Quantitative analysis system for retinopathy based on image recognition

Abstract

The invention provides a quantitative analysis system for retinopathy based on image recognition. The system comprises a retina fundus image acquisition module, an image preprocessing module, a nervefiber functional layer upper bound recognition module, a nerve fiber functional layer upper bound recognition module, a nerve fiber functional layer lower bound recognition module, a calculation module and a quantitative analysis result output module. The system has the advantages that the following characteristic parameters for quantitative analysis of retinopathy can be accurately detected and analyzed by adopting the computer intelligent image analysis method: nerve fiber functional layer nuclear number quantity A1, nerve fiber functional layer nuclear total area SA, nerve fiber functionallayer lower bound length L, nerve fiber functional layer area S total, edema index SZ and cell proliferation index PI, thus providing objective accurate detection results for ophthalmic diagnosis or animal retinal pathology research.

Description

technical field [0001] The invention belongs to the technical field of medical equipment, and in particular relates to a quantitative analysis system for retinopathy based on image recognition. Background technique [0002] There are many causes of retinopathy, including retinal vascular disease, retinal congenital abnormalities, retinal circulation disorders, and retinal vasculitis. Clinically, there are many types of retinopathy, including abnormal retinal vascular disease, diabetic retinopathy, arteriosclerosis and hypertensive retinopathy, retinal vascular disease caused by systemic diseases, retinal hemangioma, traumatic vascular retinopathy, poisoning And radiation retinopathy and choroidal disease, hemangioma, and various degenerative diseases. [0003] The retinal tissue structure is complex, and the retina consists of 10 layers from outside to inside: ①pigment epithelium; ②rod and cone; ③outer membrane; ④outer nuclear layer; ⑧ ganglion cell layer; ⑨ nerve fiber la...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, after OCT images the retina, the above-mentioned retinal parameters can only be obtained by the naked eye observation of the doctor, which relies heavily on the doctor's personal experience, and there is no uniform, objective and accurate test result, which affects the accuracy of ophthalmology clinical diagnosis sex

Similarly, when conducting pathological research on animal retinas, the existing technology is to prepare animal retinas as HE-stained sections, and judge pathological changes through manual interpretation by pathologists. This is highly subjective, and different pathologists have different reading results. , and cannot be quantitatively analyzed

Images