Thyroid eye disease screening method, system and equipment based on orbit CT image

Abstract

The invention provides a thyroid eye disease screening method, system and device based on an orbit CT image. The thyroid eye disease screening method comprises the steps: acquiring the orbit CT imageto be recognized; preprocessing the acquired orbit CT image to be identified; performing thyroid-related eye disease and non-thyroid-related eye disease recognition on the preprocessed orbit CT imageby using a classification CNN model; obtaining an orbit CT image classification result; wherein the obtained to-be-recognized orbit CT image is a 3D image, and the tomography area is an area from theeyebrow bone to the nose. According to the invention, the error problem caused by manual judgment of ophthalmologists is solved. Compared with the prior art, the method, system and equipment have theadvantage of more objectivity, and meanwhile, the accuracy and the speed of classifying the CNN model enable screening to be faster and more efficient, so that problems can be found as soon as possible.

Description

technical field [0001] The present invention is a technology in the field of artificial intelligence, and in particular relates to an intelligent screening method, system and equipment for thyroid-related eye diseases based on orbital CT images. Background technique [0002] Thyroid-associated ophthalmopathy (TAO) is the orbital disease with the highest incidence rate. It is a series of ocular clinical symptoms caused by abnormal thyroid function, extraocular muscles, retro-orbital connective tissue and adipose tissue due to cell proliferation, inflammation and accumulation of glycosaminoglycan. It manifests as physiological characteristics, leading to vision loss or even blindness, seriously endangering the patient's visual function and craniofacial appearance, and its quality of life score is lower than that of patients with diabetes, emphysema and heart failure, causing a heavy burden to the family and society. At present, the hotspots of clinical research on orbital dise...

AI Technical Summary

Problems solved by technology

However, the commonality of the above orbital disease studies is that they only focus on patients with highly suspected or even diagnosed orbital diseases, and do not involve screening

The lack of screening, untimely and inaccurate diagnosis seriously restrict the timely and effective treatment of diseases, and bring huge physical and mental burdens to patients and heavy social burdens

[0006] At present, there is no description or report of similar technology to the present invention, and no similar information has been collected at home and abroad

Images