Glaucoma is one of blind causing diseases. The cup-to-disc ratio is the main basis for glaucoma screening. Therefore, it is of great significance to precisely segment the optic cup and disc. In this article, an optic cup and disc segmentation model based on the linear attention and dual attention is proposed. Firstly, the region of interest is located and cropped according to the characteristics of the optic disc. Secondly, linear attention residual network-34 (ResNet-34) is introduced as a feature extraction network. Finally, channel and spatial dual attention weights are generated by the linear attention output features, which are used to calibrate feature map in the decoder to obtain the optic cup and disc segmentation image. Experimental results show that the intersection over union of the optic disc and cup in Retinal Image Dataset for Optic Nerve Head Segmentation (DRISHTI-GS) dataset are 0.962 3 and 0.856 4, respectively, and the intersection over union of the optic disc and cup in retinal image database for optic nerve evaluation (RIM-ONE-V3) are 0.956 3 and 0.784 4, respectively. The proposed model is better than the comparison algorithm and has certain medical value in the early screening of glaucoma. In addition, this article uses knowledge distillation technology to generate two smaller models, which is beneficial to apply the models to embedded device.
Objective To investigate the effect of nitroglycerin on preventing post-endoscopic retrograde cholangiopancreatograph (ERCP) pancreatitis (PEP) and hyperamylasemia. Methods One hundred patients diagnosed as common bile duct stones by CT or MRI and planned to undergo ERCP, EST and stones removal under endoscopy were selected from January to December 2008 in Shandong Jiaotong Hospital. These patients were randomly divided into 2 groups: nitroglycerin group (n=50), in which 0.5 mg nitroglycerin was given sublingually in 5-10 min before ERCP; control group (n=50), in which no nitroglycerin was given. The levels of serum amylase of all the patients before ERCP and at 3 h, 24 h after ERCP were detected and the incidence of hyperamylasemia and PEP were also observed. Results The level of serum amylase between 2 groups before ERCP was not significantly different (P＞0.05). The levels of serum amylase at 3 h and 24 h after ERCP were significantly higher than that before ERCP in 2 groups. The level of serum amylase in nitroglycerin group were respectively lower than that in control group at 3 h and 24 h after ERCP 〔3 h: (108.88±152.07) U/L vs. (196.30±244.41) U/L; 24 h: (97.02±113.38) U/L vs. (234.22±406.05) U/L〕， P＜0.05. The incidence of hyperamylasemia (12.00%, 6/50) and PEP (2.00%, 1/50) in nitroglycerin group was respectively significantly lower than that in control group (hyperamylasemia: 30.00%, 15/50; PEP: 14.00%, 7/50）， P＜0.05. Conclusion Sublingual nitroglycerin can decrease the level of serum amylase and prevent PEP and hyperamylasemia.
