High-Matching and Low-Cost Realization of the FHN Neuron Model on Reconfigurable FPGA Board.

The main objectives of neuromorphic engineering are the research, modeling, and implementation of neural functioning in the human brain. We provide a hardware solution that can replicate such a nature-inspired system by merging multiple scientific domains and is based on neural cell processes. This work provides a modified version of the original Fitz-Hugh Nagumo (FHN) neuron using a simple 2V term called Hybrid Piece-Wised Base-2 Model (HPWBM), which accurately reproduces numerous patterns of the original neuron model. With reduced terms, we suggest modifying the original nonlinear term to achieve high matching accuracy and little computing error. Time domain and phase portraits are used to validate the proposed model, which shows that it can reproduce all of the FHN model's properties with high accuracy and little mistake. We provide an effective digital hardware approach for large-scale neuron implementations based on resource-sharing and pipelining strategies. The Hardware Description Language (HDL) is used to construct the hardware on an FPGA as a proof of concept. The recommended model hardly uses 0.48 percent of the resources on a Virtex 4 FPGA board, according to the results of the hardware implementation. The circuit can run at a maximum frequency of 448.236 MHz, according to the static timing study.

Pancreatic cancer pathology image segmentation with channel and spatial long-range dependencies.

Based on deep learning, pancreatic cancer pathology image segmentation technology effectively assists pathologists in achieving improved treatment outcomes. However, compared to traditional image segmentation tasks, the large size of tissues in pathology images requires a larger receptive field. While methods based on dilated convolutions or attention mechanisms can enhance the receptive field, they cannot capture long-range feature dependencies. Directly applying self-attention mechanisms to capture long-range dependencies results in intolerable computational complexity. To address these challenges, we introduce a channel and spatial self-attention (CS) Module designed for efficiently capturing both channel and spatial long-range feature dependencies in pancreatic cancer pathological images. Specifically, the channel and spatial self-attention module consists of an adaptive channel self-attention module and a window-shift spatial self-attention module. The adaptive channel self-attention module adaptively pools features to a fixed size to capture long-range feature dependencies. While the window-shift spatial self-attention module captures spatial long-range dependencies in a window-based manner. Additionally, we propose a re-weighted cross-entropy loss to mitigate the impact of long-tail distribution on performance. Our proposed method surpasses state-of-the-art on both our Pancreatic Cancer Pathology Image (PCPI) dataset and the GlaS challenge dataset. The mDice and mIoU have achieved 73.93% and 59.42% in our PCPI dataset.

Learning Graph Convolutional Networks for Multi-Label Recognition and Applications.

The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model the label dependencies to improve the recognition performance. To capture and explore such important information, we propose graph convolutional networks (GCNs) based models for multi-label image recognition, where directed graphs are constructed over classes and information is propagated between classes to learn inter-dependent class-level representations. Following this idea, we design two particular models that approach multi-label classification from different views. In our first model, the prior knowledge about the class dependencies is integrated into classifier learning. Specifically, we propose Classifier Learning GCN (C-GCN) to map class-level semantic representations (e.g., word embeddings) into classifiers that maintain the inter-class topology. In our second model, we decompose the visual representation of an image into a set of label-aware features and propose prediction learning GCN (P-GCN) to encode such features into inter-dependent image-level prediction scores. Furthermore, we also present an effective correlation matrix construction approach to capture inter-class relationships and consequently guide information propagation among classes. Empirical results on generic multi-label image recognition demonstrate that both of the proposed models can obviously outperform other existing state-of-the-arts. Moreover, the proposed methods also show advantages in some other multi-label classification related applications.

SST: Spatial and Semantic Transformers for Multi-Label Image Recognition.

Multi-label image recognition has attracted considerable research attention and achieved great success in recent years. Capturing label correlations is an effective manner to advance the performance of multi-label image recognition. Two types of label correlations were principally studied, i.e., the spatial and semantic correlations. However, in the literature, previous methods considered only either of them. In this work, inspired by the great success of Transformer, we propose a plug-and-play module, named the Spatial and Semantic Transformers (SST), to simultaneously capture spatial and semantic correlations in multi-label images. Our proposal is mainly comprised of two independent transformers, aiming to capture the spatial and semantic correlations respectively. Specifically, our Spatial Transformer is designed to model the correlations between features from different spatial positions, while the Semantic Transformer is leveraged to capture the co-existence of labels without manually defined rules. Other than methodological contributions, we also prove that spatial and semantic correlations complement each other and deserve to be leveraged simultaneously in multi-label image recognition. Benefitting from the Transformer's ability to capture long-range correlations, our method remarkably outperforms state-of-the-art methods on four popular multi-label benchmark datasets. In addition, extensive ablation studies and visualizations are provided to validate the essential components of our method.

HCE: Hierarchical Context Embedding for Region-Based Object Detection.

State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The region-wise features, in spite of aligning well with the proposal locations, may still lack the crucial context information which is necessary for filtering out noisy background detections, as well as recognizing objects possessing no distinctive appearances. To address this issue, we present a simple but effective Hierarchical Context Embedding (HCE) framework, which can be applied as a plug-and-play component, to facilitate the classification ability of a series of region-based detectors by mining contextual cues. Specifically, to advance the recognition of context-dependent object categories, we propose an image-level categorical embedding module which leverages the holistic image-level context to learn object-level concepts. Then, novel RoI features are generated by exploiting hierarchically embedded context information beneath both whole images and interested regions, which are also complementary to conventional RoI features. Moreover, to make full use of our hierarchical contextual RoI features, we propose the early-and-late fusion strategies (i.e., feature fusion and confidence fusion), which can be combined to boost the classification accuracy of region-based detectors. Comprehensive experiments demonstrate that our HCE framework is flexible and generalizable, leading to significant and consistent improvements upon various region-based detectors, including FPN, Cascade R-CNN, Mask R-CNN and PA-FPN. With simple modification, our HCE framework can be conveniently adapted to fit the structure of one-stage detectors, and achieve improved performance for SSD, RetinaNet and EfficientDet.

A Band-Pass Filter Based on Half-Mode Substrate Integrated Waveguide and Spoof Surface Plasmon Polaritons.

In this paper, a band-pass filter based on half-mode substrate integrated waveguide (HMSIW) and double-layer spoof surface plasmon polaritons (SSPPs) consisting of two corrugated metal strips is proposed, which can realize band-pass transmission by etching periodic grooves at the top and bottom metal layers of the HMSIW. Moreover, the influences of important parameters on the performance of the proposed band-pass filter are analyzed by parametric study. By changing the key parameters, the low and high cut-off frequency can be controlled independently. The corresponding equivalent circuit of the proposed band-pass filter is put forward to explain the physical mechanism. Compared with the previous structures, this structure features smaller size, wider bandwidth and lower loss. Simulated results show that the proposed band-pass filter achieves a bandwidth (for |S11| < -10 dB and |S21| > -0.8 dB) of about 69.77% (15.6-32.1 GHz). The measured results have good agreements with the simulated ones, which verify that the proposed band-pass filter has good performances and potential applications at the microwave frequencies.

Induction of detoxification enzymes by quercetin in the silkworm.

Quercetin is one of the most abundant flavonoids and the defense secondary metabolites in plants. In this study, the effect of quercetin on the growth of the silkworm larvae was investigated. Cytochrome P450 monooxygenases (P450s), glutathione S-transferases (GSTs), and carboxylesterases (COE) were assayed after exposure to different concentrations of quercetin for 3 d (short-term) and 7 d (long-term), respectively. The results showed that the weight gain of the silkworm larvae significantly decreased after the larvae were treated by different concentrations of quercetin except for the treatment with 0.5% quercetin. Activities of P450, GST, and COE were induced by 0.5 or 1% concentration of quercetin. In the midgut, the induction activity of P450s was reached to the highest level (2.3-fold) by 1% quercetin for 7 d, the highest induction activities of GSTs toward CHP and CDNB were 4.1-fold and 2.6-fold of controls by 1% quercetin after 7 d exposure, respectively. For COEs, the highest activity (2.3-fold) was induced by 0.5% quercetin for 7 d. However, P450s in whole body were higher inducible activities in short-term treatment than those in long-term treatment. The responses of eight cytochrome P450 (CYP) genes belonged to CYP6 and CYP9 families and seven GST genes were detected with real-time polymerase chain reaction. In addition, the genes induced by quercetin significantly were confirmed by qRT-PCR. CYP6AB5, CYP6B29, and GSTe8 were identified as inducible genes, of which the highest induction levels were 10.9-fold (0.5% quercetin for 7 d), 6.2-fold (1% quercetin for 7 d), and 7.1-fold (1% quercetin for 7 d), respectively.

Unique pattern of fibrosing cholestatic hepatitis after liver transplantation.

OBJECTIVE: To explore the pathological features and the differential diagnosis of recurrent HBV after liver transplantation. METHODS: One case of liver transplantation for HBV cirrhosis was subjected to liver biopsies on time postoperatively. RESULTS: 25 days after liver transplantation, serologic HBsAg, HBeAg and HBV-DNA of the patient became negative, but HBsAg was positive again on day 58 after liver transplantation. Histopathological examination showed balloon-like changes of hepatocytes with fragmental necrosis, fibrosis in the portal areas and around the portal veins, cholestasis in some hepatocytes and canaliculi, and positive HBsAg and HBcAg with immunohistochemical staining. clinically hepatic enzyme levels progressively increased, maintained for some time, and decreased rapidly at last. Stubborn hypoproteinemia was associated with the aggregation of general condition of the patient. CONCLUSIONS: Fibrosing cholestatic hepatitis (FCH) is a special type in recurrent infection of HBV after liver transplantation. It has a serious clinical process and specific pathological changes different from those of the usual HBV.