FABNet: Fusion Attention Block and Transfer Learning for Laryngeal Cancer Tumor Grading in P63 IHC Histopathology Images.

Laryngeal cancer tumor (LCT) grading is a challenging task in P63 Immunohistochemical (IHC) histopathology images due to small differences between LCT levels in pathology images, the lack of precision in lesion regions of interest (LROIs) and the paucity of LCT pathology image samples. The key to solving the LCT grading problem is to transfer knowledge from other images and to identify more accurate LROIs, but the following problems occur: 1) transferring knowledge without a priori experience often causes negative transfer and creates a heavy workload due to the abundance of image types, and 2) convolutional neural networks (CNNs) constructing deep models by stacking cannot sufficiently identify LROIs, often deviate significantly from the LROIs focused on by experienced pathologists, and are prone to providing misleading second opinions. So we propose a novel fusion attention block network (FABNet) to address these problems. First, we propose a model transfer method based on clinical a priori experience and sample analysis (CPESA) that analyzes the transfer ability by integrating clinical a priori experience using indicators such as the relationship between the cancer onset location and morphology and the texture and staining degree of cell nuclei in histopathology images; our method further validates these indicators by the probability distribution of cancer image samples. Then, we propose a fusion attention block (FAB) structure, which can both provide an advanced non-uniform sparse representation of images and extract spatial relationship information between nuclei; consequently, the LROI can be more accurate and more relevant to pathologists. We conducted extensive experiments, compared with the best Baseline model, the classification accuracy is improved 25%, and It is demonstrated that FABNet performs better on different cancer pathology image datasets and outperforms other state of the art (SOTA) models.

AF-SENet: Classification of Cancer in Cervical Tissue Pathological Images Based on Fusing Deep Convolution Features.

Cervical cancer is the fourth most common cancer in the world. Whole-slide images (WSIs) are an important standard for the diagnosis of cervical cancer. Missed diagnoses and misdiagnoses often occur due to the high similarity in pathological cervical images, the large number of readings, the long reading time, and the insufficient experience levels of pathologists. Existing models have insufficient feature extraction and representation capabilities, and they suffer from insufficient pathological classification. Therefore, this work first designs an image processing algorithm for data augmentation. Second, the deep convolutional features are extracted by fine-tuning pre-trained deep network models, including ResNet50 v2, DenseNet121, Inception v3, VGGNet19, and Inception-ResNet, and then local binary patterns and a histogram of the oriented gradient to extract traditional image features are used. Third, the features extracted by the fine-tuned models are serially fused according to the feature representation ability parameters and the accuracy of multiple experiments proposed in this paper, and spectral embedding is used for dimension reduction. Finally, the fused features are inputted into the Analysis of Variance-F value-Spectral Embedding Net (AF-SENet) for classification. There are four different pathological images of the dataset: normal, low-grade squamous intraepithelial lesion (LSIL), high-grade squamous intraepithelial lesion (HSIL), and cancer. The dataset is divided into a training set (90%) and a test set (10%). The serial fusion effect of the deep features extracted by Resnet50v2 and DenseNet121 () is the best, with average classification accuracy reaching 95.33%, which is 1.07% higher than ResNet50 v2 and 1.05% higher than DenseNet121. The recognition ability is significantly improved, especially in LSIL, reaching 90.89%, which is 2.88% higher than ResNet50 v2 and 2.1% higher than DenseNet121. Thus, this method significantly improves the accuracy and generalization ability of pathological cervical WSI recognition by fusing deep features.

Surface Impedance of Metasurfaces/Graphene Hybrid Structures.

Understanding and manipulation of surface impedance in graphene hybrid structure is a significant issue for applications of graphene-based optoelectronics devices. In order to achieve this purpose in the terahertz region, analytical expressions for the impedances of metasurface were derived, which allows us to easily understand the relationship between physical dimensions and impedance. Simulation results show an excellent agreement with the analytical predictions. In addition, we focus on the synthetic impedance when square patch and graphene sheet joined together, discuss the influence of the size of metasurface as well as chemical potentiality as for graphene on the synthetic impedance. Based on these results, a number of absorbers as well as optical devices can be designed that utilize impedance metasurfaces.

Taste Recognition in E-Tongue Using Local Discriminant Preservation Projection.

Electronic tongue (E-Tongue), as a novel taste analysis tool, shows a promising perspective for taste recognition. In this paper, we constructed a voltammetric E-Tongue system and measured 13 different kinds of liquid samples, such as tea, wine, beverage, functional materials, etc. Owing to the noise of system and a variety of environmental conditions, the acquired E-Tongue data shows inseparable patterns. To this end, from the viewpoint of algorithm, we propose a local discriminant preservation projection (LDPP) model, an under-studied subspace learning algorithm, that concerns the local discrimination and neighborhood structure preservation. In contrast with other conventional subspace projection methods, LDPP has two merits. On one hand, with local discrimination it has a higher tolerance to abnormal data or outliers. On the other hand, it can project the data to a more separable space with local structure preservation. Further, support vector machine, extreme learning machine (ELM), and kernelized ELM (KELM) have been used as classifiers for taste recognition in E-Tongue. Experimental results demonstrate that the proposed E-Tongue is effective for multiple tastes recognition in both efficiency and effectiveness. Particularly, the proposed LDPP-based KELM classifier model achieves the best taste recognition performance of 98%. The developed benchmark data sets and codes will be released and downloaded in http://www.leizhang.tk/ tempcode.html.

Localized instance fusion of MRI data of Alzheimer's disease for classification based on instance transfer ensemble learning.

BACKGROUND: Diagnosis of Alzheimer's disease (AD) is very important, and MRI is an effective imaging mode of Alzheimer's disease. There are many existing studies on the diagnosis of Alzheimer's disease based on MRI data. However, there are no studies on the transfer learning between different datasets (including different subjects), thereby improving the sample size of target dataset indirectly. METHODS: Therefore, a new framework method is proposed in this paper to solve this problem. First, gravity transfer is used to transfer the source domain data closer to the target data set. Secondly, the best deviation between the transferred source domain samples and the target domain samples is searched by instance transfer learning algorithm (ITL) based on wrapper mode, thereby obtaining optimal transferred domain samples. Finally, the optimal transferred domain samples and the target domain training samples are combined for classification. If the source data and the target data have different features, a feature growing algorithm is proposed to solve this problem. RESULTS: The experimental results show that the proposed method is effective regardless of different kernel functions, different number of samples and different parameters. Besides, the transferred source domain samples by ITL algorithm can enlarge the target domain training samples and assist to improve the classification accuracy significantly. CONCLUSIONS: Therefore, the study can enlarge the samples of AD by instance transfer learning, thereby being helpful for the small sample problems of AD. Since the proposed algorithm is a framework algorithm, the study is heuristics to the relevant researchers.

A Novel Adaptive Modulation Based on Nondata-Aided Error Vector Magnitude in Non-Line-Of-Sight Condition of Wireless Sensor Network.

The high demand for multimedia applications in environmental monitoring, invasion detection, and disaster aid has led to the rise of wireless sensor network (WSN). With the increase of reliability and diversity of information streams, the higher requirements on throughput and quality of service (QoS) have been put forward in data transmission between two sensor nodes. However, lower spectral efficiency becomes a bottleneck in non-line-of-sight (NLOS) transmission of WSN. This paper proposes a novel nondata-aided error vector magnitude based adaptive modulation (NDA-EVM-AM) to solve the problem. NDA-EVM is considered as a new metric to evaluate the quality of NLOS link for adaptive modulation in WSN. By modeling the NLOS scenario as the η - µ fading channel, a closed-form expression for the NDA-EVM of multilevel quadrature amplitude modulation (MQAM) signals over the η - µ fading channel is derived, and the relationship between SER and NDA-EVM is also formulated. Based on these results, NDA-EVM state machine is designed for adaptation strategy. The algorithmic complexity of NDA-EVM-AM is analyzed and the outage capacity of NDA-EVM-AM in an NLOS scenario is also given. The performances of NDA-EVM-AM are compared by simulation, and the results show that NDA-EVM-AM is an effective technique to be used in the NLOS scenarios of WSN. This technique can accurately reflect the channel variations and efficiently adjust modulation order to better match the channel conditions, hence, obtaining better performance in average spectral efficiency.

Block-Diagonal Constrained Low-Rank and Sparse Graph for Discriminant Analysis of Image Data.

Recently, low-rank and sparse model-based dimensionality reduction (DR) methods have aroused lots of interest. In this paper, we propose an effective supervised DR technique named block-diagonal constrained low-rank and sparse-based embedding (BLSE). BLSE has two steps, i.e., block-diagonal constrained low-rank and sparse representation (BLSR) and block-diagonal constrained low-rank and sparse graph embedding (BLSGE). Firstly, the BLSR model is developed to reveal the intrinsic intra-class and inter-class adjacent relationships as well as the local neighborhood relations and global structure of data. Particularly, there are mainly three items considered in BLSR. First, a sparse constraint is required to discover the local data structure. Second, a low-rank criterion is incorporated to capture the global structure in data. Third, a block-diagonal regularization is imposed on the representation to promote discrimination between different classes. Based on BLSR, informative and discriminative intra-class and inter-class graphs are constructed. With the graphs, BLSGE seeks a low-dimensional embedding subspace by simultaneously minimizing the intra-class scatter and maximizing the inter-class scatter. Experiments on public benchmark face and object image datasets demonstrate the effectiveness of the proposed approach.

Opportunistic Capacity-Based Resource Allocation for Chunk-Based Multi-Carrier Cognitive Radio Sensor Networks.

The spectrum allocation for cognitive radio sensor networks (CRSNs) has received considerable research attention under the assumption that the spectrum environment is static. However, in practice, the spectrum environment varies over time due to primary user/secondary user (PU/SU) activity and mobility, resulting in time-varied spectrum resources. This paper studies resource allocation for chunk-based multi-carrier CRSNs with time-varied spectrum resources. We present a novel opportunistic capacity model through a continuous time semi-Markov chain (CTSMC) to describe the time-varied spectrum resources of chunks and, based on this, a joint power and chunk allocation model by considering the opportunistically available capacity of chunks is proposed. To reduce the computational complexity, we split this model into two sub-problems and solve them via the Lagrangian dual method. Simulation results illustrate that the proposed opportunistic capacity-based resource allocation algorithm can achieve better performance compared with traditional algorithms when the spectrum environment is time-varied.

A CSRR-Fed SIW Cavity-Backed Fractal Patch Antenna for Wireless Energy Harvesting and Communication.

This paper presents a novel compact dual-band and dual-polarized complementary split-ring resonator (CSRR)-fed substrate-integrated waveguide (SIW) cavity-backed fractal patch antenna for wireless energy harvesting and communication. The proposed antenna is composed of a Giuseppe Peano fractal radiation patch with a backed SIW cavity. To enhance the bandwidth and minimize the dimensions, the CSRR structure is designed to feed the Giuseppe Peano fractal patch orthogonally. A prototype of the proposed antenna is simulated, fabricated and measured. The proposed antenna exhibits good directionality and high cross-polarization level with especially compact size.

Determination of fenticonazole enantiomers by LC-ESI-MS/MS and its application to pharmacokinetic studies in female rats.

A simple, rapid, and specific high-performance liquid chromatograph coupled with a tandem mass spectrometry method has been developed and validated for the determination of fenticonazole (CAS 72479-26-6) enantiomers in rat plasma. Simple protein precipitation by acetonitrile was utilized for extracting analytes from the plasma samples. Chromatography separation was performed on a C18 analytical column (150 mm x 2.0 mm, 5 microm) with a mobile phase consisting of methanol-10 mM aqueous ammonium acetate (adjusted to pH 3.5 with acetic acid) (90:10, v/v) at a flow rate of 0.2 ml/min. Detection was carried out on a triple quadrupole mass spectrometer equipped with electrospray ionization (ESI) source, and operated in multiple-reaction monitoring (MRM) mode. The calibration curves were linear over the range 0.5 -200 ng/ml (r > 0.99). The relative recoveries of R-(-)-fenticonazole and its enantiomer were better than 85%. The intra- and inter-day precisions (R.S.D.%) and deviations of the assay accuracies were less than 10%. This newly developed and validated method was successfully applied to pharmacokinetic studies after administration at a single dose of 20 mg/ kg R-(-)-fenticonazole nitrate and its enantiomer to female rats per vagina. The Cmax value of S-(+)-fenticonazole was greater than that of R-(-)-fenticonazole by 1.36-fold, whereas, the t(1/2) beta and MRT values of R-(-)-fenticonazole were longer than those of its enantiomer by 1.95- and 1.24-fold. The results indicated that S-(+)-fenticonazole was faster in absorption and elimination in female rat. But, the Tmax and AUC(0-12) values for each of fenticonazole enantiomers were not significantly different.

Study on bioavailability difference between clopidogrel bisulfate form I and form II using liquid chromatography/tandem mass spectrometry.

The bioavailability of clopidogrel bisulfate (CAS 135046-48-9) form I was compared with that of clopidogrel bisulfate form II in 12 male Sprague-Dawley rats. The rats, randomly divided into two groups, received a single oral dose of 8 mg/kg clopidogrel (CP) bisulfate form I and form II, respectively, under fasting condition. The plasma concentrations of CP and its inactive carboxylic acid metabolite (CAS 144457-28-3, IM) were simultaneously determined by a sensitive, specific LC-MS/MS method. The pharmacokinetic parameters included C(max), T(max), t1/2, AUC(0-t), AUC(0-infinity). The AUC(0-infinity) of CP was 13.78 +/- 0.67 and 11.46 +/- 1.98 ng/ mL x h for CP form I and form II, respectively. The AUC(0-infinity) of IM was 33.08 +/- 5.76 and 21.67 +/- 8.95 microg/mL x h for CP form I and form II, respectively. The maximum plasma concentration (C(max)) of CP was 3.81 +/- 0.54 ng/mL for CP form I and 3.18 +/- 0.31 ng/mL for CP form II, the C(max) of IM was 3.42 +/- 0.41 and 2.08 +/- 0.68 microg/ mL for the CP form I and form II, respectively. There was an obvious difference between form I and form II for C(max) and the area under the plasma concentration time curve for both CP and IM after a t-test. This study shows that CP form I has better bioavailability in rats than CP form II.