Method, device and equipment for screening abnormity of fundus macular area, and storage medium

Abstract

The invention relates to the field of artificial intelligence, and provides a method, a device and equipment for screening an abnormity of a fundus macular area and a storage medium, and the method comprises the steps: receiving an adjustment instruction inputted by a user; scanning a macular area of the eyes of the testee through a single-line scanning mode of the optical coherence tomography scanner to obtain a macular area image and a macular area thickness of the testee; inputting the macular area image into a convolutional neural network, and performing convolution operation on the macular area image to obtain a convolution feature matrix of the macular area image; polling the convolutional feature matrix through a pooling layer of the convolutional neural network to obtain multiple groups of local feature sets; and inputting the thickness category into the convolutional neural network, wherein the convolutional neural network performs weighted summation on the macular region setand the thickness category through the weight of neurons. Automatic screening of macular area anomalies is achieved, the screening efficiency of macular area anomalies is improved, the labor cost is reduced, and no damage is caused to eyes in the screening process.

Description

technical field [0001] This application relates to the field of image detection, in particular to a method, device, equipment and storage medium for screening abnormalities in the macular area of ​​the fundus. Background technique [0002] At present, artificial intelligence technology has begun to play a role in the field of medical imaging. The use of artificial intelligence to analyze medical images is not only efficient but also accurate enough to reach the level of doctors. For example, in terms of screening for abnormalities in the macular area of ​​the fundus, using artificial intelligence to screen optical coherence tomography (OCT) images of the macular area of ​​the fundus has achieved relatively good results. However, due to certain uncertainties in artificial intelligence, the accuracy rate cannot reach 100%. Only using artificial intelligence cannot completely and correctly analyze OCT images, and some images will still be misjudged. For example, when some pa...

AI Technical Summary

Problems solved by technology

The traditional macular abnormality screening method is manual screening, which has the disadvantages of high labor cost and low screening efficiency

Images