Image region-of-interest division method and device and image segmentation method and device

A region of interest and image segmentation technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve problems based on artificial delineation, and the accuracy of delineation depends on the professionalism of business personnel, so as to improve the accuracy of segmentation, Possibility-enhancing effects

Active Publication Date: 2020-03-27
南京景三医疗科技有限公司
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides a method for dividing an image region of interest, an image segmentation method and a device, so as to solve the problem that the delineation of the region of interest in the existing image segmentation is still completely based on artificial delineation, and the delimitation accuracy Questions that completely depend on the professionalism of the business people

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
  • Image region-of-interest division method and device and image segmentation method and device
  • Image region-of-interest division method and device and image segmentation method and device
  • Image region-of-interest division method and device and image segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] figure 1 A flow chart showing a method for dividing an image region of interest according to an embodiment of the present invention, as figure 1 As shown, the method may include the following steps:

[0036] S101: Obtain signal strength values ​​of all pixels in the target image to obtain a signal strength set.

[0037] In the embodiment of the present invention, in order to reduce the amount of data, the signal strength value in the initial region of interest in the target image can generally be obtained first to form a signal strength set. The initial region of interest can be an artificially divided region, and what needs to be explained Yes, based on the method in the embodiment of the present invention, it is to achieve the division of the ROI in the target image. Therefore, the initial ROI here does not require high division accuracy, but only requires the ability to exclude ordinary users and The part of the target image that can be distinguished is obviously n...

Embodiment 2

[0063] image 3 Show the flowchart of the image segmentation method of the embodiment of the present invention, as image 3 As shown, the method may include the following steps:

[0064] S301: Acquire an image to be segmented including a blood vessel region, and divide the image to be segmented using an image region of interest division method to obtain several regions of interest in the image to be segmented.

[0065] The image region-of-interest division method in this step is the image region-of-interest division method described in Embodiment 1 or any one of the implementations of Embodiment 1, and its specific content can be understood with reference to Embodiment 1, and will not be repeated here. .

[0066] S302: Segment several regions of interest using a preset segmentation algorithm to obtain several segmentation results.

[0067] In the embodiment of the present invention, the preset segmentation algorithm can be a region-based segmentation algorithm and its deriv...

Embodiment 3

[0089] Figure 6 It shows a functional block diagram of a device for dividing an image region of interest according to an embodiment of the present invention, and the device can be used to implement the method for dividing an image region of interest described in Embodiment 1 or any optional implementation thereof, which has already been described I won't repeat them here. Such as Figure 6 As shown, the device includes: a signal strength set acquisition module 10 , a subset extraction module 20 , a pixel point set extraction module 30 , a connected region labeling module 40 and a region of interest generation module 50 . in,

[0090]The signal strength set acquisition module 10 is used to acquire the signal strength values ​​of all pixels in the target image to obtain a signal strength set. For details, refer to the relevant description of step S101 in the above method embodiment.

[0091] The subset extraction module 20 is used to extract several consecutive signal stren...

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 an image region-of-interest division method and device and an image segmentation method and device. The image region-of-interest division method comprises the steps: obtainingthe signal intensity values of all pixels in a target image, and obtaining a signal intensity set; extracting a plurality of signal intensity values with continuous sizes in the signal intensity set to form a subset of the signal intensity set; extracting pixel points corresponding to a plurality of subsets of the signal intensity set to form a plurality of pixel point sets, wherein the pluralityof subsets are different subsets; performing connected region marking on pixel points in each pixel point set to obtain a plurality of connected pixel point sets; judging whether the connected pixel point sets are pixel point sets belonging to the same area or not according to the distances between the central points of the connected pixel point sets, and combining the connected pixel point sets belonging to the same area; and taking a region corresponding to the merged connected pixel point set as a region of interest of the target image. By implementing the image region-of-interest divisionmethod, the region of interest of the target image containing the segmentation object can be obtained.

Description

technical field [0001] The present invention relates to the technical field of image detection, in particular to a method for dividing an image region of interest, an image segmentation method and a device. Background technique [0002] The blood vessel segmentation problem in medical imaging is the basic premise of image analysis and diagnosis, and it is a necessary means for locating vascular lesion areas and qualitatively and quantitatively analyzing normal tissues and lesions. Borders and other plaque components have shown increasingly important clinical value in assisting doctors in clinical diagnosis, assessment of disease risk, and decision-making of treatment options. However, blood vessel segmentation from medical images is a very challenging task. [0003] In recent years, a variety of different methods have been proposed and used, which are mainly divided into two categories from the general direction: one is to introduce AI algorithms such as deep learning and m...

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): G06K9/32G06K9/34G06T7/187
CPCG06T7/187G06T2207/30101G06V10/25G06V10/267
Inventor张玲玲滕忠照沈金花
Owner南京景三医疗科技有限公司