WO2021096118A2

WO2021096118A2 - Medical procedure history search method based on structured blood vessel branch information

Info

Publication number: WO2021096118A2
Application number: PCT/KR2020/015023
Authority: WO
Inventors: 권지훈; 김영학; 문영진; 이준구; 최재순
Original assignee: 울산대학교 산학협력단; 재단법인 아산사회복지재단
Priority date: 2019-11-12
Filing date: 2020-10-30
Publication date: 2021-05-20
Also published as: WO2021096118A3; KR20210057445A; KR102310740B1

Abstract

A medical procedure history search method may comprise the steps of: identifying, from a blood vessel image generated by capturing a subject to be examined, a branch point at which a blood vessel is branched and the branched blood vessel; generating target blood vessel structure data on the basis of the identified branch point and connection information of the branched blood vessel; searching for similar blood vessel structure data similar to the target blood vessel structure data, from a database that stores a plurality of blood vessel images and pieces of blood vessel structure data matching the plurality of blood vessel images, respectively; and providing procedure data mapped to the similar blood vessel structure data.

Description

Medical procedure history search method based on structured vascular branch information

Hereinafter, a technique for a method of searching a medical procedure history based on structured vascular branch information is provided.

In the treatment of cardiovascular, cerebrovascular, and peripheral blood vessels, an interventional procedure in which a stent is inserted using a catheter is widely spread. The blood vessels have a branched structure that is distinguished from each other for each person to be treated, and the location and shape of the lesion may also have various forms for each person to be treated. Accordingly, despite the existence of basic procedure guidelines, there was no choice but to be highly dependent on the experience of the operator in planning and performing the procedure in response to various disease patterns. Accordingly, there is a need for a method capable of easily searching by structuring and dataizing characteristics extracted from a blood vessel or a lesion of a blood vessel to be treated.

In the medical procedure history search method according to an embodiment, the step of identifying a branch point at which a blood vessel is branched and a branched blood vessel from a blood vessel image generated by photographing a subject for examination, and connection information of the identified branch point and the branched blood vessel Generating target blood vessel structure data based on, searching for similar blood vessel structure data similar to the target blood vessel structure data from a database storing the plurality of blood vessel images and blood vessel structure data matched to each of the plurality of blood vessel images And providing procedure data mapped to the similar blood vessel structure data.

According to one side, generating the target blood vessel structure data includes generating node data indicating the branch point and edge data indicating the branched blood vessel, and sequentially from the blood vessel introduction part in the image. And generating the target blood vessel structure data in a tree structure by connecting node data and edge data.

The node data may include data on the number of blood vessels branched at a corresponding branch point and an angle between the branched blood vessels, and the edge data may include data on blood vessels between two distinct branch points. .

In addition, generating the target blood vessel structure data may include generating the target blood vessel structure data further including lesion information on at least one of a branch point and a blood vessel at which a lesion has occurred in the blood vessel.

The searching for the similar blood vessel structure data of the search method according to an embodiment includes calculating a similarity between the target blood vessel structure data and the blood vessel structure data stored in the database, and the blood vessel structure data in which the calculated similarity exceeds a threshold value. It may include the step of selecting as the similar blood vessel structure data.

According to an embodiment, the searching of the similar blood vessel structure data includes calculating a similarity between the target blood vessel structure data and the blood vessel structure data stored in the database, and the calculated blood vessel structure data having the highest similarity as similar blood vessel structure data. It may include the step of selecting as.

In addition, searching for the similar blood vessel structure data may include calculating a similarity based on the target blood vessel structure data and lesion information and blood vessel structure of the blood vessel structure data.

The lesion information may include at least one of a constriction component, a length of the lesion, and a size of the lesion.

The searching of the similar blood vessel structure data may include calculating the similarity by setting a weight according to a degree adjacent to a point corresponding to the lesion information in the data of the branch point and the branched blood vessel.

The step of generating the target blood vessel structure data includes storing digitized information on the branch point and the branched blood vessel as branch point information and branched blood vessel information of the target blood vessel data, and the similar blood vessel structure data The searching may include comparing digitized branch point information and branched blood vessel information of the blood vessel structure data stored in the database with branch point information and branched blood vessel information of the target blood vessel structure data, and the database based on the comparison result. It may include the step of retrieving the similar blood vessel structure data from.

1 is a flowchart illustrating a procedure data search method according to an embodiment.

2 is a flowchart illustrating generating target blood vessel structure data from a blood vessel image according to an embodiment.

3 is a flowchart illustrating providing procedure data by searching for similar blood vessel structure data similar to target blood vessel structure data according to an exemplary embodiment.

4 is a table showing numerical data to search for similar blood vessel structure data according to an embodiment.

5 is a block diagram illustrating a procedure data retrieval system according to an embodiment.

Specific structural or functional descriptions of the embodiments are disclosed for the purpose of illustration only, and may be changed and implemented in various forms. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical idea.

Although terms such as first or second may be used to describe various components, these terms should be interpreted only for the purpose of distinguishing one component from other components. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

When a component is referred to as being "connected" to another component, it is to be understood that it may be directly connected or connected to the other component, but other components may exist in the middle.

Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present specification, terms such as "comprise" or "have" are intended to designate that the described feature, number, step, action, component, part, or combination thereof is present, but one or more other features or numbers, It is to be understood that the presence or addition of steps, actions, components, parts, or combinations thereof, does not preclude the possibility of preliminary exclusion.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the relevant technical field. Terms as defined in a commonly used dictionary should be construed as having a meaning consistent with the meaning of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in the present specification. Does not. Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. The same reference numerals shown in each drawing indicate the same members.

In step 110, the processor may identify a branch point at which a blood vessel is branched and a branched blood vessel from a blood vessel image generated by photographing a subject for examination. The blood vessel image may be an image taken by angiography, in which an identifiable contrast agent is injected into a blood vessel during X-ray imaging, and the shape of a blood vessel is identified when X-ray is taken. The blood vessel may be branched into at least two branches at the branch point, and the branched blood vessel may include a main branch blood vessel and at least one side branch blood vessel based on the thickness of the blood vessel. For example, the main branch blood vessel may mean the thickest blood vessel among the plurality of branch blood vessels.

The processor may identify a blood vessel based on a gray scale level of pixels from an image generated in black and white, and identify a point at which the blood vessel diverges from the identified blood vessel as a branch point.

In step 120, the processor may generate target blood vessel structure data based on the identified branch point and connection information of the branched blood vessel. According to an embodiment, the processor may generate node data indicating a branch point and edge data indicating a branched blood vessel. Since the branched blood vessels are connected to two different branch points, the processor can connect two node data to one edge data, and the node data can map edge data corresponding to the number of branched blood vessels. . The connection information of the branch point and the branched blood vessel may be information indicating a connection relationship between the branch point and the branched blood vessel, and may be generated using edge data mapped to the node data and node data to which the edge data is connected. . The processor may structure the blood vessel data based on the connection information. For example, the processor may generate a tree structure in which nodes and edges are connected using a branch point closest to the blood vessel introduction part as a root node. The root node may store information on the uppermost blood vessel that becomes the stem of the branched blood vessels before the blood vessels in the image diverge. The information on the uppermost blood vessel may include information on the thickness of the uppermost blood vessel.

In step 130, the processor may search for similar blood vessel structure data similar to the target blood vessel structure data from a database storing the plurality of blood vessel images and blood vessel structure data matched to each of the plurality of blood vessel images. The database according to an embodiment may be included in the medical procedure history search system, but is not limited thereto, and the database may be included in an external device. When the database is included in the external device, the system may communicate with the external device to receive blood vessel structure data of the database. The processor may calculate a similarity between the target blood vessel structure data and the blood vessel structure data, and according to an embodiment, select the blood vessel structure data whose calculated similarity exceeds a threshold value as the similar blood vessel structure data. According to another embodiment, the processor may select the blood vessel structure data having the highest similarity as the similar blood vessel structure data.

In step 140, the processor may provide procedure data mapped to the similar blood vessel structure data. The procedure data may be procedure information performed in a procedure in which similar vascular structure data was generated, and may include, for example, drugs used to treat a lesion during vascular intervention, a stent device, a thickness of a guide wire, and the like. The procedure data is not limited thereto, and may be all procedure information related to the procedure, and may include a procedure result and a state of a person to be treated after the procedure.

The processor may receive the blood vessel image 210 generated by the external image 210 photographing unit, and identify a blood vessel including the branch point 211 and the branched blood vessel 212 from the blood vessel image 210. When the blood vessel image 210 is generated as a black and white image 210, a blood vessel may be identified from the blood vessel image 210 based on a gray scale level. When a contrast agent is injected into a blood vessel, the blood vessel may be displayed in black during X-ray imaging, and the processor may identify a portion of the image 210 displayed in black as a blood vessel. The gray scale is configured such that the level is divided according to the brightness, and the level is gradually increased from completely white to completely black. When the grayscale level sensed from the image 210 is equal to or higher than a predetermined grayscale level, the processor may identify it as a blood vessel.

According to another embodiment, the processor may identify a blood vessel boundary based on a difference in grayscale levels between pixels. The processor may calculate a grayscale level gradient value or a difference value between pixels, and when the gradient value or difference value is large, it may be identified as a blood vessel boundary. The processor may extract the blood vessel portion based on the identified blood vessel boundary.

When a blood vessel is extracted from the blood vessel image, the processor may identify a branch point and a branched blood vessel from the extracted blood vessel 220. The processor may identify a branch point while scanning along the blood vessel from the introduction of the blood vessel to the end of the blood vessel, and identify a blood vessel branching from the identified branch point. Since the branch point includes a blood vessel extending from the blood vessel introduction part to the end and two or more blood vessels branching from the branch point, the branch point may be a location in the blood vessel where the blood vessel branches into at least three or more blood vessel branches. The processor may scan a blood vessel and identify a point where three or more blood vessel branches are formed as a branch point, and identify a blood vessel connecting the branch point and other branch points.

According to an embodiment, the processor may identify

points

213 and 223 where lesions occur in the blood vessel from the blood vessel image. As the processor scans along the blood vessel, a point that is less than the critical ratio compared to the thickness of the blood vessel may be identified as the

point

213 and 223 where the lesion occurs in the blood vessel. According to another embodiment, when the thickness of the blood vessel is less than the critical thickness, the processor may identify the corresponding portion as the

points

213 and 223 where the lesion has occurred in the blood vessel. In addition to the method for the processor to identify the lesion area (213, 223) while scanning along the blood vessel, the processor detects an input designated by the user as the point (213, 223) where the lesion occurs, It can be judged as a part.

The processor may extract only the portion 230 identified as a blood vessel from the blood vessel image, and may plot a blood vessel indicated by a curved line as a straight line having a directionality. According to an embodiment, the processor may simply generate the schematic structure 240 as target blood vessel structure data. In addition, the processor may convert a blood vessel structure including a branch point and a branched blood vessel into data, and may create a connection relationship between the branch point and the branched blood vessel based on the connection information of the branch point and the branched blood vessel, and the branch point By generating node data indicating the node data and edge data indicating the branched blood vessel, target blood vessel structure data including the node data and the edge data may be generated.

According to an embodiment, the node data may include data on the number of blood vessels branched at the branch point and the angle between the branched blood vessels, and the edge data is data on blood vessels between two distinct branch points. It may include. For example, the edge data may include a distance between two branch points indicating a blood vessel thickness and a blood vessel length.

The lesion information may be stored in node data or edge data corresponding to at least one of a branch point where a lesion occurs and a branched blood vessel. The lesion information may be information to be compared with a previous procedure stored in a database to treat the lesion. Illustratively, the lesion information may include at least one of a constriction component, a length of the lesion, and a size of the lesion.

The processor may generate the target blood vessel structure data 320 from the blood vessel image 310 according to the embodiments described above with reference to FIG. 2. The processor may search for similar blood vessel structure data similar to the target blood vessel structure data 320 from the database 330 storing the plurality of blood vessel structure data 331. Each of the plurality of blood vessel structure data 331 may be mapped to at least one of the blood vessel image and procedure data 332 and stored in the database 330.

The processor may calculate the similarity between the target blood vessel structure data 320 and the plurality of blood vessel structure data 331, and select the similar blood vessel structure data 341 according to the calculated similarity. According to an embodiment, when the target blood vessel structure data 320 is schematically generated as a tree-structured graph diagram, the processor may compare the plurality of schematic blood vessel structure data 331 with the target blood vessel structure data 320. . The processor may compare the target blood vessel structure data 320 and the plurality of blood vessel structure data 331 on a pixel or patch basis.

According to an embodiment, the processor may calculate a similarity based on the lesion information and the blood vessel structure of the target blood vessel structure data 320 and the blood vessel structure data 331. A system for providing a medical procedure history is to provide similar history data and procedure information related to a lesion treatment procedure in order to treat a lesion, and the similarity may be calculated by placing more weight on the lesion location of the subject and the adjacent vascular structure. That is, in the case where the lesion location is located closer to the end of the blood vessel than the blood vessel introduction part in the blood vessel image, the similarity may be calculated focusing on the vascular structure around the lesion location rather than the blood vessel introduction part. The processor may place the greatest weight on the node and edge data closest to the lesion location, and the weight decreases as the distance increases from the lesion location to the end of the blood vessel or the introduction of the blood vessel, so that the weight size can be inversely proportional to the distance from the lesion location.

The processor may determine the similar blood vessel structure data 341 according to the calculated similarity among the plurality of blood vessel structure data 331, and provide the procedure data 342 mapped to the similar blood vessel structure data 341 to the operator or the subject. I can.

According to an embodiment, the processor may store information on the digitized branch point and the branched blood vessel as branch point information and branched blood vessel information of target blood vessel data. The branch point information may be node data, and the branched blood vessel information may be edge data. The branch point information may include the number of branches generated at the branch point, and the branched blood vessel information may include whether or not there is a lesion in the branched blood vessel, a vessel thickness, a blood vessel length, a blood vessel level, and the like. The blood vessel level is a value indicating how far away from the blood vessel introduction part, and may correspond to the number of nodes between the highest root node and the branched blood vessel. For example, the blood vessel level of the blood vessel immediately below the highest root node may be a level of 0, but the blood vessel level is not limited thereto, and may be a level calculated to distinguish relative positions between branched blood vessels. When there is a lesion in the branched blood vessel, the processor may store the length of the lesion, the blood vessel level at which the lesion is located, and the thickness and length of the corresponding blood vessel as lesion information in at least one of edge data and node data.

The processor may compare the digitized branch point information and branched blood vessel information of the plurality of blood vessel structure data with the branch point information and blood vessel information of the target blood vessel data. The branch point information and the branched blood vessel information are numerical information, and according to an embodiment, the processor may compare the blood vessel structure data and the target blood vessel structure data with a difference between corresponding values between the blood vessel structure data and the target blood vessel structure data.

The processor may search for similar blood vessel structure data from the database based on the comparison result. The comparison result may be a degree of similarity, and the degree of similarity may be a sum of the difference between the corresponding value of the blood vessel structure data and the target blood vessel structure data, and the difference between the corresponding data of the two pieces of information to be compared is squared and summed. It can be a value taken from the square root. Specifically, it can be calculated by Equation 1.

In Equation 1, a ₁ , a _{2 and} a ₃ may be data on information to be compared, and b ₁ , b _{2 and} b ₃ may be data on information to be compared.

According to an embodiment, when a lesion occurs in a branched blood vessel, the similarity may be calculated based on node data and quantified lesion information digitized at the upper branch point and the lower branch point connected to the blood vessel. Exemplarily, at least one of the branch point information and the blood vessel information of the target blood vessel data may include the number of blood vessels branching from branch point 1 (a ₁ ) and the number of blood vessels branching from branch point 2 (a ₂ ), and , The lesion information may include at least one of _{a lesion length (a 3} ) and a blood vessel level (a _{4) at which the lesion is located.} The node data and lesion information are not limited thereto, and may include all information used to determine the similarity by quantifying node data, edge data, and lesion information.

According to FIG. 4, the number of blood vessels branching from branch point 1 and branch point 2 adjacent to the lesion may be 2 and 3, respectively, the length of the lesion may be 2 mm, and the blood vessel level at which the lesion is located may be 2 levels. Exemplarily, the blood vessel structure data stored in the database may have a value as shown in FIG. 4, and the processor calculates similarities for each of the blood vessel structure data to be compared with the target blood vessel structure data to be compared through Equation 1 can do.

The degree of similarity between the target blood vessel structure data and the blood vessel structure data 1 to 4 is shown in Equation 2.

Similarity 1 to 4 denote similarity values respectively corresponding to blood vessel structure data 1 to 4, and when Equation 1 is applied, it can be seen that the blood vessel structure corresponding to the blood vessel structure data 2 is most similar to the target blood vessel structure, and the processor May determine the blood vessel structure data 2 as similar blood vessel structure data.

According to an embodiment, the processor may calculate the similarity by assigning weights according to Equation 3. The upper branch point is a branch point that is closer to the blood vessel introduction part than the lower branch point.Since surgical devices such as guide wire, catheter, and stent are inserted through the blood vessel introduction part, the processor uses data for the upper branch point compared to the data for the lower branch point. The similarity can be calculated by giving a greater weight to.

W _1, W _2, and W ₃ are weights and may be set differently according to the importance of data that is a comparison criterion.

The system may include a processor and a memory, and the memory may manage a database storing a plurality of blood vessel images and blood vessel structure data matched to each of the plurality of blood vessel images.

The processor generates target blood vessel structure data by identifying branch points and branched blood vessels from a blood vessel image generated by photographing a subject for examination by the imaging unit, searching for similar blood vessel structure data similar to the target blood vessel structure data from the database, and searching for similar blood vessel structure data. Procedure data mapped to structural data can be provided.

The embodiments described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices, methods, and components described in the embodiments are, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. Further, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to operate as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or, to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment 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 specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

As described above, although the embodiments have been described by the limited drawings, a person of ordinary skill in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order from the described method, and/or components such as systems, structures, devices, circuits, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Claims

In the medical procedure history search method,

Identifying a branch point where a blood vessel is branched and a branched blood vessel from a blood vessel image generated by photographing a subject for examination;

Generating target blood vessel structure data based on the identified branch points and connection information of the branched blood vessels;

Searching for similar blood vessel structure data similar to the target blood vessel structure data from a database storing a plurality of blood vessel images and blood vessel structure data matched to each of the plurality of blood vessel images; And

Providing procedure data mapped to the similar blood vessel structure data

Medical procedure history search method comprising a.
The method of claim 1,

Generating the target blood vessel structure data,

The target blood vessel in a tree structure by generating node data indicating the branch point and edge data indicating the branched blood vessel, and sequentially connecting the node data and edge data from the blood vessel introduction part in the image. Steps to generate structural data

Medical procedure history search method comprising a.
The method of claim 2,

The node data includes data on the number of blood vessels branched at a corresponding branch point and an angle between the branched blood vessels,

The edge data is a medical procedure history search method including data on blood vessels between two distinct branch points.
The method of claim 1,

Generating the target blood vessel structure data,

Generating the target blood vessel structure data by mapping lesion information to at least one of a branch point and a branched blood vessel based on the location of the lesion occurring in the blood vessel

Medical procedure history search method comprising a.
The method of claim 1,

The step of searching for the similar blood vessel structure data,

Calculating a similarity between the target blood vessel structure data and the blood vessel structure data stored in the database; And

Selecting the blood vessel structure data whose calculated similarity exceeds a threshold value as the similar blood vessel structure data

Medical procedure history search method comprising a.
The method of claim 1,

The step of searching for the similar blood vessel structure data,

Calculating a similarity between the target blood vessel structure data and the blood vessel structure data stored in the database; And

Selecting the calculated blood vessel structure data with the highest similarity as the similar blood vessel structure data

Medical procedure history search method comprising a.
The method of claim 1,

The step of searching for the similar blood vessel structure data,

Calculating a similarity based on the target blood vessel structure data and lesion information and blood vessel structure of the blood vessel structure data

Medical procedure history search method comprising a.
The method according to any one of claims 4 and 7,

The lesion information,

Comprising at least one of the constriction component, the length of the lesion, and the size of the lesion.

How to search medical procedure history.
The method of claim 7,

The step of searching for the similar blood vessel structure data,

Calculating the similarity by applying a weight according to the degree to which the point corresponding to the lesion information is adjacent to the branch point and the branched blood vessel data

Medical procedure history search method comprising a.
The method of claim 1,

Generating the target blood vessel structure data,

Storing the digitized branch point and branched blood vessel information as branch point information and branched blood vessel information of the target blood vessel data

Including,

The step of searching for the similar blood vessel structure data,

Comparing digitized branch point information and branched blood vessel information of the blood vessel structure data stored in the database with branch point information and branched blood vessel information of the target blood vessel structure data based on a Euclidean distance similarity; And

Retrieving the similar blood vessel structure data from the database based on the comparison result

Medical procedure history search method comprising a.
A computer-readable recording medium storing one or more computer programs including instructions for performing the method of claim 1.
In the medical procedure history search system,

A memory for managing a database storing a plurality of blood vessel images and blood vessel structure data matched to each of the plurality of blood vessel images;

To generate target blood vessel structure data by identifying a branch point and a blood vessel branching from the branch point from a blood vessel image generated by photographing a subject to be examined, search for similar blood vessel structure data similar to the target blood vessel structure data from the database, and the A processor that provides procedure data mapped to the similar blood vessel structure data;

Medical procedure history search system comprising a.