Search

Unobtrusive sleep position classification is essential for sleep monitoring and closed-loop intervention systems that initiate position changes. In this paper, we present a novel unobtrusive under-mattress optical tactile sensor for sleep position classification. The sensor uses a camera to track particles embedded in a soft silicone layer, inferring the deformation of the silicone and therefore providing information about the pressure and shear distributions applied to its surface.We characterized the sensitivity of the sensor after placing it under a conventional mattress and applying different weights (258 g, 500 g, 5000 g) on top of the mattress in various predefined locations. Moreover, we collected multiple recordings from a person lying in supine, lateral left, lateral right, and prone positions. As a proof-of-concept, we trained a neural network based on convolutional layers and residual blocks that classified the lying positions based on the images from the tactile sensor.We observed a high sensitivity of the optical tactile sensor: Even after placing the sensor below a conventional mattress, we were able to detect our lowest test weight of 258 g. Using the neural network, we were able to classify the four sleep positions, lateral left, lateral right, prone, and supine with a classification accuracy of 91.2 %.The high sensitivity of the sensor, as well as the good performance in the classification task, demonstrate the feasibility of using such a sensor in a robotic bed setup.Clinical Relevance- Positional Obstructive Sleep Apnea is highly prevalent across the general population. Today's gold standard treatment of using CPAP ventilation is often not accepted, leading to unwanted treatment cessations. Alternative treatments, such as positional interventions through robotic beds are highly promising. However, these beds require reliable detection of the lying position. In this paper, we present a novel, scalable and completely unobtrusive sensor that is concealed under the mattress while classifying sleeping positions with high accuracy.

The images captured by vision-based tactile sensors carry information about high-resolution tactile fields, such as the distribution of the contact forces applied to their soft sensing surface. However, extracting the information encoded in the images is challenging and often addressed with learning-based approaches, which generally require a large amount of training data. This article proposes a strategy to generate tactile images in simulation for a vision-based tactile sensor based on an internal camera that tracks the motion of spherical particles within a soft material. The deformation of the material is simulated in a finite element environment under a diverse set of contact conditions, and spherical particles are projected to a simulated image. Features extracted from the images are mapped to the three-dimensional contact force distribution, with the ground truth also obtained using finite-element simulations, with an artificial neural network that is therefore entirely trained on synthetic data avoiding the need for real-world data collection. The resulting model exhibits high accuracy when evaluated on real-world tactile images, is transferable across multiple tactile sensors without further training, and is suitable for efficient real-time inference.

Sensory feedback is essential for the control of soft robotic systems and to enable deployment in a variety of different tasks. Proprioception refers to sensing the robot's own state and is of crucial importance in order to deploy soft robotic systems outside of laboratory environments, i.e. where no external sensing, such as motion capture systems, is available. A vision-based sensing approach for a soft robotic arm made from fabric is presented, leveraging the high-resolution sensory feedback provided by cameras. No mechanical interaction between the sensor and the soft structure is required and consequently the compliance of the soft system is preserved. The integration of a camera into an inflatable, fabric-based bellow actuator is discussed. Three actuators, each featuring an integrated camera, are used to control the spherical robotic arm and simultaneously provide sensory feedback of the two rotational degrees of freedom. A convolutional neural network architecture predicts the two angles describing the robot's orientation from the camera images. Ground truth data is provided by a motion capture system during the training phase of the supervised learning approach and its evaluation thereafter. The camera-based sensing approach is able to provide estimates of the orientation in real-time with an accuracy of about one degree. The reliability of the sensing approach is demonstrated by using the sensory feedback to control the orientation of the robotic arm in closed-loop., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Hofer, Sferrazza and D’Andrea.)

Human skin is capable of sensing various types of forces with high resolution and accuracy. The development of an artificial sense of touch needs to address these properties, while retaining scalability to large surfaces with arbitrary shapes. The vision-based tactile sensor proposed in this article exploits the extremely high resolution of modern image sensors to reconstruct the normal force distribution applied to a soft material, whose deformation is observed on the camera images. By embedding a random pattern within the material, the full resolution of the camera can be exploited. The design and the motivation of the proposed approach are discussed with respect to a simplified elasticity model. An artificial deep neural network is trained on experimental data to perform the tactile sensing task with high accuracy for a specific indenter, and with a spatial resolution and a sensing range comparable to the human fingertip.

Dopamine neurons in the ventral tegmental area use glutamate as a cotransmitter. To elucidate the behavioral role of the cotransmission, we targeted the glutamate-recycling enzyme glutaminase (gene Gls1 ). In mice with a dopamine transporter ( Slc6a3 )-driven conditional heterozygous (cHET) reduction of Gls1 in their dopamine neurons, dopamine neuron survival and transmission were unaffected, while glutamate cotransmission at phasic firing frequencies was reduced, enabling a selective focus on the cotransmission. The mice showed normal emotional and motor behaviors, and an unaffected response to acute amphetamine. Strikingly, amphetamine sensitization was reduced and latent inhibition potentiated. These behavioral effects, also seen in global GLS1 HETs with a schizophrenia resilience phenotype, were not seen in mice with an Emx1 -driven forebrain reduction affecting most brain glutamatergic neurons. Thus, a reduction in dopamine neuron glutamate cotransmission appears to mediate significant components of the GLS1 HET schizophrenia resilience phenotype, and glutamate cotransmission appears to be important in attribution of motivational salience.

Background: Many coeliac disease patients with atypical symptoms remain undiagnosed., Aim: To examine the frequency of oral lesions in coeliac disease patients and to assess their usefulness in making coeliac disease diagnosis., Patients and Methods: One hundred and ninety-seven coeliac disease patients and 413 controls were recruited and the oral examination was performed., Results: Forty-six out of 197 coeliac disease patients (23%) were found to have enamel defects vs. 9% in controls (P < 0.0001). Clinical delayed eruption was observed in 26% of the pediatric coeliac disease patients vs. 7% of the controls (P < 0.0001). The prevalence of oral soft tissues lesions was 42% in the coeliac disease patients and 2% in controls (P < 0.0001). Recurrent aphthous stomatitis disappeared in 89% of the patients after 1 year of gluten-free diet. Multi-logistic analysis selected the following variables as the most meaningful in coeliac disease patients: dental enamel defects (OR = 2.652 CI = 1.427-4.926) and soft tissue lesions (OR = 41.667, CI = 18.868-90.909). Artificial Neural Networks methodology showed that oral soft tissue lesions have sensitivity = 42%, specificity = 98% and test accuracy = 83% in coeliac disease diagnosis., Conclusions: The overall prevalence of oral soft tissue lesions was higher in coeliac disease patients (42%) than in controls. However, the positive-predictive value of these lesions for coeliac disease diagnosis was low.

Background: The clinical significance of the circulating levels of activin A and matrix metalloproteinase-2 (MMP-2) and -9 (MMP-9) was investigated in patients with breast cancer (BC) or prostate cancer (PC) with (M1) or without (M0) bone metastasis., Patients and Methods: MMP-2, MMP-9 and activin A blood concentrations were measured by enzyme immunoassays in 79 cancer patients and in 57 healthy blood donors (HS) who served as a control group. The diagnostic accuracy of these molecules to discriminate between M0 and M1 patients was evaluated by the receiver operating characteristic curve (ROC) and compared to that of tumor markers CA15.3 or prostate-specific antigen (PSA)., Results: Activin A and MMP-2 were significantly increased in BC and PC patients as compared to sex-matched HS while MMP-9 levels were more elevated only in the PC patients. Interestingly, in the PC patients, activin A levels were significantly higher than those measured in the BC patients. In this latter group, activin A and CA15.3 but not MMP-2 or MMP-9 were increased in the M1 patients as compared to M0 patients. Furthermore, a significant relationship was also highlighted between activin A concentration and the number of bone metastases and tumor grade, between MMP-9 and tumor grade, and between MMP-2 and CA15.3. ROC curve analysis showed a good diagnostic accuracy for activin A and CA15.3 but a poor accuracy for MMP-2 and MMP-9 in discriminating between M0 and M1 patients. However, CA15.3 retained the best diagnostic accuracy in this respect. In the PC group, only activin A and PSA levels were significantly increased in the M1 patients as compared to the M0 patients. A similar although not statistically significant trend was noted for MMP-9. Interestingly, a significant correlation was observed between PSA and activin A and MMP-9, and between Activin A and Gleason score and the number of skeletal metastases. ROC curve analysis showed a good diagnostic accuracy for activin A, MMP-9 and PSA and a poor diagnostic accuracy for MMP-2 in detecting M1 patients. However, PSA showed the highest diagnostic accuracy., Conclusion: Activin A, MMP-2 and MMP-9 may be regarded as possible therapeutic targets in the treatment of metastatic bone disease. However, their usefulness as additional markers of bone metastasis remains to be better defined.

The pathogenetic mechanisms, risk factors and relationship between densitometric data and risk of fractures have been examined. The results of treatment trials and prevention measures have been showed.

Unlabelled: PDB is genetically heterogeneous. Mutations of the sequestosome1 gene have been reported in sporadic and familial forms of Paget's in patients of French Canadian and British descent. Mutational analyses in different ethnic groups are needed to accurately investigate hereditary diseases. We describe two novel mutations of sequestosome1 in 62 Italian sporadic patients, confirming the role of the encoded protein in this disorder., Introduction: Paget's disease of bone (PDB) is a relatively common disease of bone metabolism reported to affect up to 3% of whites over 55 years of age. The disorder is genetically heterogeneous, and at present, there is scientific evidence that at least eight different human chromosomal loci are correlated with its pathogenesis. Mutations of the sequestosome1 (SQSTM1) gene were identified as responsible for most of the sporadic and familial forms of Paget in patients of French Canadian and British descent. Such mutations were located at exon 7 and 8 levels, encoding for the ubiquitin protein-binding domain (UBA) and representing a mutational hot spot area., Materials and Methods: To verify the involvement of this gene in Italian subjects affected by PDB, we performed mutational analysis in 62 sporadic PDB cases., Results: We described three different mutations at exon 8 level: P392L, already described in the French Canadian population and families predominantly of British descendent, and two novel mutations consisting of the amino acid substitutions M404V and G425R. No significant differences in the clinical history of PDB have been observed in patients with SQSTM1 mutations in respect to those without., Conclusions: Even though our findings suggest a minor involvement of the SQSTM1 gene in the pathogenesis of sporadic Italian Paget's cases, the identification of different significant mutations within the SQSTM1 gene in unrelated, but clinically similar individuals, offers extremely convincing evidence for a causal relationship between this gene and PDB. Longitudinal studies are needed to assess the penetrance of genotype/phenotype correlations. Our findings confirm the evidence of a clustered mutation area at this level in this disorder., (Copyright 2004 American Society for Bone and Mineral Research)