Intelligent auxiliary diagnosis system

Abstract

The present invention provides an intelligent auxiliary diagnosis system. The intelligent auxiliary diagnosis system includes a cloud platform and a plurality of terminals connected to the cloud platform through a network, wherein the cloud platform includes a cloud platform algorithm module, and the cloud platform algorithm Based on the huge amount of lesion pictures in the early stage, the module uses artificial intelligence technology to train an intelligent diagnostic auxiliary model. After clinical testing, the sensitivity and specificity have reached the accurate diagnostic level, and the model is embedded in the cloud platform to implement intelligent auxiliary diagnosis. The lesion image can automatically and synchronously feed back the intelligent diagnosis result consistent with the lesion image, and transmit the diagnosis result to the terminal for the doctor's reference. The intelligent auxiliary diagnosis system of the present invention promotes the intelligence and informatization of relevant medical services; establishes a telemedicine artificial intelligence service network, realizes hierarchical diagnosis and treatment services, and can ensure performance and safety; reduces use and maintenance costs; contributes to Strengthen the ability of first-diagnosis of diseases at the grassroots level, and improve the hierarchical diagnosis and treatment system.

Description

technical field [0001] The invention relates to the field of medical instruments, in particular to an intelligent auxiliary diagnosis system for diabetic retinopathy. Background technique [0002] Diabetic retinopathy (Diabetic Retinopathy, DR) is a common blinding eye disease. China is the country with the largest number of type 2 diabetes patients in the world, and the prevalence and blindness rate of DR are also increasing year by year. It is currently the number one blinding disease among working-age people. Currently, the prevalence of DR among people with diabetes in my country is 24.7%-37.5%. According to the statistics of the International Diabetes Federation, as of 2015, there were about 110 million people with diabetes in my country, and based on this, it is estimated that there are about 27 million people with DR in my country. With the substantial increase of diabetic patients, the number of DR patients will increase exponentially in the future, and the prevent...

AI Technical Summary

Problems solved by technology

Even if you master the fundus photography technology, you cannot analyze the fundus photography images independently. You need to go to an ophthalmology department with a certain scale to determine DR lesions and grades after collecting fundus images, which greatly affects the efficiency of DR screening and the experience of DR patients. , making grassroots DR screening difficult to carry out

Through preliminary market research, the project team found that some community hospitals at the grassroots level do not even have the corresponding fundus camera equipment for screening, which has a huge resource gap

Images