The accurate segmentation of retinal blood vessels in fundus is of great practical significance to help doctors diagnose fundus diseases. Aiming to solve the problems of serious segmentation errors and low accuracy in traditional retinal segmentation, a scheme based on the combination of U-Net and Dense-Net was proposed. Firstly, the vascular feature information was enhanced by fusion limited contrast histogram equalization, median filtering, data normalization and multi-scale morphological transformation, and the artifact was corrected by adaptive gamma correction. Secondly, the randomly extracted image blocks are used as training data to increase the data and improve the generalization ability. Thirdly, stochastic gradient descent was used to optimize the Dice loss function to improve the segmentation accuracy. Finally, the Dense-U-net model was used for segmentation. The specificity, accuracy, sensitivity and AUC of this algorithm are 0.9896, 0.9698, 0.7931, 0.8946 and 0.9738, respectively. The proposed method improves the segmentation accuracy of vessels and the segmentation of small vessels.
<abstract> <p>The preparation of amorphous solid dispersions using polymers is a commonly used formulation strategy for enhancing the solubility of poorly water-soluble drugs. However, a single polymer often does not bring significantly enhance the solubility or amorphous stability of a poorly water-soluble drug. We found an application of a unique and novel binary polymeric blend in the preparation of solid dispersions. The main purpose of this study is to optimize and evaluate resveratrol (Res) amorphous solid dispersions with a novel polymeric system of poly (vinyl pyrrolidone) (PVP) and carboxymethyl chitosan (CMCS). The influence of three different release factors, the ratio of CMCS to the polymer mixture (CMCS% = X<sub>1</sub>), the ratio of Res to the polymer mixture (Res% = X<sub>2</sub>) and the surfactant (Tween 80 = X<sub>3</sub>), on the characteristics of released Res at various times (Q<sub>5</sub> and Q<sub>30</sub>) was investigated. The computer optimization and contour plots were used to predict the levels of the independent variables as X<sub>1</sub> = 0.17, X<sub>2</sub> = 0.10 and X<sub>3</sub> = 2.94 for maximized responses of Q<sub>5</sub> and Q<sub>30</sub>. Fourier transform infrared spectroscopy (FTIR) results revealed that each polymer formed hydrogen bonds with Res. The solid performance and physical stability of the optimized ternary dispersions were studied with scanning electron microscopy (SEM), powder X-ray diffraction (XRD), modulated differential scanning calorimetry (MDSC) and dissolution testing. SEM, XRD and MDSC analysis demonstrated that the Res was amorphous, and MDSC showed no evidence of phase separation during storage. Dissolution testing indicated a more than fourfold increase in the apparent solubility of the optimized ternary dispersions, which maintained high solubility after 90 days. In our research, we used CMCS as a new carrier in combination with PVP, which not only improved the <italic>in vitro</italic> dissolution of Res but also had better stability.</p> </abstract>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.