CN-121999004-A - Vessel segmentation method, computing device, computer storage medium and computer program product

CN121999004ACN 121999004 ACN121999004 ACN 121999004ACN-121999004-A

Abstract

The embodiment of the application provides a blood vessel segmentation method, a computing device, a computer storage medium and a computer program product. The blood vessel segmentation method comprises the steps of obtaining original medical image data containing blood vessels, carrying out feature extraction on the original medical image data to generate image feature data, modifying pixel intensity values of pixels in the original medical image data based on the image feature data to obtain first medical image data, carrying out edge detection on the first medical image data to obtain edge information of the blood vessels to generate second medical image data containing blood vessel boundary masks, and carrying out blood vessel segmentation on the second medical image data based on the blood vessel boundary masks to obtain target blood vessel images. The technical scheme provided by the embodiment of the application can improve the accuracy of blood vessel segmentation.

Inventors

WANG HAO
WANG JIXIANG
WANG ZHENCHANG
BAI XIAOYAN
SONG LIJUN
YANG WENBO
REN PENGLING
LIU YAWEN

Assignees

首都医科大学附属北京友谊医院

Dates

Publication Date: 20260508
Application Date: 20241107

Claims (14)

1. A method of vessel segmentation, comprising: Acquiring raw medical image data comprising blood vessels; extracting features of the original medical image data to generate image feature data; Modifying pixel intensity values of pixels in the original medical image data based on the image feature data to obtain first medical image data; Performing edge detection on the first medical image data to acquire edge information of the blood vessel, and generating second medical image data containing a blood vessel boundary mask; And performing blood vessel segmentation on the second medical image data based on the blood vessel boundary mask to obtain a target blood vessel image.
2. The method of claim 1, wherein modifying pixel intensity values of pixels in the raw medical image data based on the image feature data to obtain first medical image data comprises: Preprocessing the original medical image data based on the image characteristic data to generate third medical image data; generating a pixel intensity threshold based on the image feature data and a priori knowledge of the blood vessel; and adjusting the pixel intensity of the pixels in the third medical image data based on the relation between the pixel intensity value of each pixel in the third medical image data and the intensity threshold value, so as to generate first medical image data.
3. The method of claim 2, wherein preprocessing the raw medical image data based on the image feature data to generate third medical image data comprises: normalizing the original medical image data based on the image feature data to generate fourth medical image data; and performing gradient filtering processing on the third medical image data based on the image characteristic data to generate the third medical image data.
4. A method according to claim 3, wherein normalizing the raw medical image data based on the image feature data to generate fourth medical image data comprises: Determining a normalized adjustment range based on the image feature data; And carrying out normalization processing on the original medical image data based on the normalization adjustment range to obtain fourth medical image data.
5. The method of claim 4, wherein the gradient filtering the third medical image data to generate the third medical image data comprises: Determining a plurality of filter windows; Performing gradient filtering processing on the third medical image data by using the plurality of filtering windows respectively to obtain a plurality of gradient filtering image data; and fusing the plurality of gradient filtered image data to generate the third medical image data.
6. The method of claim 5, wherein the image feature data comprises blood vessel feature data; the fusing the plurality of gradient filtered image data, generating the third medical image data comprising: Determining fusion weights of the plurality of gradient filtered images based on the vessel feature data; And fusing the plurality of gradient filtered image data based on the fusion weights to generate the third medical image data.
7. The method of claim 1, wherein edge detecting the first medical image data to obtain edge information of the blood vessel, the second medical image data including a vessel boundary mask comprises: inputting the first medical image data into a first edge detection algorithm to generate edge image data containing initial edge information; and inputting the edge image data into a second edge detection algorithm, so that the second edge detection algorithm performs edge detection on the edge image data based on the first edge information, and outputting second medical image data containing a vascular boundary mask.
8. The method of claim 7, wherein the vessel segmentation of the second medical image data based on the vessel boundary mask to obtain a target vessel image comprises: denoising the second medical image data based on the vascular boundary mask to obtain fifth medical image data; Determining a blood vessel region and a background region in the fifth medical image data; and removing the background area to obtain the target blood vessel image.
9. The method of claim 8, wherein denoising the second medical image data based on the vessel boundary mask to obtain fifth medical image data comprises: acquiring a first structural feature of the vascular boundary mask and a second structural feature of a blood vessel; Determining an expansion parameter based on the first structural feature and the second structural feature; And performing expansion operation on the second medical image based on the expansion parameter to obtain the fifth medical image.
10. The method of claim 1, wherein the acquiring raw medical image data comprising blood vessels comprises: receiving a blood vessel segmentation instruction; In response to the vessel segmentation instruction, acquiring a DICOM image from a target address indicated by the vessel segmentation instruction; Screening the DICOM images to obtain a plurality of layers; and carrying out stack construction on the plurality of layers to obtain the original medical image data.
11. The method of claim 9, wherein performing a dilation operation on the second medical image based on the dilation parameter, resulting in the fifth medical image comprises: performing an expansion operation on the second medical image based on the expansion parameter to obtain the sixth medical image; Traversing each pixel point of the sixth medical image and determining adjacent pixel points of each pixel point; For any pixel point, creating a connecting line of the pixel point and an adjacent pixel point meeting a preset condition; Determining a plurality of pixel points which are communicated with each other as the same area; And screening the multiple areas of the sixth medical image based on a preset threshold value to obtain the fifth medical image.
12. A computing device comprising a processing component and a storage component; The storage component stores one or more computer instructions for execution by the processing component to implement the vessel segmentation method of any one of claims 1-11.
13. A computer storage medium, characterized in that a computer program is stored, which, when being executed by a computer, implements the vessel segmentation method according to any one of claims 1 to 11.
14. A computer program product, characterized in that the computer program product comprises computer program code which, when executed by a computer, implements the vessel segmentation method according to any one of claims 1 to 11.

Description

Vessel segmentation method, computing device, computer storage medium and computer program product Technical Field Embodiments of the present invention relate to the field of medical image processing technology, and in particular, to a blood vessel segmentation method, a computing device, a computer storage medium, and a computer program product. Background The state of the cerebral interstitial blood vessels is inseparably closely related to the occurrence and development of brain diseases. In the pathological processes of many brain diseases (such as cerebrovascular diseases, brain tumors, etc.), the morphology, structure and function of blood vessels are significantly changed. The brain interstitial blood vessel is accurately segmented, so that clear and detailed blood vessel image information can be provided for doctors, and the doctors can know the illness state more deeply. Therefore, how to provide a high-precision blood vessel segmentation method is a technical problem to be solved. Disclosure of Invention The embodiment of the invention provides a blood vessel segmentation method, a computing device, a computer storage medium and a computer program product. In a first aspect, an embodiment of the present invention provides a blood vessel segmentation method, including: Acquiring raw medical image data comprising blood vessels; extracting features of the original medical image data to generate image feature data; Modifying pixel intensity values of pixels in the original medical image data based on the image feature data to obtain first medical image data; Performing edge detection on the first medical image data to acquire edge information of the blood vessel, and generating second medical image data containing a blood vessel boundary mask; And performing blood vessel segmentation on the second medical image data based on the blood vessel boundary mask to obtain a target blood vessel image. In a second aspect, an embodiment of the present invention provides a vascular segmentation device, including: a first acquisition module for acquiring raw medical image data containing blood vessels; the feature extraction module is used for carrying out feature extraction on the original medical image data to generate image feature data; The pixel modification module is used for modifying pixel intensity values of pixels in the original medical image data based on the image characteristic data to obtain first medical image data; The edge detection module is used for carrying out edge detection on the first medical image data so as to acquire the edge information of the blood vessel and generate second medical image data containing a blood vessel boundary mask; and the blood vessel segmentation module is used for carrying out blood vessel segmentation on the second medical image data based on the blood vessel boundary mask to obtain a target blood vessel image. In a third aspect, embodiments of the present invention provide a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions, and the one or more computer instructions are used for being called by the processing component to be executed so as to realize the blood vessel segmentation method provided by the embodiment of the application. In a fourth aspect, in an embodiment of the present application, there is provided a computer storage medium storing a computer program, where the computer program when executed by a computer implements a blood vessel segmentation method provided in the embodiment of the present application. In a fifth aspect, in an embodiment of the present application, there is provided a computer program product, where the computer program product includes computer program code, and when the computer program code is executed by a computer, the method for segmenting blood vessels provided in the embodiment of the present application is implemented. In the embodiment of the application, the pixel intensity of the original image data is adjusted based on the image characteristic data, so that the blood vessel characteristic can be enhanced in the image, the non-blood vessel characteristic can be restrained, the contrast between the blood vessel and surrounding tissues can be improved, and the edge of the blood vessel can be more clearly distinguished. These and other aspects of the invention will be more readily apparent from the following description of the embodiments. Drawings In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art. FIG. 1 shows a