KR102304420B1 - blood vessel age diagnosis apparatus, blood vessel age diagnosis method, and computer program for executing the method - Google Patents

Abstract

According to the present specification, the method comprising: receiving, by an apparatus for diagnosing a blood vessel age, an image obtained by photographing an object from an imaging apparatus; extracting, by the blood vessel age diagnosis apparatus, a three-dimensional binary blood vessel image from the image; extracting, by the blood vessel age diagnosis apparatus, blood vessel division regions for each anatomically divided region from the three-dimensional binary blood vessel image; extracting, by the blood vessel age diagnosis apparatus, a center line connecting center points of a first blood vessel section using the blood vessel division regions; calculating, by the blood vessel age diagnosis apparatus, a distortion value of a blood vessel based on the center line; and inferring, by the vascular age diagnosis apparatus, the vascular age of the subject based on the distortion value.

Description

A blood vessel age diagnosis apparatus, a blood vessel age diagnosis method, and a computer program for executing the method, and a computer program for executing the method

According to the present specification, an apparatus for diagnosing blood vessel age, a method for diagnosing blood vessel age, and a computer program for executing the method are provided.

Magnetic resonance imaging (MRI) is a device that uses a magnetic field to image an object, and it shows three-dimensional images of not only bones, but also discs, joints, nerve ligaments, heart, and cerebrovascular blood vessels from a desired angle. It is widely used for diagnosis. Magnetic resonance imaging has the advantage of obtaining various contrast ratios by adjusting various parameters, and using this, in clinical diagnosis, images of different contrast ratios are obtained for the same area for diagnosis. Korean Patent Laid-Open Publication No. 2009-0075644 discloses a magnetic resonance imaging apparatus that obtains a steady-state image of a patient by changing the spin phases of fat and water in a patient to generate a contrast ratio of the magnetic resonance image.
[Prior Literature]
WO 2017/047819 (published on March 23, 2017)

An embodiment of the present invention provides an apparatus, method, and computer program for diagnosing blood vessel age of an object based on an image of blood vessels, particularly cerebral blood vessels, of an object.

A method for diagnosing vascular age according to embodiments of the present invention includes: receiving, by an apparatus for diagnosing vascular age, an image obtained by photographing an object from an imaging apparatus; extracting, by the blood vessel age diagnosis apparatus, a three-dimensional binary blood vessel image from the image; extracting, by the blood vessel age diagnosis apparatus, blood vessel division regions for each anatomically divided region from the three-dimensional binary blood vessel image; extracting, by the blood vessel age diagnosis apparatus, a center line connecting center points of a first blood vessel section using the blood vessel division regions; calculating, by the blood vessel age diagnosis apparatus, a distortion value of a blood vessel based on the center line; and inferring, by the blood vessel age diagnosis apparatus, the blood vessel age of the object based on the distortion value.

The extracting of the 3D binary blood vessel image may include correcting the z component of each voxel by interpolating the x, y, and z components of each voxel of the image, and using a result of the correction, each voxel of the image It may be characterized in that the 3D binary blood vessel image is extracted by correcting the x, y, and z components of , and changing the position of each voxel with the corrected x, y, and z components.

The inferring of the blood vessel age may include inferring the blood vessel age of the object by using a blood vessel age diagnosis model learned from the distortion values of the blood vessel division regions for each region included in the image.

The step of extracting the center line is a point of quantifying the degree of curvature (distortion or tortuosity) of the blood vessel by tracking center points connecting the start point and the end point set by user inputs on the 3D binary blood vessel image. can be characterized. In addition, the length of the blood vessel (branch length) can be digitized and calculated as a feature. Further, more complicatedly, values calculated from the starting point to the end point of the diameter or area of the cross section of the blood vessel passing through the central point may be calculated as feature points.

After the inferring, the method may include comparing the vascular age of the subject with the actual age of the subject to evaluate the inference result of the vascular age.

The present embodiment may further include the step of overlapping the image and the extracted center line on the 3D binary blood vessel image and outputting the image through the input/output unit.

The computer program according to the embodiment of the present invention may be stored in a medium to execute any one of the methods of diagnosing blood vessel age according to the embodiment of the present invention using a computer.

In addition to this, another method for implementing the present invention, another system, and a computer readable recording medium for recording a computer program for executing the method are further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

According to an embodiment of the present invention, the blood vessel age of the object may be inferred based on distortion values of the blood vessel stems extracted from the image.

Also, according to an embodiment of the present invention, a blood vessel age recognition model may be trained from an image, and the blood vessel age of the object may be inferred using the learned blood vessel age diagnosis model.

1 is a block diagram of a vascular age diagnosis system according to embodiments of the present invention.
2 is a block diagram of an apparatus for diagnosing blood vessel age according to embodiments of the present invention.
FIG. 3 is a diagram for explaining the structure of a storage unit and a learning model apparatus of the blood vessel age diagnosis apparatus, and data transmission/reception between the storage unit and the learning model apparatus.
4 is a block diagram of a data acquisition unit and a data recognition unit of the learning model apparatus.
5 to 6 are flowcharts of a method for diagnosing vascular age according to embodiments of the present invention.
7 to 9 are exemplary views of a user interface provided through an apparatus for diagnosing blood vessel age.
10 is an exemplary diagram for inferring the age of a blood vessel through a model learned from the distortion value of the blood vessel.

Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the contents described in the accompanying drawings. In addition, a method of configuring and using an electronic device according to an embodiment of the present invention will be described in detail with reference to the contents described in the accompanying drawings. The same reference numbers or reference numerals presented in each drawing indicate parts or components that perform substantially the same functions.

Terms including an ordinal number such as 1st, 2nd, etc. may be used to describe various components, but the components are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related items or any one of a plurality of related items.

The terms used herein are used to describe the embodiments, and are not intended to limit and/or limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In this application, terms such as include or have are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features, number, step , it should be understood that it does not preclude in advance the possibility of the existence or addition of an operation, component, part, or combination thereof.

Throughout the specification, when a part is said to be connected to another part, this includes not only a case in which it is directly connected, but also a case in which it is electrically connected with another element interposed therebetween. Also, when it is said that a part includes a certain component, this means that other components may be further included, rather than excluding other components, unless otherwise stated. In addition, terms such as "...unit" and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software. .

In the present specification, an image may refer to multidimensional data composed of discrete image elements (eg, pixels in a 2D image and voxels in a 3D image). For example, the image may include a medical image of an object obtained by an X-ray apparatus, a CT apparatus, an MRI apparatus, an ultrasound diagnosis apparatus, and other medical imaging apparatuses.

As used herein, a subject may include a human or animal, or a part of a human or animal. For example, the object may include a device or blood vessel such as a liver, heart, uterus, brain, breast, abdomen, or the like. Also, the object may include a phantom. A phantom refers to a material having a volume very close to the density and effective atomic number of an organism, and may include a spherical phantom having properties similar to that of a body.

In the present specification, a user may be a medical professional, such as a doctor, a nurse, a clinical pathologist, a medical imaging specialist, or a technician repairing a medical device, but is not limited thereto.

In the present specification, time-of-flight (TOF) magnetic resonance angiography (MRA) is an imaging technique that emphasizes blood flow in a subject without using a contrast agent, and is widely used for imaging intracranial cerebral artery blood vessels. is the method used. Because TOF MRA is obtained by shortening the repetition time, the signal intensity decreases due to the application of repetitive radiofrequency (RF) pulses for a short period of time in a stationary tissue, but it moves along the blood vessel. Since the water molecules do not experience repeated RF pulses because they leave the slice to which the RF pulses are applied, the signal intensity is relatively high. Therefore, there is an advantage in that it is easy to extract blood vessels based on the signal intensity from the image acquired using TOF MRA.

1 is a block diagram of a vascular age diagnosis system according to embodiments of the present invention.

The vascular age diagnosis system 10 may include an imaging apparatus 100 and an vascular age diagnosis apparatus 200 .

The vascular age diagnosis system 10 transmits the image of the object 1 acquired through the imaging apparatus 100 to the vascular age diagnosis apparatus 200, and the vascular age diagnosis apparatus 200 receives data acquired from the blood vessels. The vascular age of the object 1 is determined based on the vascular age, and the vascular health of the object is diagnosed based on this.

The imaging apparatus 100 is an apparatus for outputting an image obtained by measuring the object 1 , and may be an X-ray apparatus, a CT apparatus, an MRI apparatus, an ultrasound diagnosis apparatus, or other medical imaging apparatus. The imaging apparatus 100 may acquire a blood vessel image of all or part of the object 1 . The imaging apparatus 100 may output a TOF image, a diffusion weighted image (DWI), or an apparent diffusion imaging (ADC) image by photographing an object.

The vascular age diagnosis apparatus 200 may extract input data necessary for vascular age diagnosis from an image of the object, and infer the vascular age of the object using the vascular age diagnosis model learned using the input data. The blood vessel age diagnosis apparatus 200 may use the blood vessel division region and/or the blood vessel center line obtained from the input image to calculate the degree of distortion of the blood vessel, and determine the blood vessel age of the object based on this. The blood vessel age diagnosis apparatus 200 may determine the age of the blood vessel using the blood vessel map information of each object as a blood vessel database (not shown) stored in the external data server 300 . The vascular age diagnosis apparatus 200 may convert the vascular health of the diagnosed object into a predetermined standard and transmit it to an external vascular database (not shown). The vascular age diagnosis apparatus 200 may be a computing device including one or more processors and a storage medium.

2 is a block diagram of an apparatus 200 for diagnosing vascular age according to embodiments of the present invention, and FIG. 3 is a structure and storage unit 250 of a storage unit 250 of the apparatus for diagnosing vascular age and a learning model apparatus 300 . ) and the learning model apparatus 300 are diagrams for explaining data transmission and reception.

The blood vessel age diagnosis apparatus 200 may include a control unit 210 , a communication unit 220 , an input/output unit 240 , and a storage unit 250 .

The controller 210 may be implemented with one or more processors, and may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. The command may be provided to the control unit 210 by the storage unit 250 and the communication unit 220 . For example, the control unit 210 may be configured to execute a received command according to a program code stored in a recording device such as the storage unit 250 .

The communication unit 220 may provide a function for communicating with an external device through a network. For example, a request generated by the control unit 210 of the vascular age diagnosis apparatus 200 according to a program code stored in a recording device such as the storage unit 250 is controlled by the communication unit 220 to capture an external image through the network. It may be transmitted to the device 100 , the database 300 , or another user terminal. For example, a control signal or command received through the communication unit 220 may be transmitted to the control unit 210 or the storage unit 250 , and the received video image may be stored in the storage unit 250 .

The storage unit 250 is a computer-readable recording medium and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. Also, the storage unit 250 may store an operating system and at least one program code. These software components may be loaded from a computer-readable recording medium separate from the storage unit 250 using a drive mechanism. The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In another embodiment, the software components may be loaded into the storage unit 250 through the communication unit 220 instead of a computer-readable recording medium. For example, the at least one program is stored in the storage unit 250 based on a program (eg, the above-described application) installed by files provided over a network by developers or a file distribution system for distributing installation files of applications. can be loaded into

The input/output unit 240 may receive an input, such as setting a division section, from a user, and display a screen showing a blood vessel image and a 3D binary blood vessel image. For example, the input/output unit 240 may include an operation panel for receiving a user input and a display panel for displaying a screen.

Specifically, the input unit may include devices capable of receiving various types of user input, such as a keyboard, a physical button, a touch screen, a camera, or a microphone. Also, the output unit may include a display panel or a speaker. However, the present invention is not limited thereto, and the input/output unit 240 may include a configuration supporting various input/output.

The vascular age diagnosis apparatus 200 analyzes and processes an image of an object to diagnose vascular health, an image receiver 251, a blood vessel extractor 252, a centerline acquirer 253, a distortion calculator 254, It may include a blood vessel age inference unit 255 and an evaluation unit 256 .

The image receiver 251 may receive one or more images obtained by photographing a body part of the object. The image receiver 251 receives an image of the object. Here, the image may be a time of flight (TOF) magnetic resonance angiography image, but is not limited thereto, and may be an image or an image of various types.

The blood vessel extractor 252 may extract a 3D binary blood vessel image from the image. In the 3D binary blood vessel image, voxels corresponding to blood vessels may be set to 1, and voxels not corresponding to blood vessels may be set to 0. The blood vessel extractor 252 may extract a plurality of blood vessel division regions for each anatomically divided region from the 3D binary blood vessel image. The blood vessel extractor 252 interpolates the x, y, and z components of each voxel of the image to correct the z component of each voxel, and corrects the x, y, and z components of each voxel of the image using the corrected result and changing the position of each voxel with the corrected x, y, and z components, a three-dimensional binary blood vessel image can be generated. For example, when the z component is somewhat larger than the x and y components of an arbitrary voxel, the readability may deteriorate as the z component is expressed long. By correcting the z component based on the x component and the y component using interpolation, it is possible to prevent the shape of blood vessels from being elongated in any one axial direction.

In more detail, the blood vessel extractor 252 may skeletalize a 3D binary blood vessel image. The blood vessel extractor 252 may obtain blood vessel segmentation regions by skeletalizing the blood vessel stems included in the 3D binary blood vessel image. Skeletalization may be performed by methods such as Hiliditch algorithm, Pavlidis algorithm, Rosenfeld algorithm, etc. known to those skilled in the art.

The centerline acquirer 253 may extract a set of center points of the first blood vessel section designated by the user using the 3D binary blood vessel image and the blood vessel segmentation regions and set it as the center line. The centerline acquirer 253 may extract a centerline, which is a calculation target of a distortion value, by tracking center points connecting a start point and an end point set by user inputs on the 3D binary blood vessel image.

After skeletalizing the 3D binary blood vessel image and the blood vessel segmentation regions, the centerline acquirer 253 may extract a set of center points of the first blood vessel section designated by the user and set it as the center line. The centerline obtainer 253 may extract a set of center points by tracking points connecting the start and end points designated by the user.

The distortion calculating unit 254 calculates the distortion value of the blood vessel based on the center line obtained by the center line obtaining unit 253 . The distortion calculator 254 calculates a distortion value of the blood vessel based on the center line included in each of the blood vessel division regions. The distortion calculator 254 calculates a distortion value set from the image of the object. The distortion value may be calculated using the length of the center line and the shortest length of the center line. For example, the distortion value may be set to a value proportional to the length of the center line/shortest length of the center line.

The blood vessel age inference unit 255 infers the blood vessel age of the object by using the distortion value set for each region. The blood vessel age inference unit 255 may infer the blood vessel age of the object by using the blood vessel age diagnosis model learned from the distortion values of the blood vessel division regions for each region included in the image.

The blood vessel age inference unit 255 may infer the blood vessel age of the object by using a distortion value corresponding to the preset blood vessel age. The blood vessel age inference unit 255 infers the blood vessel age of the object with respect to the distortion value set of the object by inputting and learning the blood vessel age diagnosed by the diagnostician or the actual biological blood vessel age of the object together with the distortion value set for each region. You may.

In this case, the inferred blood vessel age of the object may be output as a set of a plurality of values in the form of a probability map. For example, the vascular age may be inferred from the image of the measured subject, such as (20%, 28 years old), (30%, 35 years old), (50%, 32 years old). The blood vessel age inference unit 255 may determine the age of 32 with the highest probability as the blood vessel age and finally output it. Alternatively, the blood vessel age inference unit 255 may determine the blood vessel age of the object by averaging the weighted probability using the probability as a weight.

The evaluation unit 256 may evaluate the inference result of the blood vessel age by comparing the blood vessel age of the object inferred through the blood vessel age diagnosis apparatus with the actual age of the object. When the inference result does not meet the preset evaluation criteria, the evaluation unit 256 may change the vascular age diagnosis model or allow the vascular age diagnosis model to be re-learned.

The vascular age diagnosis apparatus 200 may further include a vascular state diagnosis unit (not shown) for diagnosing vascular health based on the vascular age. The inferred or measured blood vessel age may be analyzed in consideration of biometric information such as age and sex of the subject. That is, the blood vessel state according to the blood vessel age of the subject may be classified as either normal or abnormal in consideration of biometric information such as age and sex of the subject. In particular, the blood vessel state diagnosis unit communicates with a database storing average values (distortion values, etc.) of blood vessels according to the subject's gender and age based on a plurality of blood vessel images collected for inferring blood vessel age to diagnose the blood vessel state of the subject. can The diagnosed vascular state may include a risk of heart disease or a risk of cerebrovascular disease, a risk of cardiovascular disease, a risk of stroke, and the like. The diagnosed blood vessel state may be predicted based on the distortion value of each point of the blood vessel.

Through this, the vascular age diagnosis apparatus 200 according to embodiments of the present invention may diagnose the vascular age of the object using the image. In particular, the blood vessel age diagnosis apparatus 200 may calculate warpage values for a plurality of blood vessel division regions included in the blood vessel of the object, and diagnose the blood vessel age in consideration of the warpage values in the blood vessel region.

The vascular age diagnosis apparatus 200 according to an embodiment of the present invention may be linked to the learning model apparatus 300 to diagnose vascular age. The blood vessel age diagnosis apparatus 200 may learn a criterion for vascular age diagnosis by inputting the image and distortion values calculated from the image to the learning model apparatus 300 .

Specifically, the learning model apparatus 300 may include a data learning unit 310 and a data recognition unit 320 . The operation of each component is as follows.

The data learning unit 310 may learn a criterion for diagnosing blood vessel age. The data learning unit 310 may learn a criterion regarding which data to use to determine a predetermined blood vessel age and how to determine the blood vessel age using the data. The data learner 310 may learn criteria for diagnosing vascular age by acquiring images, blood vessel distortion values, and the like, which are data to be used for learning, and applying the acquired data to a blood vessel age diagnosis model to be described later.

The data recognizer 320 may determine the blood vessel age of the object based on the input data. The data recognition unit 320 may diagnose and recognize the blood vessel age of the object from predetermined data by using the learned blood vessel age diagnosis model. The data recognition unit 320 acquires predetermined data according to a preset criterion by learning, uses the acquired data as an input value, and uses the blood vessel age diagnosis model to determine the blood vessel age of the object based on the predetermined data. can In addition, a result value output by the vascular age diagnosis model using the acquired data as an input value may be used to update the vascular age diagnosis model.

At least one of the data learning unit 310 and the data recognition unit 320 may be manufactured in the form of at least one hardware chip and mounted in an electronic device. For example, at least one of the data learning unit 310 and the data recognition unit 320 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or an existing general-purpose processor (eg, CPU). Alternatively, it may be manufactured as a part of an application processor) or a graphics-only processor (eg, GPU) and mounted on the various electronic devices described above.

In this case, the data learning unit 310 and the data recognition unit 320 may be mounted on one electronic device, or may be mounted on separate electronic devices, respectively. For example, one of the data learning unit 310 and the data recognition unit 320 may be included in the electronic device, and the other may be included in the server. In addition, the data learning unit 310 and the data recognition unit 320 may provide the model information built by the data learning unit 310 to the data recognition unit 320 through wired or wireless communication, and the data recognition unit ( The data input to the 320 may be provided to the data learning unit 310 as additional learning data.

Meanwhile, at least one of the data learning unit 310 and the data recognition unit 320 may be implemented as a software module. When at least one of the data learning unit 310 and the data recognition unit 320 is implemented as a software module (or a program module including an instruction), the software module is a computer-readable, non-transitory, non-transitory It may be stored in a readable recording medium (non-transitory computer readable media). Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

As shown in FIG. 4 , the data learning unit 310 includes a data acquisition unit 311 , a preprocessing unit 312 , a training data selection unit 313 , a model learning unit 314 , and a model evaluation unit 315 . may include

The data acquisition unit 311 may acquire data necessary for determining the age of blood vessels. The data acquisition unit 311 may acquire data necessary for learning for determining the age of blood vessels. The data acquisition unit 311 may acquire an image, an image, and a text related to a blood vessel from the blood vessel age diagnosis apparatus 200 or the image photographing apparatus 100 . Specifically, the data acquisition unit 311 may acquire distortion values of parts of an image or blood vessel. The data acquisition unit 311 is not limited to the above description and is an external electronic device.

The preprocessor 312 may preprocess the acquired data so that the acquired data can be used for learning for determining the age of blood vessels. The preprocessor 312 may process the acquired data into a preset format so that the model learning unit 314, which will be described later, uses the acquired data for learning for determining the blood vessel age. The preprocessor 312 may extract a blood vessel region corresponding to a blood vessel included in the image. In order to visualize the blood vessel region in 3D, x, y, and z-axis components of each voxel may be corrected in the blood vessel region. In this case, the x, y, and z-axis components may be corrected using an interpolation method. Visibility of the blood vessel region may be increased through this correction process. Also, the preprocessor 312 may extract a center line connecting the center points of the blood vessel by skeletalizing the image corresponding to the 3D rendered blood vessel region. Also, the preprocessor 312 may calculate distortion values of the center lines extracted from the image.

The learning data selection unit 313 may select data required for learning from among the pre-processed data. The selected data may be provided to the model learning unit 314 . The learning data selection unit 313 may select data necessary for learning from among the preprocessed data according to a preset criterion for vascular health determination such as vascular age. Also, the training data selection unit 313 may select data according to a criterion set by learning by the model learning unit 314, which will be described later. The learning data selection unit 313 may select all or a part of distortion values of center lines of a plurality of branches included in the image.

The model learning unit 314 may learn a criterion regarding how to determine vascular health, such as vascular age, based on the learning data. Also, the model learning unit 314 may learn a criterion for which data, such as a distortion value of a blood vessel stem, should be used to determine blood vessel health such as blood vessel age.

Also, the model learning unit 314 may learn a blood vessel age diagnosis model used for determining blood vessel health, such as blood vessel age, using the learning data. In this case, the vascular age diagnosis model may be a pre-built model. For example, the blood vessel age diagnosis model may be a model built in advance by receiving basic training data (eg, DWI, ADC, TOF image, etc.).

The blood vessel age diagnosis model may be constructed in consideration of the field of application of the recognition model, the purpose of learning, or the computer performance of the device. The vascular age diagnosis model may be, for example, a model based on a neural network. For example, a model such as a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), or a Bidirectional Recurrent Deep Neural Network (BRDNN) may be used as the vascular age diagnosis model, but is not limited thereto.

According to various embodiments, the model learning unit 314 is configured to learn a blood vessel age diagnosis model having a high correlation between the input learning data and the basic learning data when there are a plurality of pre-built blood vessel age diagnosis models. can be decided with In this case, the basic learning data may be pre-classified for each type of data, and the blood vessel age diagnosis model may be previously built for each type of data. For example, the basic training data is pre-classified by various criteria such as the region where the training data is generated, the time when the training data is generated, the size of the training data, the genre of the training data, the creator of the training data, the type of object in the training data, etc. may have been

Also, the model learning unit 314 may train the blood vessel age diagnosis model using, for example, a learning algorithm including error back-propagation or gradient descent.

Also, the model learning unit 314 may train the blood vessel age diagnosis model through supervised learning using, for example, learning data as an input value. In addition, the model learning unit 314 is, for example, unsupervised for discovering criteria for vascular health such as vascular age by self-learning the type of data required for vascular health judgment, such as vascular age, without any guidance. Through unsupervised learning, the vascular age diagnosis model may be trained. In addition, the model learning unit 314 may train the blood vessel age diagnosis model through reinforcement learning using, for example, feedback on whether a result of vascular health determination such as vascular age according to learning is correct. have.

Also, when the blood vessel age diagnosis model is learned, the model learning unit 314 may store the learned vessel age diagnosis model. In this case, the model learning unit 314 may store the learned blood vessel age diagnosis model in the memory of the electronic device including the data recognition unit 320 . Alternatively, the model learning unit 314 may store the learned blood vessel age diagnosis model in the memory of the electronic device including the data recognition unit 320 to be described later. Alternatively, the model learning unit 314 may store the learned blood vessel age diagnosis model in a memory of a server connected to the electronic device through a wired or wireless network.

In this case, the memory in which the learned blood vessel age diagnosis model is stored may also store, for example, commands or data related to at least one other component of the electronic device. The memory may also store software and/or programs. A program may include, for example, a kernel, middleware, an application programming interface (API) and/or an application program (or "application"), and the like.

The model evaluator 315 may input evaluation data into the blood vessel age diagnosis model and, when a recognition result output from the evaluation data does not satisfy a predetermined criterion, cause the model learning unit 314 to learn again. In this case, the evaluation data may be preset data for evaluating the vascular age diagnosis model.

For example, the model evaluation unit 315 may be configured to determine if, among the recognition results of the learned blood vessel age diagnosis model for the evaluation data, the number or ratio of evaluation data for which the recognition result such as the vessel age is not accurate exceeds a preset threshold. It may be evaluated as not satisfying a predetermined criterion.

On the other hand, when there are a plurality of learned blood vessel age diagnosis models, the model evaluation unit 315 evaluates whether a predetermined criterion is satisfied with respect to each learned video recognition model, and the model that satisfies the predetermined criterion is used for final vessel age diagnosis. can be determined as a model. In this case, when there are a plurality of models satisfying the predetermined criteria, the model evaluator 315 may determine any one or a predetermined number of models preset in the order of the highest evaluation score as the final vascular age diagnosis model.

Meanwhile, at least one of the data acquiring unit 311 , the preprocessing unit 312 , the training data selection unit 313 , the model learning unit 314 , and the model evaluation unit 315 in the data learning unit 310 is at least one may be manufactured in the form of a hardware chip of For example, at least one of the data acquisition unit 311 , the preprocessor 312 , the training data selection unit 313 , the model learning unit 314 , and the model evaluation unit 315 is artificial intelligence (AI). It may be manufactured in the form of a dedicated hardware chip for this purpose, or it may be manufactured as a part of an existing general-purpose processor (eg, CPU or application processor) or graphics-only processor (eg, GPU) and mounted on the various electronic devices described above.

In addition, the data acquisition unit 311 , the preprocessor 312 , the training data selection unit 313 , the model learning unit 314 , and the model evaluation unit 315 may be mounted in one electronic device, or separate Each of the electronic devices may be mounted. In addition, at least one of the data acquisition unit 311 , the preprocessor 312 , the training data selection unit 313 , the model learning unit 314 , and the model evaluation unit 315 may be implemented as a software module. At least one of the data acquisition unit 311 , the preprocessor 312 , the training data selection unit 313 , the model learning unit 314 , and the model evaluation unit 315 includes a software module (or instruction) When implemented as a program module), the software module may be stored in a computer-readable non-transitory computer readable medium.

Next, the structure of the data recognition unit 320 will be described.

The data recognition unit 320 according to an embodiment of the present invention includes a data acquisition unit 321 , a preprocessing unit 322 , a recognition data selection unit 323 , a recognition result providing unit 324 , and a model update unit 325 . may include

The data acquisition unit 321 may acquire data necessary for vascular health determination, such as vascular age, and the preprocessor 322 may use the acquired data for vascular health judgment such as vascular age. can be pre-processed. The preprocessor 322 may process the acquired data into a preset format so that the recognition result providing unit 324, which will be described later, uses the acquired data for vascular health determination, such as vascular age. The preprocessor 322 may extract a blood vessel region corresponding to a blood vessel included in the image. In order to visualize the blood vessel region in 3D, x, y, and z-axis components of each voxel may be corrected in the blood vessel region. In this case, the x, y, and z-axis components may be corrected using an interpolation method. Visibility of the blood vessel region may be increased through this correction process. Also, the preprocessor 322 may extract a center line connecting the center points of the blood vessel by skeletalizing the image corresponding to the 3D rendered blood vessel region. Also, the preprocessor 322 may calculate distortion values of the center lines extracted from the image. Before the preprocessor 322 calculates the distortion value, a center line connecting the center points of blood vessels may be tracked.

The recognition data selection unit 323 may select data necessary for vascular health determination, such as vascular age, from among the pre-processed data. The selected data may be provided to the recognition result providing unit 324 . The recognition data selection unit 323 may select some or all of the preprocessed data according to a preset criterion for vascular health determination, such as vascular age. Also, the recognition data selection unit 323 may select data according to a preset criterion by learning by the model learning unit 314 .

The recognition result providing unit 324 may determine vascular health such as vascular age by applying the selected data to the vascular age diagnosis model. The recognition result providing unit 324 may provide a recognition result according to the purpose of data recognition. The recognition result providing unit 324 may apply the selected data to the blood vessel age diagnosis model by using the data selected by the recognition data selecting unit 323 as an input value. In addition, the recognition result is determined by the vascular age diagnosis model, and may include vascular health status such as the vascular age of the subject.

The model updater 325 may update the blood vessel age diagnosis model based on the evaluation of the recognition result provided by the recognition result provider 324 . For example, the model updating unit 325 provides the recognition result provided by the recognition result providing unit 324 to the model learning unit 324 so that the model learning unit 324 updates the blood vessel age diagnosis model. can

Meanwhile, at least one of the data acquisition unit 321 , the preprocessor 322 , the recognition data selection unit 323 , the recognition result providing unit 324 , and the model update unit 325 in the data recognition unit 320 is at least It may be manufactured in the form of a single hardware chip and mounted in an electronic device. For example, at least one of the data acquisition unit 321 , the preprocessor 322 , the recognition data selection unit 323 , the recognition result providing unit 324 , and the model update unit 325 is artificial intelligence (AI). ), or may be manufactured as a part of an existing general-purpose processor (eg, CPU or application processor) or graphics-only processor (eg, GPU) and mounted on the various electronic devices described above.

4 and 5 are flowcharts of a blood vessel health diagnosis method according to embodiments of the present invention.

As shown in FIG. 4 , the blood vessel health diagnosis method receives an image captured by the image capturing apparatus 100 .

In S120, the blood vessel age diagnosis apparatus 200 may extract a 3D binary blood vessel image from the image. In the 3D binary blood vessel image, voxels corresponding to blood vessels may be set to 1, and voxels not corresponding to blood vessels may be set to 0. The blood vessel age diagnosis apparatus 200 may extract a plurality of blood vessel division regions for each anatomically divided region from the 3D binary blood vessel image.

In S130 , the blood vessel age diagnosis apparatus 200 may extract a set of center points of the first blood vessel section designated by the user using the three-dimensional binary blood vessel image and the blood vessel segmentation regions and set it as the center line.

)을 찾고, 끝점과 가장 가까운 중심선 상의 점(

)을 찾는다.

에서 출발하여

으로 향하는 중심선 상의 점들을 자동으로 순차적으로 추적한다. 점과 점을 잇는 벡터의 방향 코사인 (directional cosine)을 근거로 하여 자동적으로 중심점들을 추적할 수 있다. 이 점들을 따라 거리를 합하면 혈관 분할 영역에 대한 혈관 길이(branch length)로 근사화 하여 다음과 같이 산출할 수 있다. In S140 , the blood vessel age diagnosis apparatus 200 may numerically calculate the distortion from the center line of the blood vessel division region (eg, the right middle cerebral artery region). For a blood vessel segmentation region, a starting point and an endpoint of the corresponding blood vessel may be given. In this case, the start point and the end point of the blood vessel segmentation region may be automatically found, or the user may view the MRI image using the interface and set it manually. Given a starting point and an ending point, the point on the centerline closest to the starting point (

) and find the point on the centerline closest to the endpoint (

) to find

starting from

The points on the center line towards Center points can be automatically tracked based on the directional cosine of the vector connecting the points. By summing the distances along these points, it can be approximated as the branch length for the blood vessel segment and calculated as follows.

는 3차원 상의 점

와 점

간의 직선 거리 (즉, Euclidean distance)이다. 해당 혈관 영역에서 혈관의 뒤틀림(tortuosity) 값을 다음과 같이 산출한다. At this time,

is a point in 3D

with dots

is the linear distance between them (ie, the Euclidean distance). The tortuosity value of the blood vessel in the corresponding blood vessel region is calculated as follows.

According to this principle, the blood vessel age diagnosis apparatus 200 calculates the distortion values of the blood vessel based on the center line included in each of all the blood vessel division regions. In general, it can be seen that there is a positive correlation between the warpage value of the vessel and the age of the vessel. The blood vessel age diagnosis apparatus 200 calculates a set of distortion values for each blood vessel segmentation region from the image of the object.

In S150, the blood vessel age diagnosis apparatus 200 infers the blood vessel age of the object by using a set of distortion values for each region. The blood vessel age diagnosis apparatus 200 may infer the blood vessel age of the object by using a distortion value corresponding to the preset blood vessel age. The vascular age diagnosis apparatus 200 inputs and learns the vascular age diagnosed by the diagnostician or the actual biological vascular age of the object along with the set of distortion values for each region, and the vascular age of the subject with respect to the set of distortion values of the object can also be inferred.

As shown in FIG. 5 , the learning model apparatus 300 may learn the blood vessel age diagnosis model in conjunction with the vessel age diagnosis apparatus.

In S210 , the learning model apparatus 300 receives the photographed image of the object from the imaging apparatus or the blood vessel age diagnosis apparatus.

In S220, the learning model apparatus 300 extracts data for determining the age of blood vessels from the captured image. The learning model apparatus 300 may extract data for determining the age of blood vessels, such as a three-dimensional binary blood vessel image, a blood vessel segmentation image divided into blood vessel stems, and distortion values of the blood vessel stems.

In S230, the learning model apparatus 300 selects data for determining the age of blood vessels from among the extracted data. In S240, the learning model apparatus 300 learns the blood vessel age diagnosis model by using the data for determining the blood vessel age.

In S250, the learning model apparatus 300 evaluates the blood vessel age diagnosis model by inputting data such as preset blood vessel age to the learned vessel age diagnosis model.

In S260, the learning model apparatus 300 transmits and updates the blood vessel age diagnosis model satisfying the predetermined evaluation criteria to the storage unit of the blood vessel age diagnosis apparatus.

Through this, the vascular age diagnosis apparatus 200 according to embodiments of the present invention may receive the vascular age diagnosis model through the learning model device 300 and infer the vascular age of the object using the vascular age diagnosis model. .

7 to 9 are exemplary views of a user interface provided through an apparatus for diagnosing blood vessel age. The blood vessel age diagnosis apparatus 200 provides an image S1 obtained by photographing an object through the input/output unit 240 and a three-dimensional binary blood vessel image S2 extracted from the image.

A start point is set by I1 for the 3D binary blood vessel image S2, and an end point is set by I2. The blood vessel age diagnosis apparatus 200 may extract a centerline of a blood vessel in consideration of I1 and I2.

The portion marked with ellipse in FIG. 8 indicates the region of the left middle cerebral artery blood vessel, and is an exemplary view showing the central points tracked through tracking by overlaying the blood vessels when the start and end points are given.

The blood vessel age diagnosis apparatus 200 may provide buttons (item1, item2, item3, item4) for calculating a distortion value of each blood vessel stem in response to a user input.

10 is an exemplary diagram for inferring the age of a blood vessel through a model learned from the distortion value of the blood vessel. Here, the blood vessel distortion values are basilar artery, posterior cerebral artery, vertebral artery, etc., but is not limited thereto, and may be calculated by various algorithms. For example, after training a model such as a linear regression model, a support vector machine (SVM) regression model, or a random forests regression model, the age of the vessel can be predicted for a new vessel using the trained model. In supervised learning, the input part is a set of blood vessel distortion values and the output part is the blood vessel age. When a missing value occurs in the input data during training or testing, it can be replaced with another value using methods such as multiple imputation and inference using statistical information of samples without missing values. .

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

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. may be permanently or temporarily embody in The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in 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, etc. 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 available to those skilled in the art of computer software. Examples of the computer readable recording medium 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 floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible for those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

10: Vascular Age Diagnosis System
100: video recording device
200: vascular age diagnosis device
300: learning model device

Claims (13)

receiving, by an apparatus for diagnosing blood vessel age, an image obtained by photographing an object from an imaging apparatus;
extracting, by the blood vessel age diagnosis apparatus, a three-dimensional binary blood vessel image from the image; in the three-dimensional binary blood vessel image, voxels corresponding to blood vessels are set to 1 and voxels not corresponding to blood vessels are set to 0;
extracting, by the vascular age diagnosis apparatus, vascular stems included in the three-dimensional binary vascular image, to extract vascular division regions for each anatomically divided region;
extracting, by the blood vessel age diagnosis apparatus, a set of center points of a first blood vessel section using the three-dimensional binary blood vessel image and the blood vessel segmentation regions, and extracting a center line connecting a start point and an end point designated by user inputs;
calculating, by the blood vessel age diagnosis apparatus, a distortion value of a blood vessel based on the center line; and
The blood vessel age diagnosis apparatus infers the blood vessel age of the subject with respect to the blood vessel image and the distortion value using the blood vessel age diagnosis model learned with the distortion values of the blood vessel division regions for each region included in the image,
Diagnosing the blood vessel state of the subject by communicating with a database storing the average value of blood vessels according to the sex and age of the subject based on the plurality of blood vessel images collected for inferring the age of the blood vessel - The blood vessel condition is the occurrence of heart disease Including risk, risk of cerebrovascular disease, risk of cardiovascular disease, or risk of stroke;
The vascular age diagnosis model is
A blood vessel performed by an apparatus for diagnosing blood vessel age, which learns a criterion for determining a blood vessel age using input data for determining the age of a blood vessel and the input data, and infers the age of the vessel by inputting the obtained image and the distortion value of the blood vessel How to diagnose age. According to claim 1,
The step of extracting the 3D binary blood vessel image is
Correcting the z component of each voxel by interpolating the x, y, and z components of each voxel of the image, and correcting the x, y, and z components of each voxel of the image using the corrected result; A method for diagnosing vascular age performed by a vascular age diagnosis apparatus, comprising extracting a three-dimensional binary vascular image by changing the position of each voxel with corrected x, y, and z components. delete delete delete According to claim 1,
The method of diagnosing vascular age performed by an apparatus for diagnosing vascular age, further comprising the step of overlapping the image and the extracted center line on the three-dimensional binary vascular image and outputting the image through an input/output unit. an image receiver configured to receive an image obtained by photographing an object from an image photographing apparatus;
A blood vessel extractor that extracts a 3D binary blood vessel image from the image, skeletalizes blood vessel stems included in the 3D binary blood vessel region, and extracts blood vessel division regions for each anatomically divided region - the 3D binary blood vessel region is to set voxels corresponding to blood vessels to 1 and voxels not corresponding to blood vessels to 0;
a centerline obtaining unit that extracts a set of center points of a first blood vessel section using the three-dimensional binary blood vessel image and the blood vessel segmentation regions, and extracts a center line connecting a start point and an end point designated by user inputs;
a distortion calculation unit for calculating a distortion value of a blood vessel based on the center line; and
a blood vessel age inference unit for inferring the blood vessel age of the object based on the blood vessel image and the warpage value using the blood vessel age diagnosis model learned with the distortion values of the blood vessel division regions for each region included in the image; and
A blood vessel state diagnosis unit communicating with a database storing an average value of blood vessels according to the sex and age of the subject based on the plurality of blood vessel images collected for inferring the blood vessel age and diagnosing the blood vessel state of the subject; and ,
The vascular state includes the risk of heart disease, the risk of cerebrovascular disease, the risk of cardiovascular disease, or the risk of stroke,
The vascular age diagnosis model is
An apparatus for diagnosing blood vessel age by learning the input data for determining the age of the vessel and a criterion for determining the age of the vessel by using the input data, and inferring the age of the vessel by inputting the obtained image and the distortion value of the vessel. 8. The method of claim 7,
The blood vessel extraction unit
Correcting the z component of each voxel by interpolating the x, y, and z components of each voxel of the image, and correcting the x, y, and z components of each voxel of the image using the corrected result; An apparatus for diagnosing blood vessel age, characterized in that a three-dimensional binary blood vessel image is extracted by changing the position of each voxel with the corrected x, y, and z components.
delete delete delete 8. The method of claim 7,
The apparatus for diagnosing blood vessel age, further comprising an input/output unit that overlaps the image and the extracted center line on the three-dimensional binary blood vessel image.
A computer program stored in a computer-readable storage medium for executing the method of any one of claims 1, 2 and 6 using a computer.

Images