Towards a Better Performance in Facial Expression Recognition: A Data-Centric Approach.

Facial expression is the best evidence of our emotions. Its automatic detection and recognition are key for robotics, medicine, healthcare, education, psychology, sociology, marketing, security, entertainment, and many other areas. Experiments in the lab environments achieve high performance. However, in real-world scenarios, it is challenging. Deep learning techniques based on convolutional neural networks (CNNs) have shown great potential. Most of the research is exclusively model-centric, searching for better algorithms to improve recognition. However, progress is insufficient. Despite being the main resource for automatic learning, few works focus on improving the quality of datasets. We propose a novel data-centric method to tackle misclassification, a problem commonly encountered in facial image datasets. The strategy is to progressively refine the dataset by successive training of a CNN model that is fixed. Each training uses the facial images corresponding to the correct predictions of the previous training, allowing the model to capture more distinctive features of each class of facial expression. After the last training, the model performs automatic reclassification of the whole dataset. Unlike other similar work, our method avoids modifying, deleting, or augmenting facial images. Experimental results on three representative datasets proved the effectiveness of the proposed method, improving the validation accuracy by 20.45%, 14.47%, and 39.66%, for FER2013, NHFI, and AffectNet, respectively. The recognition rates on the reclassified versions of these datasets are 86.71%, 70.44%, and 89.17% and become state-of-the-art performance.

Refining Stereotaxic Neurosurgery Techniques and Welfare Assessment for Long-Term Intracerebroventricular Device Implantation in Rodents.

Stereotaxic surgeries enable precise access to specific brain regions, being of particular interest for chronic intracerebroventricular drug delivery. However, the challenge of long-term studies at this level is to allow the implantation of drug storage devices and their correct intrathecal connection while guaranteeing animal welfare during the entire study period. In this study, we propose an optimized method for safe intrathecal device implantation, focusing on preoperative, intraoperative, and postoperative procedures, following the 3Rs principle and animal welfare regulations. Our optimized protocol introduces three main refinements. Firstly, we modify the dimensions of the implantable devices, notably diminishing the device-to-mouse weight ratio. Secondly, we use a combination of cyanoacrylate tissue adhesive and UV light-curing resin, which decreases surgery time, improves healing, and notably minimizes cannula detachment or adverse effects. Thirdly, we develop a customized welfare assessment scoresheet to accurately monitor animal well-being during long-term implantations. Taken together, these refinements positively impacted animal welfare by minimizing the negative effects on body weight, surgery-related complications, and anxiety-like behaviors. Overall, the proposed refinements have the potential to reduce animal use, enhance experimental data quality, and improve reproducibility. Additionally, these improvements can be extended to other neurosurgical techniques, thereby advancing neuroscience research, and benefiting the scientific community.

Oleoylethanolamide Treatment Modulates Both Neuroinflammation and Microgliosis, and Prevents Massive Leukocyte Infiltration to the Cerebellum in a Mouse Model of Neuronal Degeneration.

Neurodegenerative diseases involve an exacerbated neuroinflammatory response led by microglia that triggers cytokine storm and leukocyte infiltration into the brain. PPARα agonists partially dampen this neuroinflammation in some models of brain insult, but neuronal loss was not the triggering cause in any of them. This study examines the anti-inflammatory and immunomodulatory properties of the PPARα agonist oleoylethanolamide (OEA) in the Purkinje Cell Degeneration (PCD) mouse, which exhibits striking neuroinflammation caused by aggressive loss of cerebellar Purkinje neurons. Using real-time quantitative polymerase chain reaction and immunostaining, we quantified changes in pro- and anti-inflammatory markers, microglial density and marker-based phenotype, and overall leukocyte recruitment at different time points after OEA administration. OEA was found to modulate cerebellar neuroinflammation by increasing the gene expression of proinflammatory mediators at the onset of neurodegeneration and decreasing it over time. OEA also enhanced the expression of anti-inflammatory and neuroprotective factors and the Pparα gene. Regarding microgliosis, OEA reduced microglial density-especially in regions where it is preferentially located in PCD mice-and shifted the microglial phenotype towards an anti-inflammatory state. Finally, OEA prevented massive leukocyte infiltration into the cerebellum. Overall, our findings suggest that OEA may change the environment to protect neurons from degeneration caused by exacerbated inflammation.

Natural Aedes-Borne Virus Infection Detected in Male Adult Aedes aegypti (Diptera: Culicidae) Collected From Urban Settings in Mérida, Yucatán, México.

Aedes-borne viruses (ABVs) such as dengue (DENV), chikungunya (CHIKV), and Zika (ZIKV) contribute significantly to the global burden of infectious diseases, disproportionately affecting disadvantaged populations from tropical and subtropical urban areas. ABVs can be transmitted from female mosquitoes to their progeny by vertical transmission via transovarial and/or trans-egg vertical transmission and contribute to the maintenance of infected-mosquito populations year-round in endemic regions. This study describes the natural infection rate of DENV, CHIKV, and ZIKV in field-caught male Aedes (Sergentomyia) aegypti (Linnaeus) mosquitoes from Mérida, Yucatán, México, as a proxy for the occurrence of vertical virus transmission. We used indoor sequential sampling with Prokopack aspirators to collect all mosquitoes inside houses from ABV hotspots areas. Collections were performed in a DENV and CHIKV post-epidemic phase and during a period of active ZIKV transmission. We individually RT-qPCR tested all indoor collected Ae. aegypti males (1,278) followed by Sanger sequencing analysis for final confirmation. A total of 6.7% male mosquitoes were positive for ABV (CHIKV = 5.7%; DENV = 0.9%; ZIKV = 0.1%) and came from 21.0% (30/143) houses infested with males. Most ABV-positive male mosquitoes were positive for CHIKV (84.8%). The distribution of ABV-positive Ae. aegypti males was aggregated in a few households, with two houses having 11 ABV-positive males each. We found a positive association between ABV-positive males and females per house. These findings suggested the occurrence of vertical arbovirus transmission within the mosquito populations in an ABV-endemic area and, a mechanism contributing to viral maintenance and virus re-emergence among humans in post-epidemic periods.

Ligand Binding Prediction using Protein Structure Graphs and Residual Graph Attention Networks

MotivationComputational prediction of ligand-target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph -Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding. ResultsThe developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein-ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)- the hallmark target of SARS-CoV-2 coronavirus. AvailabilityThe code for PSG-BAR is made available at https://github.com/diamondspark/PSG-BAR Contactacherkasov@prostatecentre.com

The Selective Loss of Purkinje Cells Induces Specific Peripheral Immune Alterations.

The progression of neurodegenerative diseases is reciprocally associated with impairments in peripheral immune responses. We investigated different contexts of selective neurodegeneration to identify specific alterations of peripheral immune cells and, at the same time, discover potential biomarkers associated to this pathological condition. Consequently, a model of human cerebellar degeneration and ataxia -the Purkinje Cell Degeneration (PCD) mouse- has been employed, as it allows the study of different processes of selective neuronal death in the same animal, i.e., Purkinje cells in the cerebellum and mitral cells in the olfactory bulb. Infiltrated leukocytes were studied in both brain areas and compared with those from other standardized neuroinflammatory models obtained by administering either gamma radiation or lipopolysaccharide. Moreover, both myeloid and lymphoid splenic populations were analyzed by flow cytometry, focusing on markers of functional maturity and antigen presentation. The severity and type of neural damage and inflammation affected immune cell infiltration. Leukocytes were more numerous in the cerebellum of PCD mice, being located predominantly within those cerebellar layers mostly affected by neurodegeneration, in a completely different manner than the typical models of induced neuroinflammation. Furthermore, the milder degeneration of the olfactory bulb did not foster leukocyte attraction. Concerning the splenic analysis, in PCD mice we found: (1) a decreased percentage of several myeloid cell subsets, and (2) a reduced mean fluorescence intensity in those myeloid markers related to both antigen presentation and functional maturity. In conclusion, the selective degeneration of Purkinje cells triggers a specific effect on peripheral immune cells, fostering both attraction and functional changes. This fact endorses the employment of peripheral immune cell populations as concrete biomarkers for monitoring different neuronal death processes.

Deep Learning Techniques for Spanish Sign Language Interpretation.

Around 5% of the world population suffers from hearing impairment. One of its main barriers is communication with others since it could lead to their social exclusion and frustration. To overcome this issue, this paper presents a system to interpret the Spanish sign language alphabet which makes the communication possible in those cases, where it is necessary to sign proper nouns such as names, streets, or trademarks. For this, firstly, we have generated an image dataset of the signed 30 letters composing the Spanish alphabet. Then, given that there are static and in-motion letters, two different kinds of neural networks have been tested and compared: convolutional neural networks (CNNs) and recurrent neural networks (RNNs). A comparative analysis of the experimental results highlights the importance of the spatial dimension with respect to the temporal dimension in sign interpretation. So, CNNs obtain a much better accuracy, with 96.42% being the maximum value.

The clinical laboratory: a decision maker hub.

OBJECTIVES: We aimed to share a new laboratory model based on laboratory knowledge, meaningful use of information technology, and partnership with clinicians, to lead the appropriate use of laboratory testing and clinical decision making in the diagnosis of as-yet-undiagnosed disease. More specifically, we evaluate the role of eight different opportunistic interventions to diagnose certain asymptomatic disorders, by means of the automatic registration of appropriate laboratory testing according to different scenarios. METHODS: This is a retrospective longitudinal study to evaluate the impact of laboratory interventions on the diagnosis of different diseases and on patient care, including data from January 2012 to September 2020. RESULTS: Overall, the above strategies have so far identified 2063 patients with clinically relevant as-yet-undiagnosed disorders who would have otherwise remained occult, such as for instance, primary hyperparathyroidism, diabetes, and hypomagnesemia. CONCLUSIONS: We are facing a new laboratory model, a leading laboratory rather than a passive traditional laboratory, not just to intervene in clinical decision-making, but to make the clinical decision, through the identification of patients with occult disease.

Oleoylethanolamide Delays the Dysfunction and Death of Purkinje Cells and Ameliorates Behavioral Defects in a Mouse Model of Cerebellar Neurodegeneration.

Oleoylethanolamide (OEA) is an endocannabinoid that has been proposed to prevent neuronal damage and neuroinflammation. In this study, we evaluated the effects of OEA on the disruption of both cerebellar structure and physiology and on the behavior of Purkinje cell degeneration (PCD) mutant mice. These mice exhibit cerebellar degeneration, displaying microtubule alterations that trigger the selective loss of Purkinje cells and consequent behavioral impairments. The effects of different doses (1, 5, and 10 mg/kg, i.p.) and administration schedules (chronic and acute) of OEA were assessed at the behavioral, histological, cellular, and molecular levels to determine the most effective OEA treatment regimen. Our in vivo results demonstrated that OEA treatment prior to the onset of the preneurodegenerative phase prevented morphological alterations in Purkinje neurons (the somata and dendritic arbors) and decreased Purkinje cell death. This effect followed an inverted U-shaped time-response curve, with acute administration on postnatal day 12 (10 mg/kg, i.p.) being the most effective treatment regimen tested. Indeed, PCD mice that received this specific OEA treatment regimen showed improvements in motor, cognitive and social functions, which were impaired in these mice. Moreover, these in vivo neuroprotective effects of OEA were mediated by the PPARα receptor, as pretreatment with the PPARα antagonist GW6471 (2.5 mg/kg, i.p.) abolished them. Finally, our in vitro results suggested that the molecular effect of OEA was related to microtubule stability and structure since OEA administration normalized some alterations in microtubule features in PCD-like cells. These findings provide strong evidence supporting the use of OEA as a pharmacological agent to limit severe cerebellar neurodegenerative processes.

The UJI Aerial Librarian Robot: A Quadcopter for Visual Library Inventory and Book Localisation.

Over time, the field of robotics has provided solutions to automate routine tasks in different scenarios. In particular, libraries are awakening great interest in automated tasks since they are semi-structured environments where machines coexist with humans and several repetitive operations could be automatically performed. In addition, multirotor aerial vehicles have become very popular in many applications over the past decade, however autonomous flight in confined spaces still presents a number of challenges and the use of small drones has not been reported as an automated inventory device within libraries. This paper presents the UJI aerial librarian robot that leverages computer vision techniques to autonomously self-localize and navigate in a library for automated inventory and book localization. A control strategy to navigate along the library bookcases is presented by using visual markers for self-localization during a visual inspection of bookshelves. An image-based book recognition technique is described that combines computer vision techniques to detect the tags on the book spines, followed by an optical character recognizer (OCR) to convert the book code on the tags into text. These data can be used for library inventory. Misplaced books can be automatically detected, and a particular book can be located within the library. Our quadrotor robot was tested in a real library with promising results. The problems encountered and limitation of the system are discussed, along with its relation to similar applications, such as automated inventory in warehouses.

PHAROS 2.0-A PHysical Assistant RObot System Improved.

There are great physical and cognitive benefits for older adults who are engaged in active aging, a process that should involve daily exercise. In our previous work on the PHysical Assistant RObot System (PHAROS), we developed a system that proposed and monitored physical activities. The system used a social robot to analyse, by means of computer vision, the exercise a person was doing. Then, a recommender system analysed the exercise performed and indicated what exercise to perform next. However, the system needed certain improvements. On the one hand, the vision system captured the movement of the person and indicated whether the exercise had been done correctly or not. On the other hand, the recommender system was based purely on a ranking system that did not take into account temporal evolution and preferences. In this work, we propose an evolution of PHAROS, PHAROS 2.0, incorporating improvements in both of the previously mentioned aspects. In the motion capture aspect, we are now able to indicate the degree of completeness of each exercise, identifying the part that has not been done correctly, and a real-time performance correction. In this way, the recommender system receives a greater amount of information and so can more accurately indicate the exercise to be performed. In terms of the recommender system, an algorithm was developed to weigh the performance, temporal evolution and preferences, providing a more accurate recommendation, as well as expanding the recommendation to a batch of exercises, instead of just one.

Rehabilitation Technology: Assistance from Hospital to Home.

Rehabilitation is essential for disabled people to achieve the highest level of functional independence, reducing or preventing impairments. Nonetheless, this process can be long and expensive. This fact together with the ageing phenomenon has become a critical issue for both clinicians and patients. In this sense, technological solutions may be beneficial since they reduce the costs and increase the number of patients per caregiver, which makes them more accessible. In addition, they provide access to rehabilitation services for those facing physical, financial, and/or attitudinal barriers. This paper presents the state of the art of the assistive rehabilitation technologies for different recovery methods starting from in-person sessions to complementary at-home activities.

Does my patient really need this at admission? Seven opportunities for improving value in patient care during their hospitalization.

INTRODUCTION: Besides the main treatment for their disease, hospital patients receive multiple care measures which include venous lines (VL), urinary catheters (UC), dietary restrictions (DR), mandatory bed rest (BR), deep venous thrombosis prophylaxis (VTP), stress ulcer prophylaxis (SUP) and anticoagulation bridge therapy for atrial fibrillation (BAF). In many cases these practices are of low value. METHODS: We analysed patients admitted to Internal Medicine wards throughout 2018 (2714 inpatients). We used different methodologies to identify low-value clinical practices. RESULTS: BR or DR at admission were recommended in 37% (32-44) and 24% (19-30) of the patients respectively. In 81% (71-87) and 33% (21-45) of the cases this restriction was deemed unnecessary. Ninety-six percent (92-98) had VL and 25% (19-32) UC. VL were not used in 10% (6-12), UC had no indications for insertion in 21% (11-35) and for maintenance in 31% (12-46) patients. Fifty-seven percent (49-64) of the patients were administered VTP and 69% (62-76) were prescribed SUP. Twenty-two percent (15-31) of patients with VTP and 52% (43-60) with SUP had no indication. Chronic anticoagulation for AF was interrupted in 65% (53-75) with BAF was prescribed in 38% (25-52) of them. An intervention to reduce low-value care supporting clinical practices addressed only to the Internal Medicine Wards showed very poor results. CONCLUSION: These results demonstrate that there is ample room for reduction of low-value care. Interventions to implement clinical guidelines at admissions should be addressed to cover the entire admission process, from the emergency room to the ward. Partial approaches are discouraged.

Vision for Robust Robot Manipulation.

Advances in Robotics are leading to a new generation of assistant robots working in ordinary, domestic settings. This evolution raises new challenges in the tasks to be accomplished by the robots. This is the case for object manipulation where the detect-approach-grasp loop requires a robust recovery stage, especially when the held object slides. Several proprioceptive sensors have been developed in the last decades, such as tactile sensors or contact switches, that can be used for that purpose; nevertheless, their implementation may considerably restrict the gripper's flexibility and functionality, increasing their cost and complexity. Alternatively, vision can be used since it is an undoubtedly rich source of information, and in particular, depth vision sensors. We present an approach based on depth cameras to robustly evaluate the manipulation success, continuously reporting about any object loss and, consequently, allowing it to robustly recover from this situation. For that, a Lab-colour segmentation allows the robot to identify potential robot manipulators in the image. Then, the depth information is used to detect any edge resulting from two-object contact. The combination of those techniques allows the robot to accurately detect the presence or absence of contact points between the robot manipulator and a held object. An experimental evaluation in realistic indoor environments supports our approach.

A Biologically Inspired Approach for Robot Depth Estimation.

Aimed at building autonomous service robots, reasoning, perception, and action should be properly integrated. In this paper, the depth cue has been analysed as an early stage given its importance for robotic tasks. So, from neuroscience findings, a hierarchical four-level dorsal architecture has been designed and implemented. Mainly, from a stereo image pair, a set of complex Gabor filters is applied for estimating an egocentric quantitative disparity map. This map leads to a quantitative depth scene representation that provides the raw input for a qualitative approach. So, the reasoning method infers the data required to make the right decision at any time. As it will be shown, the experimental results highlight the robust performance of the biologically inspired approach presented in this paper.

PHAROS-PHysical Assistant RObot System.

The great demographic change leading to an ageing society demands technological solutions to satisfy the increasing varied elderly needs. This paper presents PHAROS, an interactive robot system that recommends and monitors physical exercises designed for the elderly. The aim of PHAROS is to be a friendly elderly companion that periodically suggests personalised physical activities, promoting healthy living and active ageing. Here, it is presented the PHAROS architecture, components and experimental results. The architecture has three main strands: a Pepper robot, that interacts with the users and records their exercises performance; the Human Exercise Recognition, that uses the Pepper recorded information to classify the exercise performed using Deep Leaning methods; and the Recommender, a smart-decision maker that schedules periodically personalised physical exercises in the users' agenda. The experimental results show a high accuracy in terms of detecting and classifying the physical exercises (97.35%) done by 7 persons. Furthermore, we have implemented a novel procedure of rating exercises on the recommendation algorithm. It closely follows the users' health status (poor performance may reveal health problems) and adapts the suggestions to it. The history may be used to access the physical condition of the user, revealing underlying problems that may be impossible to see otherwise.

Geoffrey: An Automated Schedule System on a Social Robot for the Intellectually Challenged.

The accelerated growth of the percentage of elder people and persons with brain injury-related conditions and who are intellectually challenged are some of the main concerns of the developed countries. These persons often require special cares and even almost permanent overseers that help them to carry out diary tasks. With this issue in mind, we propose an automated schedule system which is deployed on a social robot. The robot keeps track of the tasks that the patient has to fulfill in a diary basis. When a task is triggered, the robot guides the patient through its completion. The system is also able to detect if the steps are being properly carried out or not, issuing alerts in that case. To do so, an ensemble of deep learning techniques is used. The schedule is customizable by the carers and authorized relatives. Our system could enhance the quality of life of the patients and improve their self-autonomy. The experimentation, which was supervised by the ADACEA foundation, validates the achievement of these goals.

Utilidad de los nuevos criterios diagnósticos y la introducción de los biomarcadores en el continuum de la enfermedad de Alzheimer / Usefullness of new diagnosis criteria and introduction of biomarkers in Alzheimer’s disease continuum

Objetivos: los nuevos criterios diagnósticos de enfermedad de Alzheimer (EA) y deterioro cognitivo leve (DCL) apoyan la utilización de los biomarcadores. Valoramos la utilidad de añadir los biomarcadores en la práctica clínica habitual para confirmar y/o modificar el grado de certeza en el diagnóstico de EA y DCL. Pacientes y métodos: presentamos 40 pacientes en los que de forma consecutiva se realizó la determinación de biomarcadores en líquido cefalorraquídeo (LCR) (amilode, tau y p-tau) y evaluación neuropsicológica según los criterios establecidos en nuestra unidad. Resultados: presentamos las características demográficas de los pacientes. En el 52 % de los pacientes los biomarcadores permitieron modificar el grado de certeza del diagnóstico. La mayor aportación es poder reclasificar a los pacientes con DCL en pacientes con DCL y alto riesgo de EA (7), riesgo intermedio (6) o riesgo bajo (12). En dos casos de inicio rápidamente progresivo, los biomarcadores fueron compatibles con EA. Además, su determinación basal ayuda a predecir el riesgo de progresión a EA tras 2 años de seguimiento. Conclusiones: la utilización de los biomarcadores en la práctica clínica habitual ayuda a modificar el grado de certeza del diagnóstico clínico y, por tanto, el pronóstico de los pacientes, especialmente en fase prodrómica y en presentaciones atípicas (AU)

Background: The new diagnostic criteria for Alzheimer's disease (AD) and mild cognitive impairment (MCI) supports the use of biomarkers. We appreciate the value of adding biomarkers to routine clinical practice to confirm and/or modify the degree of certainty in the diagnosis of AD and MCI. Methods: We present 40 patients consecutively determining CSF biomarkers (amyloid, tau and p-tau) and neuropsychological evaluation was performed according to the criteria set out in our unit. Results: We present the demographic characteristics of the patients. In 52% of patients allowed biomarkers modify the degree of certainty of the diagnosis. The greatest contribution is to reclassify patients with MCI in MCI patients at high risk of AD (7), intermediate risk (7) or low risk of AD (12). In both cases of rapidly progressive onset biomarkers were consistent with AD. Besides, basal CSF biomarkers are useful to predict progression to AD after two years follow-up. Conclusion: The use of biomarkers in clinical practice helps to modify the degree of certainty of the clinical diagnosis, and therefore the prognosis of patients, especially in prodromal phase and atypical presentations (AU)

An active system for visually-guided reaching in 3D across binocular fixations.

Based on the importance of relative disparity between objects for accurate hand-eye coordination, this paper presents a biological approach inspired by the cortical neural architecture. So, the motor information is coded in egocentric coordinates obtained from the allocentric representation of the space (in terms of disparity) generated from the egocentric representation of the visual information (image coordinates). In that way, the different aspects of the visuomotor coordination are integrated: an active vision system, composed of two vergent cameras; a module for the 2D binocular disparity estimation based on a local estimation of phase differences performed through a bank of Gabor filters; and a robotic actuator to perform the corresponding tasks (visually-guided reaching). The approach's performance is evaluated through experiments on both simulated and real data.

Cyclic AMP mediates the cell cycle dynamics of energy metabolism in Saccharomyces cerevisiae.

We have investigated the role of 3',5'-cyclic-adenosine-monophosphate (cAMP) in mediating the coupling between energy metabolism and cell cycle progression in both synchronous cultures and oscillating continuous cultures of Saccharomyces cerevisiae. For the first time, a peak in intracellular cAMP was shown to precede the observed breakdown of trehalose and glycogen during cell cycle-related oscillations. Measurements in synchronous cultures demonstrated that this peak can be associated with the cell cycle dynamics of cAMP under conditions of glucose-limited growth, which was found to differ significantly from that observed in synchronous glucose-repressed cultures. Our results support the notion that cAMP plays a major role in mediating the integration of energy metabolism and cell cycle progression, both in the single cell and during cell cycle-related oscillations in continuous culture, respectively. Evidence is presented that the dynamic behaviour of intracellular cAMP during the cell cycle is modulated depending on nutrient supply. The implications of these findings regarding the role of cAMP in regulating cell cycle progression and energy metabolism are discussed.