Segmentation of the Optic Disc (OD) and Optic Cup (OC) is crucial for the early detection and treatment of glaucoma. Despite the strides made in deep neural networks, incorporating trained segmentation models for clinical application remains challenging due to domain shifts arising from disparities in fundus images across different healthcare institutions. To tackle this challenge, this study introduces an innovative unsupervised domain adaptation technique called Multi-scale Adaptive Adversarial Learning (MAAL), which consists of three key components. The Multi-scale Wasserstein Patch Discriminator (MWPD) module is designed to extract domain-specific features at multiple scales, enhancing domain classification performance and offering valuable guidance for the segmentation network. To further enhance model generalizability and explore domain-invariant features, we introduce the Adaptive Weighted Domain Constraint (AWDC) module. During training, this module dynamically assigns varying weights to different scales, allowing the model to adaptively focus on informative features. Furthermore, the Pixel-level Feature Enhancement (PFE) module enhances low-level features extracted at shallow network layers by incorporating refined high-level features. This integration ensures the preservation of domain-invariant information, effectively addressing domain variation and mitigating the loss of global features. Two publicly accessible fundus image databases are employed to demonstrate the effectiveness of our MAAL method in mitigating model degradation and improving segmentation performance. The achieved results outperform current state-of-the-art (SOTA) methods in both OD and OC segmentation. Codes are available at https://github.com/M4cheal/MAAL .

Deep vein thrombosis (DVT) and pulmonary embolism (PE) have high morbidity, reduce quality of life, and can cause death. Biomarkers or genetic risk factors have not been identified in patients with DVT. In present study, serum of 61 patients suffering from DVT and a rat DVT model (n = 10) were assayed by a proton nuclear magnetic resonance (¹H NMR) metabolomics technique combing with multivariate statistical analysis to identify the metabolites. The MetPA platform was used to identify differences in the metabolic pathways between the rat model and patients. The metabolomics results discovered that 11 different metabolites in rats and 20 different metabolites in DVT patients. Seven metabolites both altered in the rats and patients. Moreover, we observed changes in the metabolic pathways, including carbohydrate metabolism, lipid metabolism, and amino acid metabolism that were induced immediately by the thrombosis. Pathway of aminoacyl-tRNA biosynthesis perturbed only in the patients which was associated with the genetic risk factor of DVT. The study demonstrated that serum ¹H NMR metabolomics can be used to diagnose DVT in the clinic. The altered pathways related to thrombosis and genetics will provide a foundation and new strategies for understanding the pathological mechanism and pharmacological targets of DVT.