Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for segmenting and counting adipocyte image based on deep learning model

A fat cell and deep learning technology, applied in the field of image processing, can solve the problems of low analysis efficiency of high-definition cell images and limit the development of cell statistics technology, and achieve high-precision results

Pending Publication Date: 2021-10-29
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The analysis efficiency of existing cell segmentation algorithms for high-definition cell images is still low, which limits the development of cell statistics technology

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 segmenting and counting adipocyte image based on deep learning model
  • Method for segmenting and counting adipocyte image based on deep learning model
  • Method for segmenting and counting adipocyte image based on deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Such as figure 1 As shown, this embodiment relates to a method for segmenting and counting fat cell images based on a deep learning model, which specifically includes the following steps:

[0030] Step 1) Enter such as figure 2 As shown in the fat image I, initial parameters are set: area threshold T, size of the morphological closed operator, watershed length threshold L, and connected domain ellipticity threshold c.

[0031] Step 2) Grayscale the image.

[0032] Step 3) cell edge extraction, specifically including:

[0033] 3.1. Input such as Figure 8 The output probability map calculated after the Unet++ model shown, such as image 3 shown.

[0034] 3.2. Perform Gaussian filtering on the image, such as Figure 4 shown.

[0035] 3.3. Binarize the probability map to obtain a black and white image, such as Figure 5 shown.

[0036] Step 4) Image post-processing: use the watershed algorithm to re-segment, and select the watershed to add to the cell edge image ...

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

A method for segmenting and counting an adipocyte image based on a deep learning model comprises the following steps: inputting the adipocyte image into a deep learning network to obtain the segmentation probability of each pixel in the image, and further generating an adipocyte edge image based on the probability image; removing bubbles through morphological processing and performing segmentation processing through a watershed algorithm in sequence to generate an adipocyte segmentation image, and finally analyzing the cell area distribution of the adipocyte segmentation image through connected domain analysis and counting the quantity of adipocytes on the current target image. The time consumption of artificial fat cell counting is obviously shortened.

Description

technical field [0001] The present invention relates to a technique in the field of image processing, in particular to a method for segmenting and counting fat cell images based on a deep learning model. Background technique [0002] The key operations of cell image processing in the prior art include image segmentation. Accurate image segmentation can increase the accuracy of cell counting, make area analysis more accurate, and obtain better analysis results. The analysis efficiency of existing cell segmentation algorithms for high-definition cell images is still low, which limits the development of cell statistics technology. Contents of the invention [0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention proposes a method for segmenting and counting fat cell images based on a deep learning model, which significantly reduces the time-consuming manual counting of fat cells. [0004] The present invention is achieved through the follow...

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): G06T7/187G06T7/136G06T7/12G06T3/40G06K9/62G06K9/34
CPCG06T7/187G06T7/12G06T7/136G06T3/4038G06T2200/32G06T2207/30242G06F18/214
Inventor 沈红斌王春晖王计秋宁光
Owner SHANGHAI JIAO TONG UNIV