AISOA-SSformer: An Effective Image Segmentation Method for Rice Leaf Disease Based on the Transformer Architecture.

Rice leaf diseases have an important impact on modern farming, threatening crop health and yield. Accurate semantic segmentation techniques are crucial for segmenting diseased leaf parts and assisting farmers in disease identification. However, the diversity of rice growing environments and the complexity of leaf diseases pose challenges. To address these issues, this study introduces an innovative semantic segmentation algorithm for rice leaf pests and diseases based on the Transformer architecture AISOA-SSformer. First, it features the sparse global-update perceptron for real-time parameter updating, enhancing model stability and accuracy in learning irregular leaf features. Second, the salient feature attention mechanism is introduced to separate and reorganize features using the spatial reconstruction module (SRM) and channel reconstruction module (CRM), focusing on salient feature extraction and reducing background interference. Additionally, the annealing-integrated sparrow optimization algorithm fine-tunes the sparrow algorithm, gradually reducing the stochastic search amplitude to minimize loss. This enhances the model's adaptability and robustness, particularly against fuzzy edge features. The experimental results show that AISOA-SSformer achieves an 83.1% MIoU, an 80.3% Dice coefficient, and a 76.5% recall on a homemade dataset, with a model size of only 14.71 million parameters. Compared with other popular algorithms, it demonstrates greater accuracy in rice leaf disease segmentation. This method effectively improves segmentation, providing valuable insights for modern plantation management. The data and code used in this study will be open sourced at https://github.com/ZhouGuoXiong/Rice-Leaf-Disease-Segmentation-Dataset-Code.

PMANet: a time series forecasting model for Chinese stock price prediction.

Forecasting stock movements is a crucial research endeavor in finance, aiding traders in making informed decisions for enhanced profitability. Utilizing actual stock prices and correlating factors from the Wind platform presents a potent yet intricate forecasting approach. While previous methodologies have explored this avenue, they encounter challenges including limited comprehension of interrelations among stock data elements, diminished accuracy in extensive series, and struggles with anomaly points. This paper introduces an advanced hybrid model for stock price prediction, termed PMANet. PMANet is founded on Multi-scale Timing Feature Attention, amalgamating Multi-scale Timing Feature Convolution and Ant Particle Swarm Optimization. The model elevates the understanding of dependencies and interrelations within stock data sequences through Probabilistic Positional Attention. Furthermore, the Encoder incorporates Multi-scale Timing Feature Convolution, augmenting the model's capacity to discern multi-scale and significant features while adeptly managing lengthy input sequences. Additionally, the model's proficiency in addressing anomaly points in stock sequences is enhanced by substituting the optimizer with Ant Particle Swarm Optimization. To ascertain the model's efficacy and applicability, we conducted an empirical study using stocks from four pivotal industries in China. The experimental outcomes demonstrate that PMANet is both feasible and versatile in its predictive capability, yielding forecasts closely aligned with actual values, thereby fulfilling application requirements more effectively.

A Multi-Modal Open Object Detection Model for Tomato Leaf Diseases with Strong Generalization Performance Using PDC-VLD.

Precise disease detection is crucial in modern precision agriculture, especially in ensuring the health of tomato crops and enhancing agricultural productivity and product quality. Although most existing disease detection methods have helped growers identify tomato leaf diseases to some extent, these methods typically target fixed categories. When faced with new diseases, extensive and costly manual annotation is required to retrain the dataset. To overcome these limitations, this study proposes a multimodal model PDC-VLD based on the open-vocabulary object detection (OVD) technology within the VLDet framework, which can accurately identify new tomato leaf diseases without manual annotation by using only image-text pairs. First, we developed a progressive visual transformer-convolutional pyramid module (PVT-C) that effectively extracts tomato leaf disease features and optimizes anchor box positioning using the self-supervised learning algorithm DINO, suppressing interference from irrelevant backgrounds. Then, a context feature guided module (CFG) was adopted to address the low adaptability and recognition accuracy of the model in data-scarce environments. To validate the model's effectiveness, we constructed a tomato leaf disease image dataset containing 4 base classes and 2 new categories. Experimental results show that the PDC-VLD model achieved 61.2% on the main evaluation metric mAP novel 50 , and 56.4% on mAP novel 75 , 87.7% on mAP base 50 , 81.0% on mAP all 50 , and 45.5% on average recall, outperforming existing OVD models. Our research provides an innovative solution for efficiently and accurately detecting new diseases, substantially reducing the need for manual annotation, and offering critical technical support and practical reference for agricultural workers.

Purse-string suture with nylon cords and metal clips for the treatment of duodenal fistulae under the endoscope: a case report.

Purse-string suture with nylon cords and metal clips under the endoscope is a novel therapeutic technique which is minimally invasive and it is particularly indicated for the closure and repair of gastrointestinal fistula or perforations such as duodenal fistulae. Duodenal fistulae are often caused by medical manipulation, disease progression or trauma. Once this occurs, it leads to a series of pathophysiologic changes and a variety of complications. In most cases, these complications will exacerbate the damage to the organism, and the complications are difficult to treat and can lead to infections, nutrient loss, multi-organ dysfunction and many other adverse effects. In this case report, the use of endoscopic nylon cords combined with purse-string suture and metal clips in the treatment of duodenal fistula is presented and discussed. The patient was treated with endoscopic purse-string suture and the duodenal fistula was significantly improved. The results indicate that endoscopic purse-string suture is an effective strategy for the treatment of duodenal fistulae.

Identification of Pepper Leaf Diseases Based on TPSAO-AMWNet.

Pepper is a high-economic-value agricultural crop that faces diverse disease challenges such as blight and anthracnose. These diseases not only reduce the yield of pepper but, in severe cases, can also cause significant economic losses and threaten food security. The timely and accurate identification of pepper diseases is crucial. Image recognition technology plays a key role in this aspect by automating and efficiently identifying pepper diseases, helping agricultural workers to adopt and implement effective control strategies, alleviating the impact of diseases, and being of great importance for improving agricultural production efficiency and promoting sustainable agricultural development. In response to issues such as edge-blurring and the extraction of minute features in pepper disease image recognition, as well as the difficulty in determining the optimal learning rate during the training process of traditional pepper disease identification networks, a new pepper disease recognition model based on the TPSAO-AMWNet is proposed. First, an Adaptive Residual Pyramid Convolution (ARPC) structure combined with a Squeeze-and-Excitation (SE) module is proposed to solve the problem of edge-blurring by utilizing adaptivity and channel attention; secondly, to address the issue of micro-feature extraction, Minor Triplet Disease Focus Attention (MTDFA) is proposed to enhance the capture of local details of pepper leaf disease features while maintaining attention to global features, reducing interference from irrelevant regions; then, a mixed loss function combining Weighted Focal Loss and L2 regularization (WfrLoss) is introduced to refine the learning strategy during dataset processing, enhancing the model's performance and generalization capabilities while preventing overfitting. Subsequently, to tackle the challenge of determining the optimal learning rate, the tent particle snow ablation optimizer (TPSAO) is developed to accurately identify the most effective learning rate. The TPSAO-AMWNet model, trained on our custom datasets, is evaluated against other existing methods. The model attains an average accuracy of 93.52% and an F1 score of 93.15%, demonstrating robust effectiveness and practicality in classifying pepper diseases. These results also offer valuable insights for disease detection in various other crops.

IMT030122, A novel engineered EpCAM/CD3/4-1BB tri-specific antibody, enhances T-cell recruitment and demonstrates anti-tumor activity in mouse models of colorectal cancer.

Colorectal cancer is a major global health burden, with limited efficacy of traditional treatment modalities in improving survival rates. However, recently advances in immunotherapy has improved treatment outcomes for patients with this cancer. To address the continuing need for improved treatment efficacy, this study introduced a novel tri-specific antibody, IMT030122, that targets EpCAM, 4-1BB, and CD3. We evaluated the pharmacological efficacy and mechanism of action of IMT030122 in vitro and in vivo. In in vitro studies, IMT030122 exhibited differential binding to antigens and cells expressing EpCAM, 4-1BB, and CD3. Moreover, IMT030122 relied on EpCAM-targeted activation of intracellular CD3 and 4-1BB signaling and mediated T cell cytotoxicity specific to HCT116 colorectal cancer cells. In vivo, IMT030122 demonstrated potent anti-tumor activity, significantly inhibiting the growth of colon cancer HCT116 and MC38-hEpCAM subcutaneous grafts. Further pharmacological analysis revealed that IMT030122 recruited lymphocytes from peripheral blood into colorectal cancer tissue and exerted durable anti-tumor activity, predominantly by promoting the activation, proliferation, and differentiation of CD8T cells. Notably, IMT030122 still exhibited anti-tumor efficacy even in the presence of significantly depleted lymphocytes in colorectal cancer tissue. The potent pharmacological activity and anti-tumor effects of IMT030122 suggest it may enhance treatment efficacy and substantially extend the survival of patients with colorectal cancer in the future.

High-Accuracy Tomato Leaf Disease Image-Text Retrieval Method Utilizing LAFANet.

Tomato leaf disease control in the field of smart agriculture urgently requires attention and reinforcement. This paper proposes a method called LAFANet for image-text retrieval, which integrates image and text information for joint analysis of multimodal data, helping agricultural practitioners to provide more comprehensive and in-depth diagnostic evidence to ensure the quality and yield of tomatoes. First, we focus on six common tomato leaf disease images and text descriptions, creating a Tomato Leaf Disease Image-Text Retrieval Dataset (TLDITRD), introducing image-text retrieval into the field of tomato leaf disease retrieval. Then, utilizing ViT and BERT models, we extract detailed image features and sequences of textual features, incorporating contextual information from image-text pairs. To address errors in image-text retrieval caused by complex backgrounds, we propose Learnable Fusion Attention (LFA) to amplify the fusion of textual and image features, thereby extracting substantial semantic insights from both modalities. To delve further into the semantic connections across various modalities, we propose a False Negative Elimination-Adversarial Negative Selection (FNE-ANS) approach. This method aims to identify adversarial negative instances that specifically target false negatives within the triplet function, thereby imposing constraints on the model. To bolster the model's capacity for generalization and precision, we propose Adversarial Regularization (AR). This approach involves incorporating adversarial perturbations during model training, thereby fortifying its resilience and adaptability to slight variations in input data. Experimental results show that, compared with existing ultramodern models, LAFANet outperformed existing models on TLDITRD dataset, with top1, top5, and top10 reaching 83.3% and 90.0%, and top1, top5, and top10 reaching 80.3%, 93.7%, and 96.3%. LAFANet offers fresh technical backing and algorithmic insights for the retrieval of tomato leaf disease through image-text correlation.

A Precise Framework for Rice Leaf Disease Image-Text Retrieval Using FHTW-Net.

Cross-modal retrieval for rice leaf diseases is crucial for prevention, providing agricultural experts with data-driven decision support to address disease threats and safeguard rice production. To overcome the limitations of current crop leaf disease retrieval frameworks, we focused on four common rice leaf diseases and established the first cross-modal rice leaf disease retrieval dataset (CRLDRD). We introduced cross-modal retrieval to the domain of rice leaf disease retrieval and introduced FHTW-Net, a framework for rice leaf disease image-text retrieval. To address the challenge of matching diverse image categories with complex text descriptions during the retrieval process, we initially employed ViT and BERT to extract fine-grained image and text feature sequences enriched with contextual information. Subsequently, two-way mixed self-attention (TMS) was introduced to enhance both image and text feature sequences, with the aim of uncovering important semantic information in both modalities. Then, we developed false-negative elimination-hard negative mining (FNE-HNM) strategy to facilitate in-depth exploration of semantic connections between different modalities. This strategy aids in selecting challenging negative samples for elimination to constrain the model within the triplet loss function. Finally, we introduced warm-up bat algorithm (WBA) for learning rate optimization, which improves the model's convergence speed and accuracy. Experimental results demonstrated that FHTW-Net outperforms state-of-the-art models. In image-to-text retrieval, it achieved R@1, R@5, and R@10 accuracies of 83.5%, 92%, and 94%, respectively, while in text-to-image retrieval, it achieved accuracies of 82.5%, 98%, and 98.5%, respectively. FHTW-Net offers advanced technical support and algorithmic guidance for cross-modal retrieval of rice leaf diseases.

Mechanism of Nicotiflorin in San-Ye-Qing rhizome for anti-inflammatory effect in ulcerative colitis.

BACKGROUND: The incidence of ulcerative colitis (UC) is on the rise globally and the development of drugs targeting UC is urgent. Finding the target of action of natural products is important for drug discovery, elucidation of drug action mechanism, and disease mechanism. San-Ye-Qing (SYQ), is an ancient herbal medicine, but whether the powder of its rhizome has pharmacological effects against UC and its mechanism of action are not clear. PURPOSE: To evaluate the therapeutic effectiveness of rhizome powder of SYQ in treating UC, and conduct an isolation and characterization of the chemical constituents of the powder. Further, screen the most potent compounds among them and determine the potential mechanism for treating UC. METHODS: In vivo, the therapeutic effect of SYQ's rhizome powder on UC was assessed by mice's body weight, DAI score, colon length, tissue MPO activity, serum inflammatory markers, etc. Additionally, HPLC was used to isolate and identify the specific chemical components of SYQ's rhizome powder. Then, the most effective compounds and their therapeutic targets were analysed and screened in SYQ rhizome powder using network pharmacology, combined with CCK-8 assay, NO release assay and molecular docking assay, in conjunction with CETSA, DARTS, SPR and enzyme activity assay. Finally, the biological effects of the key compound on the targets were validated using Western blot and ELISA. RESULTS: In vivo, SYQ rhizome powder effectively restored mice's body weight, lowered DAI and pathological score, downregulated the expression of inflammatory biomarkers, and restored colon length, as well as the colonic epithelial and mucus barriers. Afterward, 9 compounds were isolated and identified from the powder of the rhizomes of SYQ by HPLC. Nicotiflorin is the primary compound in SYQ with the highest concentration. According to both CCK-8 and NO release tests, Nicotiflorin is also the most efficacious compound. Combined with network pharmacological prediction, molecular docking analysis, CETSA, DARTS, SPR and enzyme activity assay, Nicotiflorin may ultimately suppress inflammation by targeting p65 and inhibiting the NF-κB pathway, thereby attenuating the activation of NLRP3 inflammasome. To verify this conclusion, Western blot and ELISA experiments were conducted. CONCLUSIONS: Our results suggest that the extract from SYQ rhizomes has therapeutic properties for UC. Its active ingredient Nicotiflorin exerted potent anti-UC effects by binding to p65 and inhibiting the activation of NF-κB and NLRP3 inflammasomes.

Comprehensive Analysis of Immunobiological Effects and Prognostic Significance Related to Endoplasmic Reticulum Stress in Pancreatic Carcinoma.

Context: Pancreatic cancer (PC) has a poor response to the many treatments available for it, including surgery, chemotherapeutics, targeted therapy, and immunotherapy. It's crucial to investigate alternative methods of prognostic assessment and decision-making in choosing a therapy, making it necessary to explore its differentially expressed genes (DEGs). Objective: The study intended to assess the role of endoplasmic reticulum stress (ERS)-related genes (ERSRGs) in PC to create an effective, prognostic risk-prediction model and potential immunotherapy options. Design: The research team performed a genetic study. Setting: The study took place at the Affiliated Hospital of Nantong University in Nantong, Jiangsu, China. Outcome Measures: The research team: (1) performed molecular subtype identification and analysis, (2) developed a prognostic risk model, (3) evaluated the clinical features of the risk model, (4) identified the clinicopathological features affecting survival, (5) analyzed the potential immune roles in ERS, (6) constructed five gene signatures associated with ERS, (7) examined the association between different risk categories and sensitivity to GDSC drugs as a potential predictor of response to chemotherapy , and (8) identified the biological processes associated with different risk categories. Results: Significant differences existed in the survival prognosis of subtype C and subtype A or B (P < .001). The high-risk group with the lower TIDE score had a significantly better response to immunotherapy (P < .0057). The high-risk group had a significantly higher somatic mutation rate (P < .00017) and a worse survival prognosis (P < .001). Differences in mRNA expression existed for ERAP2 (P < .001), IGF2BP2 (P = .006), DSG3 (P = .001), MAPK10 (P = .006), and PRKCSH (P ≤ .015) in clinical samples. Conclusions: Through the analysis of ERS subtypes of pancreatic cancer, the study found that the infiltration abundance of stromal cells and immune cells can affected by ERS, thus changing the prognosis of patients. The predictive model provides reference values for clinical prognosis and immunotherapy for PC patients through its ability to evaluate patients' immune statuses. Clinical treatment can provide individualized guidance and can effectively predict the prognosis of PC patients.

[Corrigendum] FKBP11 protects intestinal epithelial cells against inflammation­induced apoptosis via the JNK­caspase pathway in Crohn's disease.

Subsequently to the publication of the above article, the authors realized that Fig. 4 in their paper had been assembled containing two erroneously placed gel slices; essentially, the GAPDH bands featured in Fig. 4A had also been included in Fig. 5, and the data for the FKBP11 bands in Fig. 4A had also been included to show the GRP78 bands in Fig. 4. The authors were able to revisit their original data and to correct the data that had been featured incorrectly in Fig. 4. The corrected version of Fig. 4, now showing the true data for the GRP78 protein bands in Fig. 4C and the correct GAPDH protein bands for Fig. 4A, is shown on the next page. Note that these errors did not significantly affect the results or the conclusions reported in this paper. All the authors agree to the publication of this Corrigendum, and are grateful to the Editor of Molecular Medicine Reports for allowing them the opportunity to correct this error. Moreover, the authors apologize to the readership for any inconvenience caused. [Molecular Medicine Reports 18: 4428­4438, 2018; DOI: 10.3892/mmr.2018.9485].

Artificial intelligence predicts direct-acting antivirals failure among hepatitis C virus patients: A nationwide hepatitis C virus registry program.

BACKGROUND/AIMS: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1-3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy. METHODS: We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment. RESULTS: The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset. CONCLUSION: Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.

An algorithm for simplified hepatitis C virus treatment with non-specialist care based on nation-wide data from Taiwan.

BACKGROUND: Both European Association for the Study of the Liver (EASL) and American Association for the Study of Liver Diseases and the Infectious Diseases Society of America (AASLD-IDSA) guidelines recommend simplified hepatitis C virus (HCV) treatment with pan-genotypic sofosbuvir/velpatasvir or glecaprevir/pibrentasvir for eligible patients. This observational study used real-world data to assess these regimens' safety in eligible patients and develop an algorithm to identify patients suitable for simplified treatment by non-specialists. METHODS: 7,677 HCV-infected patients from Taiwan Hepatitis C Registry (TACR) who received at least one dose of sofosbuvir/velpatasvir or glecaprevir/pibrentasvir, and fulfilled the EASL/AASLD-IDSA criteria for simplified treatment were analyzed. Multivariate analysis was conducted on patient characteristics and safety data. RESULTS: Overall, 92.8% (7,128/7,677) of patients achieved sustained virological response and only 1.9% (146/7,677) experienced Grades 2-4 laboratory abnormalities in key liver function parameters (alanine aminotransferase, aspartate aminotransferase, and total bilirubin), with only 18 patients (0.23%) experiencing Grades 3-4 abnormalities. Age > 70 years old, presence of hepatocellular carcinoma, total bilirubin > 1.2 mg/dL, estimated glomerular filtration rate < 60 mL/min/1.73 m2, and Fibrosis-4 > 3.25 were associated with higher risks of Grades 2-4 abnormalities. Patients with any of these had an odds of 4.53 times than that of those without in developing Grades 2-4 abnormalities (p < 0.01). CONCLUSIONS: Real-world data from Taiwan confirmed that simplified HCV treatment for eligible patients with pan-genotypic regimens is effective and well tolerated. The TACR algorithm, developed based on this study's results, can further identify patients who can be safely managed by non-specialist care.

Association of ACP5 with the tumor immune microenvironment and its role in cell proliferation and metastasis in pancreatic cancer.

BACKGROUND: Tartrate-resistant acid phosphatase (ACP5) has been implicated in the progression of most malignant tumors, but its role in pancreatic cancer (PC) remained unclear. Thus, this study aimed to elucidate the role and function of ACP5 in PC progression. METHODS: The expression of ACP5 in PC samples was assessed via R programming, TNM plot, and Gene Expression Profiling Interactive Analysis (GEPIA). Western blotting and immunohistochemistry (IHC) were performed to detect ACP5 expression in cells and tissues. The correlation between ACP5 and methylation was analyzed using the University of ALabama at Birmingham Cancer data analysis Portal (UALCAN) and cBio Cancer Genomics Portal (cBioPortal). The Database for Annotation, Visualization and Integrated Discovery (DAVID) and Gene Set Enrichment Analysis (GSEA) were used for the enrichment of ACP5 in PC. Subsequently, Cell Counting Kit-8 (CCK8), clonogenic, and wound healing assays were used to investigate the role of ACP5 in PC. Finally, Tumor Immune Estimation Resource (TIMER) and R programming was utilized in evaluating the association between ACP5 and immune cell infiltration in PC. RESULTS: The analyses confirmed that ACP5 was highly expressed in PC samples. According to UALCAN and cBioPortal analysis, ACP5 expression, and methylation levels were negatively correlated in PC. The enrichment analysis also revealed that ACP5 was enriched in the proliferation and migration pathways. Meanwhile, ACP5 knockout reduced PC cell proliferation and migration and impaired the cells' independent viability. This gene also positively correlated with immune cell infiltration in PC, particularly regulatory T cells (Tregs). CONCLUSION: ACP5 is crucial for proliferation, migration, and immune cell infiltration in PC. Therefore, ACP5 may be a valuable target for future PC treatment.

HSSNet: A End-to-End Network for Detecting Tiny Targets of Apple Leaf Diseases in Complex Backgrounds.

Apple leaf diseases are one of the most important factors that reduce apple quality and yield. The object detection technology based on deep learning can detect diseases in a timely manner and help automate disease control, thereby reducing economic losses. In the natural environment, tiny apple leaf disease targets (a resolution is less than 32 × 32 pixel2) are easily overlooked. To address the problems of complex background interference, difficult detection of tiny targets and biased detection of prediction boxes that exist in standard detectors, in this paper, we constructed a tiny target dataset TTALDD-4 containing four types of diseases, which include Alternaria leaf spot, Frogeye leaf spot, Grey spot and Rust, and proposed the HSSNet detector based on the YOLOv7-tiny benchmark for professional detection of apple leaf disease tiny targets. Firstly, the H-SimAM attention mechanism is proposed to focus on the foreground lesions in the complex background of the image. Secondly, SP-BiFormer Block is proposed to enhance the ability of the model to perceive tiny targets of leaf diseases. Finally, we use the SIOU loss to improve the case of prediction box bias. The experimental results show that HSSNet achieves 85.04% mAP (mean average precision), 67.53% AR (average recall), and 83 FPS (frames per second). Compared with other standard detectors, HSSNet maintains high real-time detection speed with higher detection accuracy. This provides a reference for the automated control of apple leaf diseases.

An Accurate Classification of Rice Diseases Based on ICAI-V4.

Rice is a crucial food crop, but it is frequently affected by diseases during its growth process. Some of the most common diseases include rice blast, flax leaf spot, and bacterial blight. These diseases are widespread, highly infectious, and cause significant damage, posing a major challenge to agricultural development. The main problems in rice disease classification are as follows: (1) The images of rice diseases that were collected contain noise and blurred edges, which can hinder the network's ability to accurately extract features of the diseases. (2) The classification of disease images is a challenging task due to the high intra-class diversity and inter-class similarity of rice leaf diseases. This paper proposes the Candy algorithm, an image enhancement technique that utilizes improved Canny operator filtering (the gravitational edge detection algorithm) to emphasize the edge features of rice images and minimize the noise present in the images. Additionally, a new neural network (ICAI-V4) is designed based on the Inception-V4 backbone structure, with a coordinate attention mechanism added to enhance feature capture and overall model performance. The INCV backbone structure incorporates Inception-iv and Reduction-iv structures, with the addition of involution to enhance the network's feature extraction capabilities from a channel perspective. This enables the network to better classify similar images of rice diseases. To address the issue of neuron death caused by the ReLU activation function and improve model robustness, Leaky ReLU is utilized. Our experiments, conducted using the 10-fold cross-validation method and 10,241 images, show that ICAI-V4 has an average classification accuracy of 95.57%. These results indicate the method's strong performance and feasibility for rice disease classification in real-life scenarios.

A Fine-Grained Image Classification Approach for Dog Feces Using MC-SCMNet under Complex Backgrounds.

In a natural environment, factors such as weathering and sun exposure will degrade the characteristics of dog feces; disturbances such as decaying wood and dirt are likely to make false detections; the recognition distinctions between different kinds of feces are slight. To address these issues, this paper proposes a fine-grained image classification approach for dog feces using MC-SCMNet under complex backgrounds. First, a multi-scale attention down-sampling module (MADM) is proposed. It carefully retrieves tiny feces feature information. Second, a coordinate location attention mechanism (CLAM) is proposed. It inhibits the entry of disturbance information into the network's feature layer. Then, an SCM-Block containing MADM and CLAM is proposed. We utilized the block to construct a new backbone network to increase the efficiency of fecal feature fusion in dogs. Throughout the network, we decrease the number of parameters using depthwise separable convolution (DSC). In conclusion, MC-SCMNet outperforms all other models in terms of accuracy. On our self-built DFML dataset, it achieves an average identification accuracy of 88.27% and an F1 value of 88.91%. The results of the experiments demonstrate that it is more appropriate for dog fecal identification and maintains stable results even in complex backgrounds, which may be applied to dog gastrointestinal health checks.

An Effective Image-Based Tomato Leaf Disease Segmentation Method Using MC-UNet.

Tomato disease control is an urgent requirement in the field of intellectual agriculture, and one of the keys to it is quantitative identification and precise segmentation of tomato leaf diseases. Some diseased areas on tomato leaves are tiny and may go unnoticed during segmentation. Blurred edge also makes the segmentation accuracy poor. Based on UNet, we propose an effective image-based tomato leaf disease segmentation method called Cross-layer Attention Fusion Mechanism combined with Multi-scale Convolution Module (MC-UNet). First, a Multi-scale Convolution Module is proposed. This module obtains multiscale information about tomato disease by employing 3 convolution kernels of different sizes, and it highlights the edge feature information of tomato disease using the Squeeze-and-Excitation Module. Second, a Cross-layer Attention Fusion Mechanism is proposed. This mechanism highlights tomato leaf disease locations via gating structure and fusion operation. Then, we employ SoftPool rather than MaxPool to retain valid information on tomato leaves. Finally, we use the SeLU function appropriately to avoid network neuron dropout. We compared MC-UNet to the existing segmentation network on our self-built tomato leaf disease segmentation dataset and MC-UNet achieved 91.32% accuracy and 6.67M parameters. Our method achieves good results for tomato leaf disease segmentation, which demonstrates the effectiveness of the proposed methods.

A Precise Image-Based Tomato Leaf Disease Detection Approach Using PLPNet.

Tomato leaf diseases have a significant impact on tomato cultivation modernization. Object detection is an important technique for disease prevention since it may collect reliable disease information. Tomato leaf diseases occur in a variety of environments, which can lead to intraclass variability and interclass similarity in the disease. Tomato plants are commonly planted in soil. When a disease occurs near the leaf's edge, the soil backdrop in the image tends to interfere with the infected region. These problems can make tomato detection challenging. In this paper, we propose a precise image-based tomato leaf disease detection approach using PLPNet. First, a perceptual adaptive convolution module is proposed. It can effectively extract the disease's defining characteristics. Second, a location reinforcement attention mechanism is proposed at the neck of the network. It suppresses the interference of the soil backdrop and prevents extraneous information from accessing the network's feature fusion phase. Then, a proximity feature aggregation network with switchable atrous convolution and deconvolution is proposed by combining the mechanisms of secondary observation and feature consistency. The network solves the problem of disease interclass similarities. Finally, the experimental results show that PLPNet achieved 94.5% mean average precision with 50% thresholds (mAP50), 54.4% average recall (AR), and 25.45 frames per second (FPS) on a self-built dataset. The model is more accurate and specific for the detection of tomato leaf diseases than other popular detectors. Our proposed method may effectively improve conventional tomato leaf disease detection and provide modern tomato cultivation management with reference experience.