KR101971764B1 - Method and device for analizing blood vessel using blood vessel image - Google Patents

Abstract

A blood vessel analysis method and apparatus capable of extracting an inner wall of a blood vessel and a stent from an angiographic image and analyzing the degree of false attachment of the stent and the thickness of the neointima is disclosed. A method for analyzing a blood vessel includes the steps of: determining a stent candidate group including a local maximum brightness value in an angiomatographic image of a target blood vessel; Extracting first characteristic information on the candidate stent using the angiogram of the target vessel; And detecting a target stent in the stent candidate group using the first characteristic information and the second characteristic information on the reference stent generated from the angiography image.

Description

Technical Field [0001] The present invention relates to a method and apparatus for analyzing blood vessels using an angiographic image,

The present invention relates to a method and an apparatus for analyzing a blood vessel using an angiographic image, and more particularly, to a method and apparatus for analyzing a blood vessel by analyzing a blood vessel wall and a stent, Analysis method and apparatus.

When inserting a stent into a blood vessel, it is important to grasp whether the stent is obstructing the outer wall of the blood vessel. And, neoplastic endothelial cells grow on the stent strut after the procedure, and the overgrowth of these endothelial cells can narrow the blood vessels again.

Therefore, it is necessary to confirm whether the stent is well stenosed after the procedure, the thickness of the neointimal membrane due to the growth of the strut and endothelial cells, and various clinical results according to the patient's condition, structure of the stent, At this time, an angiographic image is used. X-ray angiography, intravascular ultrasound, and IV-OCT (angiographic coherence tomography) are used as an angiography technique.

However, the process of calculating the thickness of the stent, the inner wall of the vessel, and the neointima using current angiographic images is mostly performed manually. Therefore, it is necessary to conduct research to analyze blood vessels automatically using an angiographic image.

Related Prior Art Korean Patent Publication No. 2014-0092102 is available.

The present invention provides a blood vessel analysis method and apparatus capable of extracting an inner wall of a blood vessel and a stent from an angiogram, analyzing the degree of false attachment of the stent and the thickness of the neointima.

According to an aspect of the present invention, there is provided a method for determining a stent candidate group including a local maximum brightness value in an angiographic CT image of a target blood vessel, Extracting first characteristic information on the candidate stent using the angiogram of the target vessel; And detecting a target stent in the stent candidate group using the first characteristic information and the second characteristic information on the reference stent generated from the angiomatographic image to provide a blood vessel analysis method using the angiographic image .

According to another aspect of the present invention, there is provided an image processing apparatus including an image input unit receiving an angiographic image of a target blood vessel; A candidate group determining unit for determining, in an angiographic image of the target blood vessel, a stent candidate group including a local maximum brightness value; A characteristic information extracting unit for extracting first characteristic information of the stent candidate group by using an angiomatography image of the target blood vessel; And a stent detecting unit for detecting a target stent in the stent candidate group using the first characteristic information and the second characteristic information on the reference stent generated from the angiomatographic image, to provide.

According to the present invention, it is possible to quickly and accurately detect the boundary line of the inner wall of the blood vessel, the target stent, and the neointima using an angiogram, and the results of the extraction can be used to estimate the thickness of the new intima, Information can be provided.

According to the present invention, it is possible to assist a doctor in diagnosis by detecting various clinical indices (blood vessel wall, target stent, neointimal boundary, neointimal thickness, stent projecting distance and erroneous attachment distance) You can increase your understanding.

1 is a view for explaining a blood vessel analyzing apparatus using an angiographic image according to an embodiment of the present invention.
2 is a diagram for explaining a data processing unit according to an embodiment of the present invention.
3 is a view showing an angiotraping image and a polar coordinate transformed image.
4 is a view for explaining vascular inner wall extraction according to the present invention.
5 is a view for explaining a stent candidate group according to the present invention.
6 is a diagram showing a line profile and an A-line profile for a reference stent.
FIG. 7 is a view for explaining the protruding distance and the erroneous attachment distance of the stent and the thickness of the neointima; FIG.
8 is a view for explaining a blood vessel analysis method using an angiographic image according to an embodiment of the present invention.
Figure 9 is a diagram illustrating a multi-layer artificial neural network for stent detection.
FIG. 10 is a graph showing the results of the correlation coefficient measurement and the Blend-Althman analysis of the calculated protrusion distance and the neointimal lining thickness of the stent according to the present invention, the manually calculated stent's protruding distance and the neointimal lining thickness;
11 is a diagram showing the correlation coefficient measurement and the Blend-Althman analysis result on the protrusion distance and the neointimal matter thickness of a relatively small level of the stent.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a blood vessel analyzing apparatus using an angiographic image according to an embodiment of the present invention.

Referring to FIG. 1, the apparatus for analyzing blood vessels according to the present invention includes an image input unit 110, a data processing unit 120, and a data output unit 130.

The image input unit 110 receives an angiographic image of a target blood vessel. An angiography image may be, for example, an intravascular ultrasound image, an intravascular optical tomography image, or the like. Alternatively, the image input unit 110 may be, for example, a catheter, and may be directly inserted into a target blood vessel to receive an angiography image.

The data processing unit 120 extracts a target stent inserted into the inner wall of the blood vessel and the target blood vessel using an angiography image of the target blood vessel. According to the embodiment, the data processing unit 120 can extract the boundary line of the neointima produced by the stent, and calculate the neointimal thickness of the neointima using the extracted inner wall of the blood vessel, the target stent, , And the protrusion distance and the malapposition distance of the stent can be calculated.

The data output unit 130 outputs the processing result of the data processing unit 120 and can output the processing result to the inputted blood vessel CT image. For example, the data output unit 130 may display the inner wall of the blood vessel, the target stent, etc. extracted in the blood vessel tomographic image.

According to the present invention, it is possible to quickly and accurately detect the boundary line of the inner wall of the blood vessel, the target stent, and the neointima using an angiogram, and the results of the extraction can be used to estimate the thickness of the new intima, Information can be provided.

According to the present invention, it is possible to assist a doctor in diagnosis by detecting various clinical indices (blood vessel wall, target stent, neointimal boundary, neointimal thickness, stent projecting distance and erroneous attachment distance) You can increase your understanding.

2 is a diagram for explaining a data processing unit 120 according to an embodiment of the present invention. FIG. 3 is a view showing an angiography image and a polar coordinate transformation image, and FIG. 4 is a view for explaining an inner wall extraction of a blood vessel according to the present invention. 5 is a view for explaining a stent candidate group according to the present invention. 6 is a diagram showing a line profile and an A-line profile for a reference stent.

2, the data processing unit 120 includes a preprocessing unit 210, an inner blood vessel wall extracting unit 220, a candidate group determining unit 230, a characteristic information extracting unit 240, a stent detecting unit 250, 260). The components of the data processing unit 120 may be variously configured according to the clinical indices to be detected. First, the process of detecting the inner wall of the blood vessel of the data processing unit 120 will be described, and the process of detecting the stent and other clinical indicators will be described.

<Intravenous wall detection>

The blood vessel CT image may be expressed by the brightness of each pixel. The preprocessing unit 210 performs a blood vessel CT scan on the target blood vessel so that a reflection profile (A-line) in the depth direction of the blood vessel, Perform polar coordinate (r, θ) conversion on the image. In this case, the preprocessing unit 210 may perform polar coordinate conversion after performing pre-processing such as Gaussian low-pass filtering to reduce noise of the angiographic imaging image.

For example, the angiomatography image as shown in FIG. 3 (a) can be transformed into an image as shown in FIG. 3 (b) through polar coordinate conversion. In FIG. 3 (b), the depth direction (r) As shown in Fig.

The preprocessing unit 210 generates a first gradient image in the depth direction using the image subjected to the polar coordinate transformation, and additionally generates a second gradient image. The primary slope image G _r and the secondary slope image G _rr can be generated through Equation (1).

는 극좌표 변환이 수행된 영상을 나타내며, 편미분을 통해 경사 영상이 얻어질 수 있다. 편미분에 의해 밝기 값이 급격히 변환되는 영역이 검출될 수 있는데, 예를 들어 에지(edge) 영역이 검출될 수 있다. 전처리부(210)는 에지 특성을 나타내는 혈관 내벽 및 스텐트를 추출하기 위해 1차 및 2차 경사 영상을 생성한다.here,

Represents an image on which polar coordinate conversion is performed, and an inclined image can be obtained through partial derivatives. An area in which the brightness value is rapidly changed by the partial derivative can be detected, for example, an edge area can be detected. The preprocessing unit 210 generates primary and secondary gradient images for extracting the inner wall and the stent showing edge characteristics.

The preprocessing unit 210 can support accurate detection by removing a catheter or a guide wire portion which can be taken together during the angiography from the primary and secondary gradient images.

The preprocessing unit 210 may additionally support various functions or selectively provide some of the functions described above, in addition to the functions described above.

The inner vessel wall extracting unit 220 determines the inner wall of the blood vessel to indicate a predetermined brightness value in the polar coordinate transformed image, and can use the first gradient image. In addition, since the border of the new intimal is also a kind of inner wall of the blood vessel, the inner wall of the blood vessel extracting unit 220 can determine the boundary of the inner wall of the new blood vessel.

More specifically, the inner blood vessel wall extracting unit 220 may determine a portion of the blood vessel to have a brightness value corresponding to a predetermined ratio with respect to a maximum brightness value of the blood vessel CT image. The predetermined ratio may be variously set according to the embodiment, for example, 20% of the maximum brightness value. Since the brightness value of the inner wall of the blood vessel is smaller than the brightness of the stent, the inner wall of the blood vessel wall extracting unit 220 ) Determines the portion of the blood vessel that is darker than the maximum brightness value of the angiographic image as the inner wall of the blood vessel.

In this case, the inner blood vessel wall extracting unit 220 can determine the inner wall of the blood vessel by using a portion indicating the predetermined brightness value in the polar coordinate transformed image without using the first gradient image. However, in order to more accurately extract the inner wall of the blood vessel, By using the car gradient image, it is possible to remove artifacts that may exist in the angiogram image.

For example, the inner blood vessel wall extracting unit 220 may generate an image as shown in FIG. 4 (b) by taking only a value indicating a negative value equal to or greater than a threshold value in the first gradient image. FIG. 4B is an image generated from the primary slope image of the polar coordinate converted angiotensography image shown in FIG. 4A, and includes edge information because it is a transformed form of the primary slope image. In FIG. 4 (b), the region through which the red dotted line passes is a temporary lumen contour, which is an edge portion in the polar coordinate transformed angiogram when compared with FIG. 4 (a). The inner vessel wall extracting unit 220 finally determines the area indicated by yellow in consideration of the distance and the relative angle based on the _largest temporary vessel inner wall candidate group C _largest among the temporary vessel inner wall candidate groups determined according to the edge information, It is decided as candidate group.

The white portion of Fig. 4 (b) is excluded from the inner wall candidate group because it is distant from the center of C _largest . Eventually, through the yellow region of Fig. 4 (b) , result of lumen contour detection) can be extracted.

< Stent  Detection>

The candidate group determining unit 230 determines an area including a local maximum intensity as a stent candidate group in an angiogram of the target blood vessel. The candidate group determination unit 230 may detect an area indicating the maximum local brightness value in the angiomatography image using the secondary gradient image described above as an embodiment. As described above, since the region where the stent is located is highly likely to exhibit the maximum brightness value due to the nature of the metal material, and the second gradient image includes the local maximum value information, the candidate group determination unit 230 determines The stent candidate group representing the maximum local brightness value of the angiogram can be determined.

In the image shown in FIG. 5, a green line represents a stent candidate group representing a local maximum brightness value obtained through a secondary oblique image, and a red dot represents a median point of a region representing a maximum local brightness value. As an example, in Fig. 4 and Fig. 5, an area including a local maximum value protruding from the inner wall of the vessel can be detected as a target stent.

The characteristic information extracting unit 240 extracts the first characteristic information on the candidate stent group by using the angiomatography image of the target blood vessel. Then, the stent detector 250 extracts the target stent from the stent candidate group using the first characteristic information and the second characteristic information on the reference stent generated from the angiography image.

The characteristic information may include at least one of statistical features and geometrical characteristics.

The statistical characteristic information represents characterization information about a stent which can be obtained literally, and may include statistical characteristic information on an angiographic image (OCT Intensity Image) and statistical characteristic information on a gradient image . Statistical characteristic information on the reference stent can be obtained by statistically analyzing the characteristics of the stent in the angiogram and the gradient image. And geometry information such as the length can also be obtained through analysis of the angiography image.

That is, the stent detector 250 extracts first characteristic information on the stent candidate group using the angiogram and the gradient image, compares the second characteristic information on the reference stent with the first characteristic information, An area showing characteristics similar to the second characteristic information can be extracted by the target stent. At this time, the polar coordinate transformation image of the angiomatographic image can be used for extracting the characteristic information.

The statistical characteristic information and the geometric characteristic information may be the same as [Table 1] as an embodiment, and may be variously set according to the embodiment.

In one embodiment, the statistical characteristic information and the geometric characteristic information for the reference stent and the candidate for the stent can be obtained from the brightness values of the polar coordinate transformed image and the gradient image. The brightness values of the polar coordinate transformed image and the gradient image with respect to the reference stent can be expressed by a line profile as shown in Figs. 6 (a) and 6 (b). 6 (a) shows a line profile (brightness value, intensity, amplitude) along a polar angle θ (horizontal axis in a polar coordinate transformed image) Line profile (brightness value intensity) according to the polar coordinate r (depth, vertical axis in the polar coordinate converted image) of the red point. Similarly, brightness values of the polar coordinate transformed image and the gradient image with respect to the stent candidate group can be expressed as shown in FIG.

Referring to [Table 1] and FIG. 6, the characteristic information for the reference stent will be described in detail. The statistical characteristic information for the angiography image of the reference stent can be obtained from the profile f _n in FIG. 6 (a) Intensity intensity, median intensity, mean intensity, intensity variance, intensity coefficient of variance, intensity skewness, And a brightness kurtosis value.

The statistical characteristic information of the second gradient image of the reference stent can be obtained from the G _rr profile of FIG. 6 (a), and the maximum amplitude, the medial amplitude, And may include at least one of Amplitude, Amplitude Variance, Amplitude Coefficient of Variance, Amplitude Skewness, and Amplitude Kurtosis.

The geometric characteristic information of the reference stent for the angiogram may include at least one of the relationship between the stent length, the first brightness value, and the second brightness value of the stent according to the brightness value in the angiogram image can do. In one embodiment, the first and second brightness values may be selected from among a maximum brightness value, a half maximum brightness value, a brightness value that is 1/5, and a brightness value at the stent end.

Referring to FIGS. 3 and 6, the length of the stent may correspond to the length of the stent in the angiomatographic image as shown in FIG. 3 (a) Can be calculated.

)은 극좌표 변환된 영상에서의 스텐트 후보군을 구성하는 극좌표 (depth, angle)을 의미한다.Where L is the length of the stent in the angiogram, N is the number of stent candidates in the polar coordinate transformed image,

) Denotes a polar coordinate (depth, angle) constituting a stent candidate group in a polar coordinate transformed image.

As a relation information, a distance (W _{half ,} A Half Length), a maximum brightness value (M) and a distance between points representing a maximum brightness value (M) and a half brightness value (M / 2) 5 gray level distance between the representing point (a Fifth Length), the brightness value of the half (M / 2) the brightness average value (behind profile mean), the brightness value of the half between the ends of the profile (μ _behind) at a point that represents the ( M / 2) the in representing points brightness distribution value between the end of the profile _{(μ behind) (behind profile variance} ), the brightness value of the half (M / 2) the brightness variation of the (μ _behind) between the ends of the profile at a point that represents the A slope between a point indicating a maximum value of a coefficient COV, a maximum brightness value M and a half brightness value M / 2, a ratio of an average brightness value of the μ _behind zone to a maximum brightness value M Peak-to-Shadow Ratio).

The characteristic information for the candidate stent may also be extracted as the characteristic information for the reference stent.

As a result, the stent detecting unit 250 can detect the target stent using the first and second characteristic information.

< target Stent  Extrusion distance and Attachment  Distance, new intimal thickness>

The protruding distance and erroneous attachment distance of the target stent and the thickness of the new intimal lining can be defined as shown in Fig. Namely, when the inner wall 710 of the blood vessel, the boundary 720 of the neointima, and the target stent 730 are detected, the numerical operation unit 260 calculates the position of the target stent 730, the inner wall 710 of the blood vessel, 720 can be used to calculate the protruding distance PD of the target stent and the erroneous attachment distance MD and the thickness NT of the neointima.

The thickness of the target stent can be obtained from the specification information of the stent.

8 is a view for explaining a blood vessel analysis method using an angiographic image according to an embodiment of the present invention. Figure 9 is a diagram illustrating a multi-layer artificial neural network for stent detection. In FIG. 8, a blood vessel analysis method of the blood vessel analyzing apparatus described in FIG. 1 is described as an embodiment.

In the blood vessel analyzing apparatus according to the present invention, a stent candidate group including a local maximum brightness value is determined (S810) in an angiographic CT image of a target blood vessel, and an angiographic image of the target blood vessel is used to determine a stent candidate group And extracts the first characteristic information (S820).

Then, the vascular analysis apparatus detects the target stent in the stent candidate group using the first characteristic information and the second characteristic information on the reference stent generated from the angiomatographic image (S830). In one embodiment, the vascular analyzer may compare the first characteristic information with the second characteristic information, and may detect a stent showing similar characteristics or matching characteristics with the target stent in the stent candidate group, and uses an artificial neural network .

In one embodiment, the artificial neural network used in the present invention may be composed of an input layer L 1, a hidden layer L 2 and an output layer L 3, as shown in FIG. Artificial neural network is a technique that is widely used for deep learning recently. The weight of a connection line connecting nodes in training mode is adjusted. In the classification mode, true is true for input values. Or a false value (false).

In the present invention, the second characteristic information is used in the training mode, and the first characteristic information on the stent candidate group is input to the input layer in the classification mode. For the training of the artificial neural network, the second characteristic information selected from the characteristic information shown in [Table 1] can be used. Through repetition of the training and classification process, characteristic information with the best classification performance can be selected.

The first characteristic information is input to the input layer and is transmitted to the output layer via the hidden layer, and each node performs a predetermined operation using the weight value and the input value. Finally, the output layer may output a result of classifying the stent representing the first characteristic information, which is similar to the second characteristic information, to the target stent.

The number of nodes in the input layer can be determined according to the number of first characteristic information to be input. When characteristic information indicated by * in Table 1 is used as the first characteristic information, eleven nodes can be used . The number of hidden layers and the number of nodes in the hidden layer can be variously set according to an artificial neural network algorithm, and the nodes of the output layer can be determined according to finally classified values.

In summary, the vascular analyzer can detect the target stent using the first characteristic information as an input value for the artificial neural network trained through the second characteristic information.

According to an embodiment of the present invention, there is provided a blood vessel analyzing method comprising: performing polar coordinate transformation on an angiographic image of a target blood vessel; and performing a polar coordinate transformation on a blood vessel image using a first- May be determined as the boundary line between the inner wall of the blood vessel and the inner wall of the new intestine.

According to another embodiment of the present invention, there is provided a method for analyzing a blood vessel according to an embodiment of the present invention, which includes calculating a protrusion distance, an erroneous attachment distance, and a thickness of a neointimal lining of a target stent using the position of a target stent, the inner wall of a blood vessel, .

FIG. 10 is a graph showing the results of Bland-Altman analysis and measurement of the correlation coefficient between the protruding distance and the neointimal lining thickness of the stent calculated according to the present invention, the manually calculated stent's protruding distance and the neointimal lining thickness to be. And FIG. 11 is a diagram showing the correlation coefficient measurement and the Blend-Althman analysis result on the protrusion distance and the neointimal lining thickness of a relatively small level of the stent.

The manual calculation was performed by a cardiovascular physician and a cardiovascular OCT researcher (R1, R2) who are experts in the field, and the calculation result according to the present invention is a result calculated through the characteristic information marked with * in [Table 1]. As shown in FIGS. 10 and 11, it can be seen that the calculation result (Algorithm) according to the present invention has a very large correlation with the manual calculation result, and it can be confirmed that a large deviation-free calculation result is derived.

Table 2 shows the results of the stent detection by the experts R1 and R2 and the positive predictive value PPV and true positive rate TPR for the stent detection result Algorithm according to the present invention. ) Were positive in various environments depending on the presence of newborns (Uncovered, Covered), type of tissue around the stent (Fibrotic, Lipid, Calcification, Side-Branch, Thrombus, Arterial Dissection) Predictability and true positive rate.

As shown in [Table 2], the stent detection result according to the present invention shows a positive predictive value of 96.5% and a true positivity rate of 92.9% as compared with the manual detection result by an expert, and shows a very high accuracy.

The above-described technical features may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, the present invention has been described with reference to particular embodiments, such as specific elements, and specific embodiments and drawings. However, it should be understood that the present invention is not limited to the above- And various modifications and changes may be made thereto by those skilled in the art to which the present invention pertains. Accordingly, the spirit of the present invention should not be construed as being limited to the embodiments described, and all of the equivalents or equivalents of the claims, as well as the following claims, belong to the scope of the present invention .

Claims (15)

A blood vessel analyzing method using an angiographic image of a blood vessel analyzer,
Determining, in an angiographic image of the target vessel, a stent candidate group including a local maximum brightness value;
Extracting first characteristic information on the candidate stent using the angiogram of the target vessel; And
Detecting a target stent in the stent candidate group using the first characteristic information and second characteristic information on a reference stent generated from the angiomatographic image
The method comprising the steps of:
The method according to claim 1,
The first and second characteristic information
Statistical characteristic information, and geometric characteristic information.
Methods of blood vessel analysis using angiographic images.
3. The method of claim 2,
The statistical characteristic information
Statistical characteristic information on the angiogram image; And
The statistical characteristic information on the gradient image of the angiomatographic image
The method comprising the steps of:
The method of claim 3,
The statistical characteristic information
A brightness variation value, a brightness variation value, a brightness variance value, and a brightness kurtosis value, which are included in at least one of a maximum brightness value, a central brightness value, an average brightness value,
Methods of blood vessel analysis using angiographic images.
The method of claim 3,
The slope image
A second gradient image with respect to the depth direction of the image obtained by converting the angiographic image into the polar coordinate system
Methods of blood vessel analysis using angiographic images.
3. The method of claim 2,
The geometric property information
The geometric characteristic information for the angiographic imaging image,
The geometric property information
Information on the relationship between the stent length, the first brightness value of the stent, and the second brightness value according to the brightness value
Methods of blood vessel analysis using angiographic images.
The method according to claim 1,
The step of detecting a target stent in the candidate stent candidate
For the artificial neural network trained through the second characteristic information, using the first characteristic information as an input value to detect the target stent
Methods of blood vessel analysis using angiographic images.
The method according to claim 1,
Performing polar coordinate transformation on an angiomatographic image of a target vessel; And
A step of determining a portion indicating a predetermined brightness value as a boundary line of an inner vessel wall or a new inner membrane using a first gradient image with respect to a depth direction of the polar coordinate transformation image,
The method comprising the steps of:
9. The method of claim 8,
Calculating a protrusion distance, a malapposition distance, and a neointimal thickness of the target stent using the position of the target stent, the inner wall of the blood vessel, and the border of the inner wall of the new intestine,
Further comprising the steps of:
An image input unit receiving an angiomatographic image of a target blood vessel;
A candidate group determining unit for determining, in an angiographic image of the target blood vessel, a stent candidate group including a local maximum brightness value;
A characteristic information extracting unit for extracting first characteristic information of the stent candidate group by using an angiomatography image of the target blood vessel; And
A stent detector for detecting a target stent in the stent candidate group using the first characteristic information and the second characteristic information for the reference stent generated from the angiomatographic image,
And a blood vessel image analyzing device.
11. The method of claim 10,
The first and second characteristic information
Statistical characteristic information, and geometric characteristic information.
An apparatus for analyzing blood vessels using an angiographic image.
12. The method of claim 11,
The statistical characteristic information
A brightness variation value, a brightness variation value, a brightness variance value, and a brightness kurtosis value, which are included in at least one of a maximum brightness value, a central brightness value, an average brightness value,
An apparatus for analyzing blood vessels using an angiographic image.
12. The method of claim 11,
The geometric property information
The geometric characteristic information for the angiographic imaging image,
The geometric property information
Information on the relationship between the stent length, the first brightness value of the stent, and the second brightness value according to the brightness value
An apparatus for analyzing blood vessels using an angiographic image.
11. The method of claim 10,
The stent detecting unit
For the artificial neural network trained through the second characteristic information, using the first characteristic information as an input value to detect the target stent
An apparatus for analyzing blood vessels using an angiographic image.
11. The method of claim 10,
A preprocessing unit for performing polar coordinate transformation on an angiomatographic image of a target blood vessel;
An inner vessel wall extracting unit for determining a portion representing a preset brightness value as a boundary line of the inner vessel wall and the inner wall of the neonatal vessel using the first gradient image with respect to the depth direction of the polar coordinate transformation image; And
A numerical value calculating a protrusion distance and a malapposition distance of the target stent and a neointimal thickness of the new intimal lining using the position of the target stent, [0040]
Further comprising an angiographic image.

Images