Algorithm of automatic identification of diabetic retinopathy foci based on ultra-widefield scanning laser ophthalmoscopy

AIM:To propose an algorithm for automatic detection of diabetic retinopathy(DR)lesions based on ultra-widefield scanning laser ophthalmoscopy(SLO).METHODS:The algorithm utilized the FasterRCNN(Faster Regions with CNN features)+ResNet50(Residua Network 50)+FPN(Feature Pyramid Networks)method for detecting hemorrhagic spots,cotton wool spots,exudates,and microaneurysms in DR ultra-widefield SLO.Subimage segmentation combined with a deeper residual network FasterRCNN+ResNet50 was employed for feature extraction to enhance intelligent learning rate.Feature fusion was carried out by the feature pyramid network FPN,which significantly improved lesion detection rates in SLO fundus images.RESULTS:By analyzing 1076 ultra-widefield SLO images provided by our hospital,with a resolution of 2600×2048 dpi,the accuracy rates for hemorrhagic spots,cotton wool spots,exudates,and microaneurysms were found to be 87.23%,83.57%,86.75%,and 54.94%,respectively.CONCLUSION:The proposed algorithm demonstrates intelligent detection of DR lesions in ultra-widefield SLO,providing significant advantages over traditional fundus color imaging intelligent diagnosis algorithms.

GRIP： A Group Recommender Based on Interactive Preference Model

Numerous applications of recommender systems can provide us a tool to understand users. A group recommender reflects the analysis of multiple users＇ behavior, and aims to provide each user of the group with the things they involve according to users＇ preferences. Currently, most of the existing group recommenders ignore the interaction among the users. However, in the course of group activities, the interactive preferences will dramatically affect the success of recommenders. The problem becomes even more challenging when some unknown preferences of users are partly influenced by other users in the group. An interaction-based method named GRIP （Group Recommender Based on Interactive Preference） is presented which can use group activity history information and recommender post-rating feedback mechanism to generate interactive preference parameters. To evaluate the performance of the proposed method, it is compared with traditional collaborative filtering on the MovieLens dataset. The results indicate the superiority of the GRIP recommender for multi-users regarding both validity and accuracy.

Method for Processing Graph Degeneracy in Dynamic Geometry Based on Domain Design

A dynamic geometry system,as an important application in the field of geometric constraint solving,is widely used in elementary mathematics education;moreover,the dynamic geometry system is also a fundamental environment for automated theorem proving in geometry.In a geometric constraint solving process,a situation involving a critical point is often encountered,and geometric element degeneracy may occur at this point.Usually,the degeneracy situation must be substantively focused on during the learning and exploration process.However,many degeneracy situations cannot be completely presented even by the well-known dynamic geometry software.In this paper,the mechanisms causing the degeneracy of a geometric element are analyzed,and relevant definitions and formalized descriptions for the problem are provided according to the relevant modern Euclidean geometry theories.To solve the problem,the data structure is optimized,and a domain model design for the geometric element and the constraint relationships thereof in the dynamic geometry system are formed;furthermore,an update algorithm for the element is proposed based on the novel domain model.In addition,instances show that the proposed domain model and the update algorithm can effectively cope with the geometric element degeneracy situations in the geometric constraint solving process,thereby achieving unification of the dynamic geometry drawing and the geometric intuition of the user.

A Simple and Quick Screening Method for Intrapulmonary Vascular Dilation in Cirrhotic Patients Based on Machine Learning

Background and Aims:Screening for hepatopulmonary syndrome in cirrhotic patients is limited due to the need to perform contrast enhanced echocardiography(CEE)and arterial blood gas(ABG)analysis.We aimed to develop a simple and quick method to screen for the presence of intrapulmonary vascular dilation(IPVD)using noninvasive and easily available variables with machine learning(ML)algorithms.Methods:Cirrhotic patients were enrolled from our hospital.All eligible patients underwent CEE,ABG analysis and physical examination.We developed a twostep model based on three ML algorithms,namely,adaptive boosting(termed AdaBoost),gradient boosting decision tree(termed GBDT)and eXtreme gradient boosting(termed Xgboost).Noninvasive variables were input in the first step(the NI model),and for the second step(the NIBG model),a combination of noninvasive variables and ABG results were used.Model performance was determined by the area under the curve of receiver operating characteristics(AUCROCs),precision,recall,F1-score and accuracy.Results:A total of 193 cirrhotic patients were ultimately analyzed.The AUCROCs of the NI and NIBG models were 0.850(0.738–0.962)and 0.867(0.760–0.973),respectively,and both had an accuracy of 87.2%.For both negative and positive cases,the recall values of the NI and NIBG models were both 0.867(0.760–0.973)and 0.875(0.771–0.979),respectively,and the precisions were 0.813(0.690–0.935)and 0.913(0.825–1.000),respectively.Conclusions:We developed a two-step model based on ML using noninvasive variables and ABG results to screen for the presence of IPVD in cirrhotic patients.This model may partly solve the problem of limited access to CEE and ABG by a large numbers of cirrhotic patients.