Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Leukocyte large-view-field image detection system and method based on deep learning

A technology of image detection and deep learning, which is applied in still image data retrieval, image enhancement, image analysis, etc., can solve the problems that the subjective state of the false positive rate inspector is greatly affected, the microscope lacks system support, and cannot realize intelligent detection. It is beneficial to promote the use, save manpower and inspection time, and improve the effect of inspection efficiency

Pending Publication Date: 2020-05-05
北京理工大学重庆创新中心 +1
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, similar to the traditional microscope, the microscope based on Fourier stack imaging technology lacks corresponding system support, cannot realize intelligent detection, and can only rely on the naked eye detection of medical workers, which is not only time-consuming, but also the false detection rate is affected by the subjective state of the examiner Big

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
  • Leukocyte large-view-field image detection system and method based on deep learning
  • Leukocyte large-view-field image detection system and method based on deep learning
  • Leukocyte large-view-field image detection system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] refer to figure 1 and figure 2 As shown, the present invention discloses a leukocyte large field of view image detection system based on deep learning, and the image detection system at least includes an image acquisition module, an image reconstruction module and an intelligent detection module. The image acquisition module is used to realize low-resolution image acquisition of sample images. The image reconstruction module is used to realize the reconstruction of high-resolution images. The intelligent detection module is used to implement the analysis and judgment of abnormal white blood cells based on the high-resolution reconstructed image.

[0038] In this embodiment, the sample to be detected is a human blood smear, and the detection object is white blood cells. The marked white blood cell and red blood cell image sets are stored in the database, and the convolutional neural network is trained using this as the training set. The convolutional neural network ...

Embodiment 2

[0059] On the basis of Embodiment 1, the present invention also discloses a leukocyte large-field image detection method based on deep learning.

[0060] Preferably, the image detection method includes at least the following steps:

[0061] Step S1: the step of establishing a database. Collect low-resolution sample images, reconstruct them to generate high-resolution reconstructed images, annotate the generated images and store them in the database.

[0062] Preferably, the labeling of the generated image in step S1 specifically includes: for white blood cells, realizing detection, classification and counting functions. That is, the size, location, and specific types of white blood cells (neutrophils, eosinophils, basophils, lymphocytes, and monocytes) need to be marked; for red blood cells, the counting function is required. That is, only the position of the red blood cells needs to be marked.

[0063] Step S2: step of training the convolutional neural network model, divid...

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 discloses a leukocyte large-view-field image detection system and method based on deep learning, and the system consists of an image collection module, an image reconstruction module, and an intelligent detection module based on deep learning, and carries out the imaging of a detection sample under different illumination conditions through a low-power microscope objective. The imagecollection module records a set of the low-resolution images; the image reconstruction module obtains a high-resolution image through adoption of a frequency spectrum iteration method; and the detection module uses a pre-trained neural network to perform feature extraction and identification on the generated high-resolution image, and finally outputs a detection result. According to the invention,leukocytes can be intelligently identified, and leukocytes and erythrocytes in a field of view are respectively counted, so that an examiner is helped to quickly and accurately obtain an analysis result; and meanwhile, the requirement of combining high resolution with a large field of view is met, the effect of obtaining higher contrast and resolution by using a low-power lens is achieved, and the manufacturing cost of the system is reduced.

Description

technical field [0001] The invention belongs to the field of computational microscopic imaging and the field of intelligent medical detection, and in particular relates to a large-field-of-view image detection system and method for white blood cells based on deep learning. Background technique [0002] Blood analysis is one of the commonly used clinical examination methods in the medical field, including white blood cell count and classification, red blood cell count, platelet count, hemoglobin count, etc. Among them, white blood cell count is closely related to inflammation and is considered to be an important predictor for early disease diagnosis. Many studies have shown that white blood cell count is positively correlated with cardiovascular diseases, type 2 diabetes and other diseases; in addition, the ratio of white blood cells to red blood cells also has certain medical value. Therefore, white blood cell count has important medical significance. [0003] White blood ...

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): G06T7/00G06T5/00G06T3/40G06F16/51G06N3/04
CPCG06T7/0012G06T3/4053G06F16/51G06T2207/10056G06T2207/20081G06N3/045G06T5/70
Inventor 许廷发王舒珊张继洲张一舟汪心
Owner 北京理工大学重庆创新中心
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com