Optical coherence tomography image retinopathy intelligent detection system and detection method

Abstract

The invention discloses an optical coherence tomography image retinopathy intelligent detection system and a detection method. Currently obtained retinal images are mainly judged by ophthalmologists relying on naked eye observation, which is not conducive to large-scale promotion. The present invention takes the idea of ​​deep learning as the technical core, combines the migration learning strategy, uses the convolutional neural network algorithm in the deep learning model to construct a classifier, realizes the classification of retinal lesions, and uses the image segmentation algorithm to realize the extraction of lesions and retinal layering , so as to obtain the specific information of the lesion position in the picture and the quantitative information of the morphological parameters, and generate relevant diagnostic reports for further diagnosis by doctors. The present invention can make up for the blank of the current optical coherence tomography system in the field of intelligent identification and precise positioning of lesions, effectively reduce the work intensity of doctors, and further promote the clinical application and technical development of the optical coherence tomography system in the diagnosis of ophthalmic diseases.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an optical coherence tomography image retinopathy intelligent detection system and detection method. Background technique [0002] Eye diseases seriously affect the quality of life of patients. The latest figures from the World Health Organization (October 2013) show that the number of visually impaired people worldwide is approximately 285 million, and the World Health Organization predicts that by 2020, if no action is taken, the number of blind people and patients with other vision problems worldwide will The total will also be doubled. At the end of the last century, the "Vision 2020" global blindness prevention strategy goal proposed that about 50% of blindness can be cured (such as cataract, trachoma, etc.), and about 30% of blindness can be prevented (such as glaucoma, diabetic retinopathy). Therefore, early detection and treatment of ophthalmic dise...

AI Technical Summary

Problems solved by technology

[0004] At present, the retinal images obtained by OCT in the examination of retinal diseases are mainly judged by ophthalmologists relying on naked eye observation. The workload is very heavy, and it is extremely dependent on the doctor's personal clinical experience. This identification method is not conducive to large-scale promotion

In addition, patients with preventable and curable blindness and low vision are more distributed in economically underdeveloped countries and regions. The reason is the lack of medical resources and uneven distribution.

Images