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

Bone marrow cell classification method and system, computer equipment and storage medium

A bone marrow cell and classification method technology, applied in the field of bone marrow cell classification, can solve the problems that the identification experience of doctors cannot be well expressed, the classification accuracy of traditional methods is limited, and the degree of similarity between features is high. Detection effect, high classification accuracy effect

Pending Publication Date: 2022-06-03
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, descriptors sometimes do not express well the recognition experience of doctors
At the same time, due to the characteristics of bone marrow cells, the difference between some classes is small, and the similarity between features is high, and the classification accuracy of traditional methods is limited.

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
  • Bone marrow cell classification method and system, computer equipment and storage medium
  • Bone marrow cell classification method and system, computer equipment and storage medium
  • Bone marrow cell classification method and system, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] Bone marrow cell classification work is often regarded as a coarse-grained classification task, and commonly used deep networks (such as ResNet) are used to classify myeloid cells. However, for practical application requirements, it is necessary to classify cells of the same genus into different types according to the maturity of bone marrow cells. Only the deep network designed for coarse-grained classification is used, and the classification accuracy is limited. To this end, this embodiment provides a method for classifying bone marrow cells.

[0078] like figure 1 As shown, the method for classifying bone marrow cells of the present embodiment includes the following steps:

[0079] S101. Acquire a first data set and a second data set.

[0080] Obtain the bone marrow cell microscopic image set of patients with different disease types as a data set, wherein the data set includes several bone marrow cell microscopic images of patients with different disease types, and...

Embodiment 2

[0132] like Figure 4 As shown, this embodiment provides a bone marrow cell classification system, which includes a first acquisition unit 401, a construction unit 402, a first training unit 403, a second training unit 404, a second acquisition unit 405, a prediction unit 406, The specific functions of the segmentation unit 407 and the classification unit 408 are as follows:

[0133] a first obtaining unit 401, configured to obtain a first data set and a second data set;

[0134] A construction unit 402 is used to construct a bone marrow cell detection network and a multi-level feature learning network based on feature fusion;

[0135] The first training unit 403 is used to select the YOLOX network as the bone marrow cell detection network, and use the first data set to train the bone marrow cell detection network to obtain a trained bone marrow cell detection network;

[0136] The second training unit 404 is configured to use the second data set to train the multi-level fea...

Embodiment 3

[0143] like Figure 5 As shown, this embodiment provides a computer device, which includes a processor 502 , a memory, an input device 503 , a display device 504 and a network interface 505 connected through a system bus 501 . The processor 502 is used to provide computing and control capabilities, the memory includes a non-volatile storage medium 506 and an internal memory 507, the non-volatile storage medium 506 stores an operating system, computer programs and databases, and the internal memory 507 is The operating system and the computer program in the non-volatile storage medium 506 provide an environment for running the computer program. When the computer program is executed by the processor 502, the method for classifying the bone marrow cells of the above-mentioned embodiment 1 is implemented, as follows:

[0144] Obtain the first data set and the second data set;

[0145] Build a bone marrow cell detection network and a multi-level feature learning network based on f...

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 bone marrow cell classification method and system, computer equipment and a storage medium. The method comprises the following steps: acquiring a first data set and a second data set; constructing a bone marrow cell fine-grained classification network; acquiring a plurality of original bone marrow cell microscopic images; inputting each original bone marrow cell microscopic image into the trained bone marrow cell detection network for prediction, and outputting a prediction mark of a cell bounding box in each original bone marrow cell microscopic image; segmenting the original bone marrow cell microscopic image according to the prediction result of the cell bounding box, so that each image only contains one complete bone marrow cell; and inputting the segmented image into a bone marrow cell fine-grained classification network for classification, and outputting to obtain a classification result of the bone marrow cells. According to the invention, through learning of multi-layer features in the deep network and introduction of a knowledge distillation mechanism, fusion information is introduced into a single-layer feature classifier, and classification precision of bone marrow cells is improved.

Description

technical field [0001] The invention relates to a method, system, computer equipment and storage medium for classifying bone marrow cells, belonging to the field of computer vision. Background technique [0002] Leukemia is a highly heterogeneous tumor with malignant proliferation of hematopoietic tissue or clonal proliferation of lymphoid tissue, mainly involving blood and bone marrow. Leukemia is one of the top ten malignant tumors in the world. In 2020 alone, there will be more than 470,000 new leukemia patients worldwide, and as many as 310,000 people will die from leukemia. The high morbidity and mortality of leukemia pose a huge threat to human health and life. Leukemia is divided into acute leukemia and chronic leukemia. Among them, acute leukemia has acute onset and severe symptoms. If there is no timely and effective treatment, the average survival period is only about three months. If correctly diagnosed and treated in a timely manner, 80% of children with acute ...

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): G06K9/62G06N3/04G06N3/08G06V10/764G06V10/774G06V10/80G06V10/82G06V10/26
CPCG06N3/08G06N3/045G06F18/241G06F18/253G06F18/214
Inventor 王伟凝郭沛榕骆美鸽尉岩石红霞谭燕
Owner SOUTH CHINA UNIV OF TECH
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