Method for evaluating liver cirrhosis index detection through platelet counting method

A technology of platelet counting and index, which is applied in the field of medical diagnosis, can solve the problems of gradient dispersion, large loss of main position, and great influence, and achieve the effects of saving time, reducing manpower, and improving efficiency

Pending Publication Date: 2021-10-29
成都云芯医联科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing platelet counting algorithm is sensitive to the resolution of the image, and at the same time has a great influence on the interference of light and scattering, requires many steps of manual processing, and will be affected by various factors to judge, and the feature extraction based on mask-rcnn network, it is easy to produce the problem of gradient disappearance and gradient dispersion, the loss of target classification is small, and the loss of main position is relatively large. The problem

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
  • Method for evaluating liver cirrhosis index detection through platelet counting method
  • Method for evaluating liver cirrhosis index detection through platelet counting method
  • Method for evaluating liver cirrhosis index detection through platelet counting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] according to figure 1 , 2 , 3, and 4, the present embodiment provides a method for evaluating liver cirrhosis index detection by platelet counting method, comprising the following steps:

[0030] Step 1. The yolo_v3 network structure is established, and the yolo_v3 network composed of the backbone network Darknet_53 and the feature prediction Yolo_head is established. The backbone network Darknet_53 is the feature extraction backbone network, which consists of five residual blocks. Each residual block has 1, 2, 8, 8, and 4 residual units, the residual unit is the DBL convolution layer, the batch normalization layer and the linear unit with leakage correction. The feature prediction Yolo_head is the prediction output network. After the backbone network Darknet_53 inputs the feature maps of three scales, To achieve diversification of the receptive field, the Yolo_head output is the prediction of three scales, and each grid of the feature map of each scale is set with thr...

Embodiment 2

[0043] according to figure 1 , 2 , 3, and 4, the present embodiment provides a method for evaluating liver cirrhosis index detection by platelet counting method, comprising the following steps:

[0044] Step 1. The yolo_v3 network structure is established, and the yolo_v3 network composed of the backbone network Darknet_53 and the feature prediction Yolo_head is established. The backbone network Darknet_53 is the feature extraction backbone network, which consists of five residual blocks. Each residual block has 1, 2, 8, 8, and 4 residual units, the residual unit is the DBL convolution layer, the batch normalization layer and the linear unit with leakage correction. The batch normalization layer is used as a regularization method to speed up convergence and avoid overfitting. As the network gets deeper and deeper, it becomes more and more difficult to learn features. The learning process of the residual block changes from directly learning features to adding some features on ...

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 method for evaluating liver cirrhosis index detection through a platelet counting method. The method comprises the following steps: step 1, building a yolo_v3 network structure; step 2, training a network model; step 3, outputting network prediction; step 4, analyzing the experiment result; according to the method, three different sizes of cells in blood can be classified by using a yolo_v3 network structure, the used backbone network darknet_53 has an excellent feature extraction capability, a residual block is introduced into a deep network, so that the algorithm is more accurate in detection, gradient disappearance caused by too large depth is avoided, meanwhile, manual counting is avoided, waste of manpower and material resources is reduced, real-time target detection, position regression and counting are achieved, and time is saved for improving efficiency of clinical research and liver cirrhosis detection.

Description

technical field [0001] The invention relates to the technical field of medical diagnosis, in particular to a method for evaluating liver cirrhosis index detection by platelet counting method. Background technique [0002] The liver is an organ in the body that mainly performs metabolic functions, as well as detoxification, hematopoiesis and blood coagulation. Alcoholism, nutritional disorders, or viruses can easily cause people to suffer from various liver diseases. The early symptoms of liver diseases are not obvious. As the disease progresses, it will affect multiple tissue systems and even cirrhosis. Liver cirrhosis detection models are complex, and the real-time effect is not ideal, which may miss the best time for disease treatment. Therefore, a separate formula for detecting liver cirrhosis came into being, that is, the APRI index: (AST(Aspartate Transaminase) to platelet ratio, this index can efficiently and accurately identify patients with liver cirrhosis, paying a...

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): G06T7/00G06K9/32G06K9/62G16H50/20G06N3/04
CPCG06T7/0012G16H50/20G06T2207/30056G06N3/045G06F18/214
Inventor 付苗苗郭劲宏
Owner 成都云芯医联科技有限公司
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