CN114419181A - CTA image reconstruction method and device, display method and device - Google Patents
CTA image reconstruction method and device, display method and device Download PDFInfo
- Publication number
- CN114419181A CN114419181A CN202210118222.8A CN202210118222A CN114419181A CN 114419181 A CN114419181 A CN 114419181A CN 202210118222 A CN202210118222 A CN 202210118222A CN 114419181 A CN114419181 A CN 114419181A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- phase
- brain
- data
- image
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 395
- 238000010969 brain CTA Methods 0.000 claims abstract description 248
- 230000011218 segmentation Effects 0.000 claims abstract description 136
- 238000010968 computed tomography angiography Methods 0.000 claims abstract description 48
- 210000004556 brain Anatomy 0.000 claims description 28
- 238000007637 random forest analysis Methods 0.000 claims description 9
- 210000005013 brain tissue Anatomy 0.000 claims description 6
- 210000000988 bone and bone Anatomy 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000014759 maintenance of location Effects 0.000 abstract description 2
- 210000003462 vein Anatomy 0.000 description 44
- 210000001367 artery Anatomy 0.000 description 23
- 210000003625 skull Anatomy 0.000 description 13
- 238000000605 extraction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 210000002376 aorta thoracic Anatomy 0.000 description 3
- 230000002490 cerebral effect Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 210000001627 cerebral artery Anatomy 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 210000001154 skull base Anatomy 0.000 description 2
- 208000022211 Arteriovenous Malformations Diseases 0.000 description 1
- 206010016717 Fistula Diseases 0.000 description 1
- 241001149900 Fusconaia subrotunda Species 0.000 description 1
- 230000008321 arterial blood flow Effects 0.000 description 1
- 230000005744 arteriovenous malformation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001054 cortical effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003890 fistula Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007917 intracranial administration Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 230000006496 vascular abnormality Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a reconstruction method, a reconstruction device, a display method and a display device of a CTA image, wherein the reconstruction method comprises the steps of obtaining brain CTA data; three-dimensional reconstruction is carried out on the brain CTA data to obtain a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase; and acquiring a target blood vessel, and identifying according to a phase corresponding to the target blood vessel, wherein the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image. The method acquires the three-dimensional blood vessel segmentation image by three-dimensionally reconstructing the acquired brain CTA data line corresponding to different phases, and identifies the target blood vessel in the three-dimensional blood vessel segmentation image according to the phase corresponding to the target blood vessel so as to realize the retention of the spatial information and the time information of the blood vessel of different phases and facilitate the observation of a reader on the blood vessel.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a reconstruction method and a reconstruction device of a CTA image, a display method and a display device.
Background
The image data of the third-phase CTA (multiple phase CTA) can provide the filling image of the whole cerebral artery, and is widely applied to clinic. At present, the clinical use of the three-phase CTA image data mainly includes displaying the blood vessel grayscale images of the artery phase, the vein phase and the vein late phase side by side on a diagnosis interface, so that the blood vessel existence condition of the patient can be obtained only by repeatedly checking and controlling the three-phase CTA image data by a reader.
Disclosure of Invention
In view of the above, the present invention provides a reconstruction method and a reconstruction device, a display method and a display device for a CTA image, and mainly aims to retain spatial information and temporal information of blood vessels corresponding to different phases in the same three-dimensional blood vessel segmentation image, so that a reader can observe the blood vessels in different phases conveniently.
According to an aspect of the present invention, there is provided a CTA image reconstruction method including:
obtaining brain CTA data, wherein the brain CTA data comprises brain CTA data corresponding to different phases;
three-dimensional reconstruction is carried out on the brain CTA data to obtain a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase;
and acquiring a target blood vessel, and identifying according to a phase corresponding to the target blood vessel, wherein the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
Further, the target blood vessel is a blood vessel of at least two phase phases, and the identification of blood vessels of different phase phases in the target blood vessel is different.
Further, the identification of vessels of different phases in the target vessel is different, including: the identification of the vessels of different phase in the target vessel is different from the identification of the vessels of the same phase.
Further, the mark comprises a color or a gray scale or a line type.
Further, the three-dimensional reconstruction of the brain CTA data to obtain a three-dimensional blood vessel segmentation image, where each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase, includes:
extracting respective global image features and local image features of each brain CTA data;
inputting the extracted global image features and local image features into a random forest classifier model which is trained in advance to obtain a three-dimensional blood vessel segmentation image;
extracting a central line corresponding to each blood vessel based on the three-dimensional blood vessel segmentation image;
drawing a time-varying curve of the gray value of each pixel point on each central line, and recording the peak time of the gray value corresponding to each blood vessel;
and judging the phase of each blood vessel according to the peak reaching time of the gray value corresponding to each blood vessel.
Further, the different phase includes at least two of an arterial phase, a venous phase, and a venous late phase.
Further, the acquiring brain CTA data comprises:
weighting each initial brain CTA data according to the exposure time corresponding to each initial brain CTA data to obtain a weighted time image, wherein the initial brain CTA image comprises initial arterial phase brain CTA data, initial venous phase brain CTA data and initial venous late brain CTA data;
performing weighted square error calculation on the weighted time image to obtain a weighted time variance image, and taking the weighted time variance image as brain CTA data; or
The acquiring brain CTA data comprises:
acquiring first middle arterial phase brain CTA data corresponding to the initial arterial phase brain CTA data according to the initial venous phase brain CTA data and/or the scanning range of the brain corresponding to the initial venous late phase brain CTA data;
respectively selecting corresponding regions of interest from the initial venous phase brain CTA data, the initial venous late brain CTA data and the first middle arterial phase brain CTA data as middle venous phase brain CTA data, middle venous late brain CTA data and second middle arterial phase brain CTA data;
separating bone images and brain tissue images in the middle venous phase brain CTA data, the middle venous phase brain CTA data and the second middle arterial phase brain CTA data respectively to obtain the arterial phase brain CTA data, the venous phase brain CTA data and the venous phase brain CTA data.
Further, the acquiring brain CTA data, further comprises:
respectively registering the arterial brain CTA data, the venous brain CTA data and the venous late brain CTA data to MNI standard space to respectively obtain arterial brain CTA registration data, venous brain CTA registration data and venous late brain CTA registration data so as to correct brain position and angle information in an image;
and removing interference information in the arterial brain CTA registration data, the venous brain CTA registration data and the venous late brain CTA registration data through a scale smoothing filter to obtain the brain CTA data.
According to another aspect of the present invention, there is provided a CTA image display method including:
acquiring a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase;
and identifying and displaying a target blood vessel in the three-dimensional blood vessel segmentation image, wherein the target blood vessel is a blood vessel corresponding to at least one stage in the three-dimensional blood vessel segmentation image.
Further, the target blood vessel is a blood vessel of at least two phase phases, and the identification of blood vessels of different phase phases in the target blood vessel is different.
Further, the identification of vessels of different phases in the target vessel is different, including: the identification of the vessels of different phase in the target vessel is different from the identification of the vessels of the same phase.
Further, the mark comprises a color or a gray scale or a line type.
According to still another aspect of the present invention, there is provided a CTA image data reconstruction apparatus including:
the data acquisition module is used for acquiring brain CTA data, wherein the brain CTA data comprises brain CTA data corresponding to different phases;
the three-dimensional blood vessel segmentation image construction module is used for carrying out three-dimensional reconstruction on the brain CTA data to obtain a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to one phase;
and the identification module is used for acquiring a target blood vessel and identifying the target blood vessel according to a phase corresponding to the target blood vessel, wherein the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
According to still another aspect of the present invention, there is provided a CTA image data display device including:
the three-dimensional blood vessel segmentation data acquisition module is used for responding to an image browsing request and acquiring a three-dimensional blood vessel segmentation image, wherein the three-dimensional blood vessel segmentation image comprises blood vessels respectively corresponding to at least two phases;
and the display module is used for identifying and displaying a target blood vessel in the three-dimensional blood vessel segmentation image, wherein the target blood vessel is a blood vessel corresponding to at least one stage in the three-dimensional blood vessel segmentation image.
According to still another aspect of the present invention, there is provided a computer-readable storage medium having stored therein instructions that, when run on a terminal device, cause the terminal device to execute the CTA image reconstruction method as described above; or the CTA image display method described above.
By the technical scheme, the technical scheme provided by the embodiment of the invention at least has the following advantages:
the invention has provided a CTA picture reconstruction method and reconstruction apparatus, display method and display device, compared with prior art, on the one hand, the invention through comprising brain CTA data row three-dimensionally reconstruction that different phases correspond to that obtained, obtain the three-dimensional vessel and cut apart the picture, and then phase according to the goal blood vessel corresponds, mark said goal blood vessel, in order to realize the space information and time information retention of the blood vessel of phase of different phases, facilitate the reader to observe the blood vessel; on the other hand, the target blood vessel in the acquired three-dimensional blood vessel segmentation image is identified and displayed according to the corresponding phase of the target blood vessel so as to display the time and space information of the target blood vessel, and a reader can distinguish the phase of each blood vessel through the blood vessels with different identifications.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating a method for reconstructing a CTA image according to an embodiment of the present invention;
FIG. 2 is a schematic representation of a scan pattern for a three-phase CTA imaging technique provided by an embodiment of the invention;
FIG. 3 is a flow chart of another CTA image reconstruction method provided by an embodiment of the invention;
FIG. 4 shows a flow chart for acquiring brain CTA data provided by an embodiment of the invention;
FIG. 5 illustrates yet another flow chart for acquiring brain CTA data provided by an embodiment of the invention;
FIG. 6 is a block diagram illustrating a method for reconstructing a CTA image according to an embodiment of the present invention;
FIG. 7 is a block diagram showing the components of a CTA image display method according to an embodiment of the present invention;
FIG. 8 is a block diagram showing another CTA image reconstruction apparatus according to an embodiment of the present invention;
fig. 9 is a block diagram showing a CTA image display device according to an embodiment of the present invention;
fig. 10 shows a physical structure diagram of a computer device according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
At present, the clinically used three-phase CTA data method is mainly to display the grayscale images of the blood vessels in the arterial phase, the venous phase and the advanced venous phase side by side on a diagnosis interface, and a reader needs to repeatedly check each slice and control each slice left and right to obtain the blood vessel existence condition of a patient. Although a two-dimensional color map display technology for three-phase CTA data has been proposed in recent two years, the technology maps the blood vessel information in the three-phase CTA data onto one two-dimensional color map, and represents the time information (arterial phase, venous phase or venous late phase) corresponding to the blood vessel filling with three colors, respectively, so as to effectively shorten the diagnosis time of a reader.
On the one hand, the three-dimensional blood vessel segmentation image is obtained by three-dimensionally reconstructing the obtained brain CTA data comprising different phases of corresponding brain CTAs, and then the target blood vessel is identified according to the phase corresponding to the target blood vessel in the three-dimensional blood vessel segmentation image, so that the target blood vessel can be observed by a reader while the spatial information and the time information of the target blood vessel in the three-dimensional blood vessel segmentation image are retained; on the other hand, each target blood vessel in the obtained three-dimensional blood vessel segmentation image is identified and displayed according to the corresponding phase to display the time and space information of the target blood vessel in the three-dimensional blood vessel segmentation image, so that a reader can distinguish the phase of each blood vessel through the blood vessels with different identifications. Therefore, the CTA image reconstruction method and the CTA image display method provided by the application can be used for evaluating the occlusion conditions of large and small intracranial blood vessels and far-end/near-end blood vessels, and can be used for accurately detecting the conditions of arteriovenous malformation, arteriovenous shunt, epidural sinus and cortical blood vessel abnormality caused by arteriovenous internal fistula and the like. In addition, the application can also well assist inexperienced doctors to complete the evaluation of the existing state of the blood vessels of the patients.
A CTA image reconstruction method of the present application is described below, and as shown in fig. 1, includes:
101. brain CTA data is acquired, wherein the brain CTA data comprises brain CTA data corresponding to different phases.
It should be noted that the brain CTA data herein is a two-dimensional image which can clearly display cerebral vessels and is obtained by using a contrast agent and an image post-processing technology, and the brain CTA data respectively corresponding to three phases can show the filling state of the whole cerebral artery vessels; referring to fig. 2, when acquiring cerebral CTA data in an arterial phase, a long solid arrow in the figure indicates a scanning range of a human body in the arterial phase, that is, an aortic arch to a cranial vertex of a patient is scanned in an arterial blood flow peak period, and the scanning duration is 7 seconds; the next two phases (venous phase, late venous phase), both indicated by short solid arrows, were acquired 4 seconds after the end of the previous data scan, and the scan duration was 3.4 seconds for consecutive bases to the vertex; wherein the dashed arrows in the figure represent the movement of the scanner between image acquisitions.
102. And performing three-dimensional reconstruction on the brain CTA data to obtain a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to one phase.
By three-dimensional reconstruction of brain CTA data, the information of blood vessels in different phases can be integrated into a three-dimensional blood vessel segmentation image, and meanwhile, the segmentation of the brain blood vessels respectively corresponding to the different phases is realized, namely, each blood vessel corresponds to one phase, so that the analysis of the brain blood vessels respectively corresponding to the different phases is facilitated. In an example, the three-dimensional blood vessel segmentation image includes an artery phase blood vessel, a vein phase blood vessel and a vein late phase blood vessel, that is, a three-dimensional blood vessel network of the three-dimensional blood vessel segmentation image composed of the artery phase blood vessel, the vein phase blood vessel and the vein late phase blood vessel.
103. And acquiring a target blood vessel, and identifying according to a phase corresponding to the target blood vessel, wherein the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
Each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase, which can be an artery phase, a vein phase or a vein late phase, a target blood vessel is obtained, the target blood vessel in the three-dimensional blood vessel segmentation image is identified according to the phase corresponding to the target blood vessel, the spatial information of the target blood vessel is reserved, a reader can identify the phase corresponding to the blood vessel according to the characteristics of the identification, wherein the target blood vessel is a blood vessel which is concerned by the reader and is to be analyzed and diagnosed, if the reader wants to read the artery blood vessel, the target blood vessel is the artery blood vessel, if the reader wants to read the artery blood vessel and the vein blood vessel, the target blood vessel is the artery blood vessel and the vein blood vessel, and the characteristics of the blood vessel identifications of different phases are different. For example, the blood vessels of different phases correspond to one color, the blood vessels in the arterial phase are marked with red on the three-dimensional blood vessel segmentation map, the blood vessels in the venous phase are marked with blue on the three-dimensional blood vessel segmentation map, and the blood vessels in the later stage of the vein are marked with green on the three-dimensional blood vessel segmentation map, so that the three-dimensional blood vessel segmentation map marks the periods of the blood vessels respectively through red, blue and green, so that the three-dimensional blood vessel segmentation map retains the time information of each blood vessel, and a reader can distinguish the phase of each blood vessel through the color of the blood vessels marked with the color. Of course, the markers may also be represented by gray scale, and the blood vessels of different phases may be distinguished by linear lines, and the blood vessel contours of the blood vessels of different phases are represented by different linear lines, such as solid lines, dotted lines, or dot-dash lines, which are not listed here. That is, the indicia includes color, grayscale, or line type.
In one example, the target vessel is at least two phase vessels, and the identification of vessels of different phase in the target vessel is different. Further, the identification of vessels of different phases in the target vessel is different, including: the identification of the vessels of different phase in the target vessel is different from the identification of the vessels of the same phase.
Compared with the prior art, the reconstruction method of the CTA image obtains the three-dimensional blood vessel segmentation image by three-dimensionally reconstructing the obtained brain CTA data comprising the corresponding brain CTA data in different periods, and identifies the target blood vessel in the three-dimensional blood vessel segmentation image according to the period phase corresponding to each blood vessel in the three-dimensional blood vessel segmentation image, so that a reader can conveniently observe the blood vessel corresponding to the period phase identified by the blood vessel through different identifications while keeping the space information and the time information of the target blood vessel in the three-dimensional blood vessel segmentation image.
Another CTA image reconstruction method is provided in an embodiment of the present invention, as shown in fig. 3, the method includes:
301. brain CTA data is acquired, wherein the brain CTA data comprises brain CTA data corresponding to different phases.
To avoid noise interference in the brain CTA data, the acquiring the brain CTA data, referring to fig. 4, may include:
3011. and weighting each initial brain CTA data according to the exposure time corresponding to each initial brain CTA data to obtain a weighted time image, wherein the initial brain CTA image comprises initial arterial phase brain CTA data, initial venous phase brain CTA data and initial venous late brain CTA data.
The initial brain CTA data contains noise interference with different properties, wherein quantum noise (caused by X-ray dose) is a main source of the noise of the initial brain CTA data, and the image data obtained by scanning at different time points receives different X-ray exposure and the noise contained in the image data is different. The arterial brain CTA data, the venous brain CTA data and the venous late brain CTA data contain 3 three-dimensional volume data VkEach VkIn which contains NiTwo-dimensional image I of a webiWherein each image data is due to exposure EjThe noise caused is different. Therefore, the present embodiment weights the arterial phase brain CTA data, the venous phase brain CTA data, and the venous phase brain CTA data according to the exposure time to obtain a weighted time image. Here, when weighting each initial brain CTA data, the formula used is:
wherein,
although the weighted time image obtained by the embodiment can well solve the influence of different noise distributions of different slices (two-dimensional images) in the initial brain CTA data, the noise distributions among different slices are the same, and the overall quality of the obtained image data is high.
3012. And performing weighted square error calculation on the weighted time image to obtain a weighted time variance image, and taking the weighted time variance image as brain CTA data.
By performing weighted square error calculation on the weighted time image, the contrast of blood vessels and background tissues in the obtained weighted time image is increased so as to facilitate the separation of the subsequent blood vessel image and the skull image. Here to weightWhen the time image is weighted, the formula used is as follows:
since the range from the aortic arch to the cranial vertex of the patient needs to be scanned as a scanning range when obtaining the brain CTA data corresponding to the arterial phase, and the observation of the condition of the brain blood vessels mainly focuses on the condition of the blood vessels in the region of interest located in the cranium, the obtaining of the brain CTA data, referring to fig. 5, may include:
3013. and acquiring first middle arterial phase brain CTA data corresponding to the initial arterial phase brain CTA data according to the initial venous phase brain CTA data and/or the scanning range of the brain corresponding to the initial venous late phase brain CTA data.
Because the range from the skull base to the skull top of the patient is used as the scanning range to scan when the brain CTA data corresponding to the vein phase and the vein late phase are obtained respectively, and the range from the skull base to the skull top is just the region range where the brain blood vessels are located, the blood vessels in the first intermediate artery phase brain CTA data obtained by interception can be only wrapped as the brain blood vessels by taking the scanning range of the brain corresponding to the vein phase and/or the vein late phase as the interception range of the artery phase brain CTA data.
3014. And respectively selecting corresponding regions of interest from the initial venous phase brain CTA data, the initial venous late brain CTA data and the first middle arterial phase brain CTA data to respectively serve as middle venous phase brain CTA data, middle venous late brain CTA data and second middle arterial phase brain CTA data.
The region of interest can be a specific region of the patient's brain that the viewer would look at, or can be a region that the viewer would determine from viewing brain CTA data.
In the embodiment, by intercepting the region of interest, the regions not interested by the reader can be separated from the initial vein phase brain CTA data, the initial vein phase brain CTA data and the first middle artery phase brain CTA data, respectively, so that the finally obtained three-dimensional blood vessel segmentation image only includes the region of interest of the reader, thereby facilitating the observation of the blood vessel state in the region of interest by the reader. Here, the brain regions of the patient corresponding to the regions of interest in the brain CTA data corresponding to the three phases are all the same region.
3015. Separating bone images and brain tissue images in the middle venous phase brain CTA data, the middle venous phase brain CTA data and the second middle arterial phase brain CTA data respectively to obtain the arterial phase brain CTA data, the venous phase brain CTA data and the venous phase brain CTA data.
It should be noted that the bone image and the brain tissue image are separated based on a threshold method.
By separating the skull image and the brain tissue image in the captured image, the influence of the image characteristics of the skull image on the subsequent construction of the three-dimensional blood vessel segmentation image can be avoided, and the spatial positions of the blood vessels respectively corresponding to the three phases in the three-phase three-dimensional blood vessel segmentation image obtained finally are more accurate.
In order to remove interference information in the brain CTA data so that the finally obtained three-dimensional vessel segmentation image can truly reflect the vessel state of the brain of the patient, the obtaining of the brain CTA data, wherein the brain CTA data includes arterial brain CTA data, venous brain CTA data and venous late brain CTA data, may further include: respectively registering the arterial brain CTA data, the venous brain CTA data and the venous late brain CTA data to MNI standard space to respectively obtain arterial brain CTA registration data, venous brain CTA registration data and venous late brain CTA registration data so as to correct brain position and angle information in an image; and removing interference information in the arterial brain CTA registration data, the venous brain CTA registration data and the venous late brain CTA registration data through a scale smoothing filter to obtain the brain CTA data.
The brain position and angle information in all brain CTA registration data is corrected by registering the artery phase brain CTA data, the vein phase brain CTA data and the vein phase brain CTA data to MNI standard space, so that the position information of each blood vessel in the three-dimensional blood vessel segmentation image obtained subsequently is consistent with the actual position information of each blood vessel on the brain of the patient. The interference information in the CTA registration data of each brain is removed through the scale smoothing filter, so that the interference of the interference information on the subsequent extraction of global image features and local image features and the interference on the judgment of the phase of each blood vessel can be avoided, and a reader can accurately judge the state of each blood vessel through the finally obtained three-dimensional blood vessel segmentation image.
302. Extracting respective global image features and local image features of each of the brain CTA data.
The brain CTA data features are information representing features in the brain, and include global image features and local image features, and the global image features refer to features which can represent the whole brain CTA data and are used for describing the whole features of the brain CTA data. The local image features are relative to the global image features, refer to local expression of features of the brain CTA data, and reflect local specificity of the brain CTA data. In the embodiment, global image features of brain CTA data are extracted as one of features according to which a subsequent three-dimensional blood vessel segmentation image is established. In this embodiment, the global image feature may be a blood vessel image feature matrix.
By extracting the features of each brain CTA data, namely extracting the global image features and the local image features, the analysis of the feature information of each brain CTA data can be realized, and the feature information of each brain CTA data is fused in one three-dimensional blood vessel segmentation image, so that the blood vessel state condition of the brain of the patient can be reflected only by one three-dimensional blood vessel segmentation image.
In this embodiment, in order to make the extracted global image features and local image features reflect the states of the respective blood vessels, the extracting of the global image features and local image features of each of the brain CTA data includes: extracting candidate blood vessel images in the brain CTA data, and taking the image characteristics of the candidate blood vessel images as global image characteristics; extracting features of the brain CTA data through filters with different scales, and taking the extracted features as local image features of the brain CTA data; wherein the local image features include at least one of a grayscale histogram feature, a Hessian matrix feature, and a grayscale feature.
Here, since there is a difference in the size of the blood vessels in the brain, the brain CTA image is feature-extracted using filters of different scales such as 3 × 3 and 5 × 5.
Since the finally obtained three-dimensional blood vessel segmentation image only needs to display the state condition of blood vessels in three stages respectively, the extracting of the candidate blood vessel image in the brain CTA data and taking the image feature of the candidate blood vessel image as the global image feature may include: separating a first skull image on the brain CTA data from the brain CTA data by a morphological method to obtain a vessel region image; and marking a connected domain on the blood vessel region image, removing the second skull image on the blood vessel region image, and acquiring the candidate blood vessel image.
Since the brain CTA data includes the first skull image and the blood vessel image, the first skull image on the brain CTA data is separated from the brain CTA data by a morphological method, and an image only having a blood vessel region can be obtained; and because the blood vessel region image usually contains a small amount of scattered second skull images which are partially remained and are close to the gray value of the blood vessel, the skull is further separated by marking the connected domain of the blood vessel region image, and a candidate blood vessel image without the skull image is obtained.
303. And inputting the extracted global image features and local image features into a random forest classifier model which is trained in advance to obtain a three-dimensional blood vessel segmentation image.
By inputting the extracted global image characteristics and local image characteristics into a random forest classifier model which is trained in advance, the information of blood vessels in an artery stage, a vein stage and a vein late stage can be integrated into a three-dimensional blood vessel segmentation image through the random forest classifier model, meanwhile, the brain blood vessels respectively corresponding to the three stages are segmented, and therefore the brain blood vessels respectively corresponding to the three stages can be conveniently analyzed.
304. And extracting the central line corresponding to each blood vessel based on the three-dimensional blood vessel segmentation image.
Because the change of the gray value of each pixel point on the centerline of the blood vessel in the three-dimensional blood vessel segmentation image can reflect the phase of the blood vessel, the embodiment extracts the centerline of each blood vessel in the three-dimensional blood vessel segmentation image, so as to judge the phase of each blood vessel in the following.
305. And drawing a time-varying curve of the gray value of each pixel point on each central line, and recording the peak time of the gray value corresponding to each blood vessel.
In order to obtain the gray value peak reaching time corresponding to the pixel point with the highest gray value on the central line corresponding to each blood vessel, the gray value peak reaching time corresponding to each blood vessel can be visually judged by drawing a time variation curve of the gray value of each pixel point on each central line and drawing the curve, and the determined gray value peak reaching time Tm is recorded.
306. And judging the phase of each blood vessel according to the peak reaching time of the gray value corresponding to each blood vessel.
Because the gray value peak reaching time of each blood vessel in different phase corresponds to the time for each blood vessel to be scanned, the phase of each blood vessel can be judged according to the comparison of the gray value peak reaching time corresponding to each blood vessel with the preset threshold values corresponding to the artery phase, the vein phase and the vein late phase respectively.
Specifically, when the cerebral CTA data in the arterial phase is obtained, the duration of scanning from the aortic arch to the vertex of the skull of a patient is 7 seconds, so that the preset threshold corresponding to the arterial phase is determined to be 8 seconds, and if Tm is less than or equal to 8 seconds, the peak reaching time of the pixel gray value is in the arterial phase; after the scanning of the artery phase of the patient is finished for 4 seconds, the scanning of the vein phase of the patient is carried out, the duration time is 3.4 seconds, therefore, the preset threshold corresponding to the vein phase is determined to be between 12 seconds and 16 seconds, and if Tm is more than or equal to 12 seconds and less than or equal to 16 seconds, the peak reaching time of the pixel gray value is in the vein phase; and after 4 seconds of completing the vein phase scanning of the patient, scanning the vein late phase of the patient for 3.4 seconds, so that the preset threshold corresponding to the vein phase is determined to be between 20 seconds and 42 seconds, and if Tm is more than or equal to 20 seconds and less than or equal to 42 seconds, the peak reaching time of the pixel gray value is in the vein late phase.
307. And acquiring a target blood vessel, and identifying according to a phase corresponding to the target blood vessel, wherein the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
If the target blood vessel is a blood vessel in three stages of an arterial stage, a venous stage and a venous late stage, the obtained three-dimensional blood vessel segmentation image can completely reserve the time information of the arterial stage, the venous stage and the venous late stage corresponding to the blood vessel by respectively carrying out color identification on the blood vessels corresponding to the arterial stage, the venous stage and the venous late stage, and further simplify the process of diagnosing a patient by a reader by using brain CTA data. In an example, an epoch and identification correspondence table can be established, and a reader can know the epoch information of the blood vessel according to the correspondence table.
The invention provides a CTA image reconstruction method, compared with the prior art, the embodiment of the invention extracts the respective global image characteristics and local image characteristics of each brain CTA data, and then inputs the extracted global image characteristics and local image characteristics into a random forest classifier model which is trained in advance to obtain a three-dimensional blood vessel segmentation image; extracting the central line corresponding to each blood vessel on the three-dimensional blood vessel segmentation image; determining the gray value peak reaching time corresponding to each blood vessel by drawing a gray value time-varying curve of each pixel point on each central line; judging the phase of each blood vessel according to the peak reaching time of the gray value corresponding to each blood vessel; finally, according to the phase corresponding to the target blood vessel, the target blood vessel in the three-dimensional blood vessel segmentation image is identified in different modes, so that the obtained three-dimensional blood vessel segmentation image completely retains the time information of the artery phase, the vein phase and the vein late phase corresponding to the blood vessel, and a reader can conveniently observe the blood vessel in the three-phase through the three-dimensional blood vessel segmentation image with different identifications.
An embodiment of the present invention provides a CTA image display method, as shown in fig. 6, the display method includes:
601. and acquiring a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase.
602. And identifying and displaying a target blood vessel in the three-dimensional blood vessel segmentation image, wherein the target blood vessel is a blood vessel corresponding to at least one stage in the three-dimensional blood vessel segmentation image.
Here, the identification includes a color or a gray scale or a line type. For example, a red mark is displayed on a blood vessel in an artery phase, a blue mark is displayed on a blood vessel in a vein phase, and a green mark is displayed on a blood vessel in a vein late phase on the three-dimensional blood vessel segmentation map, so that the periods of the blood vessels are respectively displayed through red, blue and green, the time information of each blood vessel is displayed, and a reader can distinguish the phase of each blood vessel through the color of the blood vessel marked by the color.
In one example, the target vessel is at least two phase vessels, and the identification of vessels of different phase in the target vessel is different. Specifically, the identification of the vessels of different phases in the target vessel is different, including: the identification of the vessels of different phase in the target vessel is different from the identification of the vessels of the same phase.
In the embodiment of the present invention, acquiring the three-dimensional blood vessel segmentation image includes retrieving a reconstructed three-dimensional blood vessel segmentation image, or acquiring the three-dimensional blood vessel segmentation image through reconstruction after receiving a browsing request. The reconstruction method of the three-dimensional blood vessel segmentation image can adopt the reconstruction method provided by the embodiment of the invention, and can also adopt other existing methods.
Compared with the prior art, the method for displaying the CTA image has the advantages that each target blood vessel in the obtained three-dimensional blood vessel segmentation image is displayed in an identification mode according to the corresponding phase, so that the time information of the target blood vessel in the three-dimensional blood vessel segmentation image is displayed, and a reader can distinguish the phase of each blood vessel through the blood vessels with different identifications.
Further, as an implementation of the method shown in fig. 1, an embodiment of the present invention provides an apparatus for reconstructing CTA image data, as shown in fig. 7, the apparatus includes:
a data acquisition module 71 for acquiring brain CTA data, wherein the data includes phase-out data;
a three-dimensional blood vessel segmentation image construction module 72, configured to perform three-dimensional reconstruction on the brain CTA data to obtain a three-dimensional blood vessel segmentation image, where each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase;
and the identification module 73 is configured to acquire a target blood vessel and identify the target blood vessel according to a phase corresponding to the target blood vessel, where the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
Compared with the prior art, the embodiment of the invention provides a CTA image reconstruction device, which acquires a three-dimensional blood vessel segmentation image by three-dimensionally reconstructing acquired brain CTA data comprising corresponding different phases, and identifies a target blood vessel in the three-dimensional blood vessel segmentation image according to the phase corresponding to each blood vessel in the three-dimensional blood vessel segmentation image, so that a reader can observe blood vessels in the three-phase through the three-dimensional blood vessel segmentation image with different identifications while keeping spatial information and time information of the target blood vessel in the three-dimensional blood vessel segmentation image.
As an implementation of the method shown in fig. 3, another CTA image reconstruction apparatus is provided in an embodiment of the present invention, as shown in fig. 8, the apparatus includes:
a data acquisition module 81 for acquiring brain CTA data, wherein the data includes phase-out data;
a feature extraction module 82, configured to extract a global image feature and a local image feature of each of the brain CTA data;
and the three-dimensional blood vessel segmentation data acquisition module 83 is configured to input the extracted global image features and local image features into a random forest classifier model which is trained in advance, so as to obtain a three-dimensional blood vessel segmentation image.
A centerline extraction module 84, configured to extract a centerline corresponding to each of the blood vessels based on the three-dimensional blood vessel segmentation image;
a gray value peak reaching time obtaining module 85, configured to draw a time-varying curve of the gray value of each pixel point on each centerline, and record the gray value peak reaching time corresponding to each blood vessel;
a blood vessel phase determining module 86, configured to determine a phase of each blood vessel according to a peak arrival time of a gray value corresponding to each blood vessel;
the identification module 87 is configured to obtain a target blood vessel and identify the target blood vessel according to a phase corresponding to the target blood vessel.
Wherein, the target blood vessel is a blood vessel corresponding to at least one stage in the three-dimensional blood vessel segmentation image.
Further, the feature extraction module 82 includes:
a global image feature extraction unit, configured to extract a candidate blood vessel image in the brain CTA data, and use an image feature of the candidate blood vessel image as a global image feature;
a local image feature extraction unit, configured to perform feature extraction on the brain CTA data through filters of different scales, and use the extracted features as local image features of the brain CTA data; wherein the local image features include at least one of a grayscale histogram feature, a Hessian matrix feature, and a grayscale feature.
Further, the different phases include at least two of an arterial phase, a venous phase, and a venous late phase; the data acquisition module 81 includes:
a weighted time image obtaining unit, configured to perform weighting processing on each initial brain CTA data according to an exposure time corresponding to each initial brain CTA data, so as to obtain a weighted time image, where the initial brain CTA image includes initial arterial-phase brain CTA data, initial venous-phase brain CTA data, and initial venous-late brain CTA data;
and the first brain CTA image updating unit is used for performing weighted square error calculation on the weighted time image to obtain a weighted time variance image, and taking the weighted time variance image as the brain CTA data.
Further, the data obtaining module 81 includes:
the brain CTA image obtaining unit is used for obtaining first middle artery phase brain CTA data corresponding to the initial artery phase brain CTA data according to the initial vein phase brain CTA data and/or the scanning range of the brain corresponding to the initial vein late phase brain CTA data;
an interesting region intercepting unit, configured to select respective interesting regions from the initial venous phase brain CTA data, the initial venous late brain CTA data, and the first intermediate arterial phase brain CTA data, respectively, as an intermediate venous phase brain CTA data, an intermediate venous late brain CTA data, and a second intermediate arterial phase brain CTA data;
a second brain CTA image updating unit for respectively separating bone images and brain tissue images in the middle vein phase brain CTA data, and the second middle artery phase brain CTA data to obtain the artery phase brain CTA data, the vein phase brain CTA data, and the vein phase brain CTA data.
Further, the apparatus further comprises:
the correction module is used for respectively registering the arterial brain CTA data, the venous brain CTA data and the venous late brain CTA collected data to MNI standard space to respectively obtain arterial brain CTA registered data, venous brain CTA registered data and venous late brain CTA registered data so as to correct brain position and angle information in the image;
and the image preprocessing module is used for removing interference information in the arterial-stage brain CTA registration data, the venous-stage brain CTA registration data and the venous-stage brain CTA registration data through a scale smoothing filter to obtain the brain CTA data.
Compared with the prior art, the embodiment of the invention provides another CTA image data reconstruction device, and after the global image features and the local image features of each brain CTA data are extracted, the extracted global image features and the extracted local image features are input into a pre-trained random forest classifier model to obtain a three-dimensional blood vessel segmentation image; extracting the central line corresponding to each blood vessel on the three-dimensional blood vessel segmentation image; determining the gray value peak reaching time corresponding to each blood vessel by drawing a gray value time-varying curve of each pixel point on each central line; judging the phase of each blood vessel according to the peak reaching time of the gray value corresponding to each blood vessel; finally, the target blood vessel in the three-dimensional blood vessel segmentation image is identified in different modes, so that the time information of the obtained three-dimensional blood vessel segmentation image in the artery phase, the vein phase and the vein late phase corresponding to the blood vessel can be completely reserved, and a reader can conveniently observe the blood vessel in the three-phase through the three-dimensional blood vessel segmentation image with different identifications.
As an implementation of the above-described method shown in fig. 6, an embodiment of the present invention provides another CTA image display apparatus, as shown in fig. 9, including:
a three-dimensional blood vessel segmentation data acquisition module 91, configured to acquire a three-dimensional blood vessel segmentation image, where each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase;
a display module 92, configured to identify and display a target blood vessel in the three-dimensional blood vessel segmentation image, where the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
Compared with the prior art, the embodiment of the invention displays the time information of each blood vessel in the three-dimensional blood vessel segmentation image by identifying and displaying each blood vessel in the acquired three-dimensional blood vessel segmentation image according to the corresponding phase, so that a reader can distinguish the phase of each blood vessel through the blood vessels with different identifications.
According to an embodiment of the present invention, there is provided a storage medium storing at least one executable instruction, the computer executable instruction being capable of executing a method for reconstructing a CTA image in any of the above method embodiments.
Based on the above embodiments of the method shown in fig. 1 and the apparatus shown in fig. 3, an embodiment of the present invention further provides an entity structure diagram of a computer device, as shown in fig. 10, where the computer device includes: a processor 1001, a memory 1002, and a computer program stored on the memory 1002 and executable on the processor, wherein the memory 1002 and the processor 1001 are each configured on a bus 1003 such that the following steps are achieved when the processor 1001 executes the program: obtaining brain CTA data, wherein the brain CTA data comprises brain CTA data corresponding to different phases; performing three-dimensional reconstruction on the brain CTA data to obtain a three-dimensional blood vessel segmentation image; and identifying each blood vessel in the three-dimensional blood vessel segmentation image according to the phase corresponding to each blood vessel in the three-dimensional blood vessel segmentation image.
According to the technical scheme, the method can extract the global image characteristics and the local image characteristics of the obtained artery-phase brain CT image, vein-phase brain CT image and vein late-phase brain CT image respectively, and input the extracted global image characteristics and local image characteristics into a pre-trained random forest classifier model to obtain the three-dimensional blood vessel segmentation image; and then according to the phase corresponding to each blood vessel in the three-dimensional blood vessel segmentation image, carrying out color identification on the target blood vessel in the three-dimensional blood vessel segmentation image so as to realize that a reader can observe the blood vessel in the three-phase through the three-dimensional blood vessel segmentation image after color identification while keeping the spatial information and the time information of the blood vessel corresponding to the artery phase, the vein phase and the vein late phase in the three-dimensional blood vessel segmentation image.
It will be apparent to those skilled in the art that the various modules or steps of the invention described above may be implemented using a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented using program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (15)
1. A method for reconstructing a CTA image, comprising:
obtaining brain CTA data, wherein the brain CTA data comprises brain CTA data corresponding to different phases;
three-dimensional reconstruction is carried out on the brain CTA data to obtain a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase;
and acquiring a target blood vessel, and identifying according to a phase corresponding to the target blood vessel, wherein the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
2. The reconstruction method according to claim 1, wherein the target vessel is a vessel of at least two phase phases, and the identification of vessels of different phase phases in the target vessel is different.
3. The reconstruction method according to claim 2, wherein the identification of vessels of different phases in the target vessel is different, comprising: the identification of the vessels of different phase in the target vessel is different from the identification of the vessels of the same phase.
4. The reconstruction method according to claim 1, wherein the indication comprises a color or a gray scale or a line type.
5. The reconstruction method according to claim 1, wherein the three-dimensional reconstruction of the brain CTA data to obtain a three-dimensional vessel segmentation image, each vessel in the three-dimensional vessel segmentation image corresponding to a phase comprises:
extracting respective global image features and local image features of each brain CTA data;
inputting the extracted global image features and local image features into a random forest classifier model which is trained in advance to obtain a three-dimensional blood vessel segmentation image;
extracting a central line corresponding to each blood vessel based on the three-dimensional blood vessel segmentation image;
drawing a time-varying curve of the gray value of each pixel point on each central line, and recording the peak time of the gray value corresponding to each blood vessel;
and judging the phase of each blood vessel according to the peak reaching time of the gray value corresponding to each blood vessel.
6. The reconstruction method according to claim 1, wherein the different phase includes at least two of an arterial phase, a venous phase, and a venous late phase.
7. The reconstruction method according to claim 6, wherein the acquiring brain CTA data comprises:
weighting each initial brain CTA data according to the exposure time corresponding to each initial brain CTA data to obtain a weighted time image, wherein the initial brain CTA image comprises initial arterial phase brain CTA data, initial venous phase brain CTA data and initial venous late brain CTA data;
performing weighted square error calculation on the weighted time image to obtain a weighted time variance image, and taking the weighted time variance image as brain CTA data; or
The acquiring brain CTA data comprises:
acquiring first middle arterial phase brain CTA data corresponding to the initial arterial phase brain CTA data according to the initial venous phase brain CTA data and/or the scanning range of the brain corresponding to the initial venous late phase brain CTA data;
respectively selecting corresponding regions of interest from the initial venous phase brain CTA data, the initial venous late brain CTA data and the first middle arterial phase brain CTA data as middle venous phase brain CTA data, middle venous late brain CTA data and second middle arterial phase brain CTA data;
separating bone images and brain tissue images in the middle venous phase brain CTA data, the middle venous phase brain CTA data and the second middle arterial phase brain CTA data respectively to obtain the arterial phase brain CTA data, the venous phase brain CTA data and the venous phase brain CTA data.
8. The reconstruction method according to claim 6, wherein the acquiring brain CTA data, further comprises:
respectively registering the arterial brain CTA data, the venous brain CTA data and the venous late brain CTA data to MNI standard space to respectively obtain arterial brain CTA registration data, venous brain CTA registration data and venous late brain CTA registration data so as to correct brain position and angle information in an image;
and removing interference information in the arterial brain CTA registration data, the venous brain CTA registration data and the venous late brain CTA registration data through a scale smoothing filter to obtain the brain CTA data.
9. A CTA image display method comprising:
acquiring a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase;
and identifying and displaying a target blood vessel in the three-dimensional blood vessel segmentation image, wherein the target blood vessel is a blood vessel corresponding to at least one stage in the three-dimensional blood vessel segmentation image.
10. The display method according to claim 9, wherein the target blood vessel is a blood vessel of at least two phase phases, and the identification of the blood vessels of different phase phases in the target blood vessel is different.
11. The method according to claim 10, wherein the identification of the vessels of different phases in the target vessel is different, comprising: the identification of the vessels of different phase in the target vessel is different from the identification of the vessels of the same phase.
12. The display method according to claim 9, wherein the indication comprises a color or a gray scale or a line type.
13. A CTA image reconstruction device, comprising:
the data acquisition module is used for acquiring brain CTA data, wherein the brain CTA data comprises brain CTA data corresponding to different phases;
the three-dimensional blood vessel segmentation image construction module is used for carrying out three-dimensional reconstruction on the brain CTA data to obtain a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to one phase;
and the identification module is used for acquiring a target blood vessel and identifying the target blood vessel according to a phase corresponding to the target blood vessel, wherein the target blood vessel is a blood vessel corresponding to at least one phase in the three-dimensional blood vessel segmentation image.
14. A CTA image display device, comprising:
the three-dimensional blood vessel segmentation data acquisition module is used for acquiring a three-dimensional blood vessel segmentation image, wherein each blood vessel in the three-dimensional blood vessel segmentation image corresponds to a phase;
and the display module is used for identifying and displaying a target blood vessel in the three-dimensional blood vessel segmentation image, wherein the target blood vessel is a blood vessel corresponding to at least one stage in the three-dimensional blood vessel segmentation image.
15. A computer-readable storage medium characterized in that it has stored therein instructions that, when run on a terminal device, cause the terminal device to execute the reconstruction method of a CTA image as claimed in any one of claims 1 to 8; or
The method of displaying a CTA image as claimed in any one of claims 9 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210118222.8A CN114419181A (en) | 2022-02-08 | 2022-02-08 | CTA image reconstruction method and device, display method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210118222.8A CN114419181A (en) | 2022-02-08 | 2022-02-08 | CTA image reconstruction method and device, display method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114419181A true CN114419181A (en) | 2022-04-29 |
Family
ID=81279820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210118222.8A Pending CN114419181A (en) | 2022-02-08 | 2022-02-08 | CTA image reconstruction method and device, display method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114419181A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926434A (en) * | 2022-05-19 | 2022-08-19 | 沈阳东软智能医疗科技研究院有限公司 | Blood vessel bulge detection method and related equipment thereof |
| CN115100230A (en) * | 2022-08-24 | 2022-09-23 | 首都医科大学附属北京朝阳医院 | Artery and vein separation method and device based on blood vessel image, storage medium and terminal |
| CN115546159A (en) * | 2022-10-13 | 2022-12-30 | 数坤(上海)医疗科技有限公司 | Image processing method, device, equipment and storage medium |
| CN117557724A (en) * | 2023-11-15 | 2024-02-13 | 广东工业大学 | Head presentation method and system for brain surgery patient based on pose estimation |
-
2022
- 2022-02-08 CN CN202210118222.8A patent/CN114419181A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926434A (en) * | 2022-05-19 | 2022-08-19 | 沈阳东软智能医疗科技研究院有限公司 | Blood vessel bulge detection method and related equipment thereof |
| CN115100230A (en) * | 2022-08-24 | 2022-09-23 | 首都医科大学附属北京朝阳医院 | Artery and vein separation method and device based on blood vessel image, storage medium and terminal |
| CN115100230B (en) * | 2022-08-24 | 2023-02-28 | 首都医科大学附属北京朝阳医院 | Artery and vein separation method and device based on blood vessel image, storage medium and terminal |
| CN115546159A (en) * | 2022-10-13 | 2022-12-30 | 数坤(上海)医疗科技有限公司 | Image processing method, device, equipment and storage medium |
| CN115546159B (en) * | 2022-10-13 | 2023-07-25 | 数坤(上海)医疗科技有限公司 | Image processing method, device, equipment and storage medium |
| CN117557724A (en) * | 2023-11-15 | 2024-02-13 | 广东工业大学 | Head presentation method and system for brain surgery patient based on pose estimation |
| CN117557724B (en) * | 2023-11-15 | 2024-06-04 | 广东工业大学 | Head presentation method and system for brain surgery patient based on pose estimation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110934606B (en) | Cerebral apoplexy early-stage flat-scan CT image evaluation system and method and readable storage medium | |
| CN114419181A (en) | CTA image reconstruction method and device, display method and device | |
| CN105249922B (en) | Faultage image capture apparatus and faultage image image pickup method | |
| CN110599499B (en) | MRI image heart structure segmentation method based on multipath convolutional neural network | |
| JP5601378B2 (en) | Medical image processing device | |
| CN110506278A (en) | Target detection in latent space | |
| EP1345154A1 (en) | A method for encoding image pixels and method for processing images aimed at qualitative recognition of the object reproduced by one more image pixels | |
| CN104582567B (en) | Magnetic resonance imaging apparatus | |
| JPWO2011040473A1 (en) | Medical image processing method, apparatus, and program | |
| CN106846293B (en) | Image processing method and device | |
| CN108272434A (en) | The method and device that eye fundus image is handled | |
| CN108510493A (en) | Boundary alignment method, storage medium and the terminal of target object in medical image | |
| CN110236544B (en) | Stroke perfusion imaging lesion area detection system and method based on correlation coefficient | |
| CN111950388A (en) | Vulnerable plaque tracking and identifying system and method | |
| CN106780520A (en) | The extraction method of vertebra in a kind of MRI lumbar vertebraes image | |
| CN108335270A (en) | A kind of multiple image blood vessel feature recognition and the color coding approach of information fusion | |
| CN109726752A (en) | The dividing method and system of perfusion dynamic image based on time signal curve | |
| CN111091539A (en) | Network model training method, medical image processing method, device, medium and equipment | |
| CN114862799B (en) | Full-automatic brain volume segmentation method for FLAIR-MRI sequence | |
| EP3320520B1 (en) | Apparatus, system and method for assisting in providing a diagnosis of a medical condition of a mammal brain as well a computer readable medium comprising a program for carrying out the method | |
| CN114494132A (en) | Disease classification system based on deep learning and fiber bundle spatial statistical analysis | |
| CN112669439B (en) | Method for establishing intracranial angiography enhanced three-dimensional model based on transfer learning | |
| CN114723879A (en) | Full-automatic reconstruction method of human brain cone beam based on multi-dimensional cross-modal image fusion technology | |
| CN111563877A (en) | Medical image generation method and device, display method and storage medium | |
| CN114463304B (en) | Method for segmenting and labeling brain atlas and operation navigation system |
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 |