In view of the evaluation of fundus image segmentation, a new evaluation method was proposed to make up insufficiency of the traditional evaluation method which only considers the overlap of pixels and neglects topology structure of the retinal vessel. Mathematical morphology and thinning algorithm were used to obtain the retinal vascular topology structure. Then three features of retinal vessel, including mutual information, correlation coefficient and ratio of nodes, were calculated. The features of the thinned images taken as topology structure of blood vessel were used to evaluate retinal image segmentation. The manually-labeled images and their eroded ones of STARE database were used in the experiment. The result showed that these features, including mutual information, correlation coefficient and ratio of nodes, could be used to evaluate the segmentation quality of retinal vessel on fundus image through topology structure, and the algorithm was simple. The method is of significance to the supplement of traditional segmentation evaluation of retinal vessel on fundus image.
Algorithms ; Databases, Factual ; Diagnostic Imaging ; methods ; Diagnostic Techniques, Ophthalmological ; Fundus Oculi ; Humans ; Image Processing, Computer-Assisted ; Retina ; Retinal Vessels ; anatomy & histology

Objective To explore the value of prophylactic anticoagulation in the 28-day prognosis of patients with severe COVID-19.Methods The clinical data of COVID-19 patients admitted to Guangdong Provincial People's Hospital from December 2022 to January 2023 were collected,including age,gender,past medical history,routine blood test,liver and renal function,procalcitonin,coagulation function,Padua prediction score,antiviral therapy,hormonotherapy,immunotherapy and anticoagulation therapy.The patients were divided into an anticoagula-tion group and a non-anticoagulation group.The differences in various indicators were compared between the two groups.Cox regression was performed to assess the independent risk factors for 28-day mortality and the anticoagula-tion efficacy between the subgroups.Results Among 158 patients,128 received anticoagulation;There were significant differences between the two groups in case number of hypertension and critical condition,lymphocyte count,prothrombin time,D-dimer,and case number of immunotherapy.COX logistic regression showed that antico-agulation(HR = 2.25,95%CI:1.01～5.01,P = 0.048)was an independent risk factor for all-cause mortality of COVID-19 patients within 28 days.Subgroup analysis showed that anticoagulation therapy led to an increase in the 28-day mortality as level of procalcitonin of≥0.5 pg/mL(HR = 2.72,95%CI:1.05～7.04)or D-dimer of<2 000 ng/mL(HR = 9.16,95%CI:1.63～51.48).Conclusions Prophylactic anticoagulation did not reduce all-cause mortality of COVID-19 within 28 days.