Association Between Liver Fibrosis Score and Diabetic Kidney Disease: A Retrospective Cross-Sectional Study of Hospitalized Patients.

OBJECTIVES: To investigate the association between liver fibrosis score and diabetic kidney disease (DKD) in type 2 diabetes mellitus (T2DM). METHODS: A total of 897 hospitalized patients with T2DM were included in this study. Each patient completed DKD screening. Logistic regression analysis was used to assess the predictive value of non-alcoholic fatty liver disease fibrosis score (NAFLD-FS) and fibrosis-4 (FIB-4) for the occurrence of DKD and risk for DKD progression, respectively. RESULTS: The prevalence of DKD and risk for its progression significantly increased with increasing NAFLD-FS risk category. DKD prevalence also increased with increasing FIB-4 risk category. Multivariate logistic regression analysis showed that the "high-risk" NAFLD-FS had a significantly higher risk of DKD (odds ratio [OR]: 1.89, 95% confidence interval [CI]: 1.16-3.08) and risk for DKD progression (OR: 2.88, 95% CI: 1.23-6.78), and the "intermediate-risk" FIB-4 had a significantly higher risk of DKD (OR: 1.41, 95% CI: 1.00-1.98). Subgroup analysis showed that the association between NAFLD-FS and FIB-4 and DKD was significant in the female subgroup, whereas the association between the "high-risk" NAFLD-FS and risk for DKD progression was significant in the male subgroup. CONCLUSIONS: NAFLD-FS and FIB-4 are strongly associated with DKD and risk for DKD progression in patients with T2DM. Additionally, sexual dimorphism exists in this association.

6D Object Pose Estimation Based on Cross-Modality Feature Fusion.

The 6D pose estimation using RGBD images plays a pivotal role in robotics applications. At present, after obtaining the RGB and depth modality information, most methods directly concatenate them without considering information interactions. This leads to the low accuracy of 6D pose estimation in occlusion and illumination changes. To solve this problem, we propose a new method to fuse RGB and depth modality features. Our method effectively uses individual information contained within each RGBD image modality and fully integrates cross-modality interactive information. Specifically, we transform depth images into point clouds, applying the PointNet++ network to extract point cloud features; RGB image features are extracted by CNNs and attention mechanisms are added to obtain context information within the single modality; then, we propose a cross-modality feature fusion module (CFFM) to obtain the cross-modality information, and introduce a feature contribution weight training module (CWTM) to allocate the different contributions of the two modalities to the target task. Finally, the result of 6D object pose estimation is obtained by the final cross-modality fusion feature. By enabling information interactions within and between modalities, the integration of the two modalities is maximized. Furthermore, considering the contribution of each modality enhances the overall robustness of the model. Our experiments indicate that the accuracy rate of our method on the LineMOD dataset can reach 96.9%, on average, using the ADD (-S) metric, while on the YCB-Video dataset, it can reach 94.7% using the ADD-S AUC metric and 96.5% using the ADD-S score (<2 cm) metric.