Search Results (328)

The emergence of few-shot object detection provides a new approach to address the challenge of poor generalization ability due to data scarcity. Currently, extensive research has been conducted on few-shot object detection in natural scene datasets, and notable progress has been made. However, in the realm of remote sensing, this technology is still lagging behind. Furthermore, many established methods rely on two-stage detectors, prioritizing accuracy over speed, which hinders real-time applications. Considering both detection accuracy and speed, in this paper, we propose a simple few-shot object detection method based on the one-stage detector YOLOv5 with transfer learning. First, we propose a Segmentation Assistance (SA) module to guide the network’s attention toward foreground targets. This module assists in training and enhances detection accuracy without increasing inference time. Second, we design a novel detection head called the Triplet Head (Tri-Head), which employs a dual distillation mechanism to mitigate the issue of forgetting base-class knowledge. Finally, we optimize the classification loss function to emphasize challenging samples. Evaluations on the NWPUv2 and DIOR datasets showcase the method’s superiority. Full article

Drug repositioning is a cost-effective approach to identifying new indications for existing drugs by predicting their associations with new diseases or symptoms. Recently, deep learning-based models have become the mainstream for drug repositioning. Existing methods typically regard the drug-repositioning task as a binary classification problem to find the new drug–disease associations. However, drug–disease associations may encompass some potential subcategories that can be used to enhance the classification performance. In this paper, we propose a prototype-based subcategory exploration (PSCE) model to guide the model learned with the information of a potential subcategory for drug repositioning. To achieve this, we first propose a prototype-based feature-enhancement mechanism (PFEM) that uses clustering centroids as the attention to enhance the drug–disease features by introducing subcategory information to improve the association prediction. Second, we introduce the drug–disease dual-task classification head (D3TC) of the model, which consists of a traditional binary classification head and a subcategory-classification head to learn with subcategory exploration. It leverages finer-grained pseudo-labels of subcategories to introduce additional knowledge for precise drug–disease association classification. In this study, we conducted experiments on four public datasets to compare the proposed PSCE with existing state-of-the-art approaches and our PSCE achieved a better performance than the existing ones. Finally, the effectiveness of the PFEM and D3TC was demonstrated using ablation studies. Full article

Purpose: To evaluate and compare the deliverability of ‘sawtooth’ proton arc therapy (PAT) plans relative to static intensity modulated proton therapy (IMPT) at a cyclotron-based clinical facility. Methods: The delivery of single and dual arc Sawtooth PAT plans for an abdominal CT phantom and multiple clinical cases of brain, head and neck (H&N) and base of skull (BoS) targets was emulated under the step-and-shoot and continuous PAT delivery regimes and compared to that of a corresponding static IMPT plan. Results: Continuous PAT delivery increased the time associated with beam delivery and gantry movement in single/dual PAT plans by 4.86/7.34 min (brain), 7.51/12.40 min (BoS) and 6.59/10.57 min (H&N) on average relative to static IMPT. Step-and-shoot PAT increased this delivery time further by 4.79 min on average as the delivery was limited by gantry motion. Conclusions: The emulator can approximately model clinical sawtooth PAT delivery but requires experimental validation. No clear benefit was observed regarding beam-on time for sawtooth PAT relative to static IMPT. Full article

Simple, instantaneous, contactless, multiple-point metamaterial-inspired microwave sensors, composed of multi-band, low-profile metamaterial-inspired antennas, were developed to detect and identify meningioma tumors, the most common primary brain tumors. Based on a typical meningioma tumor size of 5–20 mm, a higher operating frequency, where the wavelength is similar or smaller than the tumor target, is crucial. The sensors, designed for the microwave Ku band range (12–18 GHz), where the electromagnetic property values of tumors are available, were implemented in this study. A seven-layered head phantom, including the meningioma tumors, was defined using actual electromagnetic parametric values in the frequency range of interest to mimic the actual human head. The reflection coefficients can be recorded and analyzed instantaneously, reducing high electromagnetic radiation consumption. It has been shown that a single-band detection point is not adequate to classify the nonlinear tumor and head model parameters. On the other hand, dual-band and tri-band metamaterial-inspired antennas, with additional detecting points, create a continuous function solution for the nonlinear problem by adding extra observation points using multiple-band excitation. The point mapping values can be used to enhance the tumor detection capability. Two-point mapping showed a consistent trend between the S₁₁ value order and the tumor size, while three-point mapping can also be used to demonstrate the correlation between the S₁₁ value order and the tumor size. This proposed multi-detection point technique can be applied to a sensor for other nonlinear property targets. Moreover, a set of antennas with different polarizations, orientations, and arrangements in a network could help to obtain the highest sensitivity and accuracy of the whole system. Full article

In this manuscript, we present in detail the design and implementation of the hardware and software to produce a standalone wireless sensor node, called SensorQ system, for the detection of a toxic chemical agent. The proposed wireless sensor node prototype is composed of a micro-controller unit (MCU), a radio frequency (RF) transceiver, a dual-band antenna, a rechargeable battery, a voltage regulator, and four integrated sensing devices, all of them integrated in a package with final dimensions and weight of 200 × 80 × 60 mm and 0.422 kg, respectively. The proposed SensorQ prototype operates using the Long-Range (LoRa) wireless communication protocol at 2.4 GHz, with a sensor head implemented on a hetero-core fiber optic structure supporting the surface plasmon resonance (SPR) phenomenon with a sensing section (L = 10 mm) coated with titanium/gold/titanium and a chemically sensitive material (zinc oxide) for the detection of Di-Methyl Methyl Phosphonate (DMMP) vapor in the air, a simulant of the toxic nerve agent Sarin. The transmitted spectra with respect to different concentrations of DMMP vapor in the air were recorded, and then the transmitted power for these concentrations was calculated at a wavelength of 750 nm. The experimental results indicate the feasibility of detecting DMMP vapor in air using the proposed optical sensor head, with DMMP concentrations in the air of 10, 150, and 150 ppm in this proof of concept. We expect that the sensor and wireless sensor node presented herein are promising candidates for integration into a wireless sensor network (WSN) for chemical warfare agent (CWA) detection and contaminated site monitoring without exposure of armed forces. Full article

The diameter of the optic nerve sheath is an important indicator for assessing the intracranial pressure in critically ill patients. The methods for measuring the optic nerve sheath diameter are generally divided into invasive and non-invasive methods. Compared to the invasive methods, the non-invasive methods are safer and have thus gained popularity. Among the non-invasive methods, using deep learning to process the ultrasound images of the eyes of critically ill patients and promptly output the diameter of the optic nerve sheath offers significant advantages. This paper proposes a CBC-YOLOv5s optic nerve sheath ultrasound image segmentation method that integrates both local and global features. First, it introduces the CBC-Backbone feature extraction network, which consists of dual-layer C3 Swin-Transformer (C3STR) and dual-layer Bottleneck Transformer (BoT3) modules. The C3STR backbone’s multi-layer convolution and residual connections focus on the local features of the optic nerve sheath, while the Window Transformer Attention (WTA) mechanism in the C3STR module and the Multi-Head Self-Attention (MHSA) in the BoT3 module enhance the model’s understanding of the global features of the optic nerve sheath. The extracted local and global features are fully integrated in the Spatial Pyramid Pooling Fusion (SPPF) module. Additionally, the CBC-Neck feature pyramid is proposed, which includes a single-layer C3STR module and three-layer CReToNeXt (CRTN) module. During upsampling feature fusion, the C3STR module is used to enhance the local and global awareness of the fused features. During downsampling feature fusion, the CRTN module’s multi-level residual design helps the network to better capture the global features of the optic nerve sheath within the fused features. The introduction of these modules achieves the thorough integration of the local and global features, enabling the model to efficiently and accurately identify the optic nerve sheath boundaries, even when the ocular ultrasound images are blurry or the boundaries are unclear. The Z2HOSPITAL-5000 dataset collected from Zhejiang University Second Hospital was used for the experiments. Compared to the widely used YOLOv5s and U-Net algorithms, the proposed method shows improved performance on the blurry test set. Specifically, the proposed method achieves precision, recall, and Intersection over Union (IoU) values that are 4.1%, 2.1%, and 4.5% higher than those of YOLOv5s. When compared to U-Net, the precision, recall, and IoU are improved by 9.2%, 21%, and 19.7%, respectively. Full article

The aim of this study was to examine the association between fluoride exposure and bone mineral density (BMD) in children and adolescents. We used data from the National Health and Nutrition Examination Survey (NHANES) 2015–2016. The fluoride concentrations in the water samples, plasma samples, and urine samples were measured electrometrically using an ion-specific electrode. Total body less head BMD (TBLH BMD) was measured using dual-energy X-ray absorptiometry (DXA). Weighted generalized linear regression models and restricted cubic splines (RCS) regression models were used to analyze the relationships between the three types of fluoride exposure and TBLH BMD. We performed subgroup analyses stratified by sex. A total of 1413 US children and adolescents were included in our study. In our linear regression models, we found inverse associations between fluoride concentrations in water and plasma and TBLH BMD. Additionally, we discovered a non-linear association between fluoride concentrations in water and plasma and TBLH BMD. No significant association or non-linear relationship was found between urine fluoride levels and TBLH BMD. This nationally representative sample study provides valuable insight into the intricate connection between fluoride exposure and skeletal health in children and adolescents. Full article

Non-muscle myosin IIA (NM IIA) is a motor protein that belongs to the myosin II family. The myosin heavy chain 9 (MYH9) gene encodes the heavy chain of NM IIA. NM IIA is a hexamer and contains three pairs of peptides, which include the dimer of heavy chains, essential light chains, and regulatory light chains. NM IIA is a part of the actomyosin complex that generates mechanical force and tension to carry out essential cellular functions, including adhesion, cytokinesis, migration, and the maintenance of cell shape and polarity. These functions are regulated via light and heavy chain phosphorylation at different amino acid residues. Apart from physiological functions, NM IIA is also linked to the development of cancer and genetic and neurological disorders. MYH9 gene mutations result in the development of several autosomal dominant disorders, such as May-Hegglin anomaly (MHA) and Epstein syndrome (EPS). Multiple studies have reported NM IIA as a tumor suppressor in melanoma and head and neck squamous cell carcinoma; however, studies also indicate that NM IIA is a critical player in promoting tumorigenesis, chemoradiotherapy resistance, and stemness. The ROCK-NM IIA pathway regulates cellular movement and shape via the control of cytoskeletal dynamics. In addition, the ROCK-NM IIA pathway is dysregulated in various solid tumors and leukemia. Currently, there are very few compounds targeting NM IIA, and most of these compounds are still being studied in preclinical models. This review provides comprehensive evidence highlighting the dual role of NM IIA in multiple cancer types and summarizes the signaling networks involved in tumorigenesis. Furthermore, we also discuss the role of NM IIA as a potential therapeutic target with a focus on the ROCK-NM IIA pathway. Full article

Oral cancer, particularly oral squamous cell carcinoma (OSCC), is a significant global health challenge because of its high incidence and limited treatment options. Major risk factors, including tobacco use, alcohol consumption, and specific microbiota, contribute to the disease’s prevalence. Recently, a compelling association between diabetes mellitus (DM) and oral cancer has been identified, with metformin, a widely used antidiabetic drug, emerging as a potential therapeutic agent across various cancers, including OSCC. This review explores both preclinical and clinical studies to understand the mechanisms by which metformin may exert its anticancer effects, such as inhibiting cancer cell proliferation, inducing apoptosis, and enhancing the efficacy of existing treatments. Preclinical studies demonstrate that metformin modulates crucial metabolic pathways, reduces inflammation, and impacts cellular proliferation, thereby potentially lowering cancer risk and improving patient outcomes. Additionally, metformin’s ability to reverse epithelial-to-mesenchymal transition (EMT), regulate the LIN28/let-7 axis, and its therapeutic role in head and neck squamous cell carcinoma (HNSCC) are examined through experimental models. In clinical contexts, metformin shows promise in enhancing therapeutic outcomes and reducing recurrence rates, although challenges such as drug interactions, complex dosing regimens, and risks such as vitamin B12 deficiency remain. Future research should focus on optimizing metformin’s application, investigating its synergistic effects with other therapies, and conducting rigorous clinical trials to validate its efficacy in OSCC treatment. This dual exploration underscores metformin’s potential to play a transformative role in both diabetes management and cancer care, potentially revolutionizing oral cancer treatment strategies. Full article

In maritime transportation, a ship’s draft survey serves as a primary method for weighing bulk cargo. The accuracy of the ship’s draft reading determines the fairness of bulk cargo transactions. Human visual-based draft reading methods face issues such as safety concerns, high labor costs, and subjective interpretation. Therefore, some image processing methods are utilized to achieve automatic draft reading. However, due to the limitations in the spectral characteristics of RGB images, existing image processing methods are susceptible to water surface environmental interference, such as reflections. To solve this issue, we obtained and annotated 524 multispectral images of a ship’s draft as the research dataset, marking the first application of integrating NIR information and RGB images for automatic draft reading tasks. Additionally, a dual-branch backbone named BIF is proposed to extract and combine spectral information from RGB and NIR images. The backbone network can be combined with the existing segmentation head and detection head to perform waterline segmentation and draft detection. By replacing the original ResNet-50 backbone of YOLOv8, we reached a mAP of 99.2% in the draft detection task. Similarly, combining UPerNet with our dual-branch backbone, the mIoU of the waterline segmentation task was improved from 98.9% to 99.3%. The inaccuracy of the draft reading is less than ±0.01 m, confirming the efficacy of our method for automatic draft reading tasks. Full article

In recent years, object detection in unmanned aerial vehicle (UAV) imagery has been a prominent and crucial task, with advancements in drone and remote sensing technologies. However, detecting targets in UAV images pose challenges such as complex background, severe occlusion, dense small targets, and lighting conditions. Despite the notable progress of object detection algorithms based on deep learning, they still struggle with missed detections and false alarms. In this work, we introduce an MCG-RTDETR approach based on the real-time detection transformer (RT-DETR) with dual and deformable convolution modules, a cascaded group attention module, a context-guided feature fusion structure with context-guided downsampling, and a more flexible prediction head for precise object detection in UAV imagery. Experimental outcomes on the VisDrone2019 dataset illustrate that our approach achieves the highest $AP$ of 29.7% and $A{P}_{50}$ of 58.2%, surpassing several cutting-edge algorithms. Visual results further validate the model’s robustness and capability in complex environments. Full article

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model’s universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach. Full article

Multiple strategies for tandem severe carotid artery stenosis are reported: bilateral carotid artery endarterectomy (CEA), bilateral carotid artery stenting (CAS), and hybrid procedures (CEA and CAS). The management is controversial, considering the reported high risk of periprocedural stroke, hemodynamic distress, and cerebral hyperperfusion syndrome. We present the case of a 64-year-old patient with severe symptomatic bilateral internal carotid artery stenosis (95% stenosis on the left internal carotid artery with recent ipsilateral watershed anterior cerebral artery–medial cerebral artery (ACA-MCA) and medial cerebral artery–posterior cerebral artery (MCA-PCA) ischemic strokes and 90% stenosis on the right internal carotid artery with chronic ipsilateral frontal ischemic stroke) managed successfully with staged CEA within a 3-day interval. The patient had a history of coronary angioplasty and stenting. Strategies for brain protection included shunt placement after the evaluation of carotid stump pressure, internal carotid backflow, and near-infrared spectroscopy. A collagen and silver-coated polyester patch was used to complete the endarterectomy using a 6.0 polypropylene continuous suture in both instances. Management also included neurological consults after extubation, dual antiplatelet therapy, head CT between the two surgeries, myocardial ischemia monitoring, and general anesthesia. Staged CEA with a small time interval between surgeries can be an option to treat tandem symptomatic carotid artery stenosis in highly selected patients. The decision should be tailored according to the patient’s characteristics and should also be made by a cardiology specialist, a neurology specialist, and an anesthesia and intensive care physician. Full article

This paper proposes a novel object detection method to address the challenges posed by small objects and occlusion in object detection. This work is performed within the CenterNet framework, leveraging the MobileNetV3 backbone to model the input image’s abstract representation in a lightweight manner. A sparse convolutional skip connection is introduced in the bottleneck of MobileNetV3, specifically designed to adaptively suppress redundant and interfering information, thus enhancing feature extraction capabilities. A Dual-Path Bidirectional Feature Pyramid Network (DBi-FPN) is incorporated, allowing for high-level feature fusion through bidirectional flow and significantly improving the detection capabilities for small objects and occlusions. Task heads are applied within the feature space of multi-scale information merged by DBi-FPN, facilitating comprehensive consideration of multi-level representations. A bounding box-area loss function is also introduced, aimed at enhancing the model’s adaptability to object morphologies and geometric distortions. Extensive experiments on the PASCAL VOC 2007 and MS COCO 2017 datasets validate the competitiveness of our proposed method, particularly in real-time applications on resource-constrained devices. Our contributions offer promising avenues for enhancing the accuracy and robustness of object detection systems in complex scenarios. Full article

In recent years, EEG-based emotion recognition technology has made progress, but there are still problems of low model efficiency and loss of emotional information, and there is still room for improvement in recognition accuracy. To fully utilize EEG’s emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification and 97.69% and 98.05% in ternary classification, and on the SEED dataset, we achieved an accuracy of 98.63%, surpassing relevant algorithms. Additionally, the model’s efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption. Full article