Graph Neural Networks in Network Neuroscience.

Noninvasive medical neuroimaging has yielded many discoveries about the brain connectivity. Several substantial techniques mapping morphological, structural and functional brain connectivities were developed to create a comprehensive road map of neuronal activities in the human brain -namely brain graph. Relying on its non-euclidean data type, graph neural network (GNN) provides a clever way of learning the deep graph structure and it is rapidly becoming the state-of-the-art leading to enhanced performance in various network neuroscience tasks. Here we review current GNN-based methods, highlighting the ways that they have been used in several applications related to brain graphs such as missing brain graph synthesis and disease classification. We conclude by charting a path toward a better application of GNN models in network neuroscience field for neurological disorder diagnosis and population graph integration. The list of papers cited in our work is available at https://github.com/basiralab/GNNs-in-Network-Neuroscience.

A New Collaborative Classification Process for Microcalcification Detection Based on Graphs and Knowledge Propagation.

In this paper, we propose a new collaborative process that aims to detect macrocalcifications from mammographic images while minimizing false negative detections. This process is made up of three main phases: suspicious area detection, candidate object identification, and collaborative classification. The main concept is to operate on the entire image divided into homogenous regions called superpixels which are used to identify both suspicious areas and candidate objects. The collaborative classification phase consists in making the initial results of different microcalcification detectors collaborate in order to produce a new common decision and reduce their initial disagreements. The detectors share the information about their detected objects and associated labels in order to refine their initial decisions based on those of the other collaborators. This refinement consists of iteratively updating the candidate object labels of each detector following local and contextual analyses based on prior knowledge about the links between super pixels and macrocalcifications. This process iteratively reduces the disagreement between different detectors and estimates local reliability terms for each super pixel. The final result is obtained by a conjunctive combination of the new detector decisions reached by the collaborative process. The proposed approach is evaluated on the publicly available INBreast dataset. Experimental results show the benefits gained in terms of improving microcalcification detection performances compared to existing detectors as well as ordinary fusion operators.

Toward new multi-wavelets: associated filters and algorithms. Part I: theoretical framework and investigation of biomedical signals, ECG, and coronavirus cases.

Biosignals are nowadays important subjects for scientific researches from both theory, and applications, especially, with the appearance of new pandemics threatening the humanity such as the new coronavirus. One aim in the present work is to prove that wavelets may be a successful machinery to understand such phenomena by applying a step forward extension of wavelets to multi-wavelets. We proposed in a first step to improve multi-wavelet notion by constructing more general families using independent components for multi-scaling and multi-wavelet mother functions. A special multi-wavelet is then introduced, continuous, and discrete multi-wavelet transforms are associated, as well as new filters, and algorithms of decomposition, and reconstruction. Applied breakthroughs of the paper may be summarized in three aims. In a first direction, an approximation (reconstruction) of a classical (stationary, periodic) example dealing with Fourier modes has been conducted in order to confirm the efficiency of the HSch multi-wavelets in approximating such signals and in providing fast algorithms. The second experimentation is concerned with the decomposition and reconstruction application of the HSch multi-wavelet on an ECG signal. The last experimentation is concerned with a de-noising application on a strain of coronavirus signal permitting to localize approximately the transmembrane segments of such a series as neighborhoods of the local maxima of an numerized version of the strain. Accuracy of the method has been evaluated by means of error estimates and statistical tests.

A new conditional region growing approach for microcalcification delineation in mammograms.

Microcalcifications (MCs) are considered as the first indicator of breast cancer development. Their morphology, in terms of shape and size, is considered as the most important criterion that determines their malignity degrees. Therefore, the accurate delineation of MC is a cornerstone step in their automatic diagnosis process. In this paper, we propose a new conditional region growing (CRG) approach with the ability of finding the accurate MC boundaries starting from selected seed points. The starting seed points are determined based on regional maxima detection and superpixel analysis. The region growing step is controlled by a set of criteria that are adapted to MC detection in terms of contrast and shape variation. These criteria are derived from prior knowledge to characterize MCs and can be divided into two categories. The first one concerns the neighbourhood searching size. The second one deals with the analysis of gradient information and shape evolution within the growing process. In order to prove the effectiveness and the reliability in terms of MC detection and delineation, several experiments have been carried out on MCs of various types, with both qualitative and quantitative analysis. The comparison of the proposed approach with state-of-the art proves the importance of the used criteria in the context of MC delineation, towards a better management of breast cancer. Graphical Abstract Flowchart of the proposed approach.

Brain multigraph prediction using topology-aware adversarial graph neural network.

Brain graphs (i.e, connectomes) constructed from medical scans such as magnetic resonance imaging (MRI) have become increasingly important tools to characterize the abnormal changes in the human brain. Due to the high acquisition cost and processing time of multimodal MRI, existing deep learning frameworks based on Generative Adversarial Network (GAN) focused on predicting the missing multimodal medical images from a few existing modalities. While brain graphs help better understand how a particular disorder can change the connectional facets of the brain, synthesizing a target brain multigraph (i.e, multiple brain graphs) from a single source brain graph is strikingly lacking. Additionally, existing graph generation works mainly learn one model for each target domain which limits their scalability in jointly predicting multiple target domains. Besides, while they consider the global topological scale of a graph (i.e., graph connectivity structure), they overlook the local topology at the node scale (e.g., how central a node is in the graph). To address these limitations, we introduce topology-aware graph GAN architecture (topoGAN), which jointly predicts multiple brain graphs from a single brain graph while preserving the topological structure of each target graph. Its three key innovations are: (i) designing a novel graph adversarial auto-encoder for predicting multiple brain graphs from a single one, (ii) clustering the encoded source graphs in order to handle the mode collapse issue of GAN and proposing a cluster-specific decoder, (iii) introducing a topological loss to force the prediction of topologically sound target brain graphs. The experimental results using five target domains demonstrated the outperformance of our method in brain multigraph prediction from a single graph in comparison with baseline approaches.

Brain graph synthesis by dual adversarial domain alignment and target graph prediction from a source graph.

Developing predictive intelligence in neuroscience for learning how to generate multimodal medical data from a single modality can improve neurological disorder diagnosis with minimal data acquisition resources. Existing deep learning frameworks are mainly tailored for images, which might fail in handling geometric data (e.g., brain graphs). Specifically, predicting a target brain graph from a single source brain graph remains largely unexplored. Solving such problem is generally challenged with domain fracturecaused by the difference in distribution between source and target domains. Besides, solving the prediction and domain fracture independently might not be optimal for both tasks. To address these challenges, we unprecedentedly propose a Learning-guided Graph Dual Adversarial Domain Alignment (LG-DADA) framework for predicting a target brain graph from a source brain graph. The proposed LG-DADA is grounded in three fundamental contributions: (1) a source data pre-clustering step using manifold learning to firstly handle source data heterogeneity and secondly circumvent mode collapse in generative adversarial learning, (2) a domain alignment of source domain to the target domain by adversarially learning their latent representations, and (3) a dual adversarial regularization that jointly learns a source embedding of training and testing brain graphs using two discriminators and predict the training target graphs. Results on morphological brain graphs synthesis showed that our method produces better prediction accuracy and visual quality as compared to other graph synthesis methods.

Brain graph super-resolution for boosting neurological disorder diagnosis using unsupervised multi-topology connectional brain template learning.

Existing graph analysis techniques generally focus on decreasing the dimensionality of graph data (i.e., removing nodes, edges, or both) in diverse predictive learning tasks in pattern recognition, computer vision, and medical data analysis such as dimensionality reduction, filtering and embedding techniques. However, graph super-resolution is strikingly lacking, i.e., the concept of super-resolving low-resolution (LR) graphs with nr nodes into high-resolution graphs (HR) with [Formula: see text] nodes. Particularly, learning how to automatically generate HR brain connectomes, without resorting to the computationally expensive MRI processing steps such as image registration and parcellation, remains unexplored. To fill this gap, we propose the first technique to super-resolve undirected fully connected graphs with application to brain connectomes. First, we root our brain graph super-resolution (BGSR) framework in learning how to estimate a centered LR population-based brain graph representation, coined as connectional brain template (CBT), acting as a proxy in the target BGSR task. Specifically, we hypothesize that the estimation of a well-representative and centered CBT would help better capture the individuality of each LR brain graph via its residual distance from the population-based CBT. This will eventually allow an accurate identification of the most similar individual graphs to a new testing graph in the LR domain for the target prediction task. Second, we leverage the estimated LR CBT (i.e., population mean) to derive residual LR brain graphs, capturing the deviation of all subjects from the estimated CBT. Third, we learn multi-topology LR graph manifolds using different graph topological measurements (e.g., degree, closeness, betweenness) by estimating residual LR similarity matrices modeling the relationship between pairs of residual LR graphs. These are then fused so we can effectively identify for each testing LR subject its most K similar training LR graphs. Last, the missing testing HR graph is predicted by averaging the HR graphs of the K selected training subjects. Predicted HR from LR functional brain graphs boosted classification results for autistic subjects by 16.48% compared with LR functional graphs.

Brain multiplexes reveal morphological connectional biomarkers fingerprinting late brain dementia states.

Accurate diagnosis of mild cognitive impairment (MCI) before conversion to Alzheimer's disease (AD) is invaluable for patient treatment. Many works showed that MCI and AD affect functional and structural connections between brain regions as well as the shape of cortical regions. However, 'shape connections' between brain regions are rarely investigated -e.g., how morphological attributes such as cortical thickness and sulcal depth of a specific brain region change in relation to morphological attributes in other regions. To fill this gap, we unprecedentedly design morphological brain multiplexes for late MCI/AD classification. Specifically, we use structural T1-w MRI to define morphological brain networks, each quantifying similarity in morphology between different cortical regions for a specific cortical attribute. Then, we define a brain multiplex where each intra-layer represents the morphological connectivity network of a specific cortical attribute, and each inter-layer encodes the similarity between two consecutive intra-layers. A significant performance gain is achieved when using the multiplex architecture in comparison to other conventional network analysis architectures. We also leverage this architecture to discover morphological connectional biomarkers fingerprinting the difference between late MCI and AD stages, which included the right entorhinal cortex and right caudal middle frontal gyrus.

Polyphenolic contents, antioxidant activities and UPLC-ESI-MS analysis of Haplophyllum tuberculatum A. Juss leaves extracts.

The aim of this study is to determine the phytochemical profile, the total polyphenolic contents and the antioxidant activities of Haplophyllum tuberculatum leaves extracts. The most active extracts were analyzed by ultra-high performance liquid chromatography coupled to electrospray ionization mass spectrometry. Antioxidant activities were screened by the 3-[4,5-dimethylthiazol-2-yl]-2,5 diphenyl tetrazolium bromide (MTT) test and measured by the 2,2-diphenyl-1-picrylhydrazyl (DPPH), 2,2-azinobis 3-ethylbenzothiazoline-6-sulfonic acid (ABTS) and ß-carotene bleaching inhibition assays. Phytochemical screening of the extracts revealed the presence of various secondary metabolites. The ethyl acetate extract was the richest extract in phenolics and flavonoids with 262mg gallic acid equivalents/g and 99.1mg quercetin equivalent/g of dry weight, respectively. The same extract showed an important scavenging effect on DPPH, ABTS and ß-carotene/linoleic acid with IC50 of 0.020mg/mL, 0.029mg/mL and 0.022mg/mL, respectively. The correlations between the antioxidant capacities and the polyphenolic content were ranging between 0.889 and 0.256 and occasionally found to be significant. The UPLC-ESI-MS analysis showed the presence of polyphenolic and alkaloid compounds. Arabelline, majidine, dictamine and a qudsine derivative are found for the first time in H. tuberculatum. The results indicate that polyphenolic and alkaloid compounds may be major contributors to the antioxidant activity of these extracts.

Biological properties of Hertia cheirifolia L. flower extracts and effect of the nopol on α-glucosidase.

In screening for antioxidant and α-glucosidase inhibitors from the extracts of Hertia cheirifolia L. flowers, the petroleum ether extract showed interesting antioxidant activity and inhibitory effect on the activity of α-glucosidase. The fractionation of this extract resulted in the isolation of a compound which is characterized by NMR and ESI-MS as a nopol. The nopol exhibited potent α-glucosidase inhibitory potential with IC50 value of 220µM. The kinetic evaluation indicated that it acts as a non-competitive inhibitor. A molecular docking study proved that the nopol presented a strong affinity with amino acid residues of α-glucosidase.

Antibacterial, antifungal and cytotoxic activities of two flavonoids from Retama raetam flowers.

We have investigated the antibacterial, antifungal and cytotoxic activities of two flavonoids isolated from Retama raetam flowers using the disc diffusion and micro-dilution broth methods. The cytotoxic activity was tested against Hep-2 cells using the MTT assay. The compounds licoflavone C (1) and derrone (2) were active against Pseudomonas aeruginosa and Escherichia coli (7.81-15.62 µg/mL) and showed important antifungal activity. Strong antifungal activity against Candida species (7.81 µg/mL) was for example found with compound 2. The tested compounds also showed strong cytotoxicity against Hep-2 cells. These two compounds may be interesting antimicrobial agents to be used against infectious diseases caused by many pathogens.

Spasmolytic and anti-inflammatory effects of constituents from Hertia cheirifolia.

A sesquiterpenoid Bakkenolide (1), and two steroids, (3beta, 22E)-Stigmasta-5, 22-diène-3-ol (Stigmasterol) (2) and stigmasterol 3beta-glucoside (3), isolated from the Hertia cheirifolia (L.) chloroform extract, were evaluated respectively for their spasmolytic and anti-inflammatory activities. We note that these natural products were isolated and purified for the first time from the specie Hertia cheirifolia. Their structures have been established by spectroscopy (1 and 2D NMR experiences) and mass spectrometry. Chloroform-, ethyl acetate- and methanol-extracts were also tested for their spasmolytic and anti-inflammatory activities. Spasmolytic and anti-inflammatory screening were based respectively on the contractile response effects on rat isolated smooth muscles and on the dose-related carrageenan induced paw edema in rats. screening of the crude extracts showed spasmolytic and anti-inflammatory positive results. The antispasmodic effect of Bakkenolide was found in the same range as that of Alverine, a standard musculotropic spasmolytic agent.

Mutagenic, antimutagenic and antioxidant activities of a new polyphenolic and a flavonoid substances isolated from Anagallis monelli.

A new polyphenolic natural substance: 2,5-dihydroxy-benzoic acid 3'-formyl-5'-hydroxy-phenyl ester (1), Anamighrinal and 3-(O-alpha-L-rhamnosyl) quercetin (2) have been isolated from the methanolic aerial part extract of the plant Anagallis monelli by chromatographic separation. Their structures have been deduced essentially by one and two NMR spectroscopic procedures and mass spectrometry. Antioxidant, mutagenic, antimutagenic activities, of the natural products were realised and positive results were recorded.

Mutagenic, antimutagenic and antioxidant activities of a new class of beta-glucoside hydroxyhydroquinone from Anagallis monelli growing in Tunisia.

A new skeleton of an O-heteroside natural substance named zinolol, the first representative of a new class of aminated hydroxyhydroquinone, has been isolated from the whole plant Anagallis monelli. Its structure has been established by one and two dimensional NMR spectroscopic procedures. Antioxidant, mutagenic, antimutagenic activities were realised and positive results were recorded.

Antimicrobial and antioxidant activities of the methanolic extracts of three Salvia species from Tunisia.

This study examines the in vitro antimicrobial and antioxidant activities of the methanolic extracts of three Salvia species from Tunisia: Salvia aegyptiaca L., S. argentea L. and S. verbenaca Ssp. clandestina L. Pugsley. The extracts inhibited the growth of dermatophytes and of bacteria responsible for unpleasant odours to varying degrees; the pathogenic yeasts Candida albicans and Cryptococcus neoformans, the filamentous fungi Aspergillus fumigatus and selected dog otitis bacteria were all resistant to each of the extracts. The extracts were screened for their antioxidant activities using 2,2-diphenyl-1-picrylhydrazyl free radical scavenging and 2,2'-azinobis(3-ethylbenzothiazoline-6-sulphonic acid) test systems, and gave positive results in both tests. The extracts of S. aegyptiaca were the most active in both tests, followed by those of S. verbenaca, then S. argentea. These results confirm the antimicrobial and antioxidant activities of the genus Salvia and underline the potential of these plants either as natural preservatives or in pharmaceutical applications.

A new biflavonoid and an isobiflavonoid from Rhus tripartitum.

A new biflavonoid masazinoflavanone (1) and the isobiflavonoid calodenone (2) have been isolated and characterized from the methanolic aerial part extract of the plant Rhus tripartitum. Their structures have been deduced from extensive spectral analysis (NMR and MS). Interpretation of the nuclear overhauser effects (NOESY) permitted us to establish relative stereochemistry of these natural products.