Sperm morphology recognition method based on deep convolutional neural network and storage medium

A technology of neural network recognition and deep convolution, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problem of the subjective influence of doctors on the recognition and judgment results, affecting the accuracy of sperm morphology recognition, and cumbersome work tasks, etc. problem, to achieve the effect of speeding up the recognition accuracy, fast and accurate judgment, and increasing flexibility

Pending Publication Date: 2022-01-04
SHANGHAI FIRST MATERNITY & INFANT HOSPITAL +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the detection of sperm morphology in clinical work is to stain the semen smears and count them manually under the microscope. This process is cumbersome and takes a long time. morphology, affecting the accuracy of sperm morphology recognition

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
  • Sperm morphology recognition method based on deep convolutional neural network and storage medium
  • Sperm morphology recognition method based on deep convolutional neural network and storage medium
  • Sperm morphology recognition method based on deep convolutional neural network and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] figure 1 It is a flow chart of a sperm morphology recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of recognizing sperm morphology; specifically, it is more suitable for recognizing sperm morphology based on the part outline image of sperm parts. Condition. The method can be executed by a sperm morphology recognition device, and the device can be realized by software and / or hardware.

[0042] Before introducing the technical solution of this embodiment, an exemplary application scenario of the technical solution of this embodiment is firstly introduced. Specifically, the application scenarios include: In recent years, with the increase of life pressure and the influence of environmental pollution and other factors, the number of male infertility patients has shown an increasing trend year by year. Semen analysis is the most commonly used examination method to evaluate male fertility, and In semen anal...

Embodiment 2

[0068] figure 2 It is a flow chart of a sperm morphology recognition method provided by Embodiment 2 of the present invention. On the basis of the above-mentioned embodiments, in this embodiment, in the step of "acquiring polysperm images, and performing image segmentation processing on polysperm images, at least Before "a single sperm image", add "acquire sample data for training the initial sperm segmentation model." The explanation of terms that are the same as or corresponding to the above-mentioned embodiments will not be repeated here. see figure 2 , the sperm morphology recognition method provided in this embodiment includes:

[0069] S210. Obtain sample data for training an initial sperm segmentation model.

[0070]In an embodiment of the invention, the sample data may be at least one tagged polysperm sample image. Optionally, after obtaining each marked polysperm sample image, determine the sample size information of any polysperm sample image; if the sample size...

Embodiment 3

[0086] Figure 4 The structure schematic diagram of the sperm morphology recognition device provided by Embodiment 3 of the present invention is applicable to the situation of recognizing the sperm morphology; specifically, it is more suitable for the situation of recognizing the sperm morphology based on the outline image of the sperm parts. see Figure 4 The specific structure of the sperm morphology recognition device includes: a single sperm image acquisition module 310, a part contour image acquisition module 320 and a sperm morphology identification result determination module 330; wherein,

[0087] A single sperm image acquisition module 310, configured to acquire a polysperm image, and perform image segmentation processing on the polysperm image to obtain at least one single sperm image;

[0088] Part contour image acquisition module 320, configured to extract at least one sperm part in each of the single sperm images, and determine the part contour image of each of t...

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 embodiment of the invention discloses a sperm morphology recognition method based on a deep convolutional neural network and a storage medium. The method comprises the following steps: acquiring a multi-sperm image, and performing image segmentation processing on the multi-sperm image to obtain at least one single sperm image; extracting at least one sperm part in each single sperm image, and determining a part contour image of each sperm part, wherein the sperm part comprises at least one of a head part, an apical body, a cavitation bubble, a neck part and a tail part; and recognizing the part contour image based on a deep convolutional neural network to obtain a sperm morphology recognition result of the single sperm, wherein the sperm morphology recognition result comprises normal sperm morphology or abnormal sperm morphology. According to the technical scheme disclosed by the embodiment of the invention, the sperm morphology recognition is more accurate and rapid, and the efficiency and quality of sperm morphology analysis are improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of medical image processing, and in particular to a sperm morphology recognition method based on a deep convolutional neural network and a storage medium. Background technique [0002] In recent years, with the increase of life pressure and the impact of environmental pollution and other factors, the number of male infertility patients has shown an increasing trend year by year. Semen analysis is the most commonly used examination method to evaluate male fertility. In semen analysis, sperm morphology Detection is one of the most important evaluation factors. [0003] At present, the detection of sperm morphology in clinical work is to stain the semen smears and count them manually under the microscope. This process is cumbersome and takes a long time. morphology, affecting the accuracy of sperm morphology recognition. Contents of the invention [0004] The invention provides a sperm...

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
IPC IPC(8): G06T7/00G06T7/11G06T7/12G06T7/13G06T7/136G06T7/194G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/12G06T7/13G06T7/11G06T7/136G06T7/194G06N3/08G06T2207/10056G06T2207/20132G06T2207/20104G06T2207/20081G06T2207/30242G06T2207/30004G06N3/045G06F18/241G06F18/214
Inventor 滕晓明杨昊赵荔君王建峰梁波滕冰青
Owner SHANGHAI FIRST MATERNITY & INFANT HOSPITAL
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