Peihe Jiang’s research while affiliated with Yantai University and other places

Bronchoalveolar lavage fluid (BALF) is a liquid sample that reflects the biological status of lung tissues, containing a wealth of components such as cells and proteins. These components provide a non-invasive method to obtain pathological information about the lungs, serving as a powerful complement to traditional lung biopsies. However, the similarity in morphology and function of cells in BALF, combined with the diversity of sample processing and analysis methods, can lead to confusion in recognizing and distinguishing these cellular features. This study presents an improved Yolov10 method for the detection and classification of BALF cells, specifically targeting macrophages, lymphocytes, neutrophils, and eosinophils. The backbone network incorporates the PLWA module in place of the PSA module to enhance the acquisition of useful information, and the C2f-DC module replaces the C2f module to improve image feature extraction capabilities. Furthermore, the head network employs the Cross-Attention Fusion module (CAP) to enhance the retrieval of image information. Experimental results demonstrate that the model achieves a mean Average Precision (mAP) of 86.5% and a recall rate of 79.1%, confirming the model’s effectiveness.

Diagnosing Sjogren’s syndrome requires considerable time and effort from physicians, primarily because it necessitates rigorously establishing the presence lymphatic infiltration in the pathological tissue of the labial gland. The aim of this study is to use deep learning techniques to overcome these limitations and improve diagnostic accuracy and efficiency in pathology. We develop an auxiliary diagnostic system for Sjogren’s syndrome. The system incorporates the state-of-the-art object detection neural network, YOLOv8, and enables the precise identification and flagging of suspicious lesions. We design the multi-dimensional attention module and S-MPDIoU loss function to improve the detection performance of YOLOv8. By extracting features from multiple dimensions of the feature map, the utilization of the multi-dimensional attention mechanism enhances the feature interaction across disparate positions, enabling the network to proficiently learn and retain salient cell features. S-MPDIoU introduces an angle penalty term that efficiently minimizes the diagonal distance between predicted and ground truth boxes. Additionally, it incorporates a flexible scale factor tailored to different size feature maps, which balances the issue of sudden gradient decrease during high overlap, thereby accelerating the overall convergence rate. To verify the effectiveness of our methods, we create a dataset of lymphocytes using labial gland biopsy pathology images collected from YanTaiShan hospital and trained the model with this dataset. The proposed model is assessed using standard metrics like precision, recall, mAP. The improved model achieves an increase in recall by 9.1%, mAP.5 by 3.2%, and mAP.95 by 2%. The study demonstrated deep learning’s potential to analysis pathology images, offering a reference framework for the application of deep learning technology in the medical domain.

This paper proposes a secure wire-line telephone prototype that leverages physical layer security (PLS) techniques to protect communications from wiretapping. The system generates artificial noise (AN) in both directions over a telephone line and utilizes a telephone hybrid circuit to achieve effective AN cancellation. We conduct a thorough analysis of the secrecy capacity and evaluate the system's performance through both simulations and practical experiments. The results demonstrate that the proposed scheme significantly enhances communication security while preserving the integrity of legitimate signals, making it a robust and viable solution for secure telephone systems.

To address the burdensome and time-consuming nature of manual diagnosis of pathological sections, this study proposes an automated pathological image detection system. This system can directly detect pathological images and accurately locate lesion tissues, providing a reference for pathological diagnosis. We propose an improved MobileViT model for feature extraction in the system, which we have named CSMViT. Considering the complexity and multi-scale characteristics of pathological images, we made three significant modifications to the MobileViT model. First, the original MV2 module was replaced with an improved Ghost module to reduce the model’s parameter count, enhance detection accuracy, and accelerate inference speed. Second, we improved the backbone structure of the network to achieve multi-scale feature learning, which not only further reduces the parameter count but also allows for more effective capture of features at different scales. Lastly, we introduced a new CSA module that can simultaneously accept two feature maps of different sizes as input. Through internal attention mechanisms and feature fusion, this module achieves cross-scale feature learning. Experimental results indicate that the CSMViT model achieved accuracy, F1-score, and specificity of 99.42%, 99.4%, and 99.6%, respectively. Additionally, the detection accuracy of CSMViT for the entire pathological image is 84%, representing an 8% improvement over the original network. Notably, the FLOPs of CSMViT is 1.461G, which is a 72.19% reduction compared to the original network, significantly decreasing the model’s complexity. These results thoroughly demonstrate the effectiveness and substantial value of CSMViT in pathological image detection.

Bolt connections are widely used as structural connections in civil engineering, mechanical engineering, and bridge construction. However, problems such as loosening, or breakage can occur with bolts after prolonged use. To address the challenges of detecting bolt loosening, this study reviews existing detection technologies, analyzes their advantages and limitations, and proposes a novel bolt-loosening detection algorithm based on image matching and deep learning. The algorithm comprises the following components: a bolt target detection model based on an improved YOLOv8 algorithm, image correction using perspective transformation, bolt contour detection and image processing, and feature matching to calculate the transformation matrix between images obtained before and after loosening, thereby determining the loosening angle of the bolt. The experiments focused on a rectangular steel plate featuring four M6 standard bolts. The results demonstrate that the bolt target detection model can accurately locate and crop bolt positions and identify loosening angles under various shooting angles, distances, and lighting conditions. At specific shooting angles and appropriate distances, the detection error threshold was less than 2°. Subsequently, experiments conducted in real-world scenarios confirmed the accuracy and feasibility of the proposed algorithm.

To address the limitations of traditional burdensome and time-consuming manual diagnosis of Sjogren’s syndrome, this study proposes and implements an improved version of YOLOv5 algorithm, named YOLOv5-MSS. Using YOLOv5 MSS, we are able to detect lymphocytic infiltrative lesions in pathological images and provide assistance for pathological diagnosis. Given the small size of lymphocytes and the difficulty in distinguishing them, four improvements were made to the YOLOv5 model. Firstly, we replace the original CIOU loss function with the Focal-SIOU loss function to accelerate the model convergence and improve the detection accuracy. Additionally, we introduce a multi-head self-attention module into the backbone to enchance the model’s ability to capture long range dependencies and overcome the challenges posed by complex background. Furthermore, we introduce the Shuffle Attention module into the neck, which enhances the model’s ability to fuse features from both spatial and channel dimensions. Finally, we remove the 1/32 downsampling section in the neck and the corresponding large object detection head. This not only enhances accuracy but also reduces parameters and model complexity. Experimental results show that YOLOv5s-MSS achieves a mAP, Precision, and Recall of 93.2%, 87.2%, and 89%, representing increases of 2.9%, 2.6%, and 2.8% compared to the original YOLOv5s model. Additionally, YOLOv5s-MSS reduces the parameters by 28.2%. These results demonstrate the effectiveness and value of YOLOv5s-MSS for lymphocyte detection.