Objective To automatically segment diabetic retinal exudation features from deep learning color fundus images. Methods An applied study. The method of this study is based on the U-shaped network model of the Indian Diabetic Retinopathy Image Dataset (IDRID) dataset, introduces deep residual convolution into the encoding and decoding stages, which can effectively extract seepage depth features, solve overfitting and feature interference problems, and improve the model's feature expression ability and lightweight performance. In addition, by introducing an improved context extraction module, the model can capture a wider range of feature information, enhance the perception ability of retinal lesions, and perform excellently in capturing small details and blurred edges. Finally, the introduction of convolutional triple attention mechanism allows the model to automatically learn feature weights, focus on important features, and extract useful information from multiple scales. Accuracy, recall, Dice coefficient, accuracy and sensitivity were used to evaluate the ability of the model to detect and segment the automatic retinal exudation features of diabetic patients in color fundus images. Results After applying this method, the accuracy, recall, dice coefficient, accuracy and sensitivity of the improved model on the IDRID dataset reached 81.56%, 99.54%, 69.32%, 65.36% and 78.33%, respectively. Compared with the original model, the accuracy and Dice index of the improved model are increased by 2.35% , 3.35% respectively. Conclusion The segmentation method based on U-shaped network can automatically detect and segment the retinal exudation features of fundus images of diabetic patients, which is of great significance for assisting doctors to diagnose diseases more accurately.
Objective To determine the expression levels of micro RNA (miR)-196, miR-217, and transforming growth factor β receptor 1 (TGFβR1) protein in the pancreatic ductal adenocarcinoma tissues and its adjacent tissues, to reveal the relationship among them in the pathological process of pancreatic ductal adenocarcinoma. Methods A total of 30 cases’ pancreatic ductal adenocarcinoma tissues and its adjacent tissues were collected. The expression levels of miR-196b and miR-217 in the pancreatic ductal adenocarcinoma and adjacent tissues were detected by real-time fluorescence quantitative polymerase chain reaction method, the level of TGFβR1 protein was detected by Western blotting method. Results In the pancreatic ductal adenocarcinoma tissues, the expression levels of miR-196b and TGFβR1 protein were significantly higher than those of adjacent tissues (P<0.001), while the level of miR-217 was significantly lower than that of adjacent tissues (P=0.001). For further detection, the level of miR-196b in pancreatic ductal adenocarcinoma tissues was significantly positively correlated with the expression level of TGFβR1 protein (r=0.803, P<0.001), while the expression level of miR-217 was negatively correlated with the expression level of TGFβR1 protein (r=–0.839, P<0.001). Conclusions Expression TGFβR1 protein in pancreatic ductal adenocarcinoma tissues may be bi-directionally regulated by miR-196b and miR-217. This two-way regulating mechanism may be one of the important mechanisms for restricting the development of pancreatic ductal adenocarcinoma, implying a potential target for treatment of pancreatic cancer.