阅读说明：本技术 一种医学影像处理方法及装置 (Medical image processing method and device ) 是由 倪浩 石磊 魏子昆 华铱炜 柏慧屏 于 2019-09-30 设计创作，主要内容包括：本发明实施例公开了一种医学影像处理方法及装置,确定每帧2D医学影像中的第一区域,根据多个第一区域确定第一轴,以第一轴与每帧2D医学影像的交点为起点生成多条射线,确定多条射线与每帧2D医学影像中的第一区域相交的多个像素点的像素点信息,并作为每帧2D医学影像的第一信息,将多帧2D医学影像的第一信息映射至第一坐标系,获得与多帧2D医学影像对应的医学影像。通过放射射线的方式确定每帧2D医学影像的第一信息,并将每帧2D医学影像的第一信息映射到第一坐标系,可以自动地将多帧2D医学影像映射为全景图,而无需人工主观地判断2D医学影像与全景图的对应关系,提高映射的效率和精度。(The embodiment of the invention discloses a medical image processing method and a medical image processing device, wherein a first area in each frame of 2D medical image is determined, a first axis is determined according to a plurality of first areas, a plurality of rays are generated by taking the intersection point of the first axis and each frame of 2D medical image as a starting point, pixel point information of a plurality of pixel points of the intersection of the rays and the first area in each frame of 2D medical image is determined and is used as first information of each frame of 2D medical image, the first information of a plurality of frames of 2D medical images is mapped to a first coordinate system, and medical images corresponding to the plurality of frames of 2D medical images are obtained. The first information of each frame of 2D medical image is determined in a ray radiation mode, and the first information of each frame of 2D medical image is mapped to the first coordinate system, so that the multi-frame 2D medical image can be automatically mapped into a panorama without manually and subjectively judging the corresponding relation between the 2D medical image and the panorama, and the mapping efficiency and precision are improved.)

1. A method of medical image processing, the method comprising:

acquiring a plurality of frames of 2D medical images;

for any frame of 2D medical image, acquiring a first region located in the frame of 2D medical image, wherein the first region at least comprises: vertebral and rib regions;

determining a first axis based on vertebra and rib keypoints in a plurality of the first regions, or determining a first axis based on centers or barycenters of a plurality of the first regions, the first axis being perpendicular to the plurality of frames of 2D medical images;

for any frame of 2D medical image, generating a plurality of rays by taking the intersection point of the first axis and the frame of 2D medical image as a starting point, wherein the plurality of rays are intersected with the first region in the frame of 2D medical image, and acquiring pixel point information of a plurality of pixel points for the plurality of intersected pixel points, wherein the pixel point information of any pixel point comprises: the direction information of the ray intersected with the pixel point, the distance information from the pixel point to the first axis and the mapping pixel value of the pixel point, wherein the mapping pixel value of the pixel point is related to the pixel value of the pixel point in the neighborhood of the pixel point; taking the pixel point information of the plurality of pixel points as first information of the frame of 2D medical image;

mapping the first information of the plurality of frames of 2D medical images to a first coordinate system to obtain the medical images corresponding to the plurality of frames of 2D medical images.

2. The method of claim 1, wherein said acquiring the first region located in the frame of 2D medical image comprises:

detecting vertebra key points and rib key points in the frame of 2D medical image, and connecting the vertebra key points and the rib key points to obtain the first region;

alternatively, points on the left and right lung edges are obtained to obtain edge points, which are connected to obtain the first region comprising the left and right lungs.

3. The method of claim 1, wherein determining a first axis based on vertebral and rib keypoints in the plurality of first regions comprises:

acquiring coordinates of vertebra key points and rib key points in a plurality of first regions;

calculating the average value of the coordinates of all vertebra key points and rib key points to obtain a first coordinate;

and taking an axis passing through the first coordinate and perpendicular to the plurality of frames of 2D medical images as the first axis.

4. The method of claim 1, wherein determining a first axis based on centers or centers of gravity of a plurality of the first regions comprises:

acquiring center coordinates or barycentric coordinates of a plurality of the first areas;

calculating an average value of all the center coordinates to obtain a second coordinate, or calculating an average value of all the center coordinates to obtain a third coordinate;

and taking an axis passing through the second coordinate and perpendicular to the multi-frame 2D medical images as the first axis, or taking an axis passing through the third coordinate and perpendicular to the multi-frame 2D medical images as the first axis.

5. The method of claim 1, wherein the mapped pixel value of the pixel point is obtained by:

and taking at least one pixel point near the pixel point in the ray direction of the pixel point, and obtaining the mapping pixel value of the pixel point based on the pixel value of the at least one pixel point and the pixel value of the pixel point.

6. The method according to any one of claims 1 to 5, wherein mapping the first information of the plurality of frames of 2D medical images to the first coordinate system to obtain the medical image corresponding to the plurality of frames of 2D medical images comprises:

for any pixel point, mapping the direction information of the ray intersected with the pixel point to a first coordinate axis, mapping the distance information of the pixel point to the first axis to a second coordinate axis, and taking the mapping pixel value of the pixel point as the pixel value of the pixel point in the first coordinate system; wherein the first coordinate axis and the second coordinate axis are perpendicular.

7. A medical image processing apparatus, characterized in that the apparatus comprises:

the acquiring module is used for acquiring multiple frames of 2D medical images, and for any frame of 2D medical image, acquiring a first region located in the frame of 2D medical image, wherein the first region at least comprises: vertebral and rib regions;

a determining module, configured to determine a first axis based on vertebral key points and rib key points in a plurality of the first regions, or determine a first axis based on centers or barycenters of a plurality of the first regions, the first axis being perpendicular to the plurality of frames of 2D medical images;

the processing module is used for generating a plurality of rays by taking the intersection point of the first axis and the frame of 2D medical image as a starting point for any frame of 2D medical image, the plurality of rays are intersected with the first area in the frame of 2D medical image, and pixel point information of a plurality of pixel points is acquired for the plurality of intersected pixel points, wherein the pixel point information of any pixel point comprises: the direction information of the ray intersected with the pixel point, the distance information from the pixel point to the first axis and the mapping pixel value of the pixel point, wherein the mapping pixel value of the pixel point is related to the pixel value of the pixel point in the neighborhood of the pixel point; taking the pixel point information of the plurality of pixel points as first information of the frame of 2D medical image;

the mapping module is used for mapping the first information of the multiple frames of 2D medical images to a first coordinate system so as to obtain the medical images corresponding to the multiple frames of 2D medical images.

8. The apparatus of claim 7, wherein the mapping module is specifically configured to:

for any pixel point, mapping the direction information of the ray intersected with the pixel point to a first coordinate axis, mapping the distance information of the pixel point to the first axis to a second coordinate axis, and taking the mapping pixel value of the pixel point as the pixel value of the pixel point in the first coordinate system; wherein the first coordinate axis and the second coordinate axis are perpendicular.

9. Medical image processing apparatus comprising at least one processor and at least one memory, wherein the memory unit stores a computer program which, when executed by the processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 6.

10. A computer-readable medium, in which a computer program executable by a medical image processing apparatus is stored, which program, when run on the medical image processing apparatus, causes the medical image processing apparatus to perform the steps of the method according to any one of claims 1 to 6.

Technical Field

The invention relates to the technical field of computers, in particular to a medical image processing method and device.

Background

With the development of modern medical Imaging technology, various medical Imaging apparatuses are emerging, such as an X-ray photographing apparatus, a Computed Tomography (CT) apparatus, a Nuclear Magnetic Resonance Imaging (NMRI) apparatus, and the like. These medical imaging devices can acquire cross-sectional images (also referred to as 2D images) of various parts of the human body, and can also generate 3D images of various parts of the human body.

At present, the cross-sectional image acquired by the medical imaging device usually cannot correspond to the panoramic image, and therefore, the tissue in the cross-sectional image needs to be determined manually and corresponds to the tissue in the panoramic image. Taking the acquired chest image as an example, the chest image includes vertebrae and ribs, and after a frame of cross-sectional image of the chest is acquired, a doctor can determine which vertebrae or which ribs in the frame of cross-sectional image correspond to which vertebrae or which ribs in the panoramic image according to experience, so as to determine a subsequent treatment scheme. However, in this way, due to different experiences of different doctors, the determined mapping accuracy of the cross-sectional image and the panoramic image is greatly influenced by artificial subjective factors, and it usually takes a long time to manually view the image, resulting in low work efficiency and diagnosis efficiency.

In summary, there is a need for a medical image processing method for solving the technical problems in the prior art that the mapping accuracy is greatly affected by artificial subjective factors and the efficiency is low due to the fact that a 2D medical image and a panorama are mapped by an artificial method.

Disclosure of Invention

The embodiment of the invention provides a medical image processing method and a medical image processing device, which are used for solving the technical problems that in the prior art, the mapping precision is greatly influenced by artificial subjective factors and the efficiency is low due to the fact that a 2D medical image and a panoramic image are mapped in an artificial mode.

In a first aspect, an embodiment of the present invention provides a medical image processing method, including:

acquiring a plurality of frames of 2D medical images, and acquiring a first region located in any frame of 2D medical image, wherein the first region at least comprises: a vertebra region and a rib region, a first axis is determined based on vertebra key points and rib key points in a plurality of first regions, or a first axis is determined based on centers or barycenters of a plurality of first regions, and the first axis is perpendicular to the plurality of frames of 2D medical images; further, for any frame of 2D medical image, generating a plurality of rays with the intersection point of the first axis and the frame of 2D medical image as a starting point, where the plurality of rays intersect with the first region in the frame of 2D medical image, and acquiring pixel point information of a plurality of pixel points for the plurality of intersecting pixel points, where the pixel point information of any pixel point includes: the direction information of the ray intersected with the pixel point, the distance information from the pixel point to the first axis and the mapping pixel value of the pixel point, wherein the mapping pixel value of the pixel point is related to the pixel value of the pixel point in the neighborhood of the pixel point; taking the pixel point information of the plurality of pixel points as first information of the frame of 2D medical image; in this way, the first information of the multiple frames of 2D medical images is mapped to the first coordinate system to obtain the medical images corresponding to the multiple frames of 2D medical images.

In the design, the first information of each frame of 2D medical image is determined in a ray radiation mode, and the first information of each frame of 2D medical image is mapped to the first coordinate system, so that a plurality of frames of 2D medical images can be automatically mapped into a panoramic image without manually and subjectively judging the corresponding relation between the 2D medical images and the panoramic image, and the mapping efficiency can be improved; in addition, the direction information of the ray on the 2D medical image, the distance information from the pixel point to the first axis and the mapping pixel value of the pixel point are used as the first information of the 2D medical image, so that the 2D medical image can be accurately mapped by synthesizing the comprehensive first information, and the accuracy of the panorama obtained by mapping can be improved.

In one possible design, the acquiring a first region located in the frame of 2D medical image includes: detecting vertebra key points and rib key points in the frame of 2D medical image, and connecting the vertebra key points and the rib key points to obtain the first region; alternatively, points on the left and right lung edges are obtained to obtain edge points, which are connected to obtain the first region comprising the left and right lungs.

In the design, each vertebra key point and each rib key point in each frame of 2D medical image are detected, the vertebra region and the rib region in the 2D medical image can be enclosed by connecting the vertebra key point and the rib key point to obtain a first region, when the vertebra key point and the rib key point are sufficient, the obtained first region is high in precision, a first axis is determined based on the first region, and then the mapping precision of the panoramic image of the rib and the vertebra obtained by mapping the multi-frame 2D image to a first coordinate system based on the first region and the first axis is improved; or, the left lung edge and the right lung edge are obtained by segmentation, and then the left lung edge point and the right lung edge point are connected to obtain a polygonal region surrounding the left lung edge and the right lung edge, so that the polygonal region can be directly used as a first region including a vertebra region and a rib region, and the first region is obtained in a fast and accurate manner.

In one possible design, the determining a first axis based on vertebral and rib keypoints in a plurality of the first regions comprises: obtaining coordinates of vertebra key points and rib key points in the first areas, calculating an average value of the coordinates of all the vertebra key points and rib key points to obtain a first coordinate, and taking an axis passing through the first coordinate and perpendicular to the multi-frame 2D medical images as the first axis.

In the design, after the vertebra key points and the rib key points on each frame of 2D medical image are detected, the average coordinates of the vertebra key points and the rib key points are used as first coordinates, and then the first axis perpendicular to the multiframe 2D medical images is determined based on the coordinates of the central point.

In one possible design, the determining a first axis based on centers or centers of gravity of a plurality of the first regions includes: acquiring center coordinates or barycentric coordinates of a plurality of first areas, and calculating an average value of all the center coordinates to acquire a second coordinate, or calculating an average value of all the barycentric coordinates to acquire a third coordinate; and taking an axis passing through the second coordinate and perpendicular to the multi-frame 2D medical images as the first axis, or taking an axis passing through the third coordinate and perpendicular to the multi-frame 2D medical images as the first axis.

In the design, by determining the center point or the gravity center point of the first region on each frame of 2D medical image, the coordinate of the center point can be averaged or the coordinate of the gravity center point can be averaged, so that the first axis of the multi-frame 2D medical image can be directly determined, the mode can synthesize the coordinate of the center point or the gravity center point of the first region in the multi-frame 2D medical image to obtain the first axis, and thus the mapping precision of mapping the multi-frame 2D medical image based on the first axis can be improved to a certain extent; in addition, the design does not need to use the coordinates of a plurality of pixel points in the first area in the multi-frame 2D medical images to obtain the first axis, so that the mapping efficiency of mapping the multi-frame 2D medical images can be higher.

In one possible design, the mapped pixel value of the pixel point is obtained by: and taking at least one pixel point near the pixel point in the ray direction of the pixel point, and obtaining the mapping pixel value of the pixel point based on the pixel value of the at least one pixel point and the pixel value of the pixel point.

In the design, the mapping pixel value of the pixel point is obtained by using the joint analysis of the pixel values of the plurality of pixel points which are positioned in the front-back direction of the pixel point in the ray direction, so that the mapping pixel value can comprehensively embody the pixel values of the peripheral pixel points, and the collected pixel values of the pixel points are corrected by using the pixel values of the peripheral pixel points, so that the error of pixel value display caused by sampling jitter during sampling of the pixel points can be reduced.

In one possible design, the mapping the first information of the multiple frames of 2D medical images to the first coordinate system to obtain the medical image corresponding to the multiple frames of 2D medical images includes: for any pixel point, mapping the direction information of the ray intersected with the pixel point to a first coordinate axis, mapping the distance information of the pixel point to the first axis to a second coordinate axis, and taking the mapping pixel value of the pixel point as the pixel value of the pixel point in the first coordinate system; wherein the first coordinate axis and the second coordinate axis are perpendicular.

In the design, the mapping pixel values of the intersected pixels are determined from each frame of 2D medical image in a ray radiation mode, the direction of the ray, the positions of the pixels and the mapping pixel values of the pixels are mapped to the panorama, the mapping relation between the multi-frame 2D medical image and the panorama can be automatically established, the multi-frame 2D medical image can be flexibly mapped to the panorama, manual subjective mapping is not needed, and therefore the mapping efficiency can be improved.

In a second aspect, an embodiment of the present invention provides a medical image processing apparatus, where the apparatus includes:

the acquiring module is used for acquiring multiple frames of 2D medical images, and for any frame of 2D medical image, acquiring a first region located in the frame of 2D medical image, wherein the first region at least comprises: vertebral and rib regions;

a determining module, configured to determine a first axis based on vertebral key points and rib key points in a plurality of the first regions, or determine a first axis based on centers or barycenters of a plurality of the first regions, the first axis being perpendicular to the plurality of frames of 2D medical images;

the processing module is used for generating a plurality of rays by taking the intersection point of the first axis and the frame of 2D medical image as a starting point for any frame of 2D medical image, the plurality of rays are intersected with the first area in the frame of 2D medical image, and pixel point information of a plurality of pixel points is acquired for the plurality of intersected pixel points, wherein the pixel point information of any pixel point comprises: the direction information of the ray intersected with the pixel point, the distance information from the pixel point to the first axis and the mapping pixel value of the pixel point, wherein the mapping pixel value of the pixel point is related to the pixel value of the pixel point in the neighborhood of the pixel point; taking the pixel point information of the plurality of pixel points as first information of the frame of 2D medical image;

the mapping module is used for mapping the first information of the multiple frames of 2D medical images to a first coordinate system so as to obtain the medical images corresponding to the multiple frames of 2D medical images.

In one possible design, the obtaining module is specifically configured to: detecting vertebra key points and rib key points in the frame of 2D medical image, and connecting the vertebra key points and the rib key points to obtain the first region; alternatively, points on the left and right lung edges are obtained to obtain edge points, which are connected to obtain the first region comprising the left and right lungs.

In one possible design, the determining module is specifically configured to: obtaining coordinates of vertebra key points and rib key points in the first areas, calculating an average value of the coordinates of all the vertebra key points and rib key points to obtain a first coordinate, and taking an axis passing through the first coordinate and perpendicular to the multi-frame 2D medical images as the first axis.

In one possible design, the determining module is specifically configured to: acquiring center coordinates or barycentric coordinates of a plurality of first areas, and calculating an average value of all the center coordinates to acquire a second coordinate, or calculating an average value of all the barycentric coordinates to acquire a third coordinate; and taking an axis passing through the second coordinate and perpendicular to the multi-frame 2D medical images as the first axis, or taking an axis passing through the third coordinate and perpendicular to the multi-frame 2D medical images as the first axis.

In one possible design, the processing module obtains the mapped pixel value of the pixel point by: and taking at least one pixel point near the pixel point in the ray direction of the pixel point, and obtaining the mapping pixel value of the pixel point based on the pixel value of the at least one pixel point and the pixel value of the pixel point.

In one possible design, the mapping module is specifically configured to: for any pixel point, mapping the direction information of the ray intersected with the pixel point to a first coordinate axis, mapping the distance information of the pixel point to the first axis to a second coordinate axis, and taking the mapping pixel value of the pixel point as the pixel value of the pixel point in the first coordinate system; wherein the first coordinate axis and the second coordinate axis are perpendicular.

In a third aspect, an embodiment of the present invention provides a medical image processing apparatus, which includes at least one processor and at least one memory, where the storage unit stores a computer program, and when the program is executed by the processor, the program causes the processor to execute the steps of the medical image processing method according to any of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable medium, which stores a computer program executable by a medical image processing apparatus, and when the program runs on the medical image processing apparatus, the program causes the medical image processing apparatus to execute the steps of the medical image processing method according to any one of the first aspect.

These and other aspects of the invention are apparent from and will be elucidated with reference to the embodiments described hereinafter.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a flowchart illustrating a medical image processing method according to an embodiment of the present invention;

fig. 2 is a schematic cross-sectional view of a chest image according to an embodiment of the present invention;

fig. 3 is a schematic interface diagram for processing a plurality of frames of 2D medical images into a panorama according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a medical image processing apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a medical image processing apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The medical image processing method in the embodiment of the present invention may map multi-frame 2D medical images, for example, may map a multi-frame cross-sectional image of a chest taken by a CT device into an image including complete vertebrae and ribs (i.e., a panoramic image), and may mark a corresponding relationship with the multi-frame 2D medical images in the mapped panoramic image. It should be noted that, the embodiment of the present invention only describes the medical image processing method by taking vertebrae and ribs as examples, but does not limit the present solution; in specific implementations, the method in the embodiment of the present invention may map any type of 2D medical image, such as, but not limited to, a 2D medical image of a hand bone, a 2D medical image of a sternum, a 2D medical image of a leg bone, and the like.

Fig. 1 is a schematic flow chart of a medical image processing method according to an embodiment of the present invention, where the method includes:

step 101, acquiring a plurality of frames of 2D medical images.

In an embodiment of the present invention, the 2D medical image may be a multi-frame cross-sectional image of a chest captured by a CT apparatus, where the chest image includes vertebrae and ribs, or may also be a multi-frame cross-sectional image of a chest captured by a magnetic resonance apparatus, where the chest includes vertebrae and ribs, and is not limited in particular.

Fig. 2 is a schematic cross-sectional view of a chest image according to an embodiment of the present invention.

It is understood that the 2D medical image in the embodiment of the present invention may be of other types, such as a 2D sagittal image, a 2D coronal image, and the like, and is not limited in particular.

Step 102, for any frame of 2D medical image, acquiring a first region located in the frame of 2D medical image, wherein the first region at least includes: vertebral regions and rib regions.