CN111862312B - Brain blood vessel display device and method - Google Patents
Brain blood vessel display device and method Download PDFInfo
- Publication number
- CN111862312B CN111862312B CN202010698900.3A CN202010698900A CN111862312B CN 111862312 B CN111862312 B CN 111862312B CN 202010698900 A CN202010698900 A CN 202010698900A CN 111862312 B CN111862312 B CN 111862312B
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- image
- brain
- interest
- vessel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 261
- 210000004556 brain Anatomy 0.000 title claims abstract description 155
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000002490 cerebral effect Effects 0.000 claims abstract description 130
- 238000003709 image segmentation Methods 0.000 claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 16
- 210000004004 carotid artery internal Anatomy 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 210000002385 vertebral artery Anatomy 0.000 claims description 5
- 210000001841 basilar artery Anatomy 0.000 claims description 4
- 230000002146 bilateral effect Effects 0.000 claims description 4
- 210000001168 carotid artery common Anatomy 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 241001270131 Agaricus moelleri Species 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 10
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 230000009466 transformation Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 230000003902 lesion Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002792 vascular Effects 0.000 description 4
- 206010002329 Aneurysm Diseases 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 201000008450 Intracranial aneurysm Diseases 0.000 description 2
- 208000032851 Subarachnoid Hemorrhage Diseases 0.000 description 2
- 208000026106 cerebrovascular disease Diseases 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 208000034710 Cerebral arteriovenous malformation Diseases 0.000 description 1
- 206010053942 Cerebral haematoma Diseases 0.000 description 1
- 206010008111 Cerebral haemorrhage Diseases 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 208000002263 Intracranial Arteriovenous Malformations Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 201000000034 arteriovenous malformations of the brain Diseases 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 210000000133 brain stem Anatomy 0.000 description 1
- 210000001715 carotid artery Anatomy 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 210000001638 cerebellum Anatomy 0.000 description 1
- 210000001627 cerebral artery Anatomy 0.000 description 1
- 206010008118 cerebral infarction Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007917 intracranial administration Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000002285 radioactive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/06—Topological mapping of higher dimensional structures onto lower dimensional surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention provides a cerebral blood vessel display device and a method. The cerebral blood vessel display device includes: the brain image acquisition module is used for acquiring a brain image; the brain image segmentation module is used for segmenting the brain image to obtain a brain parenchyma image; the brain blood vessel acquisition module is used for acquiring brain blood vessels according to the brain parenchyma image; the interested blood vessel acquisition module is used for selecting an interested blood vessel from cerebral blood vessels according to the received blood vessel selection instruction; the three-dimensional image acquisition module is used for carrying out three-dimensional reconstruction on the interested blood vessel so as to obtain a three-dimensional image of the interested blood vessel; the projection image acquisition module is used for acquiring a plane projection image of the interested blood vessel; a display module for displaying the cerebral vessel, the vessel of interest, a three-dimensional image of the vessel of interest and/or a planar projection image of the vessel of interest. The cerebral blood vessel display device can independently display interested blood vessels, and is favorable for improving the diagnosis efficiency.
Description
Technical Field
The present invention relates to a brain image processing method, and more particularly, to a brain blood vessel display device and method.
Background
Common cerebrovascular diseases include cerebral apoplexy (cerebral infarction, cerebral hemorrhage, subarachnoid hemorrhage), vascular wall abnormality (intracranial aneurysm), vascular network abnormality (intracranial arteriovenous malformation, smog disease), etc. Taking an intracranial aneurysm as an example, the aneurysm generates cystic bulging due to intracranial local vascular wall abnormality, which is also one of the most common causes of spontaneous subarachnoid hemorrhage, and the risk of rupture again is as high as 40-65%, with a higher mortality rate. For patients with aneurysms, particularly those with intracerebral hematomas after highly suspected aneurysm rupture, it is desirable to minimize the time for diagnosis and evaluation, strive for surgical time, reduce mortality, and improve patient prognosis.
Magnetic Resonance Imaging (MRI) is one type of tomographic Imaging that uses the Magnetic Resonance phenomenon to acquire electromagnetic signals from a human body and reconstruct human body information. In recent years, magnetic resonance imaging has been widely used for examination of cerebral blood vessels. There are a large number of blood vessels in the human brain and in the clinic, medical personnel often need to focus only on one or more cerebral blood vessels of interest in order to achieve rapid diagnosis and assessment. However, in practical applications, the inventor finds that the existing solutions generally employ manual or AI methods to segment all brain blood vessels from the MRI images of the brain of the patient, which cannot individually display one or more brain blood vessels of interest to meet the needs of medical staff.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention aims to provide a cerebral blood vessel display device and method for solving the problem of the prior art that one or more blood vessels of interest cannot be displayed individually.
To achieve the above and other related objects, a first aspect of the present invention provides a cerebral blood vessel display device; the cerebral blood vessel display device includes: the brain image acquisition module is used for acquiring a brain image; wherein the brain image is a magnetic resonance image; the brain image segmentation module is connected with the brain image acquisition module and used for segmenting the brain image to acquire a brain parenchyma image; the brain blood vessel acquisition module is connected with the brain image segmentation module and used for acquiring brain blood vessels according to the brain parenchyma image and displaying the brain blood vessels by using the display module so as to assist medical staff to input a blood vessel selection instruction; the interested blood vessel acquisition module is connected with the cerebral blood vessel acquisition module and used for selecting an interested blood vessel from the cerebral blood vessels according to the received blood vessel selection instruction; the three-dimensional image acquisition module is connected with the interested blood vessel acquisition module and is used for carrying out three-dimensional reconstruction on the interested blood vessel so as to obtain a three-dimensional image of the interested blood vessel; the projection image acquisition module is connected with the interested blood vessel acquisition module and is used for acquiring a plane projection image of the interested blood vessel; and the display module is connected with the cerebral blood vessel acquisition module, the blood vessel of interest acquisition module, the three-dimensional image acquisition module and the projection image acquisition module and is used for displaying the cerebral blood vessel, the blood vessel of interest, the three-dimensional image of the blood vessel of interest and/or the plane projection image of the blood vessel of interest.
In an embodiment of the first aspect, the cerebral blood vessel display device further includes: and the image preprocessing module is connected with the brain image segmentation module and the brain blood vessel acquisition module and is used for preprocessing the brain parenchymal image.
In an embodiment of the first aspect, the image preprocessing module includes: the image registration unit is connected with the brain image segmentation module and is used for registering the brain parenchyma image; and/or the image reconstruction unit is connected with the brain image segmentation module and is used for reconstructing the brain parenchyma image so as to improve the resolution of the brain parenchyma image.
In one embodiment of the first aspect, the cerebral blood vessel comprises a bilateral common carotid artery, an internal carotid artery, a vertebral artery, and/or a basilar artery.
In an embodiment of the first aspect, the projection image obtaining module uses projection light to project the blood vessel of interest along a projection angle, and obtains a planar projection image of the blood vessel of interest according to a gray-scale value of a voxel point on a projection path.
In an embodiment of the first aspect, the projection angle includes a front-back position, a rear-front position, a left-front oblique position, a right-front oblique position, and/or a left-side position.
In an embodiment of the first aspect, the display module is further configured to display a projection angle selection menu for assisting medical staff in inputting a projection angle.
In an embodiment of the first aspect, the display module is further configured to display a blood vessel adjustment tool to assist medical staff in inputting a blood vessel adjustment instruction; and the interested blood vessel acquisition module adjusts the interested blood vessel according to the received blood vessel adjustment instruction.
In an embodiment of the first aspect, the blood vessel of interest acquiring module is further configured to acquire an abnormal region in the blood vessel of interest, and display the abnormal region by using the display module.
A second aspect of the present invention provides a cerebral blood vessel display method; the cerebral blood vessel display method comprises the following steps: acquiring a brain image; wherein the brain image is a magnetic resonance image; segmenting the brain image to obtain a brain parenchymal image; acquiring and displaying cerebral vessels according to the brain parenchymal image so as to assist medical staff to input a vessel selection instruction; selecting an interested blood vessel from the cerebral blood vessels according to the received blood vessel selection instruction; performing three-dimensional reconstruction on the blood vessel of interest to obtain a three-dimensional image of the blood vessel of interest; acquiring a planar projection image of the vessel of interest; displaying the cerebral vessel, the vessel of interest, a three-dimensional image of the vessel of interest, and/or a planar projection image of the vessel of interest.
As described above, one embodiment of the cerebral blood vessel display device and method according to the present invention has the following advantageous effects:
the cerebral blood vessel display device is used for obtaining a brain parenchyma image by segmenting the brain image and obtaining cerebral blood vessels according to the brain parenchyma image; based on this, the user can select the interested vessel from the brain vessels by inputting the vessel selecting instruction. The cerebral vessel display device is capable of displaying the vessel of interest, a three-dimensional image and/or a planar projection image of the vessel of interest using the display module. Therefore, the cerebral blood vessel display device can realize the independent display of the interested blood vessel, and is beneficial to medical staff to quickly observe the interested blood vessel, thereby improving the diagnosis efficiency.
Drawings
Fig. 1 is a schematic structural diagram of a cerebral blood vessel display device according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating the registration of images by the cerebral blood vessel displaying device according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a planar projection image acquired by the cerebral blood vessel display device according to an embodiment of the present invention.
Fig. 4 is a flowchart illustrating an abnormal region acquisition process of the cerebral blood vessel displaying device according to an embodiment of the present invention.
Fig. 5 is a flowchart illustrating a cerebral blood vessel displaying method according to an embodiment of the present invention.
Description of the element reference numerals
1 cerebral blood vessel display device
11 brain image acquisition module
12 brain image segmentation module
13 brain blood vessel acquisition module
14 interesting blood vessel acquisition module
15 three-dimensional image acquisition module
16 projection image acquisition module
17 display module
3 blood vessels of interest
31 image
311 voxel points
32 images
321 voxel points
33 images
331 voxel point
4 plane projection image
41 pixel point
S21-S27
S41-S42
S51-S57
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
There are a large number of blood vessels in the human brain and in the clinic, medical personnel often need to focus only on one or more cerebral blood vessels of interest in order to achieve rapid diagnosis and assessment. However, in practical applications, the inventor finds that the existing solutions generally employ manual or AI methods to segment all brain blood vessels from the MRI images of the brain of the patient, which cannot individually display one or more brain blood vessels of interest to meet the needs of medical staff.
In order to solve the problem, the invention provides a cerebral blood vessel display device. The cerebral blood vessel display device is used for obtaining a brain parenchyma image by segmenting the brain image and obtaining cerebral blood vessels according to the brain parenchyma image; based on this, the user can select the interested vessel from the brain vessels by inputting the vessel selecting instruction. The cerebral vessel display device is capable of displaying the vessel of interest, a three-dimensional image and/or a planar projection image of the vessel of interest using the display module. Therefore, the cerebral blood vessel display device can realize the independent display of the interested blood vessel, and is beneficial to medical staff to quickly observe the interested blood vessel, thereby improving the diagnosis efficiency.
Referring to fig. 1, in an embodiment of the present invention, the cerebral blood vessel display device 1 includes:
a brain image acquisition module 11, configured to acquire a brain image; wherein the brain image is a magnetic resonance image and the brain image comprises a plurality of two-dimensional slices. The brain image can be obtained by imaging the brain of the patient by using a magnetic resonance instrument, and compared with the brain CT, the brain magnetic resonance instrument has the advantages of no radioactive ray damage, no bone artifact, no need of using a contrast agent to display the vascular structure and the like.
And a brain image segmentation module 12 connected to the brain image acquisition module 11, configured to segment the brain image to acquire a brain parenchyma image. The brain parenchyma refers to a parenchyma part of a central nervous system composed of a brain, a cerebellum and a brain stem, and the brain parenchyma image also comprises a plurality of two-dimensional slices similarly to the brain image. In a specific application, a manual segmentation, a semi-automatic segmentation or a fully-automatic segmentation scheme may be adopted to segment the brain image to obtain the brain parenchymal image. For example, the segmentation of the brain image may be realized by using a deep learning network model such as Unet and Vnet, or the brain parenchymal image may be acquired by using a thresholding method. When the brain parenchyma image is obtained by adopting a threshold method, a gray value range of a brain parenchyma part needs to be obtained, and all voxel points outside the gray value range are deleted from the brain image, so that the brain parenchyma image can be obtained.
A cerebral blood vessel obtaining module 13 connected to the cerebral image segmentation module 12, for obtaining cerebral blood vessels according to the brain parenchyma image, and displaying the cerebral blood vessels by using a display module to assist medical staff in inputting a blood vessel selection instruction; wherein, the cerebral blood vessel mainly refers to cerebral artery blood vessel.
In this embodiment, any method capable of distinguishing the cerebral blood vessels from other tissues, organs, and background regions in the brain image can be used in this embodiment to achieve the acquisition of the cerebral blood vessels. Specifically, the cerebral blood vessels can be labeled in the cerebral image by a blood vessel labeling method to achieve the acquisition of the cerebral blood vessels, and the cerebral blood vessels acquired in this way are the labeling results of the cerebral blood vessels. The mask of the cerebral blood vessels can also be obtained according to the brain image so as to realize the acquisition of the cerebral blood vessels, and the cerebral blood vessels acquired in this way are the mask of the cerebral blood vessels. The cerebral blood vessels can be segmented from the cerebral image by an image segmentation method to acquire the cerebral blood vessels, the cerebral blood vessels acquired in this way are multilayer slices of the cerebral blood vessels, and each layer of the multilayer slices only comprises the cerebral blood vessels. It should be noted that the above three schemes are merely examples of the method for acquiring the cerebral vessels, and the method for acquiring the cerebral vessels may be implemented according to specific requirements in practical applications, and the specific implementation method is not limited herein.
In addition, in the embodiment, the display module is used for displaying the cerebral vessels, and medical staff can determine the vessels of interest by observing the cerebral vessels, so that the blood vessel selection instructions corresponding to the vessels of interest can be input. Therefore, the display of the cerebral vessels by the display module can assist medical staff in inputting vessel selection instructions.
And the interested blood vessel acquiring module 14 is connected with the cerebral blood vessel acquiring module 13 and is used for selecting the interested blood vessel from the cerebral blood vessel according to the received blood vessel selecting instruction. Similar to the cerebral blood vessel acquiring module 13, the blood vessel of interest acquired by the blood vessel of interest acquiring module 14 may be a labeling result of the blood vessel of interest, a mask of the blood vessel of interest, or a multi-layer slice of the blood vessel of interest, where each layer slice only includes the blood vessel of interest.
A three-dimensional image obtaining module 15, connected to the blood vessel of interest obtaining module 14, for performing three-dimensional reconstruction on the blood vessel of interest to obtain a three-dimensional image of the blood vessel of interest. For example, the three-dimensional image obtaining module 15 may respectively calculate the percentages of various substances contained in each voxel point in the blood vessel of interest and display the calculated percentages in different gray scales, so as to obtain a three-dimensional image of the blood vessel of interest; in addition, the three-dimensional image obtaining module 15 may also adjust the contrast between tissues according to actual requirements, so as to improve the display effect of the three-dimensional image.
A projection image acquisition module 16 connected to the vessel of interest acquisition module 14 for acquiring a planar projection image of the vessel of interest; wherein the planar projection image is one or more two-dimensional images. In particular, the projection image acquisition module 16 may project the vessel of interest along one or more projection angles using projection light to obtain the planar projection image.
A display module 17, connected to the cerebral blood vessel acquiring module 13, the blood vessel of interest acquiring module 14, the three-dimensional image acquiring module 15 and/or the projection image acquiring module 16, for displaying the cerebral blood vessel, the blood vessel of interest, the three-dimensional image of the blood vessel of interest and/or the planar projection image of the blood vessel of interest. Wherein the display of the cerebral vessels can assist medical personnel in inputting the vessel selection instruction.
As can be seen from the above description, the cerebral blood vessel display device of the present embodiment obtains a brain parenchyma image by segmenting the brain image, and obtains cerebral blood vessels according to the brain parenchyma image; based on this, the user can select the interested vessel from the brain vessels by inputting the vessel selecting instruction. The cerebral vessel display device is capable of displaying the vessel of interest, a three-dimensional image and/or a planar projection image of the vessel of interest using the display module. Therefore, the cerebral blood vessel display device can realize the independent display of the interested blood vessel, and is beneficial to medical staff to quickly observe the interested blood vessel, thereby improving the diagnosis efficiency.
In an embodiment of the invention, the cerebral blood vessel display device further includes an image preprocessing module. The image preprocessing module is connected with the brain image segmentation module and the brain blood vessel acquisition module, namely: the cerebral blood vessel acquisition module is connected with the cerebral image segmentation module through the image preprocessing module. The image preprocessing module is used for preprocessing the brain parenchymal image. The preprocessing refers to processing the image features of the brain parenchyma image to improve the display effect of the brain blood vessel display device, and includes, for example, registration, reconstruction, noise reduction, contrast adjustment, and the like.
In an embodiment of the present invention, it is considered that the patient may have breathing, moving, etc. movements during MRI imaging, which may cause misalignment between different slices in the brain parenchyma image. To address this problem, the image preprocessing module may comprise an image registration unit, wherein the image registration unit is connected to the brain image segmentation module for registering the brain parenchyma image. Referring to fig. 2, an implementation method of the image registration unit registering the brain parenchyma image includes:
s21, a reference image is selected from the slice of the brain parenchyma image. For example, a slice that is least affected by motion may be selected as the reference image. At this time, all slices except the reference image are to-be-registered images.
S22, acquiring the characteristic points of the image to be registered; the characteristic points refer to points with drastically changed gray values in the image to be registered or points with larger curvature on the edge of the image; in addition, for the convenience of algorithm implementation, a point of a central point or an edge of the image to be registered may also be selected as the feature point.
S23, aligning the feature points of the image to be registered with the feature points of the reference image, and carrying out affine transformation on the image to be registered so that the image to be registered and the reference image have the same or similar image size and resolution; wherein the affine transformation is for example translated, scaled and/or rotated.
And S24, segmenting the image to be registered to obtain a mask of the brain parenchyma.
S25, performing a B-spline geometric transformation on the mask of the brain parenchyma to achieve a first elastic registration.
S26, segmenting the image to be registered after the first elastic registration to obtain a blood vessel region in the brain parenchyma.
S27, B-spline geometric transformation is performed on the vessel region in the brain parenchyma to achieve a second elastic registration. Preferably, step S27 employs a B-spline geometric transformation that is finer than step S625.
The registration of the reference image and the image to be registered can be realized through the steps of S21 to S27, and further, the registration of all slices in the brain parenchymal image can be realized. The steps S21 to S22 are used for implementing rigid registration of the reference image and the image to be registered, and the steps S23 to S27 are used for implementing elastic registration of the reference image and the image to be registered; in a specific application, other rigid registration methods and/or elastic registration schemes may also be adopted to realize registration of the reference image and the image to be registered. In addition, the B-spline geometric transformation described in steps S25 and S27 can be implemented by using an existing scheme, which is not described herein.
In this embodiment, the image registration unit can realize registration of different slices in the brain parenchymal image, so as to reduce an image of a brain blood vessel display result caused by movement of a patient in an MRI imaging process.
In an embodiment of the invention, in consideration of a relatively low resolution of the MRI image, the image preprocessing module further includes an image reconstruction unit. The image reconstruction unit is connected with the brain image segmentation module and used for reconstructing the brain parenchyma image so as to improve the resolution of the brain parenchyma image. Preferably, the image reconstruction unit is connected to the brain image segmentation unit through the image registration unit, and in this case, the image reconstruction is performed on the brain parenchyma image after registration, so that the reconstruction effect is better. In this embodiment, the image reconstruction unit may be implemented by using an existing reconstruction scheme, for example, an optimal reconstruction based on an inverse problem or a reconstruction method based on deep learning, which is not described herein again.
In an embodiment of the present invention, in consideration that the MRI image may be affected by the detected object and the circuit element during the imaging process to generate thermal noise and/or physiological noise, the image preprocessing module in this embodiment further includes an image denoising unit; wherein the image denoising unit is used for removing noise of the brain parenchyma image. For example, the image denoising unit may set the gray value of each voxel point in the brain parenchymal image as a median of the gray values of all voxel points in the neighborhood window of the voxel point, so that the gray value of each voxel point in the brain parenchymal image is closer to a true value, and further, the elimination of an isolated noise point is realized.
In this embodiment, the image denoising unit is used to perform denoising processing on the brain parenchyma image, so that the influence of noise on the brain parenchyma image can be eliminated, and the display effect of the cerebral blood vessels can be improved.
In an embodiment of the present invention, in consideration of the difference between the gray scale and the contrast in different slices of the brain parenchymal image, in order to eliminate the difference, the image preprocessing module in this embodiment further includes a contrast adjustment unit; the contrast adjusting unit is used for adjusting the contrast of the slices in the brain parenchymal image so as to improve the display effect. Specifically, the contrast adjusting unit selects one slice from the brain parenchyma image as a reference image, and adjusts the contrast of other slices to be the same as or similar to the reference image, so as to reduce the influence caused by the gray scale and contrast difference between different slices.
In one embodiment of the present invention, the cerebral blood vessel includes bilateral common carotid artery, internal carotid artery, vertebral artery and/or basilar artery. In order to acquire the cerebral blood vessels, in this embodiment, the cerebral blood vessel acquiring module includes an image segmentation unit and a blood vessel extracting unit, where the image segmentation unit is connected to the cerebral image segmentation unit and is configured to segment the brain parenchyma image to acquire an image of an internal carotid artery system and/or a vertebrobasilar artery system. The image segmentation unit may implement segmentation of the brain parenchyma image by using deep learning models such as Unet and Vnet, and specific modes are not described herein again. The blood vessel extraction unit is used for extracting the bilateral carotid artery and/or the internal carotid artery from the internal carotid artery system and/or extracting the vertebral artery and/or the basilar artery from the basilar vertebral artery system.
In an embodiment of the present invention, the projection image obtaining module 16 utilizes projection light to project the blood vessel of interest along a projection angle, and obtains a planar projection image of the blood vessel of interest according to a gray-level value of a voxel point on a projection path. Referring to fig. 3, the images 31, 32 and 33 are three slices of the blood vessel of interest respectively. The projection image obtaining module 16 may project the blood vessel of interest 3 along a specific angle by using a hypothetical projection light, where the maximum gray value of all voxel points that the projection light passes through is the gray value of the corresponding point on the plane projection image, for example, a projection light passes through the voxel point 311, the voxel point 321, and the voxel point 331 respectively and is projected as a pixel point 41, and at this time, the gray value of the pixel point 41 is the maximum gray value of the three voxel points. It can further be seen that by projecting the blood vessel of interest 3 along the same angle with a large number of projection rays, a planar projection image 4 of this angle is obtained.
Preferably, the planar projection image of the vessel of interest is at the same spatial location as the three-dimensional image of the vessel of interest.
In an embodiment of the present invention, the projection angle includes a front-back position, a back-front position, a left-front oblique position, a right-front oblique position, and/or a left-side position, that is: the projection image acquisition module 16 projects the blood vessel of interest from the anterior-posterior position, the posterior-anterior position, the left-anterior oblique position, the right-anterior oblique position, and/or the left position to obtain a planar projection image of the blood vessel of interest. Wherein, the front and back position, the back front position, the left front oblique position, the right front oblique position and the left side position respectively correspond to a projection angle. In this embodiment, the planar projection image of the blood vessel of interest can be made to approach a DSA (digital subtraction) image to some extent by setting the projection angles to a front-back position, a rear-front position, a left-front oblique position, a right-front oblique position, and a left-side position.
In an embodiment of the invention, the display module is further configured to display a projection angle selection menu for assisting medical staff in inputting a projection angle. The projection image acquisition module 16 sets the angle of the projection pipeline according to the projection angle input by the medical staff, and then obtains a corresponding plane projection image.
In an embodiment of the present invention, the display module is further configured to display a blood vessel adjustment tool to assist medical staff in inputting a blood vessel adjustment instruction; and the interested blood vessel acquisition module adjusts the interested blood vessel according to the received blood vessel adjustment instruction. For example, the display module may display an icon of the vessel of interest adjustment tool, and after selecting the icon, the medical staff may drag the boundary of the vessel of interest to input a vessel adjustment instruction; and the interested vessel acquisition module adjusts the boundary of the interested vessel according to the vessel adjusting instruction.
In particular, the adjustment of the vessel of interest by the medical staff via the vessel adjustment instruction enables a layer-by-layer automatic adjustment, namely: when the medical staff adjusts the interested vessels of any slice by inputting the vessel adjusting instructions, the interested vessels in the rest slices are adjusted correspondingly.
In an embodiment of the invention, the interested vessel acquiring module is further configured to acquire an abnormal region in the interested vessel and display the abnormal region by using the display module. Preferably, the display module highlights the abnormal region by color deepening, edge blurring and the like, so that medical staff can quickly observe the abnormal region in the blood vessel of interest, and the diagnosis efficiency is further improved. Wherein the abnormal region refers to a region of the blood vessel of interest different from a normal blood vessel, for example, a stent region and/or a calcified region in the blood vessel of interest.
Specifically, the interested vessel acquiring module may process the interested vessel by using a trained convolutional neural network model to acquire an abnormal region in the interested vessel, where the training method of the convolutional neural network model includes: acquiring training data, wherein the training data comprises a training blood vessel and an abnormal region in the training blood vessel, and the abnormal region can be acquired manually; and training the convolutional neural network model by using the training data.
The interested vessel acquiring module can also acquire an abnormal region in the interested vessel according to the gray-scale value of the interested vessel and the lesion threshold value. Taking a calcified area as the abnormal area as an example, please refer to fig. 4, in this embodiment, an implementation method for the interested blood vessel acquiring module to acquire the abnormal area includes:
s41, acquiring gray values of a plurality of voxel points in the blood vessel of interest; preferably, this step acquires the gray values of all voxel points in the vessel of interest.
S42, selecting all the voxel points with the gray values larger than the lesion threshold value from the plurality of voxel points as calcified voxel points; the area composed of the calcified voxel points is a calcified area, namely an abnormal area, in the blood vessel of interest. The lesion thresholds corresponding to different abnormal regions are different from each other, and in specific application, the lesion thresholds can be selected according to experience.
In this embodiment, the abnormal region in the blood vessel of interest is acquired and displayed, so that medical staff can determine the abnormal region in the blood vessel of interest more quickly, which is beneficial to further improving the diagnosis efficiency.
Based on the description of the cerebral blood vessel display device, the invention also provides a cerebral blood vessel display method. Referring to fig. 5, in an embodiment of the present invention, the method for displaying a cerebral blood vessel includes:
s51, acquiring a brain image; wherein the brain image is a magnetic resonance image.
S52, segmenting the brain image to obtain a brain parenchyma image.
And S53, acquiring and displaying cerebral vessels according to the brain parenchyma image so as to assist medical staff to input vessel selection instructions.
And S54, selecting the interested blood vessel from the cerebral blood vessels according to the received blood vessel selecting instruction.
S55, performing three-dimensional reconstruction on the blood vessel of interest to obtain a three-dimensional image of the blood vessel of interest.
S56, acquiring a plane projection image of the interested blood vessel.
S57, displaying the cerebral blood vessel, the blood vessel of interest, a three-dimensional image of the blood vessel of interest and/or a planar projection image of the blood vessel of interest.
In this embodiment, the steps S51 to S57 can be implemented by the cerebral blood vessel display device of the present invention, and the above description of the cerebral blood vessel display device is applicable to the cerebral blood vessel display method of this embodiment, and is not repeated herein for the sake of saving the description.
The scope of the method for displaying a cerebral blood vessel according to the present invention is not limited to the order of executing steps listed in the present embodiment, and all the methods including the steps, additions, deletions, and step substitutions according to the prior art according to the principles of the present invention are included in the scope of the present invention.
The present invention also provides a cerebral blood vessel display device, which can implement the cerebral blood vessel display method of the present invention, but the implementation device of the cerebral blood vessel display method of the present invention includes, but is not limited to, the structure of the cerebral blood vessel display device described in this embodiment, and all structural modifications and substitutions of the prior art made according to the principle of the present invention are included in the protection scope of the present invention.
The cerebral blood vessel display device is used for obtaining a brain parenchyma image by segmenting the brain image and obtaining cerebral blood vessels according to the brain parenchyma image; based on this, the user can select the interested vessel from the brain vessels by inputting the vessel selecting instruction. The cerebral vessel display device is capable of displaying the vessel of interest, a three-dimensional image and/or a planar projection image of the vessel of interest using the display module. Therefore, the cerebral blood vessel display device can realize the independent display of the interested blood vessel, and is beneficial to medical staff to quickly observe the interested blood vessel, thereby improving the diagnosis efficiency.
In conclusion, the present invention effectively overcomes various disadvantages of the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A cerebral blood vessel display device characterized by comprising:
the brain image acquisition module is used for acquiring a brain image; wherein the brain image is a magnetic resonance image;
a brain image segmentation module connected to the brain image acquisition module and configured to segment the brain image to acquire a brain parenchyma image, where the brain parenchyma image includes a plurality of two-dimensional slices;
the brain blood vessel acquisition module is connected with the brain image segmentation module and used for acquiring brain blood vessels according to the brain parenchyma image and displaying the brain blood vessels by using the display module so as to assist medical staff to input a blood vessel selection instruction; the cerebral blood vessel acquired by the cerebral blood vessel acquisition module comprises a labeling result of the cerebral blood vessel, a mask of the cerebral blood vessel and/or a multi-layer slice of the cerebral blood vessel;
the interested blood vessel acquisition module is connected with the cerebral blood vessel acquisition module and used for selecting an interested blood vessel from the cerebral blood vessels according to the received blood vessel selection instruction; the vessel of interest selected by the vessel of interest acquisition module comprises an annotation result of the vessel of interest, a mask of the vessel of interest and/or a multi-layer slice of the vessel of interest; each slice of the vessel of interest contains only the vessel of interest;
the three-dimensional image acquisition module is connected with the interested blood vessel acquisition module and used for respectively calculating the percentage of various substances contained in each voxel point in the interested blood vessel and displaying the percentages with different gray levels so as to realize three-dimensional reconstruction of the interested blood vessel and obtain a three-dimensional image of the interested blood vessel;
the projection image acquisition module is connected with the interested blood vessel acquisition module and used for projecting the interested blood vessel along one or more projection angles by utilizing projection light so as to acquire a plane projection image of the interested blood vessel;
and the display module is connected with the cerebral blood vessel acquisition module, the blood vessel of interest acquisition module, the three-dimensional image acquisition module and the projection image acquisition module and is used for displaying the cerebral blood vessel, the blood vessel of interest, the three-dimensional image of the blood vessel of interest and/or the plane projection image of the blood vessel of interest.
2. The cerebral blood vessel display device according to claim 1, further comprising:
and the image preprocessing module is connected with the brain image segmentation module and the brain blood vessel acquisition module and is used for preprocessing the brain parenchymal image.
3. The cerebral blood vessel display device according to claim 2, wherein the image preprocessing module includes:
the image registration unit is connected with the brain image segmentation module and is used for registering the brain parenchyma image; and/or
And the image reconstruction unit is connected with the brain image segmentation module and is used for reconstructing the brain parenchyma image so as to improve the resolution of the brain parenchyma image.
4. The cerebral blood vessel display device according to claim 1, wherein: the cerebral vessels include bilateral common carotid arteries, internal carotid arteries, vertebral arteries, and/or basilar arteries.
5. The cerebral blood vessel display device according to claim 1, wherein: the projection image acquisition module projects the blood vessel of interest along a projection angle by using projection light, and acquires a plane projection image of the blood vessel of interest according to the gray value of voxel points on a projection path.
6. The cerebral blood vessel display device according to claim 5, wherein: the projection angle comprises a front position, a back position, a front left inclined position, a front right inclined position and/or a left side position.
7. The cerebral blood vessel display device according to claim 5, wherein: the display module is also used for displaying a projection angle selection menu for assisting medical staff to input a projection angle.
8. The cerebral blood vessel display device according to claim 1, wherein: the display module is also used for displaying a blood vessel adjusting tool so as to assist medical staff to input a blood vessel adjusting instruction; and the interested blood vessel acquisition module adjusts the interested blood vessel according to the received blood vessel adjustment instruction.
9. The cerebral blood vessel display device according to claim 1, wherein: the interesting blood vessel acquiring module is further used for acquiring an abnormal area in the interesting blood vessel and displaying the abnormal area by the display module.
10. A cerebral blood vessel display method, comprising:
acquiring a brain image; wherein the brain image is a magnetic resonance image;
segmenting the brain image to obtain a brain parenchyma image, the brain parenchyma image comprising a plurality of two-dimensional slices;
acquiring and displaying cerebral vessels according to the brain parenchymal image so as to assist medical staff to input a vessel selection instruction, wherein the acquired cerebral vessels comprise the labeling result of the cerebral vessels, the mask of the cerebral vessels and/or the multi-layer slice of the cerebral vessels;
selecting a blood vessel of interest from the cerebral blood vessels according to the received blood vessel selection instruction, wherein the selected blood vessel of interest comprises a labeling result of the blood vessel of interest, a mask of the blood vessel of interest and/or a multi-layer slice of the blood vessel of interest; each slice of the vessel of interest contains only the vessel of interest;
respectively calculating the percentage of various substances contained in each voxel point in the blood vessel of interest and displaying the percentages in different gray scales so as to realize three-dimensional reconstruction of the blood vessel of interest and obtain a three-dimensional image of the blood vessel of interest;
projecting the blood vessel of interest along one or more projection angles by using projection light to acquire a plane projection image of the blood vessel of interest;
displaying the cerebral vessel, the vessel of interest, a three-dimensional image of the vessel of interest, and/or a planar projection image of the vessel of interest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010698900.3A CN111862312B (en) | 2020-07-20 | 2020-07-20 | Brain blood vessel display device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010698900.3A CN111862312B (en) | 2020-07-20 | 2020-07-20 | Brain blood vessel display device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111862312A CN111862312A (en) | 2020-10-30 |
| CN111862312B true CN111862312B (en) | 2021-06-11 |
Family
ID=73001202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010698900.3A Active CN111862312B (en) | 2020-07-20 | 2020-07-20 | Brain blood vessel display device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111862312B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113274135B (en) * | 2021-04-26 | 2022-10-14 | 上海友脉科技有限责任公司 | Vascular cavity interventional operation system and operation robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102239495A (en) * | 2008-12-04 | 2011-11-09 | 皇家飞利浦电子股份有限公司 | A method, apparatus, and computer program product for acquiring medical image data |
| CN105934199A (en) * | 2013-11-21 | 2016-09-07 | 三星电子株式会社 | Apparatus and method for processing a medical image of a body lumen |
| CN109313248A (en) * | 2016-04-21 | 2019-02-05 | 皇家飞利浦有限公司 | The magnetic resonance imaging of artery structure |
| CN109389669A (en) * | 2017-08-04 | 2019-02-26 | 阿里健康信息技术有限公司 | Human 3d model construction method and system in virtual environment |
| US20190172205A1 (en) * | 2016-12-31 | 2019-06-06 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for extracting vasculature |
-
2020
- 2020-07-20 CN CN202010698900.3A patent/CN111862312B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102239495A (en) * | 2008-12-04 | 2011-11-09 | 皇家飞利浦电子股份有限公司 | A method, apparatus, and computer program product for acquiring medical image data |
| CN105934199A (en) * | 2013-11-21 | 2016-09-07 | 三星电子株式会社 | Apparatus and method for processing a medical image of a body lumen |
| CN109313248A (en) * | 2016-04-21 | 2019-02-05 | 皇家飞利浦有限公司 | The magnetic resonance imaging of artery structure |
| US20190172205A1 (en) * | 2016-12-31 | 2019-06-06 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for extracting vasculature |
| CN109389669A (en) * | 2017-08-04 | 2019-02-26 | 阿里健康信息技术有限公司 | Human 3d model construction method and system in virtual environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111862312A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106682636B (en) | Blood vessel extraction method and system | |
| JP6448972B2 (en) | Medical image processing apparatus and medical image processing method | |
| Prell et al. | A novel forward projection-based metal artifact reduction method for flat-detector computed tomography | |
| JP6042112B2 (en) | Medical image processing apparatus, medical image processing method, and medical image processing program | |
| US8611989B2 (en) | Multi-planar reconstruction lumen imaging method and apparatus | |
| JP5366356B2 (en) | Medical image processing apparatus and medical image processing method | |
| US10052032B2 (en) | Stenosis therapy planning | |
| JP6381895B2 (en) | Image processing apparatus, image processing method, and X-ray diagnostic apparatus | |
| WO2022105623A1 (en) | Intracranial vascular focus recognition method based on transfer learning | |
| JP2013198763A (en) | Medical image processing apparatus | |
| CN108348206A (en) | Collateral stream for noninvasive blood flow reserve score (FFR) models | |
| TW201219013A (en) | Method for generating bone mask | |
| Golla et al. | Convolutional neural network ensemble segmentation with ratio-based sampling for the arteries and veins in abdominal CT scans | |
| CN112562058B (en) | Method for quickly establishing intracranial vascular simulation three-dimensional model based on transfer learning | |
| JP2022076477A (en) | Medical information processing equipment, medical information processing system and medical information processing method | |
| US9668710B2 (en) | Tracking brain deformation during neurosurgery | |
| Sjoerdsma et al. | Spatiotemporal registration of 3-D multi-perspective ultrasound images of abdominal aortic aneurysms | |
| CN111862312B (en) | Brain blood vessel display device and method | |
| Schmitt et al. | Reconstruction of blood propagation in three-dimensional rotational X-ray angiography (3D-RA) | |
| CN115311191A (en) | Generating reformatted views of three-dimensional anatomical scans using deep learning estimated scan scheme masks | |
| Larralde et al. | Evaluation of a 3D segmentation software for the coronary characterization in multi-slice computed tomography | |
| Loeckx et al. | Nonrigid registration for subtraction CT angiography applied to the carotids and cranial arteries | |
| van der Weide et al. | CTA-based angle selection for diagnostic and interventional angiography of saccular intracranial aneurysms | |
| CN112509080A (en) | Method for establishing intracranial vascular simulation three-dimensional model based on transfer learning | |
| Garcia | Three-dimensional imaging for coronary interventions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |