Multicellular sphere recognition and classification method based on deep learning

A deep learning and classification method technology, applied in clinical application and scientific research, can solve the problem that the accuracy of microscopic image algorithm needs to be improved, and achieve the effect of reducing the amount of calculation, improving the accuracy, and enhancing the generalization performance and robustness.

Inactive Publication Date: 2020-12-01
南京英瀚斯生物科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the complexity and specificity of limited aggregate culture of multicellular spheroids, especially for the recognition and classification of cell aggregate morphology, the accuracy of existing microscopic image algorithms needs to be 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
  • Multicellular sphere recognition and classification method based on deep learning
  • Multicellular sphere recognition and classification method based on deep learning
  • Multicellular sphere recognition and classification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further illustrated below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. After reading the present invention, those skilled in the art all fall into the appended claims of the present application to the amendments of various equivalent forms of the present invention limited range.

[0033] Such as figure 1 As shown, the process of the deep learning-based multicellular spheroid identification and classification method of the present invention mainly includes algorithm model training and detection:

[0034] 1. Image segmentation and model training:

[0035] 1. Collect microscopic images of cells through a microscope and perform grayscale conversion;

[0036] 2. Build a cell detection model based on the RCNN algorithm, and use grayscale images to manually ...

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 multicellular sphere recognition and classification method based on deep learning. The method comprises the following steps: firstly, converting a multicellular sphere culture microscopic image into a grayscale image; training an RCNN algorithm model through a manually labeled training set to obtain an optimal RCNN detection model; recognizing and positioning target multicellular spheres in the image by the trained optimal detection model, and extracting sub-images of the multicellular spheres in the image; segmenting the cell spheres by adopting an algorithm based ona histogram segmentation threshold, extracting segmented multi-cell images, and training the segmented multi-cell images through artificially classified large-sample multi-cell sub-images to obtain an optimal cell classification model; and carrying out cell classification on the cell microscopic image by using the trained optimal cell classification model. According to the method, the cell recognition detection and generalization performance and robustness can be remarkably enhanced, the influence of an external environment and manual operation on a detection result is greatly reduced, the accuracy of detection analysis is improved, and meanwhile, the detection efficiency is improved.

Description

technical field [0001] The invention mainly relates to clinical application and scientific research related to sperm morphology analysis based on artificial intelligence. Background technique [0002] With the development of modern cell and molecular biology techniques, human beings have made great progress in the research on the pathogenesis and outcome mechanisms of various diseases, and based on this, various new treatment methods have been developed, thus greatly improving the Diagnosis, treatment and prognosis of various diseases. The diagnosis and treatment of cancer and the development of cell-targeted drugs all require the cultivation of cells for in vitro cell tests, which in turn provide preliminary basic research for animal tests and even human clinical trials. However, the current traditional cell culture requires frequent manual intervention and operation to determine and classify cells. Therefore, due to differences in manual experience, evaluation and classif...

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): G06T7/136G06K9/62G06N3/04G06N3/08G06T7/194
CPCG06T7/136G06N3/084G06T7/194G06T2207/10056G06N3/045G06F18/2415
Inventor 李冬冬訾红彦戴仕奎周飞
Owner 南京英瀚斯生物科技有限公司
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