Laryngeal cancer tumor (LCT) grading is a challenging task in P63 Immunohistochemical (IHC) histopathology images due to small differences between LCT levels in pathology images, the lack of precision in lesion regions of interest (LROIs) and the paucity of LCT pathology image samples. The key to solving the LCT grading problem is to transfer knowledge from other images and to identify more accurate LROIs, but the following problems occur: 1) transferring knowledge without a priori experience often causes negative transfer and creates a heavy workload due to the abundance of image types, and 2) convolutional neural networks (CNNs) constructing deep models by stacking cannot sufficiently identify LROIs, often deviate significantly from the LROIs focused on by experienced pathologists, and are prone to providing misleading second opinions. So we propose a novel fusion attention block network (FABNet) to address these problems. First, we propose a model transfer method based on clinical a priori experience and sample analysis (CPESA) that analyzes the transfer ability by integrating clinical a priori experience using indicators such as the relationship between the cancer onset location and morphology and the texture and staining degree of cell nuclei in histopathology images; our method further validates these indicators by the probability distribution of cancer image samples. Then, we propose a fusion attention block (FAB) structure, which can both provide an advanced non-uniform sparse representation of images and extract spatial relationship information between nuclei; consequently, the LROI can be more accurate and more relevant to pathologists. We conducted extensive experiments, compared with the best Baseline model, the classification accuracy is improved 25%, and It is demonstrated that FABNet performs better on different cancer pathology image datasets and outperforms other state of the art (SOTA) models.

During steel manufacturing, surface defects such as scratches, scale, and oxidation can compromise product quality and safety. Detecting these defects accurately is critical for production efficiency and product integrity. However, current target detection algorithms are often too resource-intensive for deployment on edge devices with limited computing resources. To address this challenge, we propose YOLO-RDP, an enhanced YOLOv7-tiny model. YOLO-RDP integrates RexNet, a lightweight network, for feature extraction, and employs GSConv and VOV-GSCSP modules to enhance the network’s neck layer, reducing parameter count and computational complexity. Additionally, we designed a dual-headed object detection head called DdyHead with a symmetric structure, composed of two complementary object detection heads, greatly enhancing the model’s ability to recognize minor defects. Further model optimization through pruning achieves additional lightweighting. Experimental results demonstrate the superiority of our model, with improvements in mAP values of 3.7% and 3.5% on the NEU-DET and GC10-DET datasets, respectively, alongside reductions in parameter count and computation by 40% and 30%, and 25% and 24%, respectively.

Offensive language in social media affects the social experience of individuals and groups and hurts social harmony and moral values. Therefore, in recent years, the problem of offensive language detection has attracted the attention of many researchers. However, the primary research currently focuses on detecting English offensive language, while few studies on the Chinese language exist. In this paper, we propose an innovative approach to detect Chinese offensive language. First, unlike previous approaches, we utilized both RoBERTa’s sentence-level and word-level embedding, combining the sentence embedding and word embedding of RoBERTa’s model, bidirectional GRU, and multi-head self-attention mechanism. This feature fusion allows the model to consider sentence-level and word-level semantic information at the same time so as to capture the semantic information of Chinese text more comprehensively. Second, by concatenating the output results of multi-head attention with RoBERTa’s sentence embedding, we achieved an efficient fusion of local and global information and improved the representation ability of the model. The experiments showed that the proposed model achieved 82.931% accuracy and 82.842% F1-score in Chinese offensive language detection tasks, delivering high performance and broad application potential.

The accurate segmentation of lung nodules in computed tomography (CT) images is crucial for the early screening and diagnosis of lung cancer. However, the heterogeneity of lung nodules and their similarity to other lung tissue features make this task more challenging. By using large receptive fields from large convolutional kernels, convolutional neural networks (CNNs) can achieve higher segmentation accuracies with fewer parameters. However, due to the fixed size of the convolutional kernel, CNNs still struggle to extract multi-scale features for lung nodules of varying sizes. In this study, we propose a novel network to improve the segmentation accuracy of lung nodules. The network integrates adaptive large kernel attention (ALK) blocks, employing multiple convolutional layers with variously sized convolutional kernels and expansion rates to extract multi-scale features. A dynamic selection mechanism is also introduced to aggregate the multi-scale features obtained from variously sized convolutional kernels based on selection weights. Based on this, we propose a lightweight convolutional neural network with large convolutional kernels, called ALKU-Net, which integrates the ALKA module in a hierarchical encoder and adopts a U-shaped decoder to form a novel architecture. ALKU-Net efficiently utilizes the multi-scale large receptive field and enhances the model perception capability through spatial attention and channel attention. Extensive experiments demonstrate that our method outperforms other state-of-the-art models on the public dataset LUNA-16, exhibiting considerable accuracy in the lung nodule segmentation task.

Recently, the COVID-19 pandemic coronavirus has put a lot of pressure on health systems around the world. One of the most common ways to detect COVID-19 is to use chest X-ray images, which have the advantage of being cheap and fast. However, in the early days of the COVID-19 outbreak, most studies applied pretrained convolutional neural network (CNN) models, and the features produced by the last convolutional layer were directly passed into the classification head. In this study, the proposed ensemble model consists of three lightweight networks, Xception, MobileNetV2 and NasNetMobile as three original feature extractors, and then three base classifiers are obtained by adding the coordinated attention module, LSTM and a new classification head to the original feature extractors. The classification results from the three base classifiers are then fused by a confidence fusion method. Three publicly available chest X-ray datasets for COVID-19 testing were considered, with ternary (COVID-19, normal and other pneumonia) and quaternary (COVID-19, normal) analyses performed on the first two datasets, bacterial pneumonia and viral pneumonia classification, and achieved high accuracy rates of 95.56% and 91.20%, respectively. The third dataset was used to compare the performance of the model compared to other models and the generalization ability on different datasets. We performed a thorough ablation study on the first dataset to understand the impact of each proposed component. Finally, we also performed visualizations. These saliency maps not only explain key prediction decisions of the model, but also help radiologists locate areas of infection. Through extensive experiments, it was finally found that the results obtained by the proposed method are comparable to the state-of-the-art methods.

Action recognition algorithms are widely used in the fields of medical health and pedestrian dead reckoning (PDR). The classification and recognition of non-normal walking actions and normal walking actions are very important for improving the accuracy of medical health indicators and PDR steps. Existing motion recognition algorithms focus on the recognition of normal walking actions, and the recognition of non-normal walking actions common to daily life is incomplete or inaccurate, resulting in a low overall recognition accuracy. This paper proposes a microelectromechanical system (MEMS) action recognition method based on Relief-F feature selection and relief-bagging-support vector machine (SVM). Feature selection using the Relief-F algorithm reduces the dimensions by 16 and reduces the optimization time by an average of 9.55 s. Experiments show that the improved algorithm for identifying non-normal walking actions has an accuracy of 96.63%; compared with Decision Tree (DT), it increased by 11.63%; compared with k-nearest neighbor (KNN), it increased by 26.62%; and compared with random forest (RF), it increased by 11.63%. The average Area Under Curve (AUC) of the improved algorithm improved by 0.1143 compared to KNN, by 0.0235 compared to DT, and by 0.04 compared to RF.