Background: Human vision has inspired significant advancements in computer vision, yet the human eye is prone to various silent eye diseases. With the advent of deep learning, computer vision for detecting human eye diseases has gained prominence, but most studies have focused only on a limited number of eye diseases. Results: Our model demonstrated a reduction in inherent bias and enhanced robustness. The fused network achieved an Accuracy of 0.9237, Kappa of 0.878, F1 Score of 0.914 (95% CI [0.875–0.954]), Precision of 0.945 (95% CI [0.928–0.963]), Recall of 0.89 (95% CI [0.821–0.958]), and an AUC value of ROC at 0.987. These metrics are notably higher than those of comparable studies. Conclusions: Our deep neural network-based model exhibited improvements in eye disease recognition metrics over models from peer research, highlighting its potential application in this field. Methods: In deep learning-based eye recognition, to improve the learning efficiency of the model, we train and fine-tune the network by transfer learning. In order to eliminate the decision bias of the models and improve the credibility of the decisions, we propose a model decision fusion method based on the D-S theory. However, D-S theory is an incomplete and conflicting theory, we improve and eliminate the existed paradoxes, propose the improved D-S evidence theory(ID-SET), and apply it to the decision fusion of eye disease recognition models.

Adipogenesis comprises multiple processes by which mesenchymal stem cells differentiate into adipocytes. To increase our knowledge of the mechanism underlying adipogenic differentiation of human bone marrow mesenchymal stem cells (hMSCs), we performed full-genome gene expression microarray and gene ontology analyses of induced differentiation of hMSCs. Adipogenic differentiation of hMSCs was induced by an adipogenic medium, and total RNA was extracted from undifferentiated hMSCs (day 0) and differentiated adipocytes (day 14). Then microarray hybridization of RNA samples was performed. The GeneChip Operating Software was used to analyze the hybridization data to identify differentially expressed genes, which were performed Gene Ontology categorization and pathway analysis. Pathway-act-network and genes-act-network were built according to the Kyoto Encyclopedia of Genes and Genomes database. Some differentially expressed genes were subjected to qRT-PCR to verify the microarray data. We detected a total of 3,821 differentially expressed genes, of which 753 were upregulated and 3,068 downregulated. These genes were well represented in a variety of functional categories, including collagen fibril organization, brown fat cell differentiation, cell division, and S phase of mitotic cell cycle. Subsequently, pathway analysis was conducted, and significant pathways (from top 50) were selected for pathway-act-network analysis, which indicated that the mitogen-activated protein kinase (MAPK) pathway and cell cycle were of high degrees (> 10). Gene-act-network analysis showed that insulin-like growth factor 1 receptor (IGF1R), histone deacetylase 1 (HDAC1), HDAC2, MAPK13, MAPK8, phosphoinositide-3-kinase regulatory subunit 1 (PI3KR1), and PI3KR2 also had high degrees (> 18). Collectively, these data provide novel information and could serve as a basis for future study to clarify the mechanisms underlying adipocyte differentiation of hMSCs.

Image super-resolution reconstructs high-resolution images from low-resolution inputs. However, current single-image super-resolution techniques often struggle to capture multi-scale information and extract high-frequency details, which compromises reconstruction quality. Moreover, the prevalent feed-forward network architectures lack robust feedback mechanisms for iterative refinement and enhanced acquisition of high-frequency information. To overcome these limitations, this research develops advanced strategies for multi-scale feature extraction, fusion, and feedback in single-image super-resolution. We propose an innovative error-driven, multi-scale dense residual network (EMDN) that retains a feed-forward structure while integrating error-driven feedback. Specifically, our approach utilizes dual multi-scale features: one derived from convolutional kernels of varying sizes and another extracted from diverse inputs, both processed concurrently. Comparative evaluations across different scaling factors demonstrate that our method outperforms existing approaches in both subjective and objective assessments. In particular, compared to the baseline feed-forward network, our model achieves improvements of up to 0.385% in peak signal-to-noise ratio and 0.191% in structural similarity index measure. The experimental results validate the effectiveness and practical significance of our proposed method in enhancing image resolution and restoration quality.