AI models for automated segmentation of engineered polycystic kidney tubules.

Autosomal dominant polycystic kidney disease (ADPKD) is a monogenic, rare disease, characterized by the formation of multiple cysts that grow out of the renal tubules. Despite intensive attempts to develop new drugs or repurpose existing ones, there is currently no definitive cure for ADPKD. This is primarily due to the complex and variable pathogenesis of the disease and the lack of models that can faithfully reproduce the human phenotype. Therefore, the development of models that allow automated detection of cysts' growth directly on human kidney tissue is a crucial step in the search for efficient therapeutic solutions. Artificial Intelligence methods, and deep learning algorithms in particular, can provide powerful and effective solutions to such tasks, and indeed various architectures have been proposed in the literature in recent years. Here, we comparatively review state-of-the-art deep learning segmentation models, using as a testbed a set of sequential RGB immunofluorescence images from 4 in vitro experiments with 32 engineered polycystic kidney tubules. To gain a deeper understanding of the detection process, we implemented both pixel-wise and cyst-wise performance metrics to evaluate the algorithms. Overall, two models stand out as the best performing, namely UNet++ and UACANet: the latter uses a self-attention mechanism introducing some explainability aspects that can be further exploited in future developments, thus making it the most promising algorithm to build upon towards a more refined cyst-detection platform. UACANet model achieves a cyst-wise Intersection over Union of 0.83, 0.91 for Recall, and 0.92 for Precision when applied to detect large-size cysts. On all-size cysts, UACANet averages at 0.624 pixel-wise Intersection over Union. The code to reproduce all results is freely available in a public GitHub repository.

UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images.

Purpose: The aim of this work is the development and characterization of a model observer (MO) based on convolutional neural networks (CNNs), trained to mimic human observers in image evaluation in terms of detection and localization of low-contrast objects in CT scans acquired on a reference phantom. The final goal is automatic image quality evaluation and CT protocol optimization to fulfill the ALARA principle. Approach: Preliminary work was carried out to collect localization confidence ratings of human observers for signal presence/absence from a dataset of 30,000 CT images acquired on a PolyMethyl MethAcrylate phantom containing inserts filled with iodinated contrast media at different concentrations. The collected data were used to generate the labels for the training of the artificial neural networks. We developed and compared two CNN architectures based respectively on Unet and MobileNetV2, specifically adapted to achieve the double tasks of classification and localization. The CNN evaluation was performed by computing the area under localization-ROC curve (LAUC) and accuracy metrics on the test dataset. Results: The mean of absolute percentage error between the LAUC of the human observer and MO was found to be below 5% for the most significative test data subsets. An elevated inter-rater agreement was achieved in terms of S-statistics and other common statistical indices. Conclusions: Very good agreement was measured between the human observer and MO, as well as between the performance of the two algorithms. Therefore, this work is highly supportive of the feasibility of employing CNN-MO combined with a specifically designed phantom for CT protocol optimization programs.

Discovering functional connectivity features characterizing multiple sclerosis phenotypes using explainable artificial intelligence.

Multiple sclerosis (MS) is a neurological condition characterized by severe structural brain damage and by functional reorganization of the main brain networks that try to limit the clinical consequences of structural burden. Resting-state (RS) functional connectivity (FC) abnormalities found in this condition were shown to be variable across different MS phases, according to the severity of clinical manifestations. The article describes a system exploiting machine learning on RS FC matrices to discriminate different MS phenotypes and to identify relevant functional connections for MS stage characterization. To this end, the system exploits some mathematical properties of covariance-based RS FC representation, which can be described by a Riemannian manifold. The classification performance of the proposed framework was significantly above the chance level for all MS phenotypes. Moreover, the proposed system was successful in identifying relevant RS FC alterations contributing to an accurate phenotype classification.

AIforCOVID: Predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study.

Recent epidemiological data report that worldwide more than 53 million people have been infected by SARS-CoV-2, resulting in 1.3 million deaths. The disease has been spreading very rapidly and few months after the identification of the first infected, shortage of hospital resources quickly became a problem. In this work we investigate whether artificial intelligence working with chest X-ray (CXR) scans and clinical data can be used as a possible tool for the early identification of patients at risk of severe outcome, like intensive care or death. Indeed, further to induce lower radiation dose than computed tomography (CT), CXR is a simpler and faster radiological technique, being also more widespread. In this respect, we present three approaches that use features extracted from CXR images, either handcrafted or automatically learnt by convolutional neuronal networks, which are then integrated with the clinical data. As a further contribution, this work introduces a repository that collects data from 820 patients enrolled in six Italian hospitals in spring 2020 during the first COVID-19 emergency. The dataset includes CXR images, several clinical attributes and clinical outcomes. Exhaustive evaluation shows promising performance both in 10-fold and leave-one-centre-out cross-validation, suggesting that clinical data and images have the potential to provide useful information for the management of patients and hospital resources.

Investigating the spectral features of the brain meso-scale structure at rest.

Recent studies provide novel insights into the meso-scale organization of the brain, highlighting the co-occurrence of different structures: classic assortative (modular), disassortative, and core-periphery. However, the spectral properties of the brain meso-scale remain mostly unexplored. To fill this knowledge gap, we investigated how the meso-scale structure is organized across the frequency domain. We analyzed the resting state activity of healthy participants with source-localized high-density electroencephalography signals. Then, we inferred the community structure using weighted stochastic block-model (WSBM) to capture the landscape of meso-scale structures across the frequency domain. We found that different meso-scale modalities co-exist and are diversely organized over the frequency spectrum. Specifically, we found a core-periphery structure dominance, but we also highlighted a selective increase of disassortativity in the low frequency bands (<8 Hz), and of assortativity in the high frequency band (30-50 Hz). We further described other features of the meso-scale organization by identifying those brain regions which, at the same time, (a) exhibited the highest degree of assortativity, disassortativity, and core-peripheriness (i.e., participation) and (b) were consistently assigned to the same community, irrespective from the granularity imposed by WSBM (i.e., granularity-invariance). In conclusion, we observed that the brain spontaneous activity shows frequency-specific meso-scale organization, which may support spatially distributed and local information processing.

Structurally constrained effective brain connectivity.

The relationship between structure and function is of interest in many research fields involving the study of complex biological processes. In neuroscience in particular, the fusion of structural and functional data can help to understand the underlying principles of the operational networks in the brain. To address this issue, this paper proposes a constrained autoregressive model leading to a representation of effective connectivity that can be used to better understand how the structure modulates the function. Or simply, it can be used to find novel biomarkers characterizing groups of subjects. In practice, an initial structural connectivity representation is re-weighted to explain the functional co-activations. This is obtained by minimizing the reconstruction error of an autoregressive model constrained by the structural connectivity prior. The model has been designed to also include indirect connections, allowing to split direct and indirect components in the functional connectivity, and it can be used with raw and deconvoluted BOLD signal. The derived representation of dependencies was compared to the well known dynamic causal model, giving results closer to known ground-truth. Further evaluation of the proposed effective network was performed on two typical tasks. In a first experiment the direct functional dependencies were tested on a community detection problem, where the brain was partitioned using the effective networks across multiple subjects. In a second experiment the model was validated in a case-control task, which aimed at differentiating healthy subjects from individuals with autism spectrum disorder. Results showed that using effective connectivity leads to clusters better describing the functional interactions in the community detection task, while maintaining the original structural organization, and obtaining a better discrimination in the case-control classification task.

Addressing signal alterations induced in CT images by deep learning processing: A preliminary phantom study.

PURPOSE: We investigate, by an extensive quality evaluation approach, performances and potential side effects introduced in Computed Tomography (CT) images by Deep Learning (DL) processing. METHOD: We selected two relevant processing steps, denoise and segmentation, implemented by two Convolutional Neural Networks (CNNs) models based on autoencoder architecture (encoder-decoder and UNet) and trained for the two tasks. In order to limit the number of uncontrolled variables, we designed a phantom containing cylindrical inserts of different sizes, filled with iodinated contrast media. A large CT image dataset was collected at different acquisition settings and two reconstruction algorithms. We characterized the CNNs behavior using metrics from the signal detection theory, radiological and conventional image quality parameters, and finally unconventional radiomic features analysis. RESULTS: The UNet, due to the deeper architecture complexity, outperformed the shallower encoder-decoder in terms of conventional quality parameters and preserved spatial resolution. We also studied how the CNNs modify the noise texture by using radiomic analysis, identifying sensitive and insensitive features to the denoise processing. CONCLUSIONS: The proposed evaluation approach proved effective to accurately analyze and quantify the differences in CNNs behavior, in particular with regard to the alterations introduced in the processed images. Our results suggest that even a deeper and more complex network, which achieves good performances, is not necessarily a better network because it can modify texture features in an unwanted way.

Modeling a population of retinal ganglion cells with restricted Boltzmann machines.

The retina is a complex circuit of the central nervous system whose aim is to encode visual stimuli prior the higher order processing performed in the visual cortex. Due to the importance of its role, modeling the retina to advance in interpreting its spiking activity output is a well studied problem. In particular, it has been shown that latent variable models can be used to model the joint distribution of Retinal Ganglion Cells (RGCs). In this work, we validate the applicability of Restricted Boltzmann Machines to model the spiking activity responses of a large a population of RGCs recorded with high-resolution electrode arrays. In particular, we show that latent variables can encode modes in the RGC activity distribution that are closely related to the visual stimuli. In contrast to previous work, we further validate our findings by comparing results associated with recordings from retinas under normal and altered encoding conditions obtained by pharmacological manipulation. In these conditions, we observe that the model reflects well-known physiological behaviors of the retina. Finally, we show that we can also discover temporal patterns, associated with distinct dynamics of the stimuli.

Multi-branch convolutional neural network for multiple sclerosis lesion segmentation.

In this paper, we present an automated approach for segmenting multiple sclerosis (MS) lesions from multi-modal brain magnetic resonance images. Our method is based on a deep end-to-end 2D convolutional neural network (CNN) for slice-based segmentation of 3D volumetric data. The proposed CNN includes a multi-branch downsampling path, which enables the network to encode information from multiple modalities separately. Multi-scale feature fusion blocks are proposed to combine feature maps from different modalities at different stages of the network. Then, multi-scale feature upsampling blocks are introduced to upsize combined feature maps to leverage information from lesion shape and location. We trained and tested the proposed model using orthogonal plane orientations of each 3D modality to exploit the contextual information in all directions. The proposed pipeline is evaluated on two different datasets: a private dataset including 37 MS patients and a publicly available dataset known as the ISBI 2015 longitudinal MS lesion segmentation challenge dataset, consisting of 14 MS patients. Considering the ISBI challenge, at the time of submission, our method was amongst the top performing solutions. On the private dataset, using the same array of performance metrics as in the ISBI challenge, the proposed approach shows high improvements in MS lesion segmentation compared with other publicly available tools.

MultiLink Analysis: Brain Network Comparison via Sparse Connectivity Analysis.

The analysis of the brain from a connectivity perspective is revealing novel insights into brain structure and function. Discovery is, however, hindered by the lack of prior knowledge used to make hypotheses. Additionally, exploratory data analysis is made complex by the high dimensionality of data. Indeed, to assess the effect of pathological states on brain networks, neuroscientists are often required to evaluate experimental effects in case-control studies, with hundreds of thousands of connections. In this paper, we propose an approach to identify the multivariate relationships in brain connections that characterize two distinct groups, hence permitting the investigators to immediately discover the subnetworks that contain information about the differences between experimental groups. In particular, we are interested in data discovery related to connectomics, where the connections that characterize differences between two groups of subjects are found. Nevertheless, those connections do not necessarily maximize the accuracy in classification since this does not guarantee reliable interpretation of specific differences between groups. In practice, our method exploits recent machine learning techniques employing sparsity to deal with weighted networks describing the whole-brain macro connectivity. We evaluated our technique on functional and structural connectomes from human and murine brain data. In our experiments, we automatically identified disease-relevant connections in datasets with supervised and unsupervised anatomy-driven parcellation approaches and by using high-dimensional datasets.

A novel unsupervised analysis of electrophysiological signals reveals new sleep substages in mice.

Sleep science is entering a new era, thanks to new data-driven analysis approaches that, combined with mouse gene-editing technologies, show a promise in functional genomics and translational research. However, the investigation of sleep is time consuming and not suitable for large-scale phenotypic datasets, mainly due to the need for subjective manual annotations of electrophysiological states. Moreover, the heterogeneous nature of sleep, with all its physiological aspects, is not fully accounted for by the current system of sleep stage classification. In this study, we present a new data-driven analysis approach offering a plethora of novel features for the characterization of sleep. This novel approach allowed for identifying several substages of sleep that were hidden to standard analysis. For each of these substages, we report an independent set of homeostatic responses following sleep deprivation. By using our new substages classification, we have identified novel differences among various genetic backgrounds. Moreover, in a specific experiment with the Zfhx3 mouse line, a recent circadian mutant expressing both shortening of the circadian period and abnormal sleep architecture, we identified specific sleep states that account for genotypic differences at specific times of the day. These results add a further level of interaction between circadian clock and sleep homeostasis and indicate that dissecting sleep in multiple states is physiologically relevant and can lead to the discovery of new links between sleep phenotypes and genetic determinants. Therefore, our approach has the potential to significantly enhance the understanding of sleep physiology through the study of single mutations. Moreover, this study paves the way to systematic high-throughput analyses of sleep.

Unsupervised Spike Sorting for Large-Scale, High-Density Multielectrode Arrays.

We present a method for automated spike sorting for recordings with high-density, large-scale multielectrode arrays. Exploiting the dense sampling of single neurons by multiple electrodes, an efficient, low-dimensional representation of detected spikes consisting of estimated spatial spike locations and dominant spike shape features is exploited for fast and reliable clustering into single units. Millions of events can be sorted in minutes, and the method is parallelized and scales better than quadratically with the number of detected spikes. Performance is demonstrated using recordings with a 4,096-channel array and validated using anatomical imaging, optogenetic stimulation, and model-based quality control. A comparison with semi-automated, shape-based spike sorting exposes significant limitations of conventional methods. Our approach demonstrates that it is feasible to reliably isolate the activity of up to thousands of neurons and that dense, multi-channel probes substantially aid reliable spike sorting.

Non-parametric temporal modeling of the hemodynamic response function via a liquid state machine.

Standard methods for the analysis of functional MRI data strongly rely on prior implicit and explicit hypotheses made to simplify the analysis. In this work the attention is focused on two such commonly accepted hypotheses: (i) the hemodynamic response function (HRF) to be searched in the BOLD signal can be described by a specific parametric model e.g., double-gamma; (ii) the effect of stimuli on the signal is taken to be linearly additive. While these assumptions have been empirically proven to generate high sensitivity for statistical methods, they also limit the identification of relevant voxels to what is already postulated in the signal, thus not allowing the discovery of unknown correlates in the data due to the presence of unexpected hemodynamics. This paper tries to overcome these limitations by proposing a method wherein the HRF is learned directly from data rather than induced from its basic form assumed in advance. This approach produces a set of voxel-wise models of HRF and, as a result, relevant voxels are filterable according to the accuracy of their prediction in a machine learning framework. This approach is instantiated using a temporal architecture based on the paradigm of Reservoir Computing wherein a Liquid State Machine is combined with a decoding Feed-Forward Neural Network. This splits the modeling into two parts: first a representation of the complex temporal reactivity of the hemodynamic response is determined by a universal global "reservoir" which is essentially temporal; second an interpretation of the encoded representation is determined by a standard feed-forward neural network, which is trained by the data. Thus the reservoir models the temporal state of information during and following temporal stimuli in a feed-back system, while the neural network "translates" this data to fit the specific HRF response as given, e.g. by BOLD signal measurements in fMRI. An empirical analysis on synthetic datasets shows that the learning process can be robust both to noise and to the varying shape of the underlying HRF. A similar investigation on real fMRI datasets provides evidence that BOLD predictability allows for discrimination between relevant and irrelevant voxels for a given set of stimuli.

Bridging the gap in connectomic studies: A particle filtering framework for estimating structural connectivity at network scale.

The ultimate goal of neuroscience is understanding the brain at a functional level. This requires the investigation of the structural connectivity at multiple scales: from the single-neuron micro-connectomics to the brain-region macro-connectomics. In this work, we address the study of connectomics at the intermediate mesoscale, introducing a probabilistic approach capable of reconstructing complex topologies of large neuronal networks. Suitable directional features are designed to model the local neuritic architecture and a feature-based particle filtering framework is proposed which allows the spatial tracking of neurites on microscopy images. The experimental results on cultures of increasing complexity, grown on High-Density Micro Electrode Arrays, show good stability and performance as compared to ground truth annotations drawn by domain experts. We also show how the method can be used to dissect the structural connectivity of inhibitory and excitatory subnetworks opening new perspectives towards the investigation of functional interactions among multiple cellular populations.

Sleep-stage scoring in mice: The influence of data pre-processing on a system's performance.

Sleep-stage analysis in mice and rats has received growing attention in recent years, due to the fact that mice display electrical activity during sleep which has underlying similarities with that of human sleep. Both conventional manual and automatic sleep-wakefulness scoring are rule based tasks which use brain waves measured by Electroencephalogram (EEG) and activity detected by Electromyography (EMG) of skeletal muscles. Several works have been conducted trying to provide an automatic sleep-scoring system on the basis of machine learning methods. In this study we try to understand the reasons behind the complexity of this problem and we emphasize the importance of normalization procedure that leads to a better stage discrimination comparing different classification methods.

Functional connectivity estimation over large networks at cellular resolution based on electrophysiological recordings and structural prior.

Despite many structural and functional aspects of the brain organization have been extensively studied in neuroscience, we are still far from a clear understanding of the intricate structure-function interactions occurring in the multi-layered brain architecture, where billions of different neurons are involved. Although structure and function can individually convey a large amount of information, only a combined study of these two aspects can probably shade light on how brain circuits develop and operate at the cellular scale. Here, we propose a novel approach for refining functional connectivity estimates within neuronal networks using the structural connectivity as prior. This is done at the mesoscale, dealing with thousands of neurons while reaching, at the microscale, an unprecedented cellular resolution. The High-Density Micro Electrode Array (HD-MEA) technology, combined with fluorescence microscopy, offers the unique opportunity to acquire structural and functional data from large neuronal cultures approaching the granularity of the single cell. In this work, an advanced method based on probabilistic directional features and heat propagation is introduced to estimate the structural connectivity from the fluorescence image while functional connectivity graphs are obtained from the cross-correlation analysis of the spiking activity. Structural and functional information are then integrated by reweighting the functional connectivity graph based on the structural prior. Results show that the resulting functional connectivity estimates are more coherent with the network topology, as compared to standard measures purely based on cross-correlations and spatio-temporal filters. We finally use the obtained results to gain some insights on which features of the functional activity are more relevant to characterize actual neuronal interactions.

Group-wise functional community detection through joint Laplacian diagonalization.

There is a growing conviction that the understanding of the brain function can come through a deeper knowledge of the network connectivity between different brain areas. Resting state Functional Magnetic Resonance Imaging (rs-fMRI) is becoming one of the most important imaging modality widely used to understand network functionality. However, due to the variability at subject scale, mapping common networks across individuals is by now a real challenge. In this work we present a novel approach to group-wise community detection, i.e. identification of functional coherent sub-graphs across multiple subjects. This approach is based on a joint diagonalization of two or more graph Laplacians, aiming at finding a common eigenspace across individuals, over which clustering in fewer dimension can then be applied. This allows to identify common sub-networks across different graphs. We applied our method to rs-fMRI dataset of mouse brain finding most important sub-networks recently described in literature.

Describing the Conformational Landscape of Small Organic Molecules through Gaussian Mixtures in Dihedral Space.

Due to the well-known structure-function paradigm, conformational equilibrium plays a major role in molecular recognition. Therefore, a deep understanding of the conformational profile of small organic molecules is an essential prerequisite to modern computer-assisted drug design. However, a thorough analysis and a meaningful representation of the conformational landscape of drug-like molecules remains a challenge. The thermodynamic equilibrium of conformational states can be described in terms of probability density function (PDF) defined in the space of the relevant degrees of freedom of the system. In principle, this PDF could be estimated by traditional histogram methods, which are, however, hampered by several limitations when the variables forming the space are more than two or three. Here, we present an unsupervised parametric fitting procedure based on cluster analysis, aimed at estimating the PDF in the conformational space of small drug-like molecules with low sensitivity to data dimensionality. Indeed, data are represented in the dihedral space of the molecule and clustered using a simple adaptation of the standard k-means algorithm for periodic data. In the final step of the analysis, the PDF is derived as a linear combination of multivariate circular Gaussian distributions. We show that exploiting the analytic properties of Gaussian distributions, the proposed approach makes it possible to analyze the conformational ensemble in higher dimensional spaces with several advantages over the histogram-based methods. The posterior analysis of the PDF also helps identify a minimal subset of variables able to provide a meaningful representation of the conformational space. We tested our approach on alanine dipeptide, alanine tetrapeptide, and rilpivirine with satisfactory results compared to standard histogram-based methods and to those based on chemical intuition.

Chronic and acute intranasal oxytocin produce divergent social effects in mice.

Intranasal administration of oxytocin (OXT) might be a promising new adjunctive therapy for mental disorders characterized by social behavioral alterations such as autism and schizophrenia. Despite promising initial studies in humans, it is not yet clear the specificity of the behavioral effects induced by chronic intranasal OXT and if chronic intranasal OXT could have different effects compared with single administration. This is critical for the aforementioned chronic mental disorders that might potentially involve life-long treatments. As a first step to address these issues, here we report that chronic intranasal OXT treatment in wild-type C57BL/6J adult mice produced a selective reduction of social behaviors concomitant to a reduction of the OXT receptors throughout the brain. Conversely, acute intranasal OXT treatment produced partial increases in social behaviors towards opposite-sex novel-stimulus female mice, while on the other hand, it decreased social exploration of same-sex novel stimulus male mice, without affecting social behavior towards familiar stimulus male mice. Finally, prolonged exposure to intranasal OXT treatments did not alter, in wild-type animals, parameters of general health such as body weight, locomotor activity, olfactory and auditory functions, nor parameters of memory and sensorimotor gating abilities. These results indicate that a prolonged over-stimulation of a 'healthy' oxytocinergic brain system, with no inherent deficits in social interaction and normal endogenous levels of OXT, results in specific detrimental effects in social behaviors.