Search

Diabetic retinopathy (DR) is one of the most common microvascular complications of diabetes and has become one of the leading causes of blindness and visual impairment in diabetes patients. The pathogenesis of DR is multifaceted, involving inflammation, oxidative stress, neurovascular abnormalities, and other factors that present potential targets for disease management interventions. Currently, anti-vascular endothelial growth factor (VEGF) drugs serve as the primary treatment for advanced stages of DR when irreversible neurovascular damage and visual impairment have occurred. Additionally, some patients show poor or no response to anti-VEGF treatment. There is a lack of early intervention options for the initial phases of the disease. Therefore, there is an urgent need to develop novel local or systemic therapies based on the underlying mechanisms of DR to enable early prevention and treatment with the aim of preserving patients′ vision. Medications targeting various pathways including anti-inflammatory agents (corticosteroids and nonsteroidal anti-inflammatory drugs), neurotrophic and neuroprotective drugs, drugs modulating biochemical pathways, antioxidant phytochemicals, and gene therapy can complement each other in terms of therapeutic effects to benefit a larger number of individuals affected by DR. This article reviews previous research reports on the pathogenesis, drug treatment methods, and potential therapeutic targets associated with DR in order to provide guidance for clinical practice.

We aim to develop a deep-learning-based method for automatic proximal femur segmentation in quantitative computed tomography (QCT) images. We proposed a spatial transformation V-Net (ST-V-Net), which contains a V-Net and a spatial transform network (STN) to extract the proximal femur from QCT images. The STN incorporates a shape prior into the segmentation network as a constraint and guidance for model training, which improves model performance and accelerates model convergence. Meanwhile, a multi-stage training strategy is adopted to fine-tune the weights of the ST-V-Net. We performed experiments using a QCT dataset which included 397 QCT subjects. During the experiments for the entire cohort and then for male and female subjects separately, 90% of the subjects were used in ten-fold stratified cross-validation for training and the rest of the subjects were used to evaluate the performance of models. In the entire cohort, the proposed model achieved a Dice similarity coefficient (DSC) of 0.9888, a sensitivity of 0.9966 and a specificity of 0.9988. Compared with V-Net, the Hausdorff distance was reduced from 9.144 to 5.917 mm, and the average surface distance was reduced from 0.012 to 0.009 mm using the proposed ST-V-Net. Quantitative evaluation demonstrated excellent performance of the proposed ST-V-Net for automatic proximal femur segmentation in QCT images. In addition, the proposed ST-V-Net sheds light on incorporating shape prior to segmentation to further improve the model performance.

This paper is dedicated to exploring the digital design of modern sculpture in the era of new media, addressing the challenges and opportunities encountered by traditional sculpture in digital transformation. Considering the innovation brought by digital technology to artistic creation, the precision and efficiency of sculpture digitization are improved by introducing advanced NURBS method and FCM clustering algorithm through precise analysis and characterization of surface geometric parameters of three-dimensional sculptures. The surface geometric parameters and characteristics of three-dimensional sculptures are analyzed using non-uniform rational B-spline (NURBS) and fuzzy C-mean (FCM) clustering algorithms. The high-order surfaces of the sculptures can be represented effectively by the NURBS method, whereas the FCM clustering algorithms exhibit highly efficient performance in surface partitioning planning. The NURBS-based FCM algorithm can reduce the root-mean-square error of point cloud splicing to 0.0853 mm, reduce the number of iterations to 3, and shorten the algorithm’s running time to 18.46 seconds. The practice of digital sculpture application shows that the method improves work efficiency and reduces production costs. The digital design method proposed in this study provides a new way of producing and creating modern sculpture, which helps develop and preserve traditional sculpture art in the new media era.