Convolutional neural network-based fungal keratitis detection method and system

Abstract

The invention discloses a convolutional neural network-based fungal keratitis detection method and system, and the method comprises the following steps: collecting a training sample set, and dividingthe training sample set into a fungal mycelium picture set and a fungal mycelium-free picture set; preprocessing the training sample set; constructing a convolutional neural network; Inputting the preprocessed training sample set as training data into the convolutional neural network, and performing iterative training through a gradient descent method and a back propagation algorithm to obtain a detection model with a fungal mycelium recognition function; and detecting a to-be-detected sample by using the detection model, and outputting a detection result. The detection method provided by theinvention has the advantages of high recognition speed and high recognition rate.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method and system for detecting fungal keratitis based on a convolutional neural network. Background technique [0002] Convolutional Neural Network (CNN) is an artificial neural network structure that has been developed in recent years and has attracted widespread attention. Convolutional neural network has good fault tolerance, parallel processing ability and self-learning ability, and has achieved good results in speech recognition and face recognition. Currently the most widely used is in computer image recognition. [0003] Fungal keratitis is an infectious corneal disease caused by pathogenic fungi with a high rate of blindness. Fungal keratitis has a slow onset and a long course, which can last for 2 to 3 months, and corneal ulcers often appear within a few days of onset. In our country, most of the patients are peasants. [0004] If fungal keratitis...

AI Technical Summary

Problems solved by technology

[0005] At present, there are many methods for the examination of fungal keratitis. The positive rate of smear examination is low, the culture time of fungi is long, and the examination of confocal laser microscope requires an experienced doctor to read the pictures. These methods largely depend on the obvious features. degree, the effect is poor, and the error rate is high

Images