查看更多>>摘要：Pressure injuries, a chronic disease with high incidence and costly treatment, are categorized by the National Pressure Injury Advisory Panel from stage 1 to 4 based on skin invasion severity. Variations in injury range and depth can lead to incorrect staging. A computer-aided diagnosis system using a convolutional neural network (CNN) architecture has proven reliable in object detection and classification. This study proposes a cascade R-CNN with a squeeze-and-excitation shifted windows transformer (SE-Swin transformer) model for detecting and classifying pressure injury stages. The system includes data augmentation, feature extraction, and stage classification. Using 883 images, the system achieves a mean average precision (mAP) of 81.3% in detection and accuracy of 87.1%, sensitivity of 85.7%, and positive predictive value (PPV) of 86.6% in stage classification.
查看更多>>摘要：Existing segmentation networks primarily use single downsampling to extract low-resolution semantic information, which may not adapt well to features of different scales, leading to information imbalance and distortion. Here, we propose a hybrid plus downsampling method to address this issue. Concretely, we first introduce a linear dilated convolutional unit block to capture long-range dependencies; second, we joint nonlinear pooling to construct comprehensive downsampling features; we then utilize carefully designed super-resolution reconstruction module and similarity structural loss to ensure the completeness of the downsampling features. Furthermore, considering the significance of semantic information, we propose a residual semantic encoding module to gather rich semantic information from a local and global perspective. Based on the aforementioned efforts, we propose a terrain segmentation network (TSNet) for safe navigation of mobile robots in wild environments. Extensive experimental results on the wild datasets demonstrate that TSNet outperforms other state-of-the-art methods in recognizing wild unstructured terrain.
NETL
NSTL
IEEE