Eye image recognition based diabetes diagnosis model construction method and electronic equipment

Abstract

The invention discloses a diabetes diagnosis model construction method based on eye image recognition and electronic equipment. The construction method specifically comprises the steps of obtaining multiple groups of binocular image images of a crowd based on the electronic equipment; preprocessing each group of binocular image images to obtain sclera images and iris images of each group of binocular image images, and constructing a training sample set based on all sclera images and iris images; constructing a first-step classifier by using the unhealthy samples and the healthy samples in the training sample set; constructing a second-step classifier by using other disease samples and diabetes samples in the training sample set; and integrating the classifier in the first step and the classifier in the second step to obtain a diabetes diagnosis model. According to the scheme, the diabetes diagnosis model which is a diagnostic tool for eye diagnosis can be obtained, diabetes diagnosis is carried out on a patient based on objective standards without depending on naked eye observation and personal experience of a doctor, and the stability of diabetes eye diagnosis is improved.

Description

technical field [0001] The present application relates to the technical field of medical equipment, and more specifically, relates to a method for constructing a diabetes diagnosis model based on eye image recognition and electronic equipment. Background technique [0002] Diabetes is a systemic disease that seriously endangers people's health. In order to treat this disease, it is necessary to conduct a scientific and accurate diagnosis of diabetes to obtain accurate diagnostic results. At present, the diagnosis of diabetes is mainly achieved through blood tests. During this process, multiple blood tests are required to detect blood sugar, which not only increases the time and economic costs of the subjects and medical staff, but also because this method is invasive. Therefore, There is a certain risk of infection. In addition, the subject must participate in the test at a specific time (hospital business hours) and a specific location (hospital). [0003] Traditional Chi...

AI Technical Summary

Problems solved by technology

[0004] However, due to the current visual diagnosis of diabetes lacking the carrier of the eye image entity and the lack of information and visualization presentation forms, it must rely on the doctor's naked eye observation and personal experience to complete, resulting in a huge gap in the visual diagnosis of diabetes. Ambiguity, subjectivity and instability bring a lot of inconvenience to clinic, teaching and scientific research, and severely limit the role of visual diagnosis of diabetes

Images