Discovery of novel coumarin-based KRAS-G12C inhibitors from virtual screening and Rational structural optimization.

KRAS-G12C inhibitors has been made significant progress in the treatment of KRAS-G12C mutant cancers, but their clinical application is limited due to the adaptive resistance, motivating development of novel structural inhibitors. Herein, series of coumarin derivatives as KRAS-G12C inhibitors were found through virtual screening and rational structural optimization. Especially, K45 exhibited strong antiproliferative potency on NCI-H23 and NCI-H358 cancer cells harboring KRAS-G12C with the IC50 values of 0.77 µM and 1.50 µM, which was 15 and 11 times as potent as positive drug ARS1620, respectively. Furthermore, K45 reduced the phosphorylation of KRAS downstream effectors ERK and AKT by reducing the active form of KRAS (KRAS GTP) in NCI-H23 cells. In addition, K45 induced cell apoptosis by increasing the expression of anti-apoptotic protein BAD and BAX in NCI-H23 cells. Docking studies displayed that the 3-naphthylmethoxy moiety of K45 extended into the cryptic pocket formed by the residues Gln99 and Val9, which enhanced the interaction with the KRAS-G12C protein. These results indicated that K45 was a potent KRAS-G12C inhibitor worthy of further study.

Lightweight Seizure Detection Based on Multi-Scale Channel Attention.

Epilepsy is one kind of neurological disease characterized by recurring seizures. Recurrent seizures can cause ongoing negative mental and cognitive damage to the patient. Therefore, timely diagnosis and treatment of epilepsy are crucial for patients. Manual electroencephalography (EEG) signals analysis is time and energy consuming, making automatic detection using EEG signals particularly important. Many deep learning algorithms have thus been proposed to detect seizures. These methods rely on expensive and bulky hardware, which makes them unsuitable for deployment on devices with limited resources due to their high demands on computer resources. In this paper, we propose a novel lightweight neural network for seizure detection using pure convolutions, which is composed of inverted residual structure and multi-scale channel attention mechanism. Compared with other methods, our approach significantly reduces the computational complexity, making it possible to deploy on low-cost portable devices for seizures detection. We conduct experiments on the CHB-MIT dataset and achieves 98.7% accuracy, 98.3% sensitivity and 99.1% specificity with 2.68[Formula: see text]M multiply-accumulate operations (MACs) and only 88[Formula: see text]K parameters.

Vision-based food nutrition estimation via RGB-D fusion network.

With the development of deep learning technology, vision-based food nutrition estimation is gradually entering the public view for its advantage in accuracy and efficiency. In this paper, we designed one RGB-D fusion network, which integrated multimodal feature fusion (MMFF) and multi-scale fusion for visioin-based nutrition assessment. MMFF performed effective feature fusion by a balanced feature pyramid and convolutional block attention module. Multi-scale fusion fused different resolution features through feature pyramid network. Both enhanced feature representation to improve the performance of the model. Compared with state-of-the-art methods, the mean value of the percentage mean absolute error (PMAE) for our method reached 18.5%. The PMAE of calories and mass reached 15.0% and 10.8% via the RGB-D fusion network, improved by 3.8% and 8.1%, respectively. Furthermore, this study visualized the estimation results of four nutrients and verified the validity of the method. This research contributed to the development of automated food nutrient analysis (Code and models can be found at http://123.57.42.89/codes/RGB-DNet/nutrition.html).

Recent development of multi-target VEGFR-2 inhibitors for the cancer therapy.

Vascular epidermal growth factor receptor-2 (VEGFR-2), as an important tyrosine transmembrane protein, plays an important role in regulating endothelial cell proliferation and migration, regulating angiogenesis and other biological functions. VEGFR-2 is aberrantly expressed in many malignant tumors, and it is also related to the occurrence, development, and growth of tumors and drug resistance. Currently, there are nine VEGFR-2 targeted inhibitors approved by US.FDA for clinical use as anticancer drugs. Due to the limited clinical efficacy and potential toxicity of VEGFR inhibitors, it is necessary to develop new strategies to improve the clinical efficacy of VEGFR inhibitors. The development of multitarget therapy, especially dual-target therapy, has become a hot research field of cancer therapy, which may provide an effective strategy with higher therapeutic efficacy, pharmacokinetic advantages and low toxicity. Many groups have reported that the therapeutic effects could be improved by simultaneously inhibiting VEGFR-2 and other targets, such as EGFR, c-Met, BRAF, HDAC, etc. Therefore, VEGFR-2 inhibitors with multi-targeting capabilities have been considered to be promising and effective anticancer agents for cancer therapy. In this work, we reviewed the structure and biological functions of VEGFR-2, and summarized the drug discovery strategies, and inhibitory activities of VEGFR-2 inhibitors with multi-targeting capabilities reported in recent years. This work might provide the reference for the development of VEGFR-2 inhibitors with multi-targeting capabilities as novel anticancer agents.

Long-Range Dependence Involutional Network for Logo Detection.

Logo detection is one of the crucial branches in computer vision due to various real-world applications, such as automatic logo detection and recognition, intelligent transportation, and trademark infringement detection. Compared with traditional handcrafted-feature-based methods, deep learning-based convolutional neural networks (CNNs) can learn both low-level and high-level image features. Recent decades have witnessed the great feature representation capabilities of deep CNNs and their variants, which have been very good at discovering intricate structures in high-dimensional data and are thereby applicable to many domains including logo detection. However, logo detection remains challenging, as existing detection methods cannot solve well the problems of a multiscale and large aspect ratios. In this paper, we tackle these challenges by developing a novel long-range dependence involutional network (LDI-Net). Specifically, we designed a strategy that combines a new operator and a self-attention mechanism via rethinking the intrinsic principle of convolution called long-range dependence involution (LD involution) to alleviate the detection difficulties caused by large aspect ratios. We also introduce a multilevel representation neural architecture search (MRNAS) to detect multiscale logo objects by constructing a novel multipath topology. In addition, we implemented an adaptive RoI pooling module (ARM) to improve detection efficiency by addressing the problem of logo deformation. Comprehensive experiments on four benchmark logo datasets demonstrate the effectiveness and efficiency of the proposed approach.

Image Matting With Deep Gaussian Process.

We observe a common characteristic between the classical propagation-based image matting and the Gaussian process (GP)-based regression. The former produces closer alpha matte values for pixels associated with a higher affinity, while the outputs regressed by the latter are more correlated for more similar inputs. Based on this observation, we reformulate image matting as GP and find that this novel matting-GP formulation results in a set of attractive properties. First, it offers an alternative view on and approach to propagation-based image matting. Second, an application of kernel learning in GP brings in a novel deep matting-GP technique, which is pretty powerful for encapsulating the expressive power of deep architecture on the image relative to its matting. Third, an existing scalable GP technique can be incorporated to further reduce the computational complexity to O(n) from O(n3) of many conventional matting propagation techniques. Our deep matting-GP provides an attractive strategy toward addressing the limit of widespread adoption of deep learning techniques to image matting for which a sufficiently large labeled dataset is lacking. A set of experiments on both synthetically composited images and real-world images show the superiority of the deep matting-GP to not only the classical propagation-based matting techniques but also modern deep learning-based approaches.

Rapid Non-Destructive Analysis of Food Nutrient Content Using Swin-Nutrition.

Food non-destructive detection technology (NDDT) is a powerful impetus to the development of food safety and quality. One of the essential tasks of food quality regulation is the non-destructive detection of the food's nutrient content. However, existing food nutrient NDDT performs poorly in terms of efficiency and accuracy, which hinders their widespread application in daily meals. Therefore, this paper proposed an end-to-end food nutrition non-destructive detection method, named Swin-Nutrition, which combined deep learning and NDDT to evaluate the nutrient content of food. The method aimed to fully capture the feature information from the food images and thus accurately estimate the nutrient content. Swin-Nutrition resorted to Swin Transformer, the feature fusion module (FFM), and the nutrient prediction module to evaluate nutrient content. In particular, Swin Transformer acted as the backbone network for feature extraction of food images, and FFM was used to obtain the discriminative feature representation to improve the accuracy of prediction. The experimental results on the Nutrition5k dataset demonstrated the effectiveness and efficiency of our proposed method. Specifically, the mean value of the percentage mean absolute error (PMAE) for calories, mass, fat, carbohydrate, and protein were only 15.3%, 12.5%, 22.1%, 20.8%, and 15.4%, respectively. We hope that our simple and effective method will provide a solid foundation for the research of food NDDT.

Design and Implementation of Intelligent Monitoring System for Head and Neck Surgery Care Based on Internet of Things (IoT).

As a chronic disease, cervical spondylosis is prone to recurrent attacks as we age if we do not pay attention to protection, which can easily lead to symptoms such as osteophytes and herniated discs. In the early stage of cervical spondylosis, it is possible to alleviate the disease and prevent its aggravation by improving poor cervical posture and increasing cervical activities. This article analyzes the current situation and medical prospect of smart wearable devices with the prevention and treatment of cervical spondylosis in white-collar people as the starting point and smart wearable devices as the focus and provides a detailed analysis of the functions, categories, technologies, and applications of smart wearable devices to provide a technical theoretical basis for the construction of the subsequent research system. For the user's health state, some other physiological parameters are sent to data also through mobile Internet, and the user's physiological information is obtained on the computer database in also, which not only provides the monitoring function for the user's health but also provides the information of medical big data elements for medical and health institutions and so on. This article elaborates the requirement analysis of this system, based on which the system architecture design and module division are elaborated. It provides a practical and theoretical basis for further realizing the seamless integration of IoT technology and nursing information management system and improving its depth and breadth in the application of nursing information management system. From the perspective of the way of quantification of nursing practice activities, real-time monitoring, scientific management, and intelligent decision-making, it provides the basis for achieving the quality of nursing services, reducing errors, reducing labor intensity, and improving work efficiency and clinical research.

Clinical Care of Hyperthyroidism Using Wearable Medical Devices in a Medical IoT Scenario.

This paper presents an in-depth study and analysis of clinical care of patients with hyperthyroidism using wearable medical devices in the context of medical IoT scenarios. According to the use scenario of the gateway and the connectivity of the equipment, the hardware architecture, hardware interfaces, functionality, and performance of the gateway were briefly designed, so as to monitor patients with hyperthyroidism more comprehensively and save labor costs. The gateway can provide access to different devices and adaptation functions to different hardware interfaces and provide hardware support for the subsequent deployment of the proposed new medical communication protocols and related information systems. A medical data convergence information system based on multidevice management and multiprotocol parsing was designed and implemented. The system enables the management and configuration of different medical devices and access to data through the targeted parsing of the underlying medical device communication protocols. The system also provides the automatic adaptation of multiple types of underlying medical device communication protocols and automatic parsing of multiple versions and can provide multiple devices to process fused data streams or device information and data from a single device. The use of event-driven asynchronous communication eliminates the tight dependency on service invocation in the synchronous communication approach. The use of a metadata-based data model structure enables model extensions to accommodate the impact of iterative business requirements on the database structure. Real-time patient physiological data transmission for intraoperative monitoring based on the MQTT protocol and video transmission for intraoperative patient monitoring based on the RTMP protocol were implemented. The development of the intelligent medical monitoring service system was completed, and the system was tested, optimized, and deployed. The functionality and performance of the system were tested, the performance issue of slow query speed was optimized, and the deployment of the project using Docker containers was automated.

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks.

There is a growing consensus in computer vision that symmetric optical flow estimation constitutes a better model than a generic asymmetric one for its independence of the selection of source/target image. Yet, convolutional neural networks (CNNs), that are considered the de facto standard vision model, deal with the asymmetric case only in most cutting-edge CNNs-based optical flow techniques. We bridge this gap by introducing a novel model named SDOF-GAN: symmetric dense optical flow with generative adversarial networks (GANs). SDOF-GAN realizes a consistency between the forward mapping (source-to-target) and the backward one (target-to-source) by ensuring that they are inverse of each other with an inverse network. In addition, SDOF-GAN leverages a GAN model for which the generator estimates symmetric optical flow fields while the discriminator differentiates the "real" ground-truth flow field from a "fake" estimation by assessing the flow warping error. Finally, SDOF-GAN is trained in a semi-supervised fashion to enable both the precious labeled data and large amounts of unlabeled data to be fully-exploited. We demonstrate significant performance benefits of SDOF-GAN on five publicly-available datasets in contrast to several representative state-of-the-art models for optical flow estimation.

Online Multi-expert Learning for Visual Tracking.

The correlation filters based trackers have achieved an excellent performance for object tracking in recent years. However, most existing methods use only one filter but ignore the information of the previous filters. In this paper, we propose a novel online multi-expert learning algorithm for visual tracking. In our proposed scheme, there are former trackers which retain the previous filters, and those trackers will give their predictions in each frame. The current tracker represents the filter of current frame, and both the current tracker and the former trackers constitute our expert ensemble. We use an adaptive Second-order Quantile strategy to learn the weights of each expert, which can take full advantage of all the experts. To simplify our model and remove some bad experts, we prune our models via a minimum entropy criterion. Finally, we propose a new update strategy to avoid the model corruption problem. Extensive experimental results on both OTB2013 and OTB2015 benchmarks demonstrate that our proposed tracker performs favorably against state-of-the-art methods.

MAMDA: Inferring microRNA-Disease associations with manifold alignment.

Uncovering disease-related microRNAs (miRNAs) by inferring miRNA-disease associations is of critical importance for understanding the pathogenesis of disease and carrying out treatment and prevention. Recently developed computational models for inferring miRNA-disease associations assume that functionally related miRNAs are associated with phenotypically similar diseases and hence infer miRNA-disease associations by using miRNA-miRNA and disease-disease similarities, which are concretely determined by mining existing biological resources. From the perspective of manifold learning, miRNA-miRNA similarities and disease-disease similarities determine a low-dimensional manifold for miRNAs and diseases, respectively, and the basic assumption of current computational models is equivalent to consistency between the manifold structures of miRNA and disease. In this paper, we propose a novel microRNA-disease inference framework (MAMDA) that explicitly takes advantage of this consistency property and infers miRNA-disease associations by aligning the manifold structure of miRNA with that of disease together with supervision of experimentally verified miRNA-disease associations. Based on three aspects, experimental results show that the proposed framework outperforms several representative state-of-the-art techniques. First, AUC values using k-fold cross-validation indicate that our method acquires more reliable predictions than four classical techniques (HGIMDA, HDMP, RLSMDA, and NCPMDA). Second, 48/48 predicted associations between miRNAs and breast cancer are validated with the HMDD and dbDEMC to show the effectiveness of predicting isolated diseases with unknown miRNAs. Third, two case studies of colon neoplasms and lung neoplasms validate the superior accuracy of MAMDA, with 48/50 and 48/50 predicted associations in the HMDD and dbDEMC, respectively.

Multimodal Image Alignment via Linear Mapping between Feature Modalities.

We propose a novel landmark matching based method for aligning multimodal images, which is accomplished uniquely by resolving a linear mapping between different feature modalities. This linear mapping results in a new measurement on similarity of images captured from different modalities. In addition, our method simultaneously solves this linear mapping and the landmark correspondences by minimizing a convex quadratic function. Our method can estimate complex image relationship between different modalities and nonlinear nonrigid spatial transformations even in the presence of heavy noise, as shown in our experiments carried out by using a variety of image modalities.

Joint alignment of multispectral images via semidefinite programming.

In this paper, we introduce a novel feature-point-matching based framework for achieving an optimized joint-alignment of sequential images from multispectral imaging (MSI). It solves a low-rank and semidefinite matrix that stores all pairwise-image feature-mappings by minimizing the total amount of point-to-point matching cost via a convex optimization of a semidefinite programming formulation. This unique strategy takes a complete consideration of the information aggregated by all point-matching costs and enables the entire set of pairwise-image feature-mappings to be solved simultaneously and near-optimally. Our framework is capable of running in an automatic or interactive fashion, offering an effective tool for eliminating spatial misalignments introduced into sequential MSI images during the imaging process. Our experimental results obtained from a database of 28 sequences of MSI images of human eye demonstrate the superior performances of our approach to the state-of-the-art techniques. Our framework is potentially invaluable in a large variety of practical applications of MSI images.