KR102071774B1 - Method for predicting cardio-cerebrovascular disease using eye image - Google Patents

Abstract

Computing the eye image of the subject and predicting the cardiovascular disease of the subject based on the correlation between the eye image and one or more markers for determining the cardiovascular disease, cardiac brain using the eye image A method for predicting vascular disease is disclosed.

Description

Method for predicting cardiovascular disease using eye image {METHOD FOR PREDICTING CARDIO-CEREBROVASCULAR DISEASE USING EYE IMAGE}

The present invention relates to a method for predicting cardiovascular disease using eye images.

Optical Coherence Tomography (OCT) imaging, also known as optical coherence tomography, is a medical imaging technique that uses light to capture micrometer-resolution three-dimensional images in optical scattering media (such as biological tissue).

It is generally based on interferometers with low interference properties using near infrared. Using relatively long wavelength light can penetrate into the scattering medium. Another optical technique, confocal microscopy, generally penetrates deeper into the sample but with higher resolution.

Depending on the nature of the light source (high brightness diodes, very short pulse lasers and long term continuous lasers), optical coherence tomography has a submicrometer resolution (with a very broad spectral source emitted in the wavelength range of ~ 100 nm).

Recently, development of a method of acquiring necessary information by processing various medical images using deep learning has been actively conducted.

Deep learning is defined as a set of machine learning algorithms that attempts to achieve high levels of abstraction (summarizing key content or functions in large amounts of data or complex data) through a combination of several nonlinear transformations. Deep learning can be seen as a field of machine learning that teaches computers how people think in a large framework.

US20040064057A1 (2004-04-01) US20110242306A1 (2011-10-06)

The problem to be solved by the present invention is to provide a cardiovascular disease prediction method using an eye image.

Problems to be solved by the present invention are not limited to the above-mentioned problems, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

Cardiovascular disease prediction method using an eye image according to an aspect of the present invention for solving the above problems, the step of the computer acquiring the eye image of the subject and the one or more markers for determining the eye image and cardiovascular disease Predicting cardiovascular disease of the subject based on the correlation.

In addition, the at least one marker may be a value derived from a test result according to at least one test method used to determine whether a cardiovascular disease.

In addition, the at least one test method may include at least one of a CT scan, an ultrasound test, and a blood pressure test of the heart and the coronary artery.

In addition, the derived value may include at least one of intravascular calcium index, vessel thickness, central blood pressure, and arterial sclerosis (PWV).

In addition, the predicting of the cardio- cerebrovascular disease may include predicting one or more marker values corresponding to the obtained eye images by using a model trained using the eye images labeled with one or more marker values. It may include.

In addition, predicting whether the cardio- cerebrovascular disease, may include predicting whether the cardiovascular disease of the subject using the predicted one or more marker values.

The predicting of the cardiovascular disease may include predicting the cardiovascular disease of the subject corresponding to the acquired eye image, using a model trained using the eye image labeled with one or more marker values. It may include the step.

The method may further include extracting a new marker having a correlation with the eye image using the trained model, and retraining the model using the eye image labeled with the extracted new marker value. .

The method may further include predicting cardiovascular disease of the subject corresponding to the obtained eye image by using the retrained model.

A computer program according to an aspect of the present invention for solving the above problems is stored in a computer-readable recording medium that can be combined with a computer, which is hardware, to perform a cardiovascular disease prediction method using an eye image.

Other specific details of the invention are included in the detailed description and drawings.

According to the disclosed embodiment, an ocular image including an OCT image may be used to easily derive cardiovascular disease retention of a subject.

In addition, by determining whether the subject possesses cardiovascular disease by using one or more markers, there is an effect that enables more accurate and multifaceted examination.

Effects of the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a conceptual diagram schematically illustrating an eyeball image analyzing system according to an exemplary embodiment.
2 is a flowchart illustrating a method for predicting cardiovascular disease using eye images according to an embodiment.
3 is a diagram illustrating an example of predicting a cardiovascular disease of a subject by using an eyeball image.
4 is a diagram illustrating an example of a method of determining whether a subject has cardiovascular or cerebrovascular disease from an eyeball image using one or more markers.
5 is a diagram illustrating a method of extracting a new marker according to one embodiment.

Advantages and features of the present invention, and methods for achieving them will be apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be embodied in various different forms, only the present embodiments are intended to complete the disclosure of the present invention, and those skilled in the art It is provided to fully inform the skilled person of the scope of the invention, which is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and / or “comprising” does not exclude the presence or addition of one or more other components in addition to the mentioned components. Like reference numerals refer to like elements throughout, and "and / or" includes each and all combinations of one or more of the mentioned components. Although "first", "second", etc. are used to describe various components, these components are of course not limited by these terms. These terms are only used to distinguish one component from another. Therefore, of course, the first component mentioned below may be the second component within the technical spirit of the present invention.

Unless otherwise defined, all terms used in the present specification (including technical and scientific terms) may be used in a sense that can be commonly understood by those skilled in the art. In addition, terms that are defined in a commonly used dictionary are not ideally or excessively interpreted unless they are specifically defined clearly.

The term "part" or "module" as used herein refers to a hardware component such as software, FPGA or ASIC, and the "part" or "module" plays certain roles. However, "part" or "module" is not meant to be limited to software or hardware. The “unit” or “module” may be configured to be in an addressable storage medium or may be configured to play one or more processors. Thus, as an example, a "part" or "module" may include components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. Functions provided within components and "parts" or "modules" may be combined into smaller numbers of components and "parts" or "modules" or into additional components and "parts" or "modules". Can be further separated.

The spatially relative terms " below ", " beneath ", " lower ", " above ", " upper " It can be used to easily describe a component and its correlation with other components. Spatially relative terms are to be understood as including terms in different directions of components in use or operation in addition to the directions shown in the figures. For example, when flipping a component shown in the drawing, a component described as "below" or "beneath" of another component may be placed "above" the other component. Can be. Thus, the exemplary term "below" can encompass both an orientation of above and below. Components may be oriented in other directions as well, so spatially relative terms may be interpreted according to orientation.

Hereinafter, with reference to the accompanying drawings will be described an embodiment of the present invention;

As used herein, “image” may mean multi-dimensional data composed of discrete image elements (eg, pixels in a 2D image and voxels in a 3D image).

As used herein, an "object" may be a person or an animal, or part or all of a person or an animal. For example, the subject may include at least one of an organ, such as the liver, heart, uterus, brain, breast, abdomen, and blood vessels.

In the present specification, the "user" may be a doctor, a nurse, a clinical pathologist, a medical imaging expert, or the like, and may be a technician who repairs a medical device, but is not limited thereto.

1 is a conceptual diagram schematically illustrating an eyeball image analyzing system according to an exemplary embodiment.

Referring to FIG. 1, an eyeball imaging apparatus 10, a user client 20, and a server 100 are included.

In one embodiment, the eyeball image capturing apparatus 10 includes all types of devices capable of capturing an eyeball image of an object.

For example, the ocular image photographing apparatus 10 may be a fundus image photographing apparatus photographing a fundus of an object. The fundus image photographing apparatus photographs the vitreous, the retina, the choroid, and the optic nerve papilla in the eye through the pupil of the subject.

In addition, the ocular imaging apparatus 10 may be an OCT apparatus that photographs the vicinity of the retina of the eyeball of a subject for each tomography. The OCT device may acquire information about the retinal nerve fiber layer, optic nerve papilla, and the macula of the subject.

In one embodiment, the user client 20 refers to a user client of a computing device including at least one processor, and the server 100 refers to a computing device including at least one processor.

In one embodiment, the eyeball imaging apparatus 10 and the user client 20 may be embedded in a single device, the eyeball imaging apparatus 10 is physically or electrically connected to the user client 20 to be used. May be

The user client 20 obtains an eyeball image of the object from the eyeball imaging apparatus 10.

The user client 20 transmits the obtained eyeball image to the server 100.

The server 100 analyzes the eyeball image obtained from the user client 20 and transmits the analysis result to the user client 20.

In an embodiment, the user client 20 and the server 100 may not be separated, and the user client 20 may analyze the obtained eyeball image and provide the analysis result to the user.

Analyzing the fundus photograph showing the inside of the eyeball of the subject is difficult, and the ophthalmologist generally performs the analysis. According to the disclosed embodiment, even if a medical institution in which an ophthalmologist does not reside, the fundus image photographing apparatus may be provided, it may be determined whether the subject has disease by analyzing the user client 20 or the server 100.

In an embodiment, the determination result of the user client 20 or the server 100 may be used to assist the judgment of a general practitioner or a specialist.

In an embodiment, the user client 20 or the server 100 may provide the determination result to the user when the determination result is determined that the object does not have a disease, and the eyeball image of the subject when the object is determined to have a disease Can be classified for review.

Eye images classified as subjects to be reviewed may be determined by using the same or different algorithm as the initial determination, and furthermore, the types of the retained diseases may be determined. In an embodiment, the eye image classified as a subject to be reviewed may determine whether the disease is retained and the type of disease retained by a specialist, and the reading result may be provided to the user through the user client 20 or the server 100. have.

According to the disclosed embodiment, even if a patient who needs to undergo frequent fundus examination, such as a diabetic patient, does not have to see a specialist every time, the patient can easily undergo fundus examination, thereby improving convenience of a patient and a doctor.

In the disclosed embodiment, angiography may be used to acquire an eye image of the subject.

Imaging is a method used to specifically observe blood vessels in a subject, by administering a contrast agent to the subject.

For example, Fluorescein Fundus Angiography (FA) is a method of taking a fundus image of a subject by administering a fluorescent pigment, fluorescein, to the subject. In this case, information about blood flow change of the blood vessels in the eyeball of the subject and the degree of damage of the retinal vessel of the subject may be obtained.

As another example, using optical computed tomography (OCT) angiography, the movement of eye blood vessels can be observed, and information on blood flow changes in the blood vessels of the eyeball and the degree of damage of the subject's retinal blood vessels can be obtained. . In addition, OCT imaging can capture changes in blood vessels tomography, and thus, there is an advantage of detecting minute blood flow changes and local blood vessel damage.

In addition, OCT contrast is a complete non-invasive method that does not need to use the contrast agent has the advantage of not having to worry about the side effects of the contrast agent.

In the disclosed embodiment, the server 100 stores a pretrained model using the labeled eye images. The server 100 determines whether the subject has disease by inputting the fundus image of the subject to the model.

For example, the server 100 determines whether the fundus of the object is normal or abnormal using the fundus image of the object. That is, the server 100 determines whether the subject has eye disease using the fundus image of the subject.

As another example, the server 100 determines whether the subject possesses a heart or kidney disease by using an eye image of the subject photographed using an imaging technique.

The server 100 may determine whether the subject possesses various diseases by using various types of eye images captured by the above-described methods.

Hereinafter, as a preferred embodiment according to the disclosed embodiment, a method of determining whether a subject possesses cardiovascular disease by using an OCT image of an object acquired using an OCT imaging apparatus will be described. However, the cardiovascular disease prediction method according to the disclosed embodiment is not limited to the method using the ocular OCT, it is understood to encompass the use of all kinds of eye images. In addition, the cardiovascular disease prediction method according to the disclosed embodiment can be applied to predict the cardiovascular disease of the subject using information obtained through all kinds of retina and eye examination.

2 is a flowchart illustrating a method for predicting cardiovascular disease using eye images according to an embodiment.

2 is a time series illustrating each step performed by the user client 20 or the server 100 illustrated in FIG. 1 to perform a method of analyzing an eyeball image of an object according to the disclosed embodiment.

Hereinafter, for convenience of description, it will be described that the server 100 performs each step. However, all or at least some of the steps shown in FIG. 2 may all be performed in each of the user client 20 or server 100.

In operation S210, the server 100 obtains an optical coherence tomography (OCT) image of the eyeball of the object.

The OCT image is mainly an image of the retina of the subject, and may be used as an indicator for determining whether cardiac cerebrovascular disease is based on the thickness of the retina, the degree of injury, and the state of blood vessels.

In operation S220, the server 100 may predict whether the subject has cardiovascular or cerebrovascular disease based on the ocular OCT image of the subject obtained in operation S210.

Referring to FIG. 3, an example of predicting a cardiovascular disease of a subject using an eyeball image is illustrated.

In an embodiment, the server 100 may derive a correlation between the OCT image 300 and the cardiac cerebrovascular disease, thereby obtaining a model for determining whether the subject has cardiovascular disease from the OCT image 300. .

In one embodiment, the model may be a model trained using OCT images labeled as having cardiovascular disease as training data.

In one embodiment, deep learning may be used to train the model.

Deep learning is defined as a set of machine learning algorithms that attempts to achieve high levels of abstraction (summarizing key content or functions in large amounts of data or complex data) through a combination of several nonlinear transformations. Deep learning can be seen as a field of machine learning that teaches computers how people think in a large framework.

When there is any data, it is represented in a form that can be understood by a computer (for example, in the case of an image, the pixel information is represented by a column vector), and a lot of research is performed to apply it to learning. How to create expression techniques and how to build models to learn them). As a result of these efforts, various deep learning techniques have been developed. Deep learning techniques include Deep Neural Networks (DNN), Convolutional Deep Neural Networks (CNN), Reccurent Neural Networks (RNN), and Deep Belief Networks (DBN). have.

Deep Neural Networks (DNNs) are artificial neural networks (ANNs) made up of a plurality of hidden layers between an input layer and an output layer.

The above-described algorithm or learning method is described as an example, and the first model according to the disclosed embodiment may be learned by any learning method. For example, the first model according to the disclosed embodiment includes supervised learning in which input data and output data are provided as learning data, unsupervised learning in which no separate labeled data is provided, and learning results. Feedback may be provided by reinforcement learning, for example, but is not limited thereto.

In the disclosed embodiment, the model may be trained using the labeled data and the CNN, but the method of learning the model is not limited thereto.

That is, a model that reflects the correlation between the characteristics of the OCT image 300 and the occurrence of cardiovascular disease is learned by deep learning, and using the learned model, it is determined whether the subject possesses the cardiovascular disease by using only the eye OCT image. can do.

Furthermore, according to the disclosed embodiment, in addition to directly linking the OCT image 300 with the cardiovascular disease of the subject, cardiovascular and cardiovascular disease of the subject from the OCT image 300 of the subject, directly or indirectly, or indirectly through various methods. It can be determined.

By determining whether the subject has cardiovascular disease through various methods to be described later, it is possible to determine whether the subject possesses cardiovascular disease by performing a cross-check on the determination result or by combining a plurality of determination results.

There are a variety of test methods used to determine whether a subject has cardiovascular disease. As a more direct method than using the OCT image, there are various markers used to determine whether the subject has cardiovascular disease.

Referring to FIG. 3, a first marker 410, a second marker 420, and a third marker 430, which are used to determine whether a subject has cardiovascular disease, are shown. The first marker 410 to the third marker 430 are shown for illustrative purposes, and the type or number of markers that may be used to determine whether the subject has cardiovascular disease is not limited thereto.

For example, as a direct marker used to determine whether a subject has cardiovascular disease, it indicates the coronary artery calcification index of the subject, which is determined by coronary CT, or the like, that is, the degree of calcium in the coronary artery of the subject. Indexes can be utilized.

In addition, as a direct marker used to determine whether the subject possesses cardiovascular disease, the thickness of the carotid artery of the subject or other blood vessels (artery or vein), which can be confirmed by using ultrasound imaging, may be used.

In addition, as a direct marker used to determine whether the subject has cardiovascular disease, the central blood pressure of the subject may be used. Central blood pressure may be a more direct indicator of cardiovascular disease than peripheral blood pressure.

In addition, arterial sclerosis (PWV) may be utilized as a direct marker used to determine whether the subject has cardiovascular disease.

In addition, the 24-hour ABPM (Ambulatory Blood Pressure Monitoring) result may be utilized as a direct marker used to determine whether the subject has cardiovascular disease. The 24-hour ABPM, also known as an active blood pressure test, refers to a test that continuously measures the blood pressure during activity with a portable automatic sphygmomanometer for 24 hours.

The direct markers used to determine whether a subject has cardiovascular disease are complex, time consuming, or expensive tests compared to OCT imaging.

On the other hand, in the case of OCT photography, only the OCT equipment can be used to take pictures without the presence of a specialist, and the photographed images are judged through the server, and after determining whether the subject possesses cardiovascular disease, selectively by a specialist according to the judgment result. Good access because it allows you to carry out care.

In the case of the elderly who are susceptible to cardiovascular disease, even if they live in an area with low hospital access, if they have only OCT equipment in a local clinic or public health center, the cardiovascular disease can be easily checked regularly according to the disclosed embodiment. There is a profit.

Furthermore, in the disclosed embodiment, the correlation between the OCT image and the markers described above may be determined, and the cardiovascular disease of the subject may be predicted based on the correlation.

Referring to FIG. 4, an example of a method for determining whether a subject has cardiovascular disease from an eyeball image using one or more markers is illustrated.

In an embodiment, the server 100 may train a model indicating a correlation between the OCT image and the at least one marker by using training data that labels at least one marker value on the OCT image 300.

For example, when the first marker 410 is the coronary artery calcification index (or calcium index) of the subject, the server 100 may train the model using OCT images labeled with the coronary artery calcification index of the subject. have.

The server 100 may input the OCT image 300 of the object to the trained model to estimate the coronary artery calcification index of the object from the OCT image.

Similarly, server 100 generates a trained model for each of one or more markers (eg, first marker 410 through third marker 430), or one or more trained for a plurality of markers. You can create a model.

As described with reference to FIG. 3, the server 100 may determine whether the subject has cardiovascular disease by using a model that directly determines whether the subject has cardiovascular disease.

In addition, as described in FIG. 4, the server 100 estimates and estimates one or more marker values from an object's OCT image using a model trained on one or more markers used to determine whether the subject has cardiovascular disease. Based on the marker value, it may be determined whether the subject has cardiovascular disease.

In addition, the server 100 may generate a model that may determine whether the subject has cardiovascular disease based on one or more marker values. The model that can determine whether the subject possesses cardiovascular disease based on one or more marker values may be a model learned by deep learning, or simply determine whether the subject possesses cardiovascular or cardiovascular risk from a marker value according to a predetermined criterion. It may also be a model composed of algorithms that can be determined.

In one embodiment, the server 100 may be a model for estimating one or more marker values from the OCT image 300 of the subject, and a model for determining whether the subject possesses cardiovascular disease or risk from one or more marker values. Using the OCT image 300 of the subject can automatically determine whether the cardiovascular disease or the risk of the subject.

In one embodiment, the server 100 retains the cardiovascular disease of the subject using one or more markers according to the method of determining whether or not the cardiovascular disease of the subject according to the method shown in FIG. The use of the method of determining whether or not together can determine whether the subject has cardiovascular disease.

For example, the server 100 may determine whether the subject possesses cardiovascular disease by using the method illustrated in FIG. 3 and the method illustrated in FIG. 4, and compare the results of the determination. If the comparison result does not match, the server 100 may review or request a review from the user.

As another example, the server 100 may classify as a subject to be closely examined and request a closer examination if it is determined that either of the two determination methods possesses or is at risk of having cardiovascular disease.

In addition, the server 100 may determine that there is a risk of disease retention or disease retention only if cardiovascular disease retention or retention risk is confirmed by both determination methods.

In addition, the server 100 may comprehensively calculate a cardiovascular disease retention probability of the object in consideration of both determination methods.

That is, the server 100 estimates one or more markers that can determine whether the subject has cardiovascular disease from the OCT image 300 of the subject, or maintains the cardiovascular disease of the subject based on correlation with each marker. (Or risk) can be determined.

5 is a diagram illustrating a method of extracting a new marker according to one embodiment.

In an embodiment, the server 100 may extract a new marker having a correlation with the OCT image using the model trained in FIG. 4.

For example, the server 100 may use the trained model representing the correlation between the OCT image and the one or more markers, which are learned in FIG. 4, so that a new fourth marker 440 is predetermined with the OCT image 300 of the object. It can be determined whether or not having a correlation of.

For example, when adding OCT images labeled with a fourth marker to the model trained in FIG. 4 as training data, a new fourth marker according to whether a model capable of estimating the fourth marker more than a predetermined probability is trained. It may be determined whether 440 has a predetermined correlation with the OCT image 300 of the object.

As another example, when the OCT images labeled with the fourth marker are added to the model trained in FIG. 4 as the training data, the model trained by the added training data has a predetermined probability of having the cardiovascular disease of the subject from the OCT image. The new fourth marker 440 may determine whether the new fourth marker 440 has a predetermined correlation with the OCT image 300 of the object.

As another example, when training is performed using OCT images labeled with a fourth marker on the untrained model as training data, is a model capable of estimating the fourth marker more than a predetermined probability from the OCT image of the object being trained? The new fourth marker 440 may determine whether the new fourth marker 440 has a predetermined correlation with the OCT image 300 of the object.

The method of extracting a new marker is not limited thereto, and when the new fourth marker 440 is extracted, the server 100 retrains an existing model using an OCT image labeled with a fourth marker, or a new marker. By training the model, a model capable of estimating whether the fourth marker or the subject possesses cardiovascular disease and risk may be obtained from the OCT image of the subject.

The server 100 may determine whether the subject possesses cardiovascular and cardiovascular disease from the OCT image 300 of the subject using a newly acquired model or a newly learned model.

In addition, the server 100 obtains various markers correlated with the OCT image 300 according to the above-described method in addition to the cardiovascular disease, and can obtain various body information of the object using only the ocular OCT image 300. Can be obtained. Accordingly, a model capable of replacing or assisting various types of other inspection methods by acquiring eye OCT of the object may be obtained by the method according to the disclosed embodiment.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, in a software module executed by hardware, or by a combination thereof. Software modules may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains may realize the present invention in other specific forms without changing the technical spirit or essential features thereof. I can understand that. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive.

10: eyeball imaging device
20: user client
100: server

Claims (10)

An acquisition unit for acquiring an eyeball image of the object by a computer; And
A first model for obtaining prediction values for a first marker from the eyeball image, and obtaining a first determination result of predicting a first disease from the derived prediction value of the first marker, wherein the first model is the first model. The predictive value for the marker is learned with a plurality of labeled set of eye images,
A second model is retrained to predict whether or not a second disease is obtained by adding, as training data, a plurality of eyeball image sets labeled with a second marker to the first model.
The first marker is information which is at least one of information obtained by a test method for a heart or a coronary artery for determining whether a cardiovascular disease is present, wherein the first marker and the second marker are different information. ,
Diagnostic aid. According to claim 1,
The eyeball image may be obtained by a second determination result of predicting whether a second disease of the subject is obtained through the second model.
Diagnostic aid. The method of claim 2,
When the first disease corresponds to the second disease, diagnostic assistant information is provided by comparing the first and second judgment results.
Diagnostic aid. The method of claim 2,
When the first disease and the second disease is different, the first judgment result and the second judgment result is provided as diagnostic assistance information,
Diagnostic aid. According to claim 1,
The test method may include at least one of a CT scan, an ultrasound test, and a blood pressure test.
Diagnostic aid. According to claim 1,
The predictive value for the first marker may include at least one of intravascular calcium index, intravascular thickness, central blood pressure, and atherosclerosis for the heart or coronary artery.
Diagnostic aid. An acquiring step of acquiring an eyeball image of the object by a computer; And
Diagnosis of the first marker is derived from the eyeball image, the diagnostic step of diagnosing through a first model for obtaining a first determination result of predicting a first disease from the derived prediction value of the first marker-the first The model is trained with a plurality of sets of eye images labeled with prediction values for the first marker,
A second model is retrained to predict whether or not a second disease is obtained by adding, as training data, a plurality of eyeball image sets labeled with a second marker to the first model.
The first marker is information which is at least one of information obtained by a test method for a heart or a coronary artery for determining whether a cardiovascular disease is present, wherein the first marker and the second marker are different information. ,
Diagnostic assistant method. A computer program, coupled to a computer, which is hardware, stored on a recording medium readable by a computer so as to perform the method of claim 7. delete delete

Images