of Alzheimer disease (AD). Our techniques can supply a convenient mathematical framework to model structural inter- and intra-subject brain similarities in magnetic resonance images (MRI) within Alzheimer disease studies. We used a set of 100 structural T1 brain scans, from subjects of the Alzheimer’s Disease Neuroimaging Initiative, including AD patients, normal controls (NC) and mild cognitive impairment (MCI) subjects. We evaluated the classification performances including the comparison of two state-of-the-art techniques, Random Forests (RF) and Support Vector Machines (SVM) . Our results show that multiplex networks can significantly improve the classification performance obtained only with the use of structural features. They can also effectively distinguish NC, MCI and AD patterns with an area under the receiver-operating-characteristic curve (AUC) \(\ge 0.89 \pm 0.04\).

Salient Networks: A Novel Application to Study Brain Connectivity

Extracting meaningful structures and data, thus unveiling the underlying base of knowledge, is a common challenging task in social, physical and life sciences. In this paper we apply a novel complex network approach based on the detection of salient links to reveal the effect of atrophy on brain connectivity. Starting from structural Magnetic Resonance Imaging (MRI) data, we firstly define a complex network model of brain connectivity, then we show how salient networks extracted from the original ones can emphasize the presence of the disease significantly reducing data complexity and computational requirements. As a proof of concept, we discuss the experimental results on a mixed cohort of 29 normal controls (NC) and 38 Alzheimer disease (AD) patients from the Alzheimer Disease Neuroimaging Initiative (ADNI). In particular, the proposed framework can reach state-of-the-art classification performances with an area under the curve \(\mathrm{AUC} = 0.93\, \pm \, 0.01\) for the NC-AD classification.

Multivariate regression analysis of structural MRI connectivity matrices in Alzheimer’s disease

Alzheimer’s disease (AD) is the most common form of dementia among older people and increasing longevity ensures its prevalence will rise even further. Whether AD originates by disconnecting a localized brain area and propagates to the rest of the brain across disease-severity progression is a question with an unknown answer. An important related challenge is to predict whether a given subject, with a mild cognitive impairment (MCI), will convert or not to AD. Here, our aim is to characterize the structural connectivity pattern of MCI and AD subjects using the multivariate distance matrix regression (MDMR) analysis, and to compare it to those of healthy subjects. MDMR is a technique developed in genomics that has been recently applied to functional brain network data, and here applied to identify brain nodes with different connectivity patterns, in controls and patients, because of brain atrophy. We address this issue at the macroscale by looking to differences in individual structural MRI brain networks, obtained from MR images according to a recently proposed definition of connectivity which measures the image similarity between patches at different locations in the brain. In particular, using data from ADNI, we selected four groups of subjects (all of them matched by age and sex): HC (healthy control participants), ncMCI (mild cognitive impairment not converting to AD), cMCI (mild cognitive impairment converting to AD) and AD. Next, we built structural MRI brain networks and performed group comparison for all the pairs of groups. Our results were three-fold: (i) considering the comparison of HC with the three other groups, the number of significant brain regions was 4 for ncMCI, 290 for cMCI and 74 for AD, out of a total of 549 regions; hence, in terms of the structural MRI connectivity here adopted, cMCI subjects have the maximal altered pattern w.r.t. healthy conditions. (ii) Eight and seven nodes were significant for the comparisons AD-ncMCI and AD-cMCI, respectively; six nodes, among them, were significant in both comparisons and these nodes form a connected brain region (corresponding to hippocampus, amygdala, Parahippocampal Gyrus, Planum Polare, Frontal Orbital Cortex, Temporal Pole and subcallosal cortex) showing reduced strength of connectivity in the MCI stages; (iii) The connectivity maps of cMCI and ncMCI subjects significantly differ from the connectome of healthy subjects in three regions all corresponding to Frontal Orbital Cortex.

Topological Complex Networks Properties for Gene Community Detection Strategy: DRD2 Case Study

Gene interactions can suitably be modeled as communities through weighted complex networks. However, the problem to efficiently detect these communities , eventually gaining biological insight from them, is still an open question. This paper presents a novel data-driven strategy for community detection and tests it on the specific case study of DRD2 gene coding for the D2 dopamine receptor, which plays a prominent role in risk for Schizophrenia . We adopt a combined use of centrality and topological properties to detect an optimal network partition. We find that 21 genes belongs with our target community with probability \(P \ge 90\,\%\). The robustness of the partition is assessed with two independent methodologies: (i) fuzzy c-means and (ii) consensus analyses . We use the first one to measure how strong the membership of these genes to the DRD2 community is and the latter to confirm the stability of the detected partition. These results show an interesting reduction (\({\sim }80\,\%\)) of the target community size. Moreover, to allow this validation on different case studies, the proposed methodology is available on an open cloud infrastructure, according to the Software as a Service paradigm (SaaS).

A novel approach to brain connectivity reveals early structural changes in Alzheimer’s disease

OBJECTIVE Recent studies have shown that complex networks along with diffusion weighted imaging (DWI) can be efficient and promising techniques for early detection of structural pathological changes in Alzheimers disease. Besides, connectivity studies, specifically assessing the organization of a graph and its topology, could represent the best chance to discover how brain activity is shaped and driven. Accordingly, we propose a methodology to evaluate how Alzheimers disease affects brain networks through a novel way to look at graph connectivity. In fact, we use the combination of network features related to brain organization with network features related to the variations in connectivity between several subjects. APPROACH From a DWI brain scan we reconstruct a probabilistic tractography by evaluating the number of white matter fibers connecting two anatomical districts, thus obtaining a weighted undirected network. The nodes of this network are the cerebral regions provided by the reference brain atlas, the weights are the intensity of linkage among them. We investigated brain connectivity graphs retrieved from a set of 222 publicly available DWI scans from the Alzheimers Disease Neuroimaging Initiative (ADNI): 47 Alzheimers disease (AD) patients, 52 normal controls (NC) and 123 mild cognitive impairment (MCI) subjects, this latter cohort includes 85 early and 38 late MCI subjects, EMCI and LMCI respectively. MAIN RESULTS The proposed brain connectivity approach effectively characterizes Alzheimers disease, especially in its early stages. In fact, MCI is a prodromal phase of Alzheimers disease. We report a [Formula: see text] accuracy for the discrimination of NC and AD subjects and accuracies of [Formula: see text] and [Formula: see text] for the discrimination of MCI from respectively NC and AD subjects. SIGNIFICANCE Our complex network approach offers an innovative and effective instrument to model brain connectivity and detect in DWI tractographies early changes due to Alzheimers.

Complex networks reveal early MRI markers of Parkinson’s disease

HighlightsOur work demonstrates that MRI data, and in particular complex network measures, provide an efficient and accurate description of PD patterns;Novel MRI markers combined with clinical scores typical of prodromal PD can be used for an accurate early diagnosis;The proposed approach compares favorably with state‐of‐the‐art methodologies basing on MRI data;This work demonstrates that MRI data allows diagnostic accuracy which compares well with methodologies including other imaging modalities such as SPECT. Graphical abstract Figure. No caption available. ABSTRACT Parkinsons disease (PD) is the most common neurological disorder, after Alzheimers disease, and is characterized by a long prodromal stage lasting up to 20 years. As age is a prominent factor risk for the disease, next years will see a continuous increment of PD patients, making urgent the development of efficient strategies for early diagnosis and treatments. We propose here a novel approach based on complex networks for accurate early diagnoses using magnetic resonance imaging (MRI) data; our approach also allows us to investigate which are the brain regions mostly affected by the disease. First of all, we define a network model of brain regions and associate to each region proper connectivity measures. Thus, each brain is represented through a feature vector encoding the local relationships brain regions interweave. Then, Random Forests are used for feature selection and learning a compact representation. Finally, we use a Support Vector Machine to combine complex network features with clinical scores typical of PD prodromal phase and provide a diagnostic index. We evaluated the classification performance on the Parkinsons Progression Markers Initiative (PPMI) database, including a mixed cohort of 169 normal controls (NC) and 374 PD patients. Our model compares favorably with existing state‐of‐the‐art MRI approaches. Besides, as a difference with previous approaches, our methodology ranks the brain regions according to disease effects without any a priori assumption.

A multi-layer MRI description of Parkinson's disease

Magnetic resonance imaging (MRI) along with complex network is currently one of the most widely adopted techniques for detection of structural changes in neurological diseases, such as Parkinsons Disease (PD). In this paper, we present a digital image processing study, within the multi-layer network framework, combining more classifiers to evaluate the informative power of the MRI features, for the discrimination of normal controls (NC) and PD subjects. We define a network for each MRI scan; the nodes are the sub-volumes (patches) the images are divided into and the links are defined using the Pearsons pairwise correlation between patches. We obtain a multi-layer network whose important network features, obtained with different feature selection methods, are used to feed a supervised multi-level random forest classifier which exploits this base of knowledge for accurate classification. Method evaluation has been carried out using T1 MRI scans of 354 individuals, including 177 PD subjects and 177 NC from the Parkinsons Progression Markers Initiative (PPMI) database. The experimental results demonstrate that the features obtained from multiplex networks are able to accurately describe PD patterns. Besides, also if a privileged scale for studying PD disease exists, exploring the informative content of more scales leads to a significant improvement of the performances in the discrimination between disease and healthy subjects. In particular, this method gives a comprehensive overview of brain regions statistically affected by the disease, an additional value to the presented study.

Machine learning for the assessment of Alzheimer's disease through DTI

Digital imaging techniques have found several medical applications in the development of computer aided detection systems, especially in neuroimaging. Recent advances in Diffusion Tensor Imaging (DTI) aim to discover biological markers for the early diagnosis of Alzheimer’s disease (AD), one of the most widespread neurodegenerative disorders. We explore here how different supervised classification models provide a robust support to the diagnosis of AD patients. We use DTI measures, assessing the structural integrity of white matter (WM) fiber tracts, to reveal patterns of disrupted brain connectivity. In particular, we provide a voxel-wise measure of fractional anisotropy (FA) and mean diffusivity (MD), thus identifying the regions of the brain mostly affected by neurodegeneration, and then computing intensity features to feed supervised classification algorithms. In particular, we evaluate the accuracy of discrimination of AD patients from healthy controls (HC) with a dataset of 80 subjects (40 HC, 40 AD), from the Alzheimer’s Disease Neurodegenerative Initiative (ADNI). In this study, we compare three state-of-the-art classification models: Random Forests, Naive Bayes and Support Vector Machines (SVMs). We use a repeated five-fold cross validation framework with nested feature selection to perform a fair comparison between these algorithms and evaluate the information content they provide. Results show that AD patterns are well localized within the brain, thus DTI features can support the AD diagnosis.