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

A heart image segmentation method and device

An image segmentation, heart technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of unstable segmentation accuracy and low degree of automation

Active Publication Date: 2020-08-28
神州医疗科技股份有限公司
View PDF18 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method effectively improves the accuracy and speed of heart segmentation. However, when segmenting the heart, it is necessary to manually select the initial model of the prior model and set the relevant setting parameters. The degree of automation is low, and the segmentation accuracy largely depends on the doctor. experience, the segmentation accuracy is not stable

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
  • A heart image segmentation method and device
  • A heart image segmentation method and device
  • A heart image segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] This embodiment discloses a heart image segmentation method, which can extract accurate heart target images from the captured thoracic tomographic images, specifically, as figure 1 As shown, the method includes:

[0082] S110. Acquire a thoracic tomographic image, and extract a heart subject image from the thoracic tomographic image.

[0083] Here, the thoracic tomographic image is a sequence of thoracic tomographic images obtained by photographing the area including the chest cavity in the positive or negative direction of the axis (take the supine position, the direction of the head is the positive direction of the Z axis). It should be noted that, the method in this embodiment is to extract a heart target image from a thoracic tomographic image. The heart target image obtained by the method of this embodiment is not a complete and three-dimensional image of the heart, and it is necessary to perform three-dimensional reconstruction on all heart target images correspo...

Embodiment 2

[0093] Based on the previous embodiment, this embodiment specifically discloses specific implementations of heart subject image extraction and liver image removal in the cardiac image segmentation method. Specifically, the cardiac image segmentation method of this embodiment includes:

[0094] S210. Acquire a thoracic tomographic image, and extract a heart subject image from the thoracic tomographic image.

[0095] here, as Figure 2A As shown, the following steps can be used to realize the extraction of the main body image of the heart:

[0096] S2101. Perform mean centering processing on the gray values ​​of pixels in the thoracic tomographic image, and perform binarization processing on the data after mean value centering to obtain a binarized image with the largest area, and obtain a mask for removing the bed image image.

[0097]In this step, the gray value of the pixel in the chest tomographic image is subjected to mean centering processing according to the mean and v...

Embodiment 3

[0141] Based on the above embodiments, this embodiment specifically discloses a specific implementation manner of removing blood vessel images from heart images in the cardiac image segmentation method. Specifically, the cardiac image segmentation method of this embodiment includes:

[0142] S310. Acquire a thoracic tomographic image, and extract a heart subject image from the thoracic tomographic image.

[0143] S320. Based on the shape of the main heart image, determine whether the main heart image includes a liver image adhered to the heart.

[0144] S330. If the main heart image includes a liver image, remove the liver image from the main heart image based on the right local maximum point obtained by performing distance transformation on the main heart image to obtain a heart image.

[0145] S340. Based on the local maximum points obtained by performing distance transformation on the heart image, remove the blood vessel image from the heart image to obtain a heart target ...

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 and apparatus for cardiac image segmentation are provided. An embodiment of that present application first extracts a cardiac body image from a thoracic sectional image; according to the shape of the heart body image, judging whether or not the liver image adhered to the heart is included in the heart main body image, and when the liver image is included in the heart main body image, removing the liver image from the heart main body image by using a clustering algorithm to obtain the heart image based on the right local maximum point obtained by the distance transformation of the heart main body image; finally, based on the local maximum points of the heart image, the blood vessel image is removed from the heart image, and the heart target image is obtained. The heart target imageobtained by the technical scheme has high accuracy and strong anti-interference, and the heart image automatic segmentation is realized, and the segmentation accuracy and stability are good.

Description

technical field [0001] The present application relates to the technical fields of data processing and image processing, in particular to a heart image segmentation method and device. Background technique [0002] The structure of the heart is complex, including the new atrium, ventricle, coronary artery, superior and inferior vena cava, and valves, and the gray scale of the heart tissue is very similar to that of the surrounding tissue. Therefore, the heart will adhere to other tissues when the heart image is segmented. , causing great difficulty in heart segmentation. [0003] Existing heart image segmentation methods include segmentation methods based on image features and segmentation methods based on prior models. Wherein, the segmentation method based on image features specifically performs image segmentation based on regions or edges. The segmentation speed of this method is fast, but it is easily affected by noise, and it is easy to over-segment the heart image, and...

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 Patents(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/136G06T7/155
CPCG06T7/0012G06T7/11G06T7/136G06T7/155G06T2207/10081G06T2207/20152G06T2207/30048G06T2207/30101
Inventor 史文钊李小英史晓林
Owner 神州医疗科技股份有限公司