Construction method of onychomycosis diagnosis model, diagnosis model and diagnosis device

A diagnostic model and technology for onychomycosis, applied in neural learning methods, medical automated diagnosis, biological neural network models, etc., can solve problems such as difficulty in diagnosing onychomycosis, improve clinical diagnostic efficiency, and improve diagnostic accuracy and efficiency. , Improve the effect of false negative detection rate

Pending Publication Date: 2022-05-31
SUN YAT SEN MEMORIAL HOSPITAL SUN YAT SEN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In clinical practice, onychomycosis, nail psoriasis, and irritant onychomycosis may have common dermoscopic features, so the diagnosis of onychomycosis under dermatoscopy is difficult
Especially for young doctors, the diagnostic accuracy of onychomycosis through dermoscopy needs to be further improved

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
  • Construction method of onychomycosis diagnosis model, diagnosis model and diagnosis device
  • Construction method of onychomycosis diagnosis model, diagnosis model and diagnosis device
  • Construction method of onychomycosis diagnosis model, diagnosis model and diagnosis device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Embodiment one: the construction method of onychomycosis diagnosis model

[0050] figure 1 A schematic flow chart of a method for constructing a diagnosis model of onychomycosis is exemplarily shown. Onychomycosis diagnostic model construction methods include:

[0051] S101: Collect samples, and analyze the dermoscopic features of the samples. The samples include dermoscopic images of healthy nails and diseased nails, and the dermoscopic images are statistically analyzed to obtain dermoscopic features with positive predictive factors for the diagnosis of onychomycosis;

[0052] Further, the dermoscopic images of diseased nails include dermoscopic images of onychomycosis, nail psoriasis, and irritant nail disease;

[0053] Further, said onychomycosis has a positive predictive factor, and the dermoscopic features include one or more of longitudinal striations, jagged edges, marble-like cloudy areas, distal irregular interruptions, and / or conical onychokeratosis variou...

Embodiment 2

[0070] Embodiment two: onychomycosis diagnostic device

[0071] This embodiment provides a diagnostic device comprising the onychomycosis diagnostic model obtained by the construction method in Embodiment 1. Such as Figure 4 As shown, the onychomycosis diagnosis device 200 includes a data collection module 201 , a onychomycosis diagnosis model module 301 , and a display module 401 .

[0072] Further, the collection module 201 is selected from a dermatoscope, and is used to collect a dermoscopic image of a subject;

[0073] Further, the onychomycosis diagnostic model module 301 includes three diagnostic model sub-modules 302, 303 and 304, the diagnostic sub-module 302 is used to set the diagnostic model I, the diagnostic sub-module 303 is used to set the diagnostic model II, and the diagnostic model Submodule 304 is used for setting diagnosis model III, and described diagnosis model submodule 302 is used for distinguishing disease first and healthy first, and described diagn...

Embodiment 3

[0080] Embodiment three: Diagnose using the onychomycosis diagnostic model

[0081] 1. Analysis of dermoscopic features of onychomycosis

[0082] The dermoscopic images of samples of onychomycosis, nail psoriasis, irritant nail disease and healthy nails were collected and analyzed statistically to obtain the dermoscopic features that are positive predictive factors for the diagnosis of onychomycosis: longitudinal stripes, jagged Margins, areas of marbled opacity, distal irregular interruptions, and / or conical onychokeratosis.

[0083] 2. Build an artificial intelligence diagnosis model for onychomycosis

[0084] Using dermoscopic images to train an artificial intelligence model to construct a dermoscopic artificial intelligence diagnostic model for onychomycosis. Specifically, the artificial intelligence model is selected from RCNN, FastRCNN, FasterRCNN, preferably FasterRCNN.

[0085] 2.1. Build a dataset

[0086] A total of 835 cases of dermoscopic images were collected,...

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 provides a construction method of an onychomycosis diagnosis model, the diagnosis model and a diagnosis device. The construction method of the onychomycosis diagnosis model comprises the following steps that a training set is constructed, the training set comprises dermatoscope images of a diseased nail and a healthy nail, the images in the training set are marked, and the marked training set is obtained; and constructing a diagnosis model of the onychomycosis, carrying out modeling by adopting a deep learning algorithm model, inputting the marked images of the training set into the deep learning algorithm model for training, and obtaining the diagnosis model of the onychomycosis after the training is completed.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence diagnosis, and in particular to a method for constructing a diagnosis model of onychomycosis, a diagnosis model, a computer-readable storage medium and a diagnosis device. Background technique [0002] Dermoscopy is a skin magnifying glass (10×-200×), which can eliminate the reflected light on the skin surface at the same time. As a non-invasive detection technology for observing the skin surface and its underlying structure, dermoscopy can reflect specific tissue structure patterns, reduce unnecessary biopsies, and improve the accuracy of diagnosis. Under the dermatoscope, onychomycosis (is the nail plate or subungual tissue infection caused by various fungi, mainly caused by dermatophytes, yeasts and non-dermatophyte molds, wherein the onychomycosis caused by dermatophytes infection Onychomycosis is called onychomycosis. The incidence of onychomycosis accounts for 2%-18% of the n...

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): G16H50/20G16H30/00G06T7/00G06V10/764G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG16H50/20G16H30/00G06T7/0012G06N3/08G06T2207/20081G06T2207/20084G06T2207/30088G06N3/045G06F18/24G06F18/214
Inventor 鲁莎席丽艳李希清朱显忠张军民蔡文莹张静
Owner SUN YAT SEN MEMORIAL HOSPITAL SUN YAT SEN UNIV
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