S2DA-Net: Spatial and spectral-learning double-branch aggregation network for liver tumor segmentation in CT images.

Accurate liver tumor segmentation is crucial for aiding radiologists in hepatocellular carcinoma evaluation and surgical planning. While convolutional neural networks (CNNs) have been successful in medical image segmentation, they face challenges in capturing long-term dependencies among pixels. On the other hand, Transformer-based models demand a high number of parameters and involve significant computational costs. To address these issues, we propose the Spatial and Spectral-learning Double-branched Aggregation Network (S2DA-Net) for liver tumor segmentation. S2DA-Net consists of a double-branched encoder and a decoder with a Group Multi-Head Cross-Attention Aggregation (GMCA) module, Two branches in the encoder consist of a Fourier Spectral-learning Multi-scale Fusion (FSMF) branch and a Multi-axis Aggregation Hadamard Attention (MAHA) branch. The FSMF branch employs a Fourier-based network to learn amplitude and phase information, capturing richer features and detailed information without introducing an excessive number of parameters. The FSMF branch utilizes a Fourier-based network to capture amplitude and phase information, enriching features without introducing excessive parameters. The MAHA branch incorporates spatial information, enhancing discriminative features while minimizing computational costs. In the decoding path, a GMCA module extracts local information and establishes long-term dependencies, improving localization capabilities by amalgamating features from diverse branches. Experimental results on the public LiTS2017 liver tumor datasets show that the proposed segmentation model achieves significant improvements compared to the state-of-the-art methods, obtaining dice per case (DPC) 69.4 % and global dice (DG) 80.0 % for liver tumor segmentation on the LiTS2017 dataset. Meanwhile, the pre-trained model based on the LiTS2017 datasets obtain, DPC 73.4 % and an DG 82.2 % on the 3DIRCADb dataset.

Computational mechanistic investigation of the kinetic resolution of α-methyl-phenylacetaldehyde by norcoclaurine synthase.

Norcoclaurine synthase from Thalictrum flavum (TfNCS) demonstrated high stereospecificity and yield in catalyzing the Pictet-Spengler reaction of dopamine with chiral aldehydes, achieving kinetic resolution of aldehydes. However, the mechanism and the factors contributing to the stereoselectivity remain unclear. Herein, by using quantum chemical calculations, the mechanisms of TfNCS-catalyzed reactions of dopamine with both enantiomers of α-methyl-phenylacetaldehyde are studied. The calculations reveal a mechanism mirroring the reaction of natural substrates, for which the deprotonation of the C5-H of the cyclized intermediate is rate-limiting. The calculated overall barriers are 20.1 kcal mol-1 and 21.6 kcal mol-1 for the reactions of (R)- and (S)-α-methyl-phenylacetaldehyde, respectively. The M97 and L72 residues are proposed to be the key residues contributing to the stereospecificity. The obtained detailed information is helpful for designing new variants of TfNCS with extended substrate scope, and also advancing our understanding of TfNCS reactions for potential applications.

Ultrasensitive and Multiple Biomarker Discrimination for Alzheimer's Disease via Plasmonic & Microfluidic Sensing Technologies.

As the population ages, the worldwide prevalence of Alzheimer's disease (AD) as the most common dementia in the elderly is increasing dramatically. However, a long-term challenge is to achieve rapid and accurate early diagnosis of AD by detecting hallmarks such as amyloid beta (Aß42). Here, a multi-channel microfluidic-based plasmonic fiber-optic biosensing platform is established for simultaneous detection and differentiation of multiple AD biomarkers. The platform is based on a gold-coated, highly-tilted fiber Bragg grating (TFBG) and a custom-developed microfluidics. TFBG excites a high-density, narrow-cladding-mode spectral comb that overlaps with the broad absorption of surface plasmons for high-precision interrogation, enabling ultrasensitive monitoring of analytes. In situ detection and in-parallel discrimination of different forms of Aß42 in cerebrospinal fluid (CSF) are successfully demonstrated with a detection of limit in the range of ≈30-170 pg mL-1, which is one order of magnitude below the clinical cut-off level in AD onset, providing high detection sensitivity for early diagnosis of AD. The integration of the TFBG sensor with multi-channel microfluidics enables simultaneous detection of multiple biomarkers using sub-µL sample volumes, as well as combining initial binding rate and real-time response time to differentiate between multiple biomarkers in terms of binding kinetics. With the advantages of multi-parameter, low consumption, and highly sensitive detection, the sensor represents an urgently needed potentials for large-scale diagnosis of diseases at early stage.

[Exploration of Application of Essential Principles of Safety and Performance of Medical Devices and IVD Medical Devices: Take Artificial Joint Products as Example].

Through the effective application of Essential Principles of Safety and Performance of Medical Devices and IVD Medical Devices (EP), to continuously improve the corresponding management tools to ensure the safety and effectiveness of medical device in the quality management system, risk management system, evaluation of safety and effectiveness for the supervision departments and manufacturers. The current status of the application of EP and the application issues are analyzed in the study. Take artificial joint products for example, the idea of using EP in quality management system, risk management system and evaluation of safety and effectiveness is investigated, and several thoughts are proposed. Supervision departments should strengthen the unified understanding of EP, develop requirements according to the classification of medical device，and refine specific execution requirements.

Discovery of Unusual Ajmaline-Macroline Type Bisindole Alkaloids from Alstonia macrophylla by Building Blocks-Based Molecular Networking.

Three unusual ajmaline-macroline type bisindole alkaloids, alsmaphylines A-C, together with their postulated biogenetic precursors, were isolated from the stem barks and leaves of Alstonia macrophylla via the building blocks-based molecular network (BBMN) strategy. Alsmaphyline A represents a rare ajmaline-macroline type bisindole alkaloid with an S-shape polycyclic ring system. Alsmaphylines B and C are two novel ajmaline-macroline type bisindole alkaloids with N-1-C-21' linkages, and the former possesses an unconventional stacked conformation due to the presence of intramolecular noncovalent interactions. The chemical structures including absolute configurations of alsmaphylines A-C were established by comprehensive spectroscopic analyses, electronic circular dichroism (ECD) calculations, and single-crystal X-ray crystallography. In addition, a plausible biosynthetic pathway of these bisindole alkaloids as well as their ability to promote the protein synthesis on HT22 cells were discussed.

The volume regulated anion channel VRAC regulates NLRP3 inflammasome by modulating itaconate efflux and mitochondria function.

The NLRP3 inflammasome is a supramolecular complex that is linked to sterile and pathogen-dependent inflammation, and its excessive activation underlies many diseases. Ion flux disturbance and cell volume regulation are both reported to mediate NLRP3 inflammasome activation, but the underlying orchestrating signaling remains not fully elucidated. The volume-regulated anion channel (VRAC), formed by LRRC8 proteins, is an important constituent that controls cell volume by permeating chloride and organic osmolytes in response to cell swelling. We now demonstrate that Lrrc8a, the essential component of VRAC, plays a central and specific role in canonical NLRP3 inflammasome activation. Moreover, VRAC acts downstream of K+ efflux for NLRP3 stimuli that require K+ efflux. Mechanically, our data demonstrate that VRAC modulates itaconate efflux and damaged mitochondria production for NLRP3 inflammasome activation. Further in vivo experiments show mice with Lrrc8a deficiency in myeloid cells were protected from lipopolysaccharides (LPS)-induced endotoxic shock. Taken together, this work identifies VRAC as a key regulator of NLRP3 inflammasome and innate immunity by regulating mitochondrial adaption for macrophage activation and highlights VRAC as a prospective drug target for the treatment of NLRP3 inflammasome and itaconate related diseases.

Starch/polyvinyl alcohol with ionic liquid/graphene oxide enabled highly tough, conductive and freezing-resistance hydrogels for multimodal wearable sensors.

With ever-growing demand for eco-friendly materials for wearable electronics, biopolymer-based hydrogels have drawn significant attention. As one of the most abundant and biodegradable biopolymers, starch-based hydrogels have a great potential for wearable electronics. However, mechanical fragility, low conductivity and subzero freeze restrict their applications. Here, a multifunctional hydrogel was facilely fabricated by integrating ionic liquid and graphene oxide into potato starch/polyvinyl alcohol skeleton via a green physical-crosslinking method. The abundant hydrogen-bond and electrostatic interactions endowed the hydrogel with excellent stretchability (657.5 %), strength (0.64 MPa), high conductivity (1.98 S·m-1) and good anti-freezing property (< -20 °C). Multiple characterizations and theoretical simulation (DFT) were combined to understand and confirm the interactions among different components. Taking advantage of these properties, multimodal wearable sensors were constructed for sensing tension (gauge factor: 6.04), compression (gauge factor: 3.27) and temperature (sensitivity: 0.71 %/°C), which are applied for monitoring human motion, daily-life pressure and body temperature. The sensor had a good anti-fatigue property with stable signals during 2000 cycles. Moreover, the sensor can effectively recognize handwriting and perform human-computer interaction. This work provides a promising route to develop sustainable and multifunctional biopolymer hydrogels for wearable sensors with versatile applications in human health, exercise monitors and soft robots.

Epidemiological characteristics of ankylosing spondylitis in Guangxi Province of China from 2014 to 2021.

Introduction: To explore the epidemiological characteristics of ankylosing spondylitis (AS) in Guangxi Province of China through a large sample survey of more than 50 million aboriginal aboriginal population. Material and methods: A systematic search was conducted using the International Classification of Diseases 10 (ICD-10) codes M45.x00(AS), M45.x03+(AS with iridocyclitis), and M40.101(AS with kyphosis) to search the database in the National Health Statistics Network Direct Reporting System (NHSNDRS). 14004 patients were eventually included in the study. The parameters analyzed included the number of patients, gender, marriage, blood type, occupation, age at diagnosis, and location of household registration data each year, and statistical analysis was performed. Results: AS incidence rates increased from 1.30 (95% CI: 1.20-1.40) per 100,000 person-years in 2014 to 5.71 (95% CI: 5.50-5.92) in 2020 in Guangxi Province, and decreased slightly in 2021. Males have a higher incidence than females; the ratio was 5.61 : 1. The mean age of diagnosis in male patients was 45.4 (95% CI: 45.1-45.7) years, in females 47.6 (95% CI: 46.8-48.4) years. The most frequent blood type was O, and the most frequent occupation was farmer. The AS incidence rate was disparate in different cities. Liuzhou city had the highest eight-year average AS incidence rates from 2014 to 2021, and Chongzuo city had the lowest (p < 0.05). There was no significant difference in the incidence between different ethnic groups (p > 0.05). Conclusions: The AS person-years incidence rate was increasing in Guangxi province of China from 2014 to 2020, which had obvious gender and regional differences, showing the characteristics of local area aggregation.

Natural Products and Biological Activity from Actinomycetes Associated with Marine Algae.

Marine natural products have been recognized as the most promising source of bioactive substances for drug discovery research. This review illustrates the diversity of culturable actinobacteria associated with marine algae, their bioactivity and metabolites, and approaches to their isolation and determination of their biological properties. Furthermore, actinobacteria associated with marine algae are presented as a new subject for an extensive investigation to find novel and active natural products, which make them a potentially rich and innovative source for new drug development deserving more attention and exploration.

BreastDM: A DCE-MRI dataset for breast tumor image segmentation and classification.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has shown high sensitivity to diagnose breast cancer. However, few computer-aided algorithms focus on employing DCE-MR images for breast cancer diagnosis due to the lack of publicly available DCE-MRI datasets. To address this issue, our work releases a new DCE-MRI dataset called BreastDM for breast tumor segmentation and classification. In particular, a dataset of 232 patients selected with DCE-MR images for benign and malignant cases is established. Each case consists of three types of sequences: pre-contrast, post-contrast, and subtraction sequences. To show the difficulty of breast DCE-MRI tumor image segmentation and classification tasks, benchmarks are achieved by state-of-the-art image segmentation and classification algorithms, including conventional hand-crafted based methods and recently-emerged deep learning-based methods. More importantly, a local-global cross attention fusion network (LG-CAFN) is proposed to further improve the performance of breast tumor images classification. Specifically, LG-CAFN achieved the highest accuracy (88.20%, 83.93%) and AUC value (0.9154,0.8826) in both groups of experiments. Extensive experiments are conducted to present strong baselines based on various typical image segmentation and classification algorithms. Experiment results also demonstrate the superiority of the proposed LG-CAFN to other breast tumor images classification methods. The related dataset and evaluation codes are publicly available at smallboy-code/Breast-cancer-dataset.

S1PR1-dependent migration of ILC3s from intestinal tissue to the heart in a mouse model of viral myocarditis.

Type 3 innate lymphocytes have recently been reported as key factors in inflammatory diseases, but their role in viral myocarditis is unclear. By flow cytometry, coxsackievirus B3-induced myocarditis mice were detected to increase the number of type 3 innate lymphocytes, and their main type was NKp46+ type 3 innate lymphocytes. In contrast, application of CD90.2 neutralizing antibody in T-cell-deficient mice reduced the number of innate lymphocytes and improved myocarditis. Innate lymphocytes from CD45.1 mouse intestinal lamina propria lymphocytes were adoptively transferred into recipient mice, and a comparable proportion of CD45.1+ cells were observed in the hearts of coxsackievirus B3-infected recipient mice. The upregulation of S1PR1, KLF2, CXCR6, and CXCL16 in the hearts of coxsackievirus B3-infected mice, as well as the greatly reduced numbers of innate lymphocytes infiltrating the hearts after S1PR1 inhibition, suggests that intestinal innate lymphocytes may migrate to the hearts via the CXCL16/CXCR6 axis. Taken together, our results demonstrate that increased type 3 innate lymphocytes in the heart during viral myocarditis may contribute to inflammatory progression and that this increased population of type 3 innate lymphocytes likely originates from the intestine.

New Isocoumarin and Pyrone Derivatives from the Chinese Mangrove Plant Rhizophora mangle-Associated Fungus Phomopsis sp. DHS-11.

Mangrove-associated fungi are important sources for the discovery of new bioactive natural products. Three new isocoumarins (1-3) and one new pyrone derivative (4) were isolated from the ethyl acetate extract of the fermentation broth of the mangrove endophytic fungus Phomopsis sp. DHS-11. Nuclear magnetic resonance (NMR) spectroscopy (one-dimensional and two-dimensional) and mass spectrometry were used to determine the structures of these new compounds. The absolute configurations for the new isocoumarins 1-3 were determined by comparing their experimental and calculated electronic circular dichroism (ECD) spectra, while the configuration for the new pyrone-derivative 4 was tentatively solved by comparison of its 13C NMR data with reported data. In the biological activity test, compounds 1 and 3 showed cytotoxic activity against HeLa cells with IC50 values of 11.49 ± 1.64 µM and 8.70 ± 0.94 µM, respectively. The initial structure and activity relationship (SAR) analysis revealed that the length of the side chain at C-3 for isocoumarin-type compounds 1-3 could affect the cytotoxicity against HeLa cells. Compound 4 exhibited cytotoxic activities against human hepatoma cells HepG2 with an IC50 value of 34.10 ± 2.92 µM. All compounds have no immunosuppressive activity.

Uncovering the Mechanism of Azepino-Indole Skeleton Formation via Pictet-Spengler Reaction by Strictosidine Synthase: A Quantum Chemical Investigation.

Strictosidine synthase (STR) catalyzes the Pictet-Spengler (PS) reaction of tryptamine and secologanin to produce strictosidine. Recent studies demonstrated that the enzyme can also catalyze the reaction of non-natural substrates to form new alkaloid skeletons. For example, the PS condensation of 1H-indole-4-ethanamine with secologanin could be promoted by the STR from Rauvolfia serpentina (RsSTR) to generate a rare class of skeletons with a seven-membered ring, namely azepino-[3,4,5-cd]-indoles, which are precursors for the synthesis of new compounds displaying antimalarial activity. In the present study, the detailed reaction mechanism of RsSTR-catalyzed formation of the rare seven-membered azepino-indole skeleton through the PS reaction was revealed at the atomic level by quantum chemical calculations. The structures of the transition states and intermediates involved in the reaction pathway were optimized, and the energetics of the complete reaction were analyzed. Based on our calculation results, the most likely pathway of the enzyme-catalyzed reaction was determined, and the rate-determining step of the reaction was clarified. The mechanistic details obtained in the present study are important in understanding the promiscuous activity of RsSTR in the formation of the rare azepino-indole skeleton molecule and are also helpful in designing STR enzymes for the synthesis of other new alkaloid skeleton molecules.

Bimetallic infinite coordination nanopolymers via phototherapy and STING activation for eliciting robust antitumor immunity.

Phototherapy can trigger immunogenic cell death of tumors in situ, whereas it is virtually impossible to eradicate the tumor due to the intrinsic resistance and inefficient anti-tumor immunity. To overcome these limitations, novel bimetallic infinite coordination nanopolymers (TA-Fe/Mn-OVA@MB NPs) were synthesized using model antigen ovalbumin (OVA) as a template to assemble tannic acid (TA) and bi-metal, supplemented with methylene blue (MB) surface absorption. The formulated TA-Fe/Mn-OVA@MB NPs possess excellent photothermal and photodynamic therapy (PTT/PDT) performance, which is adequate to destroy tumor cells by physical and chemical attack. Especially, these TA-Fe/Mn-OVA@MB NPs are capability of promoting the dendritic cells (DCs) maturation and antigen presentation via manganese-mediated cGAS-STING pathway activation, finally activating cytotoxicity T lymphocyte and promoting memory T lymphocyte differentiation in the peripheral lymphoid organs. In conclusion, this research offers a versatile metal-polyphenol nanoplatform to integrate functional metals and therapeutic molecule for topical phototherapy and robust anti-tumor immune activation.

A traditional prescription comprising Astragali Radix and Schisandra chinensis Fructus induces apoptosis and protective autophagy in hepatocellular carcinoma cells.

ETHNOPHARMACOLOGICAL RELEVANCE: Hepatocellular carcinoma (HCC) poses a growing challenge to global health efforts. The 5-year survival rate of HCC patients is still dismal. A traditional prescription Qi-Wei-Wan (QWW) comprising Astragali Radix and Schisandra chinensis Fructus has traditionally been used for HCC treatment according to traditional Chinese medicine theory, but the pharmacological basis is not clear. AIM OF THE STUDY: This study aims to investigate the anti-HCC effects of an ethanolic extract of QWW (hereafter, QWWE) and the mechanism of action. MATERIALS AND METHODS: An UPLC-Q-TOF-MS/MS method was developed to control the quality of QWWE. Two human HCC cell lines (HCCLM3 and HepG2) and a HCCLM3 xenograft mouse model were employed to investigate the anti-HCC effects of QWWE. The anti-proliferative effect of QWWE in vitro was determined by MTT, colony formation and EdU staining assays. Apoptosis and protein levels were examined by flow cytometry and Western blotting, respectively. Nuclear presence of signal transducer and activator of transcription 3 (STAT3) was examined by immunostaining. Transient transfection of pEGFP-LC3 and STAT3C plasmids was performed to assess autophagy and determine the involvement of STAT3 signaling in QWWE's anti-HCC effects, respectively. RESULTS: We found that QWWE inhibited the proliferation of and triggered apoptosis in HCC cells. Mechanistically, QWWE inhibited the activation of SRC and STAT3 at Tyr416 and Tyr705, respectively; inhibited the nuclear translocation of STAT3; lowered Bcl-2 protein levels, while increased Bax protein levels in HCC cells. Over-activating STAT3 attenuated the cytotoxic and apoptotic effects of QWWE in HCC cells. Moreover, QWWE induced autophagy in HCC cells by inhibiting mTOR signaling. Blocking autophagy with autophagy inhibitors (3-methyladenine and chloroquine) enhanced the cytotoxicity, apoptotic effect and the inhibitory effect on STAT3 activation of QWWE. Intragastric administration of QWWE at 10 mg/kg and 20 mg/kg potently repressed tumor growth and inhibited STAT3 and mTOR signaling in tumor tissues, but did not significantly affect mouse body weight. CONCLUSION: QWWE exhibited potent anti-HCC effects. Inhibiting the STAT3 signaling pathway is involved in QWWE-mediated apoptosis, while blocking mTOR signaling contributes to QWWE-mediated autophagy induction. Blockade of autophagy enhanced the anti-HCC effects of QWWE, indicating that the combination of an autophagy inhibitor and QWWE might be a promising therapeutic strategy for HCC management. Our findings provide pharmacological justifications for the traditional use of QWW in treating HCC.

Exocarpium Citri Grandis alleviates the aggravation of NAFLD by mitigating lipid accumulation and iron metabolism disorders.

ETHNOPHARMACOLOGICAL RELEVANCE: Exocarpium Citri grandis (ECG, Huajuhong in Chinese), the epicarp of C. grandis 'Tomentosa', has been used for hundreds of years as an anti-inflammatory, expectorant, hypoglycemic, and lipid-lowering medication in China. Nevertheless, there have been few papers that have explored the mechanism behind ECG's hypolipidemic characteristics from the perspective of treating nonalcoholic fatty liver disease (NAFLD). AIM OF STUDY: The purpose of our study was to confirm the therapeutic and preventative effects of ECG in NAFLD by regulating lipid accumulation and iron metabolism, and to explore the specific mechanism of ECG in enhancing hepatic iron transport and excretion capabilities. STUDY DESIGN: We constructed a NAFLD model by feeding male C57BL/6 J mice with a high-fat diet for 12 weeks. Mice were gavaged with ECG beginning in the seventh week of modeling, and three dosage gradients were established: low dose group (2.5 g/kg/d), medium dose group (5 g/kg/d) y, and high dose group (10 g/kg/d) until the end of model construction in week 12. MATERIALS AND METHODS: We used network pharmacology to analyze the relationship between ECG and NAFLD. In addition, we constructed a nonalcoholic fatty liver disease model by feeding male C57BL/6 J mice a high-fat diet for 12 weeks. Finally, lipid accumulation, iron accumulation, inflammation and oxidative stress were evaluated by serological index detection, histological detection, immunofluorescent and immunohistochemical staining, and western blotting. RESULTS: Network pharmacology confirmed the treatment effect of ECG in NAFLD. Three active components of ECG, including Naringenin, Naringin and Neohesperidin, were detected by UHPLC-HRMS analysis. The results of serum TC, TG, LDL concentration, HE staining, Oil red staining and Nile red staining demonstrated that ECG could improve lipid metabolism disorders. The results of serum iron concentration, liver tissue iron concentration, iron metabolism-related proteins Ferritin light chain, Ferroportin1, Transferrin receptor, and Transferrin demonstrated that ECG improved the iron transport and storage capacities of hepatic cells. CONCLUSIONS: Our results demonstrated that ECG relieved liver injury by inhibiting lipid accumulation and iron accumulation in NAFLD.

First Report of Bark Split Disease Caused by Pectobacterium carotovorum on Artocarpus heterophyllus (Jackfruit) in China.

Jackfruit (Artocarpus heterophyllus) is widely cultivated in the tropical areas in the world. Jackfruit bark split disease occurred in the large-scale plantations of 18 cities and counties surveyed in Hainan since 2021, among which the incidence rate of serious orchards reached about 70%, and the mortality rate reached about 35%. Jackfruit bark split disease mainly harms tree branches and trunks, manifested as water stains, bark gumming, bark depression, bark cracking, and ultimately plant death. To identify the pathogen, Four samples with jackfruit bark split disease symptoms were collected, sterilized with 75% ethanol for 30 s, then soaked in 2% sodium hypochlorite (NaClO) for 5 mins, and finally rinsed continuously with sterilized distilled water. The sterilized tissues were placed on LB agar medium and incubated in illumination incubator at 28 ℃. Four milky white, round with neat edges, convex and smooth, translucent colonies were obtained. All isolates (JLPs-1 to JLPs-4) were Gram-negative, negative for oxidase, catalase and gelatin liquefaction. Amplification and sequencing of 16S rDNA gene from 4 isolates were conducted with the universal primers 27f /1492r (Lane et al. 1991). The BLASTn analysis of obtained JLPs-1 and JLPs-3 sequences (GenBank accession nos. OP942452 and OP942453) showed an identity percentage of 98.99% and 98.93% with Pectobacterium sp. (CP104733), respectively. Phylogenetic analysis based on 16S rDNA gene using the neighbor-joining method with MEGA 7.0 software revealed that JLPs-1 and JLPs-3 were clustered together with P. carotovorum reference strains. The four housekeeping genes gyrA, recA, rpoA and rpoS were partially sequenced for JLPs-1 isolates using primers gyrA1/gyrA4, recA1/recA2c, rpoS1/rpoS2 and rpoA F1/rpoA R1 (Loc et al. 2022), respectively. Multilocus sequence analyses identified the isolates from jackfruit as P. carotovorum. To further confirm the identification of Pectobacterium carotovorum, pelY gene, P. carotovorum subsp. Brasiliensis 16S-23S intergenic region (Pcb IGS) and P. carotovorum subsp. carotovorum (Pcc) specific fragment were amplified with primers Y1/Y2 (Darrasse et al. 1994), BR1f/L1r (Duarte et al. 2004) and EXPCCF/EXPCCR (Kang et al. 2003), respectively. A 540 bp target fragment was successfully amplified from JTPs only by EXPCCF/EXPCCR and there no bands for the other two primers. Pathogenicity test was performed in the field, and all the inoculated trees were 2-3-year-old 'Qiong Yin No.1' variety. Dense small holes were pierced with sterilized inoculation needle on four healthy jackfruit trees. Then punctured wounds were spraying-inoculated with bacteria suspension of JLPs-1 (108 CFU/ml), and finally wrapped with plastic wrap to moisturize. Two trees inoculated with sterile distilled water served as negative control. Typical symptoms of bark gumming, bark depression, bark cracking were observed on all of the inoculated trees at 17 dpi which just similar to those originally caused by P. carotovorum in the field, whereas negative control trees remained asymptomatic. The strains were re-isolated successfully from symptomatic jackfruit trees and were consistent with the biological and molecular biological characteristics of original strains, confirming that the pathogen of jackfruit bark split disease was Pectobacterium carotovorum. To our knowledge, this is the first report of P. carotovorum causing bark split disease on jackfruit in China.

BAF-Net: Bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation.

The segmentation of pepper leaves from pepper images is of great significance for the accurate control of pepper leaf diseases. To address the issue, we propose a bidirectional attention fusion network combing the convolution neural network (CNN) and Swin Transformer, called BAF-Net, to segment the pepper leaf image. Specially, BAF-Net first uses a multi-scale fusion feature (MSFF) branch to extract the long-range dependencies by constructing the cascaded Swin Transformer-based and CNN-based block, which is based on the U-shape architecture. Then, it uses a full-scale feature fusion (FSFF) branch to enhance the boundary information and attain the detailed information. Finally, an adaptive bidirectional attention module is designed to bridge the relation of the MSFF and FSFF features. The results on four pepper leaf datasets demonstrated that our model obtains F1 scores of 96.75%, 91.10%, 97.34% and 94.42%, and IoU of 95.68%, 86.76%, 96.12% and 91.44%, respectively. Compared to the state-of-the-art models, the proposed model achieves better segmentation performance. The code will be available at the website: https://github.com/fangchj2002/BAF-Net.

Approximate solutions to several classes of Volterra and Fredholm integral equations using the neural network algorithm based on the sine-cosine basis function and extreme learning machine.

In this study, we investigate a new neural network method to solve Volterra and Fredholm integral equations based on the sine-cosine basis function and extreme learning machine (ELM) algorithm. Considering the ELM algorithm, sine-cosine basis functions, and several classes of integral equations, the improved model is designed. The novel neural network model consists of an input layer, a hidden layer, and an output layer, in which the hidden layer is eliminated by utilizing the sine-cosine basis function. Meanwhile, by using the characteristics of the ELM algorithm that the hidden layer biases and the input weights of the input and hidden layers are fully automatically implemented without iterative tuning, we can greatly reduce the model complexity and improve the calculation speed. Furthermore, the problem of finding network parameters is converted into solving a set of linear equations. One advantage of this method is that not only we can obtain good numerical solutions for the first- and second-kind Volterra integral equations but also we can obtain acceptable solutions for the first- and second-kind Fredholm integral equations and Volterra-Fredholm integral equations. Another advantage is that the improved algorithm provides the approximate solution of several kinds of linear integral equations in closed form (i.e., continuous and differentiable). Thus, we can obtain the solution at any point. Several numerical experiments are performed to solve various types of integral equations for illustrating the reliability and efficiency of the proposed method. Experimental results verify that the proposed method can achieve a very high accuracy and strong generalization ability.