How path integration abilities of blind people change in different exploration conditions.

For animals to locate resources and stay safe, navigation is an essential cognitive skill. Blind people use different navigational strategies to encode the environment. Path integration significantly influences spatial navigation, which is the ongoing update of position and orientation during self-motion. This study examines two separate things: (i) how guided and non-guided strategies affect blind individuals in encoding and mentally representing a trajectory and (ii) the sensory preferences for potential navigational aids through questionnaire-based research. This study first highlights the significant role that the absence of vision plays in understanding body centered and proprioceptive cues. Furthermore, it also underscores the urgent need to develop navigation-assistive technologies customized to meet the specific needs of users.

Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities.

Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.

Computational modeling of human multisensory spatial representation by a neural architecture.

Our brain constantly combines sensory information in unitary percept to build coherent representations of the environment. Even though this process could appear smooth, integrating sensory inputs from various sensory modalities must overcome several computational issues, such as recoding and statistical inferences problems. Following these assumptions, we developed a neural architecture replicating humans' ability to use audiovisual spatial representations. We considered the well-known ventriloquist illusion as a benchmark to evaluate its phenomenological plausibility. Our model closely replicated human perceptual behavior, proving a truthful approximation of the brain's ability to develop audiovisual spatial representations. Considering its ability to model audiovisual performance in a spatial localization task, we release our model in conjunction with the dataset we recorded for its validation. We believe it will be a powerful tool to model and better understand multisensory integration processes in experimental and rehabilitation environments.

Nanocatalyst-Enabled Physically Unclonable Functions as Smart Anticounterfeiting Tags with AI-Aided Smartphone Authentication.

Counterfeiting is a worldwide issue affecting many industrial sectors, ranging from specialized technologies to retail market, such as fashion brands, pharmaceutical products, and consumer electronics. Counterfeiting is not only a huge economic burden (>$ 1 trillion losses/year), but it also represents a serious risk to human health, for example, due to the exponential increase of fake drugs and food products invading the market. Considering such a global problem, numerous anticounterfeit technologies have been recently proposed, mostly based on tags. The most advanced category, based on encryption and cryptography, is represented by physically unclonable functions (PUFs). A PUF tag is based on a unique physical object generated through chemical methods with virtually endless possible combinations, providing remarkable encoding capability. However, most methods adopted nowadays are based on expensive and complex technologies, relying on instrumental readouts, which make them not effective in real-world applications. To achieve a simple yet cryptography-based anticounterfeit method, herein we exploit a combination of nanotechnology, chemistry, and artificial intelligence (AI). Notably, we developed platinum nanocatalyst-enabled visual tags, exhibiting the properties of PUFs (encoding capability >10300) along with fast (1 min) ON/OFF readout and full reversibility, enabling multiple onsite authentication cycles. The development of an accurate AI-aided algorithm powers the system, allowing for smartphone-based PUF authentications.

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.

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.

Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets.

In this article, we explore the correlation between people trajectories and their head orientations. We argue that people trajectory and head pose forecasting can be modelled as a joint problem. Recent approaches on trajectory forecasting leverage short-term trajectories (aka tracklets) of pedestrians to predict their future paths. In addition, sociological cues, such as expected destination or pedestrian interaction, are often combined with tracklets. In this article, we propose MiXing-LSTM (MX-LSTM) to capture the interplay between positions and head orientations (vislets) thanks to a joint unconstrained optimization of full covariance matrices during the LSTM backpropagation. We additionally exploit the head orientations as a proxy for the visual attention, when modeling social interactions. MX-LSTM predicts future pedestrians location and head pose, increasing the standard capabilities of the current approaches on long-term trajectory forecasting. Compared to the state-of-the-art, our approach shows better performances on an extensive set of public benchmarks. MX-LSTM is particularly effective when people move slowly, i.e., the most challenging scenario for all other models. The proposed approach also allows for accurate predictions on a longer time horizon.

Revisiting Projective Structure from Motion: A Robust and Efficient Incremental Solution.

This paper presents a solution to the Projective Structure from Motion (PSfM) problem able to deal efficiently with missing data, outliers and, for the first time, large scale 3D reconstruction scenarios. By embedding the projective depths into the projective parameters of the points and views, we decrease the number of unknowns to estimate and improve computational speed by optimizing standard linear Least Squares systems instead of homogeneous ones. In order to do so, we show that an extension of the linear constraints from the Generalized Projective Reconstruction Theorem can be transferred to the projective parameters, ensuring also a valid projective reconstruction in the process. We use an incremental approach that, starting from a solvable sub-problem, incrementally adds views and points until completion with a robust, outliers free, procedure. To prevent error accumulation, a refinement based on alternation between new estimations of views and points is used. This can also be done with constrained non-linear optimization. Experiments with simulated data shows that our approach is performing well, both in term of the quality of the reconstruction and the capacity to handle missing data and outliers with a reduced computational time. Finally, results on real datasets shows the ability of the method to be used in medium and large scale 3D reconstruction scenarios with high ratios of missing data (up to 98 percent).

Machine learning approach for single molecule localisation microscopy.

Single molecule localisation (SML) microscopy is a fundamental tool for biological discoveries; it provides sub-diffraction spatial resolution images by detecting and localizing "all" the fluorescent molecules labeling the structure of interest. For this reason, the effective resolution of SML microscopy strictly depends on the algorithm used to detect and localize the single molecules from the series of microscopy frames. To adapt to the different imaging conditions that can occur in a SML experiment, all current localisation algorithms request, from the microscopy users, the choice of different parameters. This choice is not always easy and their wrong selection can lead to poor performance. Here we overcome this weakness with the use of machine learning. We propose a parameter-free pipeline for SML learning based on support vector machine (SVM). This strategy requires a short supervised training that consists in selecting by the user few fluorescent molecules (∼ 10-20) from the frames under analysis. The algorithm has been extensively tested on both synthetic and real acquisitions. Results are qualitatively and quantitatively consistent with the state of the art in SML microscopy and demonstrate that the introduction of machine learning can lead to a new class of algorithms competitive and conceived from the user point of view.

3D Object Localisation from Multi-View Image Detections.

In this work we present a novel approach to recover objects 3D position and occupancy in a generic scene using only 2D object detections from multiple view images. The method reformulates the problem as the estimation of a quadric (ellipsoid) in 3D given a set of 2D ellipses fitted to the object detection bounding boxes in multiple views. We show that a closed-form solution exists in the dual-space using a minimum of three views while a solution with two views is possible through the use of non-linear optimisation and object constraints on the size of the object shape. In order to make the solution robust toward inaccurate bounding boxes, a likely occurrence in object detection methods, we introduce a data preconditioning technique and a non-linear refinement of the closed form solution based on implicit subspace constraints. Results on synthetic tests and on different real datasets, involving challenging scenarios, demonstrate the applicability and potential of our method in several realistic scenarios.

Nanoscale Molecular Reorganization of the Inhibitory Postsynaptic Density Is a Determinant of GABAergic Synaptic Potentiation.

Gephyrin is a key scaffold protein mediating the anchoring of GABAA receptors at inhibitory synapses. Here, we exploited superresolution techniques combined with proximity-based clustering analysis and model simulations to investigate the single-molecule gephyrin reorganization during plasticity of inhibitory synapses in mouse hippocampal cultured neurons. This approach revealed that, during the expression of inhibitory LTP, the increase of gephyrin density at postsynaptic sites is associated with the promoted formation of gephyrin nanodomains. We demonstrate that the gephyrin rearrangement in nanodomains stabilizes the amplitude of postsynaptic currents, indicating that, in addition to the number of synaptic GABAA receptors, the nanoscale distribution of GABAA receptors in the postsynaptic area is a crucial determinant for the expression of inhibitory synaptic plasticity. In addition, the methodology implemented here clears the way to the application of the graph-based theory to single-molecule data for the description and quantification of the spatial organization of the synapse at the single-molecule level.SIGNIFICANCE STATEMENT The mechanisms of inhibitory synaptic plasticity are poorly understood, mainly because the size of the synapse is below the diffraction limit, thus reducing the effectiveness of conventional optical and imaging techniques. Here, we exploited superresolution approaches combined with clustering analysis to study at unprecedented resolution the distribution of the inhibitory scaffold protein gephyrin in response to protocols inducing LTP of inhibitory synaptic responses (iLTP). We found that, during the expression of iLTP, the increase of synaptic gephyrin is associated with the fragmentation of gephyrin in subsynaptic nanodomains. We demonstrate that such synaptic gephyrin nanodomains stabilize the amplitude of inhibitory postsynaptic responses, thus identifying the nanoscale gephyrin rearrangement as a key determinant for inhibitory synaptic plasticity.

Bilinear modeling via augmented Lagrange multipliers (BALM).

This paper presents a unified approach to solve different bilinear factorization problems in computer vision in the presence of missing data in the measurements. The problem is formulated as a constrained optimization where one of the factors must lie on a specific manifold. To achieve this, we introduce an equivalent reformulation of the bilinear factorization problem that decouples the core bilinear aspect from the manifold specificity. We then tackle the resulting constrained optimization problem via Augmented Lagrange Multipliers. The strength and the novelty of our approach is that this framework can seamlessly handle different computer vision problems. The algorithm is such that only a projector onto the manifold constraint is needed. We present experiments and results for some popular factorization problems in computer vision such as rigid, non-rigid, and articulated Structure from Motion, photometric stereo, and 2D-3D non-rigid registration.

Live-cell 3D super-resolution imaging in thick biological samples.

We demonstrate three-dimensional (3D) super-resolution live-cell imaging through thick specimens (50-150 µm), by coupling far-field individual molecule localization with selective plane illumination microscopy (SPIM). The improved signal-to-noise ratio of selective plane illumination allows nanometric localization of single molecules in thick scattering specimens without activating or exciting molecules outside the focal plane. We report 3D super-resolution imaging of cellular spheroids.