Search

In the realm of modern medicine, medical imaging stands as an irreplaceable pillar for accurate diagnostics. The significance of precise segmentation in medical images cannot be overstated, especially considering the variability introduced by different practitioners. With the escalating volume of medical imaging data, the demand for automated and efficient segmentation methods has become imperative. This study introduces an innovative approach to heart image segmentation, embedding a multi-scale feature and attention mechanism within an inverted pyramid framework. Recognizing the intricacies of extracting contextual information from low-resolution medical images, our method adopts an inverted pyramid architecture. Through training with multi-scale images and integrating prediction outcomes, we enhance the network’s contextual understanding. Acknowledging the consistent patterns in the relative positions of organs, we introduce an attention module enriched with positional encoding information. This module empowers the network to capture essential positional cues, thereby elevating segmentation accuracy. Our research resides at the intersection of medical imaging and sensor technology, emphasizing the foundational role of sensors in medical image analysis. The integration of sensor-generated data showcases the symbiotic relationship between sensor technology and advanced machine learning techniques. Evaluation on two heart datasets substantiates the superior performance of our approach. Metrics such as the Dice coefficient, Jaccard coefficient, recall, and F-measure demonstrate the method’s efficacy compared to state-of-the-art techniques. In conclusion, our proposed heart image segmentation method addresses the challenges posed by diverse medical images, offering a promising solution for efficiently processing 2D/3D sensor data in contemporary medical imaging.

In the era of artificial intelligence, the significance of images and videos as intuitive conveyors of information cannot be overstated. Computer vision techniques rooted in deep learning have revolutionized our ability to autonomously and accurately identify objects within visual media, making them a focal point of contemporary research. This study addresses the pivotal role of image object detection, particularly in the contexts of autonomous driving and security surveillance, by presenting an in-depth exploration of this field with a focus on enhancing the feature pyramid network. One of the key challenges in existing object detection methodologies lies in mitigating information loss caused by multi-scale feature fusion. To tackle this issue, we propose the enhanced feature pyramid, which adeptly amalgamates features extracted across different scales. This strategic enhancement effectively curbs information attrition across various layers, thereby strengthening the feature extraction capabilities of the foundational network. Furthermore, we confront the issue of excessive classification loss in image object detection tasks by introducing the gradient density loss function, designed to mitigate classification discrepancies. Empirical results unequivocally demonstrate the efficacy of our approach in enhancing the detection of multi-scale objects within images. When evaluated across benchmark datasets, including MS COCO 2017, MS COCO 2014, Pascal VOC 2007, and Pascal VOC 2012, our method achieves impressive average precision scores of 39.4%, 42.0%, 51.5%, and 49.9%, respectively. This performance clearly outperforms alternative state-of-the-art methods in the field. This research not only contributes to the evolving landscape of computer vision and object detection but also has practical implications for a wide range of applications, aligning with the transformative trends in the automotive industry and security technologies.

Prefabricated buildings’ quality, safety, and construction efficiency are closely related to the connections between various prefabricated components. This study optimizes the design of corrugated pipe-restrained grout anchor lap connections, further simplifying the construction methodology while ensuring reliable connection performance. The objective is to achieve cost savings and accelerate construction progress. A pull-out test of this new type of joint is conducted, generating two sets of 17 specimens each. The research examines the effects of grouting material strength, grout anchor steel bar anchorage length, and U-shaped stirrup spacing on the connection performance of corrugated pipe grout anchor connections. The results indicated that the specimens primarily experience two types of failure: anchorage failure with steel bar pull-out and steel bar tensile failure without anchorage failure. The strength of the grouting material and the anchorage length of the grout anchor steel bar positively correlate with bond anchorage performance. U-shaped stirrups contribute to restraint and enhance the bonding force between the corrugated pipe, grouting materials, and the grout anchor steel bar to a certain extent.

Visual saliency refers to the human’s ability to quickly focus on important parts of their visual field, which is a crucial aspect of image processing, particularly in fields like medical imaging and robotics. Understanding and simulating this mechanism is crucial for solving complex visual problems. In this paper, we propose a salient object detection method based on boundary enhancement, which is applicable to both 2D and 3D sensors data. To address the problem of large-scale variation of salient objects, our method introduces a multi-level feature aggregation module that enhances the expressive ability of fixed-resolution features by utilizing adjacent features to complement each other. Additionally, we propose a multi-scale information extraction module to capture local contextual information at different scales for back-propagated level-by-level features, which allows for better measurement of the composition of the feature map after back-fusion. To tackle the low confidence issue of boundary pixels, we also introduce a boundary extraction module to extract the boundary information of salient regions. This information is then fused with salient target information to further refine the saliency prediction results. During the training process, our method uses a mixed loss function to constrain the model training from two levels: pixels and images. The experimental results demonstrate that our salient target detection method based on boundary enhancement shows good detection effects on targets of different scales, multi-targets, linear targets, and targets in complex scenes. We compare our method with the best method in four conventional datasets and achieve an average improvement of 6.2% on the mean absolute error (MAE) indicators. Overall, our approach shows promise for improving the accuracy and efficiency of salient object detection in a variety of settings, including those involving 2D/3D semantic analysis and reconstruction/inpainting of image/video/point cloud data.

Anomaly detection is the foundation of intelligent operation and maintenance (O&M), and detection objects are evaluated by key performance indicators (KPIs). For almost all computer O&M systems, KPIs are usually the machine-level operating data. Moreover, these high-frequency KPIs show a non-Gaussian distribution and are hard to model, i.e., they are intricate KPI profiles. However, existing anomaly detection techniques are incapable of adapting to intricate KPI profiles. In order to enhance the performance under intricate KPI profiles, this study presents a seasonal adaptive KPI anomaly detection algorithm ASAD (Adaptive Seasonality Anomaly Detection). We also propose a new eBeats clustering algorithm and calendar-based correlation method to further reduce the detection time and error. Through experimental tests, our ASAD algorithm has the best overall performance compared to other KPI anomaly detection methods.

Milk has two main components that have high nutritional value—milk protein (casein and whey protein), and lactose. These components are extensively used in various areas, especially in food, i.e., as sweeteners, stabilizers, functional food ingredients, nutritional fortifiers, etc. Non-enzymatic browning refers to a series of chemical reactions between sugars and proteins that make food more appetizing. Non-enzymatic browning reactions include degradation of ascorbic acid, lipid peroxidation, caramel reaction, and the Maillard reaction (MR). The MR, as one of the four non-enzymatic browning reactions, has been well studied and utilized in food fields. Milk protein and lactose, as two main components of milk, have high chemical activities; they are used as reactants to participate in the MR, generating Maillard reaction products (MRPs). The MR involves a condensation reaction between carbonyl groups of various sugars and amino groups of amino acids/proteins. These MRPs have different applications in various areas, including food flavor, food oxidation resistance, drug carriers, etc. This work presents the positive and negative effects of the MR, based on the two main components of milk, used in food and medicine, as well as avoidance approaches to prevent the occurrence of negative effects.

Maintenance of dental health has attracted attention of researchers at present. Various materials have been constructed and applied for curing different dental diseases, although limitation of biocompatibility and safety is still a big challenge. To overcome these limitations, nanomaterials with unique properties are incorporated into various dental treatment materials used in dental applications, including endodontic treatment, periodontal treatment, implant treatment, oral surgery, and restorative treatment, etc. Especially, reactive oxygen species-based nanomaterials equipped with nanoscale properties and reactive oxygen activities can be used as sterilization agents in dentistry, along with being used as good fillers in the dental field. This review concludes the common reactive oxygen species (ROS) nanomaterials and reviews the utilization of ROS in dentistry, highlighting the potential application and safety in clinical treatment. The future prospect will also be proposed to conduct the clinic dental cure.

Due to the lack of an effective method for the treatment of fibrosis, there are numerous patients suffering from the effects of fibrosis. Severe fibrosis can cause dysfunction of relevant organs characterized by excessive deposition of extracellular matrix components. Metastasis-associated lung adenocarcinoma transcript 1 (MALAT1) is a long non-coding RNA that is widely expressed and highly conserved in human tissues. It can regulate gene expression at various molecular levels, involved in the fibrosis of the liver, heart, lung, and kidney. In this review, we first described the pathogenesis by which MALAT1 promotes fibrosis. Furthermore, we summarized current studies of MALAT1 in the fibrosis of various organs. Hope this review will contribute to a better understanding of the molecular mechanism of fibrosis and the potential of MALAT1 as a novel therapeutic target for fibrosis.