Pseudohypha detection method and device by increasing direction dimension and storage medium

A detection method and mycelium technology, applied in the fields of equipment and storage media, and deep learning methods, can solve the problems of different bending directions, large intra-class gaps, background information interference, etc.

Active Publication Date: 2021-03-19
山东仕达思生物产业有限公司 +1
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although pseudomycelium is generally filamentous, its shape is ever-changing, with different lengths and bending directions. Even a single hyphae may bend and extend in multiple directions, that is, there is a large gap within the class, and if the pseudomycelium If the length of the wire is longer, the interference caused by the background information is also great
If all forms of hyphae are processed with only one label, then there will be a problem in the pseudo-hyphae training set constructed in this way: the intra-class gap is too large, and there are large differences in the same category, which is good for deep learning methods. characteristics are more difficult

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Pseudohypha detection method and device by increasing direction dimension and storage medium
  • Pseudohypha detection method and device by increasing direction dimension and storage medium
  • Pseudohypha detection method and device by increasing direction dimension and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] A method of pseudohyphae detection by increasing the dimensionality of orientation means:

[0087] The image to be detected is input to the artificial intelligence detection model of false hyphae, and the category label of the image to be detected is obtained; the generation method of the artificial intelligence detection model of false hyphae includes: the original image is manually classified, and the category label is marked The artificial intelligence detection model of false hyphae obtained by training the original image;

[0088] Category labels include horizontal_hypha, vertical_hypha, leftTop_hypha, rightTop_hypha, horizontal_hypha, vertical_hypha, leftTop_hypha, rightTop_hypha respectively refer to the pseudo-hyphae in the horizontal direction, the pseudo-hyphae in the vertical direction, the pseudo-hyphae in the upper-left direction, and the pseudo-bacteria in the upper-right direction Silk,

[0089] Pseudo-hyphae in the horizontal direction refer to pseudo-h...

Embodiment 2

[0091] According to a kind of false hypha detection method described in embodiment 1 by increasing direction dimension, its difference is:

[0092] Label the original image manually, including:

[0093] (1) Manual or automatic microscopic image acquisition equipment collects pictures of pseudohyphae with different backgrounds and shapes for wet slides; to ensure the integrity of the data.

[0094](2) hand over the false hyphae pictures collected in step (1) to experts in related fields for manual labeling,

[0095] For the pseudohyphae with a long length and a single direction, divide it into several pseudohyphae with a short length and a single direction, and mark them according to the following method ①; for the pseudohyphae with a long length and multiple directions, Divide it into several sections of short-length pseudo-hyphae, and mark them according to the following method ②; for short-length pseudo-hyphae with a single direction, directly mark them according to the fol...

Embodiment 3

[0142] According to a kind of false hypha detection method described in embodiment 3 by increasing direction dimension, its difference is:

[0143] Manual or automatic microscopic image acquisition equipment collects pictures of pseudohyphae with different backgrounds and shapes for Gram-stained slides;

[0144] An example of labeling rules for pseudohyphae with short length and single direction in Gram-stained slices, as shown in Figure 2(a). In Figure 2(a), there are two short lengths, which are inclined to the upper right and upper left Slanted pseudohyphae; an example of labeling rules for pseudohyphae of shorter length and multiple orientations in Gram-stained slides, as shown in Figure 2(b) with a shorter pseudohyphae However, the direction of the pseudohyphae is changeable. At this time, it is necessary to mark the part of each section of the pseudohyphae in a single direction separately, which are the pseudohyphae in the vertical direction and the pseudohyphae inclined...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a pseudohypha detection method and device by increasing direction dimensions and a storage medium, and the method comprises the steps: inputting a to-be-detected image into anartificial intelligence detection model of pseudohypha, and obtaining a category label of the to-be-detected image. The method for generating the artificial intelligence detection model of the pseudohypha comprises the following steps: marking the artificial category of an original image, and training the original image marked with a category label to obtain the artificial intelligence detectionmodel of the pseudohypha. By constructing the training set of the pseudohyphae with large inter-class difference and small intra-class difference, convergence of the loss function is accelerated, andthe model training time is shortened.

Description

technical field [0001] The invention relates to a method for detecting false hyphae in the microecology of the female reproductive tract, in particular to a deep learning method, equipment and storage medium for effectively improving the detection rate of false hyphae by increasing direction dimension information. Background technique [0002] Under certain conditions, Candida invades the female lower genital tract and causes inflammation of the skin and mucous membranes of the vulva, so it is called vulvovaginal candidiasis (VVC for short), also often called Candida candidiasis. Vaginitis, fungal vaginitis, or fungal vaginitis. 80%-90% of VVC is caused by Candida albicans, and its morphology has three common types: spores, blastospores, and pseudohyphae. The spores are oval single-walled cells, and the spores germinate. Called blastospores, they then continue to grow into germ tubes, which gradually elongate into filaments called hyphae. During the production process of m...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/62G06N3/04
CPCG06V20/698G06V10/267G06N3/045G06F18/214
Inventor 谢晓鸿谢时灵付树军张平
Owner 山东仕达思生物产业有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap