RESUMO
Tactile sensors for robotic applications enhance the performance of robotic end-effectors as they ca n provide tactile information to operate various tasks. In particular, tactile sensors can measure multi-axial force and detect slip can aid the end-effectors in grasping diverse objects in an unstructured environment. We propose BaroTac, which measures three-axial forces and detects slip with a barometric pressure sensor chip (BPSC) for robotic applications. A BPSC is an off-the-shelf commercial sensor that is inexpensive, easy to customize, robust, and simple to use. While a single BPSC-based tactile sensor can measure pressure, an array of BPSC-based tactile sensors can measure multi-axial force through the reactivity of each sensor and detect slip by observing high frequency due to slip vibration. We first experiment with defining the fundamental characteristics of a single-cell BPSC-based sensor to set the design parameters of our proposed sensor. Thereafter, we suggest the sensing method of BaroTac: calibration matrix for three-axis force measurement and discrete wavelet transform (DWT) for slip detection. Subsequently, we validate the three-axis force measuring ability and slip detectability of the fabricated multi-cell BPSC-based tactile sensor. The sensor measures three-axis force with low error (0.14, 0.18, and 0.3% in the X-, Y- and Z-axis, respectively) and discriminates slip in the high-frequency range (75-150 Hz). We finally show the practical applicability of BaroTac by installing them on the commercial robotic gripper and controlling the gripper to grasp common objects based on our sensor feedback.
Assuntos
Robótica , Tato , Vibração , Calibragem , Força da MãoRESUMO
The prevalence of microplastic (MP) contamination has become a significant environmental concern due to its pervasive nature and persistent effects. While sediments are considered major repositories for MPs, information on their spatial distribution within these matrices is insufficient. This research examined both the horizontal and vertical presence of MPs in the sediments surrounding Lake Paldang in South Korea, alongside a comprehensive evaluation of the physicochemical characteristics of the samples obtained. The total content of MPs varied from 2.15 to 122.2 particles g-1. The average contents of MPs on surface sediments were 40.47, 34.14, 5.01, and 8.19 particles g-1 in north mainstream (NM), south mainstream (SM), tributary (TB), and Tributary catchment (TC) based on Sonae Island, Gyeongan stream, respectively. The most abundant MP types were polyethylene (PE), polytetrafluoroethylene (PTFE), and polypropylene (PP), accounting for more than 70% of the total MPs. The most abundant sizes of MPs were within 45-100 µm. At all sediment depths, polymers were distributed in the order PE, PP, and polyester in NM, SM, and TC, respectively, whereas PTFE mainly occurred in the surface layer. MPs distribution also exhibited seasonal variation as larger inflows and flow rates varied with season.
RESUMO
Label-free optical coherence tomography angiography (OCTA) has become a premium imaging tool in clinics to obtain structural and functional information of microvasculatures. One primary technical drawback for OCTA, however, is its imaging speed. The current protocols require high sampling density and multiple acquisitions of cross-sectional B-scans to form one image frame, resulting in low acquisition speed. Recently, deep learning (DL)-based methods have gained attention in accelerating the OCTA acquisition process. They achieve faster acquisition using two independent reconstructing approaches: high-quality angiograms from a few repeated B-scans and high-resolution angiograms from undersampled data. While these approaches have shown promising results, they provide limited solutions that only partially account for the OCTA scanning mechanism. Herein, we propose an integrated DL method to simultaneously tackle both factors and further enhance the reconstruction performance in speed and quality. We designed an end-to-end deep neural network (DNN) framework with a two-staged adversarial training scheme to reconstruct fully-sampled, high-quality (8 repeated B-scans) angiograms from their corresponding undersampled, low-quality (2 repeated B-scans) counterparts by successively enhancing the pixel resolution and the image quality. Using an in-vivo mouse brain vasculature dataset, we evaluate our proposed framework through quantitative and qualitative assessments and demonstrate that our method can achieve superior reconstruction performance compared to the conventional means. Our DL-based framework can accelerate the OCTA imaging speed from 16 to 256[Formula: see text] while preserving the image quality, thus enabling a convenient software-only solution to enhance preclinical and clinical studies.
Assuntos
Angiografia por Tomografia Computadorizada/métodos , Aprendizado Profundo , Microvasos/diagnóstico por imagem , Tomografia de Coerência Óptica/métodos , Animais , Encéfalo/irrigação sanguínea , Masculino , Camundongos Endogâmicos C57BL , Redes Neurais de Computação , SoftwareRESUMO
Mesenchymal stem cells (MSCs) are increasingly used as regenerative therapies for patients in the preclinical and clinical phases of various diseases. However, the main limitations of such therapies include functional heterogeneity and the lack of appropriate quality control (QC) methods for functional screening of MSC lines; thus, clinical outcomes are inconsistent. Recently, machine learning (ML)-based methods, in conjunction with single-cell morphological profiling, have been proposed as alternatives to conventional in vitro/vivo assays that evaluate MSC functions. Such methods perform in silico analyses of MSC functions by training ML algorithms to find highly nonlinear connections between MSC functions and morphology. Although such approaches are promising, they are limited in that extensive, high-content single-cell imaging is required; moreover, manually identified morphological features cannot be generalized to other experimental settings. To address these limitations, we propose an end-to-end deep learning (DL) framework for functional screening of MSC lines using live-cell microscopic images of MSC populations. We quantitatively evaluate various convolutional neural network (CNN) models and demonstrate that our method accurately classifies in vitro MSC lines to high/low multilineage differentiating stress-enduring (MUSE) cells markers from multiple donors. A total of 6,120 cell images were obtained from 8 MSC lines, and they were classified into two groups according to MUSE cell markers analyzed by immunofluorescence staining and FACS. The optimized DenseNet121 model showed area under the curve (AUC) 0.975, accuracy 0.922, F1 0.922, sensitivity 0.905, specificity 0.942, positive predictive value 0.940, and negative predictive value 0.908. Therefore, our DL-based framework is a convenient high-throughput method that could serve as an effective QC strategy in future clinical biomanufacturing processes.
Assuntos
Aprendizado Profundo , Células-Tronco Mesenquimais , Humanos , Ensaios de Triagem em Larga Escala , Alprostadil/metabolismo , Aprendizado de MáquinaRESUMO
A superresolution imaging approach that localizes very small targets, such as red blood cells or droplets of injected photoacoustic dye, has significantly improved spatial resolution in various biological and medical imaging modalities. However, this superior spatial resolution is achieved by sacrificing temporal resolution because many raw image frames, each containing the localization target, must be superimposed to form a sufficiently sampled high-density superresolution image. Here, we demonstrate a computational strategy based on deep neural networks (DNNs) to reconstruct high-density superresolution images from far fewer raw image frames. The localization strategy can be applied for both 3D label-free localization optical-resolution photoacoustic microscopy (OR-PAM) and 2D labeled localization photoacoustic computed tomography (PACT). For the former, the required number of raw volumetric frames is reduced from tens to fewer than ten. For the latter, the required number of raw 2D frames is reduced by 12 fold. Therefore, our proposed method has simultaneously improved temporal (via the DNN) and spatial (via the localization method) resolutions in both label-free microscopy and labeled tomography. Deep-learning powered localization PA imaging can potentially provide a practical tool in preclinical and clinical studies requiring fast temporal and fine spatial resolutions.
RESUMO
Although accurate detection of breast cancer still poses significant challenges, deep learning (DL) can support more accurate image interpretation. In this study, we develop a highly robust DL model based on combined B-mode ultrasound (B-mode) and strain elastography ultrasound (SE) images for classifying benign and malignant breast tumors. This study retrospectively included 85 patients, including 42 with benign lesions and 43 with malignancies, all confirmed by biopsy. Two deep neural network models, AlexNet and ResNet, were separately trained on combined 205 B-mode and 205 SE images (80% for training and 20% for validation) from 67 patients with benign and malignant lesions. These two models were then configured to work as an ensemble using both image-wise and layer-wise and tested on a dataset of 56 images from the remaining 18 patients. The ensemble model captures the diverse features present in the B-mode and SE images and also combines semantic features from AlexNet and ResNet models to classify the benign from the malignant tumors. The experimental results demonstrate that the accuracy of the proposed ensemble model is 90%, which is better than the individual models and the model trained using B-mode or SE images alone. Moreover, some patients that were misclassified by the traditional methods were correctly classified by the proposed ensemble method. The proposed ensemble DL model will enable radiologists to achieve superior detection efficiency owing to enhance classification accuracy for breast cancers in ultrasound (US) images.
Assuntos
Neoplasias da Mama , Técnicas de Imagem por Elasticidade , Mama , Neoplasias da Mama/diagnóstico por imagem , Feminino , Humanos , Aprendizado de Máquina , Estudos Retrospectivos , Sensibilidade e Especificidade , Ultrassonografia , Ultrassonografia MamáriaRESUMO
As touch screen technologies advanced, a digital stylus has become one of the essential accessories for a smart device. However, most of the digital styluses so far provide limited tactile feedback to a user. Therefore we focused on the limitation and noted the potential that a digital stylus may offer the sensation of realistic interaction with virtual environments on a touch screen using a 2.5D haptic system. Thus, we developed a haptic stylus with SMA (Shape Memory Alloy) and a 2.5D haptic rendering algorithm to provide lateral skin-stretch feedback to mimic the interaction force between fingertip and a stylus probing over a bumpy surface. We conducted two psychophysical experiments to evaluate the effect of 2.5D haptic feedback on the perception of virtual object geometry. Experiment 1 investigated the human perception of virtual bump size felt via the proposed lateral skin-stretch stylus and a vibrotactile stylus as reference. Experiment 2 tested the participants' ability to count the number of virtual bumps rendered via the two types of haptic styluses. The results of Experiment 1 indicate that the participants felt the size of virtual bumps rendered with lateral skin-stretch stylus significantly sensitively than the vibrotactile stylus. Similarly, the participants counted the number of virtual bumps rendered with the lateral skin-stretch stylus significantly better than with the vibrotactile stylus. A common result of the two experiments is a significantly longer mean trial time for the skin-stretch stylus than the vibrotactile stylus.
RESUMO
This study presents an up-to-date survey of the use of artificial intelligence (AI) in the field of otorhinolaryngology, considering opportunities, research challenges, and research directions. We searched PubMed, the Cochrane Central Register of Controlled Trials, Embase, and the Web of Science. We initially retrieved 458 articles. The exclusion of non-English publications and duplicates yielded a total of 90 remaining studies. These 90 studies were divided into those analyzing medical images, voice, medical devices, and clinical diagnoses and treatments. Most studies (42.2%, 38/90) used AI for image-based analysis, followed by clinical diagnoses and treatments (24 studies). Each of the remaining two subcategories included 14 studies. Machine learning and deep learning have been extensively applied in the field of otorhinolaryngology. However, the performance of AI models varies and research challenges remain.
RESUMO
Perforation of the gastrointestinal tract by ingested foreign bodies is extremely rare in otherwise healthy patients, accounting for < 1% of cases. Accidentally ingested foreign bodies could cause small bowel perforation through a hernia sac, Meckel's diverticulum, or the appendix, all of which are uncommon. Despite their sharp ends and elongated shape, bowel perforation caused by ingested fish bones is rarely reported, particularly in patients without intestinal disease. We report a case of 57-year-old female who visited the emergency room with periumbilical pain and no history of underlying intestinal disease or intra-abdominal surgery. Abdominal computed tomography and exploratory laparotomy revealed a small bowel micro-perforation with a 2.7-cm fish bone penetrating the jejunal wall.