Harnessing the flexibility of neural networks to predict dynamic theoretical parameters underlying human choice behavior.

Reinforcement learning (RL) models are used extensively to study human behavior. These rely on normative models of behavior and stress interpretability over predictive capabilities. More recently, neural network models have emerged as a descriptive modeling paradigm that is capable of high predictive power yet with limited interpretability. Here, we seek to augment the expressiveness of theoretical RL models with the high flexibility and predictive power of neural networks. We introduce a novel framework, which we term theoretical-RNN (t-RNN), whereby a recurrent neural network is trained to predict trial-by-trial behavior and to infer theoretical RL parameters using artificial data of RL agents performing a two-armed bandit task. In three studies, we then examined the use of our approach to dynamically predict unseen behavior along with time-varying theoretical RL parameters. We first validate our approach using synthetic data with known RL parameters. Next, as a proof-of-concept, we applied our framework to two independent datasets of humans performing the same task. In the first dataset, we describe differences in theoretical RL parameters dynamic among clinical psychiatric vs. healthy controls. In the second dataset, we show that the exploration strategies of humans varied dynamically in response to task phase and difficulty. For all analyses, we found better performance in the prediction of actions for t-RNN compared to the stationary maximum-likelihood RL method. We discuss the use of neural networks to facilitate the estimation of latent RL parameters underlying choice behavior.

Genetic and behavioural factors affecting interpopulation colour pattern variation in two congeneric chameleon species.

We conducted a study on interpopulation variation of colour patterns in two congeneric chameleon species, which have an analogous life history. Both species are able to rapidly change colour pattern, and their context-dependent colour patterns often vary across a wide geographical range. Specifically, we tested four hypotheses that can explain the observed interpopulation variation of colour patterns by a series of behavioural field trials where the colour patterns of individuals were recorded and later analysed by a deep neural network algorithm. We used redundancy analysis to relate genetic, spectral and behavioural predictors to interpopulation colour pattern distance. Our results showed that both isolation by distance (IBD) and alternative mating tactics were significant predictors for interpopulation colour pattern variation in Chamaeleo chamaeleon males. By contrast, in Chamaeleo dilepis, the interpopulation colour pattern variation was largely explained by IBD, and evidence for alternative mating tactics was absent. In both chameleon species, the environmental colours showed no evidence of influencing chameleon interpopulation colour pattern variation, regardless of sex or behavioural context. This contrasting finding suggests that interpopulation context-dependent colour pattern variations in each species are maintained under a different set of selective pressures or circumstances.

Perturbed actin cap as a new personalized biomarker in primary fibroblasts of Huntington's disease patients.

Primary fibroblasts from patient's skin biopsies are directly isolated without any alteration in the genome, retaining in culture conditions their endogenous cellular characteristics and biochemical properties. The aim of this study was to identify a distinctive cell phenotype for potential drug evaluation in fibroblasts from Huntington's Disease (HD) patients, using image-based high content analysis. We show that HD fibroblasts have a distinctive nuclear morphology associated with a nuclear actin cap deficiency. This in turn affects cell motility in a similar manner to fibroblasts from Hutchinson-Gilford progeria syndrome (HGPS) patients used as known actin cap deficient cells. Moreover, treatment of the HD cells with either Latrunculin B, used to disrupt actin cap formation, or the antioxidant agent Mitoquinone, used to improve mitochondrial activity, show expected opposite effects on actin cap associated morphological features and cell motility. Deep data analysis allows strong cluster classification within HD cells according to patients' disease severity score which is distinct from HGPS and matching controls supporting that actin cap is a biomarker in HD patients' cells correlated with HD severity status that could be modulated by pharmacological agents as tool for personalized drug evaluation.

Toward next-generation endoscopes integrating biomimetic video systems, nonlinear optical microscopy, and deep learning.

According to the World Health Organization, the proportion of the world's population over 60 years will approximately double by 2050. This progressive increase in the elderly population will lead to a dramatic growth of age-related diseases, resulting in tremendous pressure on the sustainability of healthcare systems globally. In this context, finding more efficient ways to address cancers, a set of diseases whose incidence is correlated with age, is of utmost importance. Prevention of cancers to decrease morbidity relies on the identification of precursor lesions before the onset of the disease, or at least diagnosis at an early stage. In this article, after briefly discussing some of the most prominent endoscopic approaches for gastric cancer diagnostics, we review relevant progress in three emerging technologies that have significant potential to play pivotal roles in next-generation endoscopy systems: biomimetic vision (with special focus on compound eye cameras), non-linear optical microscopies, and Deep Learning. Such systems are urgently needed to enhance the three major steps required for the successful diagnostics of gastrointestinal cancers: detection, characterization, and confirmation of suspicious lesions. In the final part, we discuss challenges that lie en route to translating these technologies to next-generation endoscopes that could enhance gastrointestinal imaging, and depict a possible configuration of a system capable of (i) biomimetic endoscopic vision enabling easier detection of lesions, (ii) label-free in vivo tissue characterization, and (iii) intelligently automated gastrointestinal cancer diagnostic.

DeepFake Detection Based on Discrepancies Between Faces and Their Context.

We propose a method for detecting face swapping and other identity manipulations in single images. Face swapping methods, such as DeepFake, manipulate the face region, aiming to adjust the face to the appearance of its context, while leaving the context unchanged. We show that this modus operandi produces discrepancies between the two regions (e.g., Fig. 1). These discrepancies offer exploitable telltale signs of manipulation. Our approach involves two networks: (i) a face identification network that considers the face region bounded by a tight semantic segmentation, and (ii) a context recognition network that considers the face context (e.g., hair, ears, neck). We describe a method which uses the recognition signals from our two networks to detect such discrepancies, providing a complementary detection signal that improves conventional real versus fake classifiers commonly used for detecting fake images. Our method achieves state of the art results on the FaceForensics++ and Celeb-DF-v2 benchmarks for face manipulation detection, and even generalizes to detect fakes produced by unseen methods.

Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors.

Early intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae. We introduce a novel end-to-end neural network that employs resting-state and task-based functional MRI (fMRI) datasets, obtained one month after trauma exposure, to predict PTSD symptoms at one-, six- and fourteen-months after the exposure. FMRI data, as well as PTSD status and symptoms, were collected from adults at risk for PTSD development, after admission to emergency room following a traumatic event. Our computational method utilized a per-region encoder to extract brain regions embedding, which were subsequently updated by applying the algorithmic technique of pairwise attention. The affinities obtained between each pair of regions were combined to create a pairwise co-activation map used to perform multi-label classification. The results demonstrate that the novel method's performance in predicting PTSD symptoms, in a prospective manner, outperforms previous analytical techniques reported in the fMRI literature, all trained on the same dataset. We further show a high predictive ability for predicting PTSD symptom clusters and PTSD persistence. To the best of our knowledge, this is the first deep learning method applied on fMRI data with respect to prospective clinical outcomes, to predict PTSD status, severity and symptom clusters. Future work could further delineate the mechanisms that underlie such a prediction, and potentially improve single patient characterization.

Inverse design of unparametrized nanostructures by generating images from spectra.

Recently, there has been an increasing number of studies applying machine learning techniques for the design of nanostructures. Most of these studies train a deep neural network (DNN) to approximate the highly nonlinear function of the underlying physical mapping between spectra and nanostructures. At the end of training, the DNN allows an on-demand design of nanostructures, i.e., the model can infer nanostructure geometries for desired spectra. While these approaches have presented a new paradigm, they are limited in the complexity of the structures proposed, often bound to parametric geometries. Here we introduce spectra2pix, which is a DNN trained to generate 2D images of the target nanostructures. By predicting an image, our model architecture is not limited to a closed set of nanostructure shapes, and can be trained for the design of a much wider space of geometries. We show, for the first time, to the best of our knowledge, a successful generalization ability, by designing completely unseen shapes of geometries. We attribute the successful generalization to the ability of a pixel-wise architecture to learn local properties of the meta-material, therefore mimicking faithfully the underlying physical process. Importantly, beyond synthetical data, we show our model generalization capability on real experimental data.

Unsupervised Generation of Free-Form and Parameterized Avatars.

We study two problems involving the task of mapping images between different domains. The first problem, transfers an image in one domain to an analog image in another domain. The second problem, extends the previous one by mapping an input image to a tied pair, consisting of a vector of parameters and an image that is created using a graphical engine from this vector of parameters. Similar to the first problem, the mapping's objective is to have the output image as similar as possible to the input image. In both cases, no supervision is given during training in the form of matching inputs and outputs. We compare the two unsupervised learning problems to the problem of unsupervised domain adaptation, define generalization bounds that are based on discrepancy, and employ a GAN to implement network solutions that correspond to these bounds. Experimentally, our methods are shown to solve the problem of automatically creating avatars.

Microvascular Dynamics from 4D Microscopy Using Temporal Segmentation.

Recently developed methods for rapid continuous volumetric two-photon microscopy facilitate the observation of neuronal activity in hundreds of individual neurons and changes in blood flow in adjacent blood vessels across a large volume of living brain at unprecedented spatio-temporal resolution. However, the high imaging rate necessitates fully automated image analysis, whereas tissue turbidity and photo-toxicity limitations lead to extremely sparse and noisy imagery. In this work, we extend a recently proposed deep learning volumetric blood vessel segmentation network, such that it supports temporal analysis. With this technology, we are able to track changes in cerebral blood volume over time and identify spontaneous arterial dilations that propagate towards the pial surface. This new capability is a promising step towards characterizing the hemodynamic response function upon which functional magnetic resonance imaging (fMRI) is based.

Predicting Affect Classification in Mental Status Examination Using Machine Learning Face Action Recognition System: A Pilot Study in Schizophrenia Patients.

Classifying patients' affect is a pivotal part of the mental status examination. However, this common practice is often widely inconsistent between raters. Recent advances in the field of Facial Action Recognition (FAR) have enabled the development of tools that can act to identify facial expressions from videos. In this study, we aimed to explore the potential of using machine learning techniques on FAR features extracted from videotaped semi-structured psychiatric interviews of 25 male schizophrenia inpatients (mean age 41.2 years, STD = 11.4). Five senior psychiatrists rated patients' affect based on the videos. Then, a novel computer vision algorithm and a machine learning method were used to predict affect classification based on each psychiatrist affect rating. The algorithm is shown to have a significant predictive power for each of the human raters. We also found that the eyes facial area contributed the most to the psychiatrists' evaluation of the patients' affect. This study serves as a proof-of-concept for the potential of using the machine learning FAR system as a clinician-supporting tool, in an attempt to improve the consistency and reliability of mental status examination.

Plasmonic nanostructure design and characterization via Deep Learning.

Nanophotonics, the field that merges photonics and nanotechnology, has in recent years revolutionized the field of optics by enabling the manipulation of light-matter interactions with subwavelength structures. However, despite the many advances in this field, the design, fabrication and characterization has remained widely an iterative process in which the designer guesses a structure and solves the Maxwell's equations for it. In contrast, the inverse problem, i.e., obtaining a geometry for a desired electromagnetic response, remains a challenging and time-consuming task within the boundaries of very specific assumptions. Here, we experimentally demonstrate that a novel Deep Neural Network trained with thousands of synthetic experiments is not only able to retrieve subwavelength dimensions from solely far-field measurements but is also capable of directly addressing the inverse problem. Our approach allows the rapid design and characterization of metasurface-based optical elements as well as optimal nanostructures for targeted chemicals and biomolecules, which are critical for sensing, imaging and integrated spectroscopy applications.

Computer-Aided Recognition of Facial Attributes for Fetal Alcohol Spectrum Disorders.

OBJECTIVES: To compare the detection of facial attributes by computer-based facial recognition software of 2-D images against standard, manual examination in fetal alcohol spectrum disorders (FASD). METHODS: Participants were gathered from the Fetal Alcohol Syndrome Epidemiology Research database. Standard frontal and oblique photographs of children were obtained during a manual, in-person dysmorphology assessment. Images were submitted for facial analysis conducted by the facial dysmorphology novel analysis technology (an automated system), which assesses ratios of measurements between various facial landmarks to determine the presence of dysmorphic features. Manual blinded dysmorphology assessments were compared with those obtained via the computer-aided system. RESULTS: Areas under the curve values for individual receiver-operating characteristic curves revealed the computer-aided system (0.88 ± 0.02) to be comparable to the manual method (0.86 ± 0.03) in detecting patients with FASD. Interestingly, cases of alcohol-related neurodevelopmental disorder (ARND) were identified more efficiently by the computer-aided system (0.84 ± 0.07) in comparison to the manual method (0.74 ± 0.04). A facial gestalt analysis of patients with ARND also identified more generalized facial findings compared to the cardinal facial features seen in more severe forms of FASD. CONCLUSIONS: We found there was an increased diagnostic accuracy for ARND via our computer-aided method. As this category has been historically difficult to diagnose, we believe our experiment demonstrates that facial dysmorphology novel analysis technology can potentially improve ARND diagnosis by introducing a standardized metric for recognizing FASD-associated facial anomalies. Earlier recognition of these patients will lead to earlier intervention with improved patient outcomes.

Automatic recognition of the XLHED phenotype from facial images.

X-linked hypohidrotic ectodermal dysplasia (XLHED) is a genetic disorder that affects ectodermal structures and presents with a characteristic facial appearance. The ability of automated facial recognition technology to detect the phenotype from images was assessed . In Phase 1 of this study we examined if the age of male patients affected the technology's recognition. In Phase 2 we investigated how well the technology discriminated affected males cases from female carriers and from individuals with other ectodermal dysplasia syndromes. The system detected XLHED to be the most likely diagnosis in all genetically confirmed affected male patients of all ages, and in 55% of heterozygous females. Interestingly, patients with other ED syndromes were also detected by the XLHED-targeted analysis, consistent with shared developmental features. Thus the automated facial recognition system represents a promising non-invasive technology to screen patients at all ages for a possible diagnosis of ectodermal dysplasia, with greatest sensitivity and specificity for males affected with XLHED.

Glucose tolerance female-specific QTL mapped in collaborative cross mice.

Type-2 diabetes (T2D) is a complex metabolic disease characterized by impaired glucose tolerance. Despite environmental high risk factors, host genetic background is a strong component of T2D development. Herein, novel highly genetically diverse strains of collaborative cross (CC) lines from mice were assessed to map quantitative trait loci (QTL) associated with variations of glucose-tolerance response. In total, 501 mice of 58 CC lines were maintained on high-fat (42 % fat) diet for 12 weeks. Thereafter, an intraperitoneal glucose tolerance test (IPGTT) was performed for 180 min. Subsequently, the values of Area under curve for the glucose at zero and 180 min (AUC0-180), were measured, and used for QTL mapping. Heritability and coefficient of variations in glucose tolerance (CVg) were calculated. One-way analysis of variation was significant (P < 0.001) for AUC0-180 between the CC lines as well between both sexes. Despite Significant variations for both sexes, QTL analysis was significant, only for females, reporting a significant female-sex-dependent QTL (~2.5 Mbp) associated with IPGTT AUC0-180 trait, located on Chromosome 8 (32-34.5 Mbp, containing 51 genes). Gene browse revealed QTL for body weight/size, genes involved in immune system, and two main protein-coding genes involved in the Glucose homeostasis, Mboat4 and Leprotl1. Heritability and coefficient of genetic variance (CVg) were 0.49 and 0.31 for females, while for males, these values 0.34 and 0.22, respectively. Our findings demonstrate the roles of genetic factors controlling glucose tolerance, which significantly differ between sexes requiring independent studies for females and males toward T2D prevention and therapy.

Alternative Mating Tactics in Male Chameleons (Chamaeleo chamaeleon) Are Evident in Both Long-Term Body Color and Short-Term Courtship Pattern.

Alternative mating tactics in males of various taxa are associated with body color, body size, and social status. Chameleons are known for their ability to change body color following immediate environmental or social stimuli. In this study, we examined whether the differential appearance of male common chameleon during the breeding season is indeed an expression of alternative mating tactics. We documented body color of males and used computer vision techniques to classify images of individuals into discrete color patterns associated with seasons, individual characteristics, and social contexts. Our findings revealed no differences in body color and color patterns among males during the non-breeding season. However, during the breeding season males appeared in several color displays, which reflected body size, social status, and behavioral patterns. Furthermore, smaller and younger males resembled the appearance of small females. Consequently, we suggest that long-term color change in males during the breeding season reflects male alternative mating tactics. Upon encounter with a receptive female, males rapidly alter their appearance to that of a specific brief courtship display, which reflects their social status. The females, however, copulated indiscriminately in respect to male color patterns. Thus, we suggest that the differential color patterns displayed by males during the breeding season are largely aimed at inter-male signaling.

[Telemedicine: a novel service in pediatric emergency care].

INTRODUCTION: Telemedicine is a field that deals with monitoring and caring for patients who are physically apart from the caregivers, so they cannot communicate without technological means. The use of telemedicine has been recognized by a number of official organizations worldwide. This article reviews a unique service, "pediatrician online", provided by Clalit HMO, through Medtrix Ltd, with Schneider Children's Hospital specialists' supervision. With this service, parents can receive medical consultation from pediatricians beyond community clinic hours. The service is provided by telephone, computer or a mobile application, and when possible video calls are made. AIMS: To describe and analyze four years of telemedicine experience of the "pediatrician online" service. METHODS: A retrospective study was performed including analysis of all consultation calls conducted between November 2009 (the beginning of the project) and December 2013. Every call to the service was recorded and documented. Furthermore, analysis was conducted of follow-up calls to 4% of the applicants in order to monitor medical outcome and satisfaction. RESULTS: During the first four years approximately half a million consultation calls were provided. The average time from referral to obtaining medical advice was eight minutes. The duration of the consultation was four and a half minutes on average. Most of the calls were related to young children under 4 years (74%), dealing with common pediatric problems - fever (23%), respiratory complaints (17%), and gastrointestinal problems (12%). One-third of the applicants intended to go to the emergency department before they called the service, but only about one-sixth were referred at the end of the consultation. Among those referred, only about 60% actually went to the emergency department. The use of video-calls has been increasing, and reached an average of 30% of the applications. Satisfaction with the service was very high according to surveys, scoring 9.8 out of ten. Eighty-two percent of patients sampled reported medical improvement on the next day. CONCLUSIONS: There is a very high demand for consulting pediatricians beyond clinic hours. The use of telemedicine, as provided by the "pediatrician online" service, addresses this need safely and effectively with high patient satisfaction. Discussion: The use of telemedicine is expected to expand. In order to ensure its proper use while recognizing the capabilities and limitations, controlled studies should be conducted, exploring the outcome of different approaches in various situations.

Characterization of facial phenotypes of children with congenital hypopituitarism and their parents: a matched case-control study.

Congenital Hypopituitarism (CH) has traditionally been associated with specific facial phenotypes subsumed under the term midface retrusion, based on cephalometric studies. In this study, we used a systematic anthropometric approach to facial morphology in 37 individuals with CH and their parents, primarily of French Canadian ancestry, and compared them to a control group of 78 French Canadian patients with well-controlled type 1 diabetes and their parents. We were able to demonstrate clear morphological differences, which were more prevalent in the affected group than in the control group. More specifically, we showed the presence of a shorter skull base width (P < 0.001) and reduced inner canthal distance (P = 0.006) in the CH face, as well as a relative underdevelopment of the mandible (P = 0.001). These findings were present in individuals of all ages, and were independent of the duration of growth hormone treatment (median treatment 90.8 months; range 7.2-175.8 months). In addition, skull base width was significantly reduced in both mothers and fathers of affected children compared to the parents of the controls (P < 0.001), despite comparable parental heights, supporting an underlying genetic etiology. Such extensive phenotypic studies have not been done in congenital hypopituitarism and will provide further opportunities for data mining.

Propagating waves of directionality and coordination orchestrate collective cell migration.

The ability of cells to coordinately migrate in groups is crucial to enable them to travel long distances during embryonic development, wound healing and tumorigenesis, but the fundamental mechanisms underlying intercellular coordination during collective cell migration remain elusive despite considerable research efforts. A novel analytical framework is introduced here to explicitly detect and quantify cell clusters that move coordinately in a monolayer. The analysis combines and associates vast amount of spatiotemporal data across multiple experiments into transparent quantitative measures to report the emergence of new modes of organized behavior during collective migration of tumor and epithelial cells in wound healing assays. First, we discovered the emergence of a wave of coordinated migration propagating backward from the wound front, which reflects formation of clusters of coordinately migrating cells that are generated further away from the wound edge and disintegrate close to the advancing front. This wave emerges in both normal and tumor cells, and is amplified by Met activation with hepatocyte growth factor/scatter factor. Second, Met activation was found to induce coinciding waves of cellular acceleration and stretching, which in turn trigger the emergence of a backward propagating wave of directional migration with about an hour phase lag. Assessments of the relations between the waves revealed that amplified coordinated migration is associated with the emergence of directional migration. Taken together, our data and simplified modeling-based assessments suggest that increased velocity leads to enhanced coordination: higher motility arises due to acceleration and stretching that seems to increase directionality by temporarily diminishing the velocity components orthogonal to the direction defined by the monolayer geometry. Spatial and temporal accumulation of directionality thus defines coordination. The findings offer new insight and suggest a basic cellular mechanism for long-term cell guidance and intercellular communication during collective cell migration.

Combined neuroimaging and gene expression analysis of the genetic basis of brain plasticity indicates across species homology.

Brain plasticity and memory formation depend on the expression of a large number of genes. This relationship had been studied using several experimental approaches and researchers have identified genes regulating plasticity through a variety of mechanisms. Despite this effort, a great deal remains unknown regarding the role of different genes in brain plasticity. Previous studies usually focused on specific brain structures and many of the genes influencing plasticity have yet to be identified. In this work, we integrate results of in vivo neuroimaging studies of plasticity with whole-brain gene expression data for the study of neuroplasticity. Brain regions, found in the imaging study to be involved in plasticity, are first spatially mapped to the anatomical framework of the genetic database. Feature ranking methods are then applied to identify genes that are differentially expressed in these regions. We find that many of our highly ranked genes are involved in synaptic transmission and that some of these genes have been previously associated with learning and memory. We show these results to be consistent when applying our method to gene expression data from four human subjects. Finally, by performing similar experiments in mice, we reveal significant cross species correlation in the ranking of genes. In addition to the identification of plasticity related candidate genes, our results also demonstrate the potential of data integration approaches as a tool to link high level phenomena such as learning and memory to underlying molecular mechanisms.

Velopharyngeal anatomy in patients with obstructive sleep apnea versus normal subjects.

PURPOSE: Obesity can cause disturbed breathing and is one of the most significant risk factors for obstructive sleep apnea (OSA). However, the anatomic basis of OSA and, specifically, the anatomic mechanisms leading from obesity to OSA are still unclear. We examined the anatomic features of the velopharynx in patients with OSA versus those without in correlation with the body mass index (BMI), age, history of snoring, and OSA severity and re-evaluated the contribution of adding a frontal view to the cephalometric analysis of patients with OSA. MATERIALS AND METHODS: Lateral and frontal cephalometric measurements were taken to assess the velopharyngeal anatomic features of 306 men with various degrees of OSA and 64 men without OSA and without a history of snoring. The demographic, polysomnographic, and cephalometric features were compared. RESULTS: The patients with OSA had an increased pharyngeal length, thicker velum, a thicker posterior pharyngeal wall, a reduced pharyngeal width, and a consequent narrowing of the pharyngeal lumen. As the BMI increased, the OSA severity increased. Also, in parallel, the velum and posterior pharyngeal wall thickness increased and the pharyngeal width decreased. Three types of velopharyngeal narrowing, with an increased occurrence in severe degrees of OSA, were identified: bottle shape, hourglass shape, and tube shape. These aerodynamically unfavorable changes might cause increased upper airway resistance, explaining the development of both OSA and hypoventilation syndrome in obese patients. CONCLUSIONS: Velopharyngeal thickening and lumen narrowing were shown to be features of obese men with OSA. However, these features developed only above a threshold BMI value. The combination of frontal and lateral cephalometry is important for comprehensive evaluation of patients with OSA.