Search

[Objective]Traditional object detection algorithms applied in the agricultural field, such as those used for crop growth monitoring and harvesting, often suffer from insufficient accuracy. This is particularly problematic for small crops like mushrooms, where recognition and detection are more challenging. The introduction of small object detection technology promises to address these issues, potentially enhancing the precision, efficiency, and economic benefits of agricultural production management. However, achieving high accuracy in small object detection has remained a significant challenge, especially when dealing with varying image sizes and target scales. Although the YOLO series models excel in speed and large object detection, they still have shortcomings in small object detection. To address the issue of maintaining high accuracy amid changes in image size and target scale, a novel detection model, Multi-Strategy Handling YOLOv8 (MSH-YOLOv8), was proposed.[Methods]The proposed MSH-YOLOv8 model builds upon YOLOv8 by incorporating several key enhancements aimed at improving sensitivity to small-scale targets and overall detection performance. Firstly, an additional detection head was added to increase the model's sensitivity to small objects. To address computational redundancy and improve feature extraction, the Swin Transformer detection structure was introduced into the input module of the head network, creating what was termed the "Swin Head (SH)". Moreover, the model integrated the C2f_Deformable convolutionv4 (C2f_DCNv4) structure, which included deformable convolutions, and the Swin Transformer encoder structure, termed "Swinstage", to reconstruct the YOLOv8 backbone network. This optimization enhanced feature propagation and extraction capabilities, increasing the network's ability to handle targets with significant scale variations. Additionally, the normalization-based attention module (NAM) was employed to improve performance without compromising detection speed or computational complexity. To further enhance training efficacy and convergence speed, the original loss function CIoU was replaced with wise-intersection over union (WIoU) Loss. Furthermore, experiments were conducted using mushrooms as the research subject on the open Fungi dataset. Approximately 200 images with resolution sizes around 600×800 were selected as the main research material, along with 50 images each with resolution sizes around 200×400 and 1 000×1 200 to ensure representativeness and generalization of image sizes. During the data augmentation phase, a generative adversarial network (GAN) was utilized for resolution reconstruction of low-resolution images, thereby preserving semantic quality as much as possible. In the post-processing phase, dynamic resolution training, multi-scale testing, soft non-maximum suppression (Soft-NMS), and weighted boxes fusion (WBF) were applied to enhance the model's small object detection capabilities under varying scales.[Results and Discussions]The improved MSH-YOLOv8 achieved an average precision at 50% (AP50) intersection over union of 98.49% and an AP@50-95 of 75.29%, with the small object detection metric APs reaching 39.73%. Compared to mainstream models like YOLOv8, these metrics showed improvements of 2.34%, 4.06% and 8.55%, respectively. When compared to the advanced TPH-YOLOv5 model, the improvements were 2.14%, 2.76% and 6.89%, respectively. The ensemble model, MSH-YOLOv8-ensemble, showed even more significant improvements, with AP50 and APs reaching 99.14% and 40.59%, respectively, an increase of 4.06% and 8.55% over YOLOv8. These results indicate the robustness and enhanced performance of the MSH-YOLOv8 model, particularly in detecting small objects under varying conditions. Further application of this methodology on the Alibaba Cloud Tianchi databases "Tomato Detection" and "Apple Detection" yielded MSH-YOLOv8-t and MSH-YOLOv8-a models (collectively referred to as MSH-YOLOv8). Visual comparison of detection results demonstrated that MSH-YOLOv8 significantly improved the recognition of dense and blurry small-scale tomatoes and apples. This indicated that the MSH-YOLOv8 method possesses strong cross-dataset generalization capability and effectively recognizes small-scale targets. In addition to quantitative improvements, qualitative assessments showed that the MSH-YOLOv8 model could handle complex scenarios involving occlusions, varying lighting conditions, and different growth stages of the crops. This demonstrates the practical applicability of the model in real-world agricultural settings, where such challenges are common.[Conclusions]The MSH-YOLOv8 improvement method proposed in this study effectively enhances the detection accuracy of small mushroom targets under varying image sizes and target scales. This approach leverages multiple strategies to optimize both the architecture and the training process, resulting in a robust model capable of high-precision small object detection. The methodology's application to other datasets, such as those for tomato and apple detection, further underscores its generalizability and potential for broader use in agricultural monitoring and management tasks.

The disease burden of renal cell carcinoma (RCC) has decreased in recent years with advances in treatment, but its pathogeny still remains elusive. We aim to study the role of homeobox A3 (HOXA3)/ubiquitin-specific peptidase 15 (USP15)/SQSTM1 axis on autophagy and M2-type macrophage polarization in RCC. In this study, cell apoptosis and proliferation were assessed by flow cytometry and CCK-8. Autolysosome fusion was observed by immunofluorescence detection of LC3 and LAMP2. The binding between HOXA3 and USP15 promoter was tested by chromatin immunoprecipitation (ChIP), EMSA, and dual-luciferase reporter assays. Also, the interaction between deubiquitinated enzyme (DUB) USP15 and SQSTM1, and ubiquitinated level of SQSTM1 were determined by co-immunoprecipitation (Co-IP) assay. Expression levels of HOXA3, USP15, C-C motif chemokine 2 (CCL2), CCL2 receptor (CCR2), M2-type macrophages, and autophagy-related markers were measured by Western blot, quantitative reverse transcription PCR (RT-qPCR), ELISA, and immunohistochemistry. Role of HOXA3/USP15 axis was verified by xenograft tumor experiment in vivo. We showed upregulated HOXA3 in RCC tissues and cells, and RCC tissues with metastasis showed higher HOXA3 level. The higher HOXA3 expression was relevant to worse overall survival in patients with RCC. HOXA3 induced RCC cell proliferation, and suppressed autophagy and apoptosis via transcriptionally activating USP15 expression. USP15 then induced deubiquitination modification of SQSTM1 in RCC cells. SQSTM1 supported M2-type macrophage polarization by inducing CCL2 secretion. HOXA3 or USP15 knockdown suppressed tumor growth and M2-type macrophage infiltration in vivo. In conclusion, HOXA3 transcriptionally activates USP15 expression, and upregulated USP15 facilitates the deubiquitination of SQSTM1 in RCC. This process on the one hand suppresses autophagy, on the other hand increases M2-type macrophage polarization through stimulating the secretion of CCL2. NEW & NOTEWORTHY: We report a novel finding that highly expressed homeobox A3 (HOXA3) transcriptionally activates the expression of ubiquitin-specific peptidase 15 (USP15), resulting in the promotion of deubiquitination of SQSTM1. This process on the one hand suppresses autophagy in renal cell carcinoma (RCC), on the other hand increases M2-type macrophage polarization in the tumor microenvironment through stimulating the secretion of C-C motif chemokine 2 (CCL2). [ABSTRACT FROM AUTHOR]

Duck Tembusu virus (DTMUV), a novel positive-sense RNA virus, has caused significant economic losses in the poultry industry of Eastern and Southeast Asia since its outbreak in 2010. Furthermore, the rapid transmission and potential zoonotic nature of DTMUV pose a threat to public health safety. In this study, a 4D-DIA quantitative proteomics approach was employed to identify differentially expressed cellular proteins in DTMUV-infected DF-1 cells, which are routinely used for virus isolation and identification for DTMUV, as well as the development of vaccines against other poultry viruses. One hundred fifty-seven differentially expressed cellular proteins were identified, including 84 upregulated and 73 downregulated proteins at 48 h post-infection, among which CXCL8, DDX3X, and TRPV2 may play crucial roles in viral propagation. Notably, for the upregulated protein TRPV2, the DTMUV replication was inhibited in TRPV2-low-expressing DF-1 cells. In summary, our research represents the application of 4D-DIA quantitative proteomics to analyze the proteomic landscape of DTMUV-infected poultry cells. These findings may provide valuable insights into understanding the interaction mechanism between DTMUV and poultry cells, as well as the identification of disease-resistant host factors in poultry breeding research. [ABSTRACT FROM AUTHOR]

Although immune checkpoint blockade (ICB) therapies have been approved for bladder cancer (BLCA), only a minority of patients respond to these therapies, and there is an urgent need to explore combined therapies. Systematic multi‐omics analysis identified S100A5 as a novel immunosuppressive target for BLCA. The expression of S100A5 in malignant cells inhibited CD8+ T cell recruitment by decreasing pro‐inflammatory chemokine secretion. Furthermore, S100A5 attenuated effector T cell killing of cancer cells by inhibiting CD8+ T cell proliferation and cytotoxicity. In addition, S100A5 acted as an oncogene, thereby promoting tumor proliferation and invasion. Targeting S100A5 synergized with the efficacy of anti‐PD‐1 treatment by enhancing infiltration and cytotoxicity of CD8+ T cells in vivo. Clinically, there was a spatially exclusive relationship between S100A5+ tumor cells and CD8+ T cells in tissue microarrays. Moreover, S100A5 negatively correlated with immunotherapy efficacy in our real‐world and several public immunotherapy cohorts. In summary, S100A5 shapes a non‐inflamed tumor microenvironment in BLCA by inhibiting the secretion of pro‐inflammatory chemokines and the recruitment and cytotoxicity of CD8+ T cells. Targeting S100A5 converts cold tumors into hot tumors, thus enhancing the efficacy of ICB therapy in BLCA. [ABSTRACT FROM AUTHOR]