An improved pathogen detection method, device and storage medium based on an improved loop-guided filtering algorithm

Abstract

The present invention relates to an improved pathogen detection method, device and storage medium based on an improved cycle-guided filtering algorithm, comprising the following steps: S1: constructing a pathogen training set for detecting spores and blastospores; S2: constructing spores and blastospores based on S1 Pathogen training set of blastospores, training artificial intelligence target detection model for detecting spores and blastospore pathogens; S3: Filtering the original image based on the improved loop-guided filtering algorithm; S4: Detecting pathogens in the input image: the input image according to S3 performs a filtering operation, and then inputs the filtered image to the pathogen artificial intelligence target detection model trained by S2 to detect the pathogen, and obtain the location information of the pathogen. The invention effectively improves the detection rate of pathogens by adopting an improved loop-guided filtering algorithm and inputting processed images into a deep learning target detection model based on a convolutional neural network.

Description

technical field [0001] The invention relates to a method for detecting pathogens in the microecology of female reproductive tract, in particular to a method, equipment and storage medium for improving pathogen detection based on an improved cycle-guided filtering algorithm. Background technique [0002] Spores and blastospores are common pathogens in the female reproductive tract. Under certain conditions, they invade the female lower reproductive tract and cause inflammation of the skin and mucous membranes of the vulva, resulting in female fungal vaginitis, also known as fungal vaginitis. The detection rate of spores plays a crucial role in diagnosing mycotic vaginitis in women. At present, the Gram staining method for biological specimens of female genital tract secretions combined with the morphological examination of pathogens under a microscope with a 100x high-power objective lens is the most commonly used test method, and it is also the gold standard for the detectio...

AI Technical Summary

Problems solved by technology

However, the common loop-guided filtering has the following problems: First, the common loop-guided filtering has three parameters, which are the filter window size, the variance of the color difference and the variance of the distance difference, but the same set of parameters cannot be used for different images. At the same time, the desired effect can be achieved, that is, for different images, three different parameters need to be adjusted separately to achieve the desired results. Even for the same image, these parameters often need to be obtained from multiple debugging experiments, so the general The loop-guided filtering method is cumbersome and has no versatility in detecting and identifying pathogens in the special scenario of Gram-stained microscopic images of female genital secretion biological specimens

The second is that after using ordinary loop-guided filtering, although the background in the image is blurred, some of the pathogens in the image become clear and some become blurred, and even the shape of the pathogen cannot be clearly distinguished. The overall image and the surrounding area of ​​​​the pathogen The overall background blur effect is not good, and the edge contours of other objects can still be seen; third, there are situations where pathogens are interfered by other objects, or even connected to other objects, which affects the shape of pathogens, which is likely to cause missed detection of pathogens

Images