Intelligent digital tools for screening of brain connectivity and dementia risk estimation in people affected by mild cognitive impairment: the AI-Mind clinical study protocol

More than 10 million Europeans show signs of mild cognitive impairment (MCI), a transitional stage between normal brain aging and dementia stage memory disorder. The path MCI takes can be divergent; while some maintain stability or even revert to cognitive norms, alarmingly, up to half of the cases progress to dementia within 5 years. Current diagnostic practice lacks the necessary screening tools to identify those at risk of progression. The European patient experience often involves a long journey from the initial signs of MCI to the eventual diagnosis of dementia. The trajectory is far from ideal. Here, we introduce the AI-Mind project, a pioneering initiative with an innovative approach to early risk assessment through the implementation of advanced artificial intelligence (AI) on multimodal data. The cutting-edge AI-based tools developed in the project aim not only to accelerate the diagnostic process but also to deliver highly accurate predictions regarding an individual's risk of developing dementia when prevention and intervention may still be possible. AI-Mind is a European Research and Innovation Action (RIA H2020-SC1-BHC-06-2020, No. 964220) financed between 2021 and 2026. First, the AI-Mind Connector identifies dysfunctional brain networks based on high-density magneto- and electroencephalography (M/EEG) recordings. Second, the AI-Mind Predictor predicts dementia risk using data from the Connector, enriched with computerized cognitive tests, genetic and protein biomarkers, as well as sociodemographic and clinical variables. AI-Mind is integrated within a network of major European initiatives, including The Virtual Brain, The Virtual Epileptic Patient, and EBRAINS AISBL service for sensitive data, HealthDataCloud, where big patient data are generated for advancing digital and virtual twin technology development. AI-Mind's innovation lies not only in its early prediction of dementia risk, but it also enables a virtual laboratory scenario for hypothesis-driven personalized intervention research. This article introduces the background of the AI-Mind project and its clinical study protocol, setting the stage for future scientific contributions.

SynCoPa: Visualizing Connectivity Paths and Synapses Over Detailed Morphologies

Brain complexity has traditionally fomented the division of neuroscience into somehow separated compartments; the coexistence of the anatomical, physiological, and connectomics points of view is just a paradigmatic example of this situation. However, there are times when it is important to combine some of these standpoints for getting a global picture, like for fully analyzing the morphological and topological features of a specific neuronal circuit. Within this framework, this article presents SynCoPa, a tool designed for bridging gaps among representations by providing techniques that allow combining detailed morphological neuron representations with the visualization of neuron interconnections at the synapse level. SynCoPa has been conceived for the interactive exploration and analysis of the connectivity elements and paths of simple to medium complexity neuronal circuits at the connectome level. This has been done by providing visual metaphors for synapses and interconnection paths, in combination with the representation of detailed neuron morphologies. SynCoPa could be helpful, for example, for establishing or confirming a hypothesis about the spatial distributions of synapses, or for answering questions about the way neurons establish connections or the relationships between connectivity and morphological features. Last, SynCoPa is easily extendable to include functional data provided, for example, by any of the morphologically-detailed simulators available nowadays, such as Neuron and Arbor, for providing a deep insight into the circuits features prior to simulating it, in particular any analysis where it is important to combine morphology, network topology, and physiology.

ConGen—A Simulator-Agnostic Visual Language for Definition and Generation of Connectivity in Large and Multiscale Neural Networks

An open challenge on the road to unraveling the brain's multilevel organization is establishing techniques to research connectivity and dynamics at different scales in time and space, as well as the links between them. This work focuses on the design of a framework that facilitates the generation of multiscale connectivity in large neural networks using a symbolic visual language capable of representing the model at different structural levels—ConGen. This symbolic language allows researchers to create and visually analyze the generated networks independently of the simulator to be used, since the visual model is translated into a simulator-independent language. The simplicity of the front end visual representation, together with the simulator independence provided by the back end translation, combine into a framework to enhance collaboration among scientists with expertise at different scales of abstraction and from different fields. On the basis of two use cases, we introduce the features and possibilities of our proposed visual language and associated workflow. We demonstrate that ConGen enables the creation, editing, and visualization of multiscale biological neural networks and provides a whole workflow to produce simulation scripts from the visual representation of the model.

Neuronize v2: Bridging the Gap Between Existing Proprietary Tools to Optimize Neuroscientific Workflows

Knowledge about neuron morphology is key to understanding brain structure and function. There are a variety of software tools that are used to segment and trace the neuron morphology. However, these tools usually utilize proprietary formats. This causes interoperability problems since the information extracted with one tool cannot be used in other tools. This article aims to improve neuronal reconstruction workflows by facilitating the interoperability between two of the most commonly used software tools—Neurolucida (NL) and Imaris (Filament Tracer). The new functionality has been included in an existing tool—Neuronize—giving rise to its second version. Neuronize v2 makes it possible to automatically use the data extracted with Imaris Filament Tracer to generate a tracing with dendritic spine information that can be read directly by NL. It also includes some other new features, such as the ability to unify and/or correct inaccurately-formed meshes (i.e., dendritic spines) and to calculate new metrics. This tool greatly facilitates the process of neuronal reconstruction, bridging the gap between existing proprietary tools to optimize neuroscientific workflows.

ViSimpl: Multi-View Visual Analysis of Brain Simulation Data

After decades of independent morphological and functional brain research, a key point in neuroscience nowadays is to understand the combined relationships between the structure of the brain and its components and their dynamics on multiple scales, ranging from circuits of neurons at micro or mesoscale to brain regions at macroscale. With such a goal in mind, there is a vast amount of research focusing on modeling and simulating activity within neuronal structures, and these simulations generate large and complex datasets which have to be analyzed in order to gain the desired insight. In such context, this paper presents ViSimpl, which integrates a set of visualization and interaction tools that provide a semantic view of brain data with the aim of improving its analysis procedures. ViSimpl provides 3D particle-based rendering that allows visualizing simulation data with their associated spatial and temporal information, enhancing the knowledge extraction process. It also provides abstract representations of the time-varying magnitudes supporting different data aggregation and disaggregation operations and giving also focus and context clues. In addition, ViSimpl tools provide synchronized playback control of the simulation being analyzed. Finally, ViSimpl allows performing selection and filtering operations relying on an application called NeuroScheme. All these views are loosely coupled and can be used independently, but they can also work together as linked views, both in centralized and distributed computing environments, enhancing the data exploration and analysis procedures.

PyramidalExplorer: A New Interactive Tool to Explore Morpho-Functional Relations of Human Pyramidal Neurons

This work presents PyramidalExplorer, a new tool to interactively explore and reveal the detailed organization of the microanatomy of pyramidal neurons with functionally related models. It consists of a set of functionalities that allow possible regional differences in the pyramidal cell architecture to be interactively discovered by combining quantitative morphological information about the structure of the cell with implemented functional models. The key contribution of this tool is the morpho-functional oriented design that allows the user to navigate within the 3D dataset, filter and perform Content-Based Retrieval operations. As a case study, we present a human pyramidal neuron with over 9000 dendritic spines in its apical and basal dendritic trees. Using PyramidalExplorer, we were able to find unexpected differential morphological attributes of dendritic spines in particular compartments of the neuron, revealing new aspects of the morpho-functional organization of the pyramidal neuron.

Musical representation of dendritic spine distribution: a new exploratory tool

Dendritic spines are small protrusions along the dendrites of many types of neurons in the central nervous system and represent the major target of excitatory synapses. For this reason, numerous anatomical, physiological and computational studies have focused on these structures. In the cerebral cortex the most abundant and characteristic neuronal type are pyramidal cells (about 85 % of all neurons) and their dendritic spines are the main postsynaptic target of excitatory glutamatergic synapses. Thus, our understanding of the synaptic organization of the cerebral cortex largely depends on the knowledge regarding synaptic inputs to dendritic spines of pyramidal cells. Much of the structural data on dendritic spines produced by modern neuroscience involves the quantitative analysis of image stacks from light and electron microscopy, using standard statistical and mathematical tools and software developed to this end. Here, we present a new method with musical feedback for exploring dendritic spine morphology and distribution patterns in pyramidal neurons. We demonstrate that audio analysis of spiny dendrites with apparently similar morphology may “sound” quite different, revealing anatomical substrates that are not apparent from simple visual inspection. These morphological/music translations may serve as a guide for further mathematical analysis of the design of the pyramidal neurons and of spiny dendrites in general.