Search Results (1,058)

Frozen section biopsy, introduced in the early 1900s, still remains the gold standard methodology for rapid histologic evaluations. Although a valuable tool, it is labor-, time-, and cost-intensive. Other challenges include visual and diagnostic variability, which may complicate interpretation and potentially compromise the quality of clinical decisions. Raman spectroscopy, with its high specificity and non-invasive nature, can be an effective tool for dependable and quick histopathology. The most promising modality in this context is stimulated Raman histology (SRH), a label-free, non-linear optical process which generates conventional H&E-like images in short time frames. SRH overcomes limitations of conventional Raman scattering by leveraging the qualities of stimulated Raman scattering (SRS), wherein the energy gets transferred from a high-power pump beam to a probe beam, resulting in high-energy, high-intensity scattering. SRH’s high resolution and non-requirement of preprocessing steps make it particularly suitable when it comes to intrasurgical histology. Combining SRH with artificial intelligence (AI) can lead to greater precision and less reliance on manual interpretation, potentially easing the burden of the overburdened global histopathology workforce. We review the recent applications and advances in SRH and how it is tapping into AI to evolve as a revolutionary tool for rapid histologic analysis. Full article

Venous blood collection is a widely used medical diagnostic technique, and with rapid advancements in robotics, robotic venous blood collection has the potential to replace traditional manual methods. The success of this robotic approach is heavily dependent on the quality of vein imaging. In this paper, we develop a vein imaging device based on the simulation analysis of vein imaging parameters and propose a U-Net+ResNet18 neural network for vein image segmentation. The U-Net+ResNet18 neural network integrates the residual blocks from ResNet18 into the encoder of the U-Net to form a new neural network. ResNet18 is pre-trained using the Bootstrap Your Own Latent (BYOL) framework, and its encoder parameters are transferred to the U-Net+ResNet18 neural network, enhancing the segmentation performance of vein images with limited labelled data. Furthermore, we optimize the AD-Census stereo matching algorithm by developing a variable-weight version, which improves its adaptability to image variations across different regions. Results show that, compared to U-Net, the BYOL+U-Net+ResNet18 method achieves an 8.31% reduction in Binary Cross-Entropy (BCE), a 5.50% reduction in Hausdorff Distance (HD), a 15.95% increase in Intersection over Union (IoU), and a 9.20% increase in the Dice coefficient (Dice), indicating improved image segmentation quality. The average error of the optimized AD-Census stereo matching algorithm is reduced by 25.69%, and the improvement of the image stereo matching performance is more obvious. Future research will explore the application of the vein imaging system in robotic venous blood collection to facilitate real-time puncture guidance. Full article

Remote sensing and computer vision technologies are increasingly leveraged for rapid post-disaster building damage assessment, becoming a crucial and practical approach. In this context, the accuracy of employing various AI models in pixel-level change detection methods is significantly dependent on the consistency between pre- and post-disaster building images, particularly regarding variations in resolution, viewing angle, and lighting conditions; in object-level feature recognition methods, the low richness of semantic details of damaged buildings in images leads to a poor detection accuracy. This paper proposes a novel method, OCD-BDA (Object-Level Change Detection for Post-Disaster Building Damage Assessment), as an alternative to pixel-level change detection and object-level feature recognition methods. Inspired by human cognitive processes, this method incorporates three key steps: an efficient sample acquisition for object localization, labeling via HGC (Hierarchical and Gaussian Clustering), and model training and prediction for classification. Furthermore, this study establishes a change detection dataset based on Google Earth imagery of regions in Hatay Province before and after the Turkish earthquake. This dataset is characterized by pixel inconsistency and significant differences in photographic angles and lighting conditions between pre- and post-disaster images, making it a valuable test dataset for other studies. As a result, in the experiments of comparative generalization capabilities, OCD-BDA demonstrated a significant improvement, achieving an accuracy of 71%, which is twice that of the second-ranking method. Moreover, OCD-BDA exhibits superior performance in tasks with small sample amounts and rapid training time. With only 1% of the training samples, it achieves a prediction accuracy exceeding that of traditional transfer learning methods with 60% of samples. Additionally, it completes assessments across a large disaster area (450 km²) with 93% accuracy in under 23 min. Full article

Osteoarthritis (OA) is a chronic disease affecting over 500 million people worldwide. As the population ages and obesity rates rise, the societal burden of OA is increasing. Pro-inflammatory cytokines, particularly interleukin-1β, are implicated in the pathogenesis of OA. Recent studies suggest that crosstalk between cartilage and synovium contributes to OA development, but the mechanisms remain unclear. Extracellular vesicles (EVs) were purified from cell culture-conditioned medium via ultracentrifugation and confirmed using transmission electron microscopy, nanoparticle tracking analysis, and western blotting. We demonstrated that EVs were taken up by human synoviocytes and chondrocytes in vitro, while in vivo experiments revealed that fluorescent-labelled EVs injected into mouse joints were incorporated into chondrocytes and synoviocytes. EV uptake was significantly inhibited by dynamin-mediated endocytosis inhibitors, indicating that endocytosis plays a major role in this process. Additionally, co-culture experiments with HEK-293 cells expressing red fluorescent protein (RFP)-tagged CD9 and the chondrocytic cell line OUMS-27 confirmed the transfer of RFP-positive EVs across a 600-nm but not a 30-nm filter. These findings suggest that EVs from chondrocytes are released into joint fluid and taken up by cells within the cartilage, potentially facilitating communication between cartilage and synovium. The results underscore the importance of EVs in OA pathophysiology. Full article

Brain tumors can be serious; consequently, rapid and accurate detection is crucial. Nevertheless, a variety of obstacles, such as poor imaging resolution, doubts over the accuracy of data, a lack of diverse tumor classes and stages, and the possibility of misunderstanding, present challenges to achieve an accurate and final diagnosis. Effective brain cancer detection is crucial for patients’ safety and health. Deep learning systems provide the capability to assist radiologists in quickly and accurately detecting diagnoses. This study presents an innovative deep learning approach that utilizes the Swin Transformer. The suggested method entails integrating the Swin Transformer with the pretrained deep learning model Resnet50V2, called (SwT+Resnet50V2). The objective of this modification is to decrease memory utilization, enhance classification accuracy, and reduce training complexity. The self-attention mechanism of the Swin Transformer identifies distant relationships and captures the overall context. Resnet 50V2 improves both accuracy and training speed by extracting adaptive features from the Swin Transformer’s dependencies. We evaluate the proposed framework using two publicly accessible brain magnetic resonance imaging (MRI) datasets, each including two and four distinct classes, respectively. Employing data augmentation and transfer learning techniques enhances model performance, leading to more dependable and cost-effective training. The suggested model achieves an impressive accuracy of 99.9% on the binary-labeled dataset and 96.8% on the four-labeled dataset, outperforming the VGG16, MobileNetV2, Resnet50V2, EfficientNetV2B3, ConvNeXtTiny, and convolutional neural network (CNN) algorithms used for comparison. This demonstrates that the Swin transducer, when combined with Resnet50V2, is capable of accurately diagnosing brain tumors. This method leverages the combination of SwT+Resnet50V2 to create an innovative diagnostic tool. Radiologists have the potential to accelerate and improve the detection of brain tumors, leading to improved patient outcomes and reduced risks. Full article

Background: Domain adaptation (DA) techniques have emerged as a pivotal strategy in addressing the challenges of cross-subject classification. However, traditional DA methods are inherently limited by the assumption of a homogeneous space, requiring that the source and target domains share identical feature dimensions and label sets, which is often impractical in real-world applications. Therefore, effectively addressing the challenge of EEG classification under heterogeneous spaces has emerged as a crucial research topic. Methods: We present a comprehensive framework that addresses the challenges of heterogeneous spaces by implementing a cross-domain class alignment strategy. We innovatively construct a cross-encoder to effectively capture the intricate dependencies between data across domains. We also introduce a tailored class discriminator accompanied by a corresponding loss function. By optimizing the loss function, we facilitate the aggregation of features with corresponding classes between the source and target domains, while ensuring that features from non-corresponding classes are dispersed. Results: Extensive experiments were conducted on two publicly available EEG datasets. Compared to advanced methods that combine label alignment with transfer learning, our method demonstrated superior performance across five heterogeneous space scenarios. Notably, in four heterogeneous label space scenarios, our method outperformed the advanced methods by an average of 7.8%. Moreover, in complex scenarios involving both heterogeneous label spaces and heterogeneous feature spaces, our method outperformed the state-of-the-art methods by an average of 4.1%. Conclusions: This paper presents an efficient model for cross-subject EEG classification under heterogeneous spaces, which significantly addresses the challenges of EEG classification within heterogeneous spaces, thereby opening up new perspectives and avenues for research in related fields. Full article

Blood is a common biological fluid in forensic investigations, offering significant evidential value. Currently employed presumptive blood tests often lack specificity and are sample destructive, which can compromise downstream analysis. Within this study, the development of an optical biosensor for detecting human red blood cells (RBCs) has been explored to address such limitations. Aptamer-based biosensors, termed aptasensors, offer a promising alternative due to their high specificity and affinity for target analytes. Aptamers are short, single-stranded DNA or RNA sequences that form stable three-dimensional structures, allowing them to bind to specific targets selectively. A nanoflare design has been employed within this work, consisting of a quenching gold nanoparticle (AuNP), DNA aptamer sequences, and complementary fluorophore-labelled flares operating through a fluorescence resonance energy transfer (FRET) mechanism. In the presence of RBCs, the aptamer–flare complex is disrupted, restoring fluorescence and indicating the presence of blood. Two aptamers, N1 and BB1, with a demonstrated binding affinity to RBCs, were selected for inclusion within the nanoflare. This study aimed to optimise three features of the design: aptamer conjugation to AuNPs, aptamer hybridisation to complementary flares, and flare displacement in the presence of RBCs. Fluorescence restoration was achieved with both the N1 and BB1 nanoflares, demonstrating the potential for a functional biosensor to be utilised within the forensic workflow. It is hoped that introducing such an aptasensor could enhance the forensic workflow. This aptasensor could replace current tests with a specific and sensitive reagent that can be used for real-time detection, improving the standard of forensic blood analysis. Full article

This paper introduces an advanced acoustic imaging system leveraging multibeam water column data at various frequencies to detect and classify marine litter. This study encompasses (i) the acquisition of test tank data for diverse types of marine litter at multiple acoustic frequencies; (ii) the creation of a comprehensive acoustic image dataset with meticulous labelling and formatting; (iii) the implementation of sophisticated classification algorithms, namely support vector machine (SVM) and convolutional neural network (CNN), alongside cutting-edge detection algorithms based on transfer learning, including single-shot multibox detector (SSD) and You Only Look once (YOLO), specifically YOLOv8. The findings reveal discrimination between different classes of marine litter across the implemented algorithms for both detection and classification. Furthermore, cross-frequency studies were conducted to assess model generalisation, evaluating the performance of models trained on one acoustic frequency when tested with acoustic images based on different frequencies. This approach underscores the potential of multibeam data in the detection and classification of marine litter in the water column, paving the way for developing novel research methods in real-life environments. Full article

Unsupervised domain adaptation (UDA) focuses on transferring knowledge from the labeled source domain to the unlabeled target domain, reducing the costs of manual data labeling. The main challenge in UDA is bridging the substantial feature distribution gap between the source and target domains. To address this, we propose Polarized Attention Network Domain Adaptation (PANDA), a novel approach that leverages Polarized Self-Attention (PSA) to capture the intricate relationships between the source and target domains, effectively mitigating domain discrepancies. PANDA integrates both channel and spatial information, allowing it to capture detailed features and overall structures simultaneously. Our proposed method significantly outperforms current state-of-the-art unsupervised domain adaptation (UDA) techniques for semantic segmentation tasks. Specifically, it achieves a notable improvement in mean intersection over union (mIoU), with a 0.2% increase for the GTA→Cityscapes benchmark and a substantial 1.4% gain for the SYNTHIA→Cityscapes benchmark. As a result, our method attains mIoU scores of 76.1% and 68.7%, respectively, which reflect meaningful advancements in model accuracy and domain adaptation performance. Full article

Sensory data are the basis for the intelligent health state awareness of planetary gearboxes, which are the critical components of electromechanical systems. Despite the advantages of intelligent diagnostic techniques for detecting intricate fault patterns and improving diagnostic speed, challenges still persist, which include the limited availability of fault data, the lack of labeling information and the discrepancies in features across different signals. Targeting this issue, a subdomain distribution adversarial adaptation diagnosis method (SDAA) is proposed for faults diagnosis of planetary gearboxes across different conditions. Firstly, nonstationary vibration signals are converted into a two-dimensional time–frequency representation to extract intrinsic information and avoid frequency overlapping. Secondly, an adversarial training mechanism is designed to evaluate subclass feature distribution differences between the source and target domain. A conditional distribution adaptation is employed to account for correlations among data from different subclasses. Finally, the proposed method is validated through experiments on planetary gearboxes, and the results demonstrate that SDAA can effectively diagnose faults under crossing conditions with an accuracy of 96.7% in diagnosing gear faults and 95.2% in diagnosing planet bearing faults. It outperforms other methods in both accuracy and model robustness. This confirms that this approach can refine domain-invariant information for transfer learning with less information loss from the sub-class level of fault data instead of the overall class level. Full article

Image super-resolution (SR) algorithms based on deep learning yield good visual performances on visible images. Due to the blurred edges and low contrast of infrared (IR) images, methods transferred directly from visible images to IR images have a poor performance and ignore the demands of downstream detection tasks. Therefore, an Inception Dilated Super-Resolution (IDSR) network with multiple branches is proposed. A dilated convolutional branch captures high-frequency information to reconstruct edge details, while a non-local operation branch captures long-range dependencies between any two positions to maintain the global structure. Furthermore, deformable convolution is utilized to fuse features extracted from different branches, enabling adaptation to targets of various shapes. To enhance the detection performance of low-resolution (LR) images, we crop the images into patches based on target labels before feeding them to the network. This allows the network to focus on learning the reconstruction of the target areas only, reducing the interference of background areas in the target areas’ reconstruction. Additionally, a feature-driven module is cascaded at the end of the IDSR network to guide the high-resolution (HR) image reconstruction with feature prior information from a detection backbone. This method has been tested on the FLIR Thermal Dataset and the M3FD Dataset and compared with five mainstream SR algorithms. The final results demonstrate that our method effectively maintains image texture details. More importantly, our method achieves 80.55% mAP, outperforming other methods on FLIR Dataset detection accuracy, and with 74.7% mAP outperforms other methods on M3FD Dataset detection accuracy. Full article

Background/Objectives: Predicting the biochemical pathway involvement of a compound could facilitate the interpretation of biological and biomedical research. Prior prediction approaches have largely focused on metabolism, training machine learning models to solely predict based on metabolic pathways. However, there are many other types of pathways in cells and organisms that are of interest to biologists. Methods: While several publications have made use of the metabolites and metabolic pathways available in the Kyoto Encyclopedia of Genes and Genomes (KEGG), we downloaded all the compound entries with pathway annotations available in the KEGG. From these data, we constructed a dataset where each entry contained features representing compounds combined with features representing pathways, followed by a binary label indicating whether the given compound is associated with the given pathway. We trained multi-layer perceptron binary classifiers on variations of this dataset. Results: The models trained on 6485 KEGG compounds and 502 pathways scored an overall mean Matthews correlation coefficient (MCC) performance of 0.847, a median MCC of 0.848, and a standard deviation of 0.0098. Conclusions: This performance on all 502 KEGG pathways represents a roughly 6% improvement over the performance of models trained on only the 184 KEGG metabolic pathways, which had a mean MCC of 0.800 and a standard deviation of 0.021. These results demonstrate the capability to effectively predict biochemical pathways in general, in addition to those specifically related to metabolism. Moreover, the improvement in the performance demonstrates additional transfer learning with the inclusion of non-metabolic pathways. Full article

In the parent, gestational diabetes mellitus (GDM) causes both hyperglycemia and hyperlipidemia. Despite excess lipid availability, infants exposed to GDM are at risk for essential long-chain polyunsaturated fatty acid (LCPUFA) deficiency. Isotope studies have confirmed less LCPUFA transfer from the parent to the fetus, but how diabetic fuels impact placental fatty acid (FA) uptake and lipid droplet partitioning is not well-understood. We evaluated the effects of high glucose conditions, high lipid conditions, and their combination on trophoblast growth, viability, mitochondrial bioenergetics, BODIPY-labeled fatty acid (FA) uptake, and lipid droplet dynamics. The addition of four carbons or one double bond to FA acyl chains dramatically affected the uptake in both BeWo and primary isolated cytotrophoblasts (CTBs). The uptake was further impacted by media exposure. The combination-exposed trophoblasts had more mitochondrial protein (p = 0.01), but impaired maximal and spare respiratory capacities (p < 0.001 and p < 0.0001), as well as lower viability (p = 0.004), due to apoptosis. The combination-exposed trophoblasts had unimpaired uptake of BODIPY C12 but had significantly less whole-cell and lipid droplet uptake of BODIPY C16, with an altered lipid droplet count, area, and subcellular localization, whereas these differences were not seen with individual high glucose or lipid exposure. These findings bring us closer to understanding how GDM perturbs active FA transport to increase the risk of adverse outcomes from placental and neonatal lipid accumulation alongside LCPUFA deficiency. Full article

Background/Objectives: The study of oxidative stress in cells and ways to prevent it attract increasing attention. Antioxidant defense of cells can be activated by releasing the transcription factor Nrf2 from a complex with Keap1, its inhibitor protein. The aim of the work was to study the effect of the modular nanotransporter (MNT) carrying an R1 anti-Keap1 monobody (MNT_R1) on cell homeostasis. Methods: The murine hepatocyte AML12 cells were used for the study. The interaction of fluorescently labeled MNT_R1 with Keap1 fused to hrGFP was studied using the Fluorescence-Lifetime Imaging Microscopy–Förster Resonance Energy Transfer (FLIM-FRET) technique on living AML12 cells transfected with the Keap1-hrGFP gene. The release of Nrf2 from the complex with Keap1 and its levels in the cytoplasm and nuclei of the AML12 cells were examined using a cellular thermal shift assay (CETSA) and confocal laser scanning microscopy, respectively. The effect of MNT on the formation of reactive oxygen species was studied by flow cytometry using 6-carboxy-2′,7′-dichlorodihydrofluorescein diacetate. Results: MNT_R1 is able to interact with Keap1 in the cytoplasm, leading to the release of Nrf2 from the complex with Keap1 and a rapid rise in Nrf2 levels both in the cytoplasm and nuclei, ultimately causing protection of cells from the action of hydrogen peroxide. The possibility of cleavage of the monobody in endosomes leads to an increase in the observed effects. Conclusions: These findings open up a new approach to specifically modulating the interaction of intracellular proteins, as demonstrated by the example of the Keap1-Nrf2 system. Full article

Data augmentation is commonly utilized to increase the size and diversity of training sets for deep learning tasks. In this study, we propose a novel application of an existing image generation approach in the domain of realistic eye images that leverages data collected from 40 subjects. This hybrid method combines the benefits of precise control over the image content provided by 3D rendering, while introducing the previously lacking photorealism and diversity into synthetic images through neural style transfer. We prove its general efficacy as a data augmentation tool for appearance-based gaze estimation when generated data are mixed with a sparse train set of real images. It improved the results for 39 out of 40 subjects, with an $11.22\%$ mean and a $19.75\%$ maximum decrease in gaze estimation error, achieving similar metrics for train and held-out subjects. We release our data repository of eye images with gaze labels used in this work for public access. Full article