An Image Recognition Method of Fungal Keratitis Based on Ambp Improved Algorithm

Abstract

The invention discloses an image recognition method for fungal keratitis based on the AMBP improved algorithm, which comprises the following steps: using the RX abnormal detection algorithm to preprocess and binarize the mycelium image and the normal corneal nerve image, and then perform expansion and corrosion processing , strengthen the hyphae and neural characteristic information in the image; improve the AMBP algorithm, calculate the mean value of the pixels in the analysis window except the center pixel, and use it as a new parameter; calculate the average value and median value of the pixels in the analysis window respectively pixels, calculate the variance between the two and the rest of the pixels in the analysis window, and use the difference as a new discriminant condition to extract image texture features; use the extracted features to train a classifier, and use this classifier to identify images acquired by confocal microscopes. Identify nerves and hyphae in images.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and specifically relates to an image recognition method for fungal keratitis based on an improved AMBP algorithm. Background technique [0002] Fungal keratitis is an infectious corneal disease with a high blinding rate caused by pathogenic fungi. In recent years, due to the extensive use of antibiotics, immunosuppressants and glucocorticoids, its incidence has increased significantly. The lack of rapid and effective early diagnosis methods often leads to misdiagnosis of the disease and delays in early treatment. It is very easy to cause serious consequences such as corneal perforation, anterior chamber empyema, and endophthalmitis, which is extremely harmful. Early diagnosis and treatment are particularly important. [0003] At present, the routine examination methods for fungal keratitis include corneal scraping mirror method, corneal biopsy, corneal scraping culture, and intravital confocal...

AI Technical Summary

Problems solved by technology

However, the confocal microscope method also has some shortcomings: low light level reflection of corneal tissue and eye movement often lead to low signal-to-noise ratio, strong light causes eye discomfort, and thick corneal lesions often cause blurred pictures and their examination. Expensive, etc., and the confocal microscope method is only a kind of imaging diagnosis, which is highly subjective

The acquisition of these massive medical images brings two problems: on the one hand, doctors need to spend a lot of time reading the examination images of patients, which is a very heavy work

But in its feature extraction step, the traditional texture analysis algorithm does not achieve many good results in fungal keratitis images

Images