Method for measuring myocardial thickness and computing device for performing the same

Abstract

The present invention relates to a method and apparatus for measuring the thickness of the myocardium in a cardiac imaging image, and more specifically, to a method for extracting spatial coordinates of the myocardium within a cardiac imaging image and measuring the thickness of the myocardium based thereon. A method for measuring the thickness of the myocardium performed on a computing device according to the present invention may include the steps of: acquiring an image of the heart using a medical imaging device; simultaneously segmenting the inner and outer boundaries of the myocardium using a learned artificial intelligence model based on the acquired cardiac image data; calculating the center point of the segmented inner boundary, wherein the learned artificial intelligence model includes a deep learning-based neural network model; generating straight lines at predetermined angular intervals based on the center point; calculating the intersection points where each of the generated straight lines intersects the inner boundary and the outer boundary; and calculating the thickness of the myocardium using the distance values ​​between each calculated intersection point. According to the present invention, the accuracy of thickness measurement can be improved by analyzing and calculating the thickness of the myocardium using image processing technology and an artificial intelligence model. In addition, the present invention can improve diagnostic efficiency by rapidly detecting abnormal thickness changes associated with cardiomyopathy and simplifying the diagnostic process, thereby contributing to appropriate treatment and further enabling its utilization in various medical environments.

Description

Technology Field

[0001] The present invention relates to a method and apparatus for measuring the thickness of the myocardium in a cardiac imaging image, and more specifically, to a method for extracting spatial coordinates of the myocardium within a cardiac imaging image and measuring the thickness of the myocardium based thereon. Background Technology

[0002] Cardiomyopathy is a disease characterized by structural and functional abnormalities of the heart muscle. Since it can lead to symptoms such as reduced contractility, arrhythmias, and heart failure, it is important to improve patient survival rates through early diagnosis and treatment.

[0003] Measuring myocardial thickness is a key factor in the diagnosis of such cardiomyopathy, and in particular, for hypertrophic cardiomyopathy, an increase in myocardial thickness serves as a major diagnostic criterion.

[0004] However, existing methods for measuring myocardial thickness have limitations. For example, in the case of cardiac ultrasound, accuracy varies depending on the resolution of the ultrasound or the skill of the operator, and there are limitations in detecting subtle changes in the heart structure. Additionally, in the case of magnetic resonance imaging (MRI), image distortion can occur due to the heartbeat, which increases the possibility of errors when measuring myocardial thickness.

[0005] For this reason, it is difficult to precisely measure the thickness of the myocardium and detect abnormal thickness changes associated with cardiomyopathy using existing technology.

[0006] Therefore, since this can make the early diagnosis of myocardial diseases such as cardiomyopathy difficult, there is a need to devise a more accurate and reliable method for measuring myocardial thickness to address the aforementioned problem. The problem to be solved

[0007] The present invention aims to provide a method for more accurately measuring the thickness of the myocardium within a cardiac image captured using a medical imaging device for the diagnosis of myocardial diseases such as cardiomyopathy, and for providing reliable diagnostic information. means of solving the problem

[0008] A method for measuring the thickness of a myocardium performed on a computing device according to the present invention to solve the above technical problem may include the steps of: acquiring an image of a heart using a medical imaging device; simultaneously segmenting the inner and outer boundaries of the myocardium using a learned artificial intelligence model based on the acquired heart image data; the learned artificial intelligence model including a deep learning-based neural network model; calculating the center point of the segmented inner boundary; generating straight lines at predetermined angular intervals based on the center point; calculating the intersection point where each of the generated straight lines intersects the inner boundary and the outer boundary; and calculating the thickness of the myocardium using the distance value between each calculated intersection point.

[0009] In addition, the above-mentioned trained artificial intelligence model may further include a step of analyzing the acquired heart image to determine the systolic and diastolic states, and then calculating the final thickness value for each state.

[0010] In addition, the above-mentioned predetermined angle intervals can be set to equal intervals or variable intervals that can be adjusted according to the characteristics of the acquired cardiac image data.

[0011] In addition, if the thickness value of the myocardium deviates from a predetermined threshold value, the method further includes a step of evaluating the risk of cardiomyopathy based on the calculated thickness value, and said risk can be evaluated by comparing it with the average value of the thickness value in the database.

[0012] Additionally, the method further includes a step of calculating the center point of the identified outer membrane boundary, and if the distance value between each calculated intersection point is greater than a predetermined reference distance value, a straight line can be generated based on the center point of the outer membrane boundary.

[0013] In addition, the method further includes a step of visualizing and providing related diagnostic information based on the risk of cardiomyopathy evaluated above, wherein the diagnostic information includes information on the type and severity of cardiomyopathy and can be visualized and provided through a graphical user interface (GUI).

[0014] Meanwhile, a computing device for performing the above-described method for measuring the thickness of the myocardium includes a processor and a memory that communicates with the processor, wherein the memory stores instructions that cause the processor to perform operations, and the operations may include the operation of acquiring an image of the heart using a medical imaging device, the operation of simultaneously segmenting the inner and outer boundaries of the myocardium using a learned artificial intelligence model of the acquired heart image data, the operation of calculating the center point of the segmented inner boundary, the operation of generating a straight line at a predetermined angle interval based on the center point, the operation of calculating the intersection point where each of the generated straight lines intersects the inner boundary and the outer boundary, and the operation of calculating the thickness of the myocardium using the distance value between each calculated intersection point.

[0015] In addition, the above-mentioned trained artificial intelligence model may further include the operation of analyzing the acquired heart image to determine the systolic and diastolic states, and then calculating the final thickness value for each state.

[0016] In addition, the above-mentioned predetermined angle intervals can be set to equal intervals or variable intervals that can be adjusted according to the characteristics of the acquired cardiac image data.

[0017] In addition, if the thickness value of the myocardium deviates from a predetermined threshold value, the method further includes an operation to evaluate the risk of cardiomyopathy based on the calculated thickness value, and the risk can be evaluated by comparing it with the average value of the thickness value in the database.

[0018] Additionally, the method further includes an operation to calculate the center point of the identified outer membrane boundary, and if the distance value between each calculated intersection point is greater than a predetermined reference distance value, a straight line can be generated based on the center point of the outer membrane boundary.

[0019] In addition, it further includes an operation to visualize and provide related diagnostic information based on the risk of cardiomyopathy evaluated above, wherein the diagnostic information includes information on the type and severity of cardiomyopathy and can be visualized and provided through a graphical user interface (GUI). Effects of the invention

[0020] The present invention can improve the accuracy of thickness measurement by utilizing image processing technology and an artificial intelligence model to analyze and calculate the thickness of the myocardium.

[0021] In addition, the present invention can improve diagnostic efficiency by rapidly detecting abnormal thickness changes associated with cardiomyopathy and simplifying the diagnostic process, thereby contributing to appropriate treatment and further enabling its utilization in various medical environments. Brief explanation of the drawing

[0022] FIG. 1 is a conceptual diagram showing a system for measuring the thickness of a myocardium according to one embodiment of the present invention. FIG. 2 is a flowchart illustrating a method for measuring the thickness of a myocardium according to one embodiment of the present invention. FIG. 3 is a flowchart illustrating a method for calculating the thickness value of a myocardium according to one embodiment of the present invention. FIGS. 4 to 9 are drawings for explaining a method of measuring the thickness of the myocardium using an image of the heart taken according to an embodiment of the present invention. FIG. 10 is an exemplary drawing that further illustrates a method for measuring the thickness of the myocardium using an image of the heart taken according to one embodiment of the present invention. FIG. 11 is an exemplary drawing for explaining the process of measuring and providing the thickness of a myocardium according to one embodiment of the present invention. FIG. 12 is a diagram showing the implementation of a computing device that performs a method for measuring the thickness of a myocardium according to one embodiment of the present invention. Specific details for implementing the invention

[0023] The following description merely illustrates the principles of the invention. Therefore, those skilled in the art may invent various devices that embody the principles of the invention and are included within the concept and scope of the invention, even if they are not explicitly described or illustrated in this specification. Furthermore, all conditional terms and embodiments listed in this specification are, in principle, explicitly intended only for the purpose of enabling an understanding of the concept of the invention and should be understood as not being limited to the embodiments and conditions specifically listed elsewhere.

[0024] The aforementioned objectives, features, and advantages will become clearer through the following detailed description in conjunction with the attached drawings, and accordingly, a person skilled in the art to which the invention pertains will be able to easily implement the technical concept of the invention.

[0025] In addition, in describing the invention, if it is determined that a detailed description of known technology related to the invention may unnecessarily obscure the essence of the invention, such detailed description will be omitted. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

[0026] FIG. 1 is a conceptual diagram showing a system for measuring the thickness of a myocardium according to one embodiment of the present invention.

[0027] Referring to FIG. 1, after a subject whose heart muscle thickness is to be measured undergoes cardiac imaging with a medical imaging device (10), the medical imaging device (10) can transmit the image obtained by photographing the subject to a computing device (300).

[0028] Here, the medical imaging device (10) refers to a device that non-invasively acquires a diagnostic image of a subject and may include, for example, an MRI (magnetic resonance imaging) device. The following description of the medical imaging device (10) of the present invention will be explained using an MRI device as an example.

[0029] In addition, while the subjects of examination can be exemplified by the human body, this is not limited to this and may also apply to other animals.

[0030] Here, the captured image may correspond to any of the cardiac magnetic resonance imaging (Cardiac MRI) images, and among them, Cine-MRI SAX (Cine Magnetic Resonance Imaging Short-Axis) images used to evaluate the structure and function of the heart may be applicable.

[0031] Specifically, because Cine-MRI shows movement over time, it allows for the quantitative analysis of cardiac wall movement, blood flow, and changes in ventricular volume. Cine-MRI SAX is primarily used to evaluate the systolic and diastolic functions of the left ventricle of the heart. SAX stands for Short-Axis Plane, and through images of cross-sections (transverse planes) of the heart, it enables accurate analysis of cardiac motility disorders, wall motion evaluation, and intracardiac blood flow.

[0032] Therefore, the computing device (300) can provide important information for diagnosing heart diseases such as left ventricular hypertrophy, cardiomyopathy, and myocardial infarction. The computing device (300) can train an artificial intelligence model that simultaneously segments the inner and outer membrane boundaries (500 and 400) of the myocardium using heart image data obtained through the received image.

[0033] Additionally, the computing device (300) can train an artificial intelligence model using each heart image data acquired based on the received image, and as a result, extract the spatial coordinates of the heart muscle.

[0034] Here, the spatial coordinates of the myocardium are coordinates for the region of the myocardium among the structures of the heart, and may be configured to include boundary points such as the region of the myocardium, the boundary of the inner membrane of the myocardium (500), or the boundary of the outer membrane of the myocardium (400), but are not limited thereto and may be configured to include additional specific points within the myocardium required by medical personnel.

[0035] Hereinafter, with reference to FIG. 2, a method for measuring the thickness of the myocardium of a computing device (300) will be explained in more detail.

[0036] FIG. 2 is a flowchart illustrating a method for measuring the thickness of a myocardium according to one embodiment of the present invention.

[0037] First, referring to FIG. 2, a computing device (300) can obtain an image of the heart from a medical imaging device (10) (S100). This step may include the step of photographing the heart using a Magnetic Resonance Imaging (MRI) scanner, the step of generating image data that the computing device (300) can understand from the captured magnetic resonance signal, and the step of transmitting the generated image data to the computing device (300).

[0038] Specifically, an MRI scanner can measure the magnetic resonance of internal tissues using a strong magnetic field and radio frequency waveforms, and can image various parts of the body to create images. In addition, the image data is stored in the DICOM (Digital Imaging and Communications in Medicine) format, and DICOM is a standardized format for medical imaging that can include metadata related to the images.

[0039] Here, the image of the heart obtained can also be obtained in the form of an image as shown in Fig. 4.

[0040] Next, the computing device (300) can simultaneously segment the inner and outer membrane boundaries (500 and 400) of the myocardium using an artificial intelligence model learned based on acquired cardiac image data (S200).

[0041] Here, the type of the captured video can be determined according to the video technology used and the purpose of the recording.

[0042] In general, MRI is a non-invasive method used to evaluate the structure and function of the heart. MRI helps to detect and evaluate the structure and function of heart tissue, and as a result, can be used to diagnose various heart diseases.

[0043] Here, the trained artificial intelligence model may include a deep learning-based neural network model. In particular, it can be implemented with a deep learning-based neural network model such as U-Net and can be trained using a loss function such as the Dice Loss function.

[0044] Specifically, a U-net model is a network architecture primarily used for segmentation tasks in bio or medical imaging, and can refer to a model used to perform accurate segmentation of myocardial boundaries, such as the intima and adventitia, or to detect abnormalities.

[0045] Meanwhile, the structure of the artificial intelligence model is not limited to the aforementioned UNet model and may also be implemented as a separately trained encoder-decoder-based CNN (Convolutional Neural Network) model.

[0046] In addition, the Dice loss function is one of the loss functions used to train a model by measuring the overlap between the actual boundary and the model's predicted boundary, and can be derived as Equation 1.

[0047] [Mathematical Formula 1]

[0048]

[0049] Here, Dice Loss represents the loss of the Dice coefficients, T represents the actual boundary, and P represents the predicted boundary. |P| and |T| are the sum (union) of the predicted boundary and the actual boundary regions, respectively; therefore, |P∩T| in the numerator and denominator can represent the size of the overlapping portion (intersection) between the actual boundary and the predicted boundary.

[0050] In other words, since training a model to minimize the Dice loss function causes the model's predicted boundaries to become closer to the actual boundaries, it can be an effective function for deep learning models, such as UNET models, where the predicted boundaries must match the actual boundaries as closely as possible. Additionally, it can be effective for boundary prediction in small regions, such as the heart muscle.

[0051] In this embodiment, a deep learning model can be trained so that the loss of the Dice coefficient for each prediction probability regarding the boundary between the intima and adventitia of the myocardium is minimized.

[0052] In summary, the artificial intelligence model according to the present embodiment can receive an image as input and, based on the anatomical location output by the artificial intelligence model, simultaneously segment the boundary of the myocardial intima (500) and the boundary of the outer membrane (400) as shown in FIG. 5.

[0053] In addition, the artificial intelligence model according to the present embodiment may analyze acquired heart images to determine the systolic and diastolic states, and after determining the state, calculate the final thickness value for each state to calculate the thickness value of the myocardium more accurately.

[0054] In addition, the artificial intelligence model according to the present embodiment can measure the thickness of the myocardium to diagnose whether a disease such as cardiomyopathy exists, or can predict risk factors for a disease such as cardiomyopathy that may occur in the future based on image data through the pattern of change in anatomical position in conjunction with a time series model.

[0055] A specific method for extracting the thickness value of the myocardium will be explained with reference to FIGS. 3 to 9.

[0056] FIG. 3 is a flowchart illustrating a method for calculating the thickness of a myocardium according to an embodiment of the present invention, and FIGS. 4 to 9 are drawings for explaining a method for measuring the thickness of a myocardium using an image of a heart taken according to an embodiment of the present invention.

[0057] Referring to FIG. 3, the computing device (300) can calculate the center point (550) of the endocardial boundary (500) of the segmented myocardium (S210).

[0058] Here, as shown in FIG. 6, the center point (550) is a coordinate value representing an area inside the myocardium, and can be composed of at least one coordinate value.

[0059] Additionally, the value of the center point (550) may be determined variably according to the characteristics of the myocardium in the image, and the value may be configured to include a value for a specific point inside the myocardium required by medical staff or personnel.

[0060] Specifically, to calculate the center point (550), the computing device (300) can calculate the average value of the coordinates on the intima-boundary (500) using the spatial coordinates of the extracted myocardium, and the calculation of the center point (550) is not limited to the above method, but can also be calculated using a method using the average of the centroids of the intima-boundary region, an algorithm, etc., depending on the judgment of medical staff or examination personnel.

[0061] Additionally, the calculated center point (550) may be labeled according to the location of the myocardium in the image, and may be fed into a deep learning model to be used for producing training data.

[0062] Next, the computer device (300) can generate a straight line (600) at predetermined angle intervals based on a calculated center point (550) (S220).

[0063] Specifically, referring to FIG. 7, the computing device (300) can generate a predetermined number of straight lines (600) by using a polar coordinate system based on an acquired center point (550) to calculate the slope of a straight line according to a predetermined angle.

[0064] Here, the angle can be expressed in units of radians or degrees, and the interval of the angle can be set as an equal interval or a variable interval adjustable according to the characteristics of the acquired cardiac image data. Specifically, the interval of the angle set can be adjusted by medical staff or personnel before or after the shot according to variables such as the characteristics of the subject being shot, such as a history of diagnosis of cardiomyopathy, and the type of medical imaging device (10).

[0065] Additionally, the straight line (600) in FIGS. 7 and FIGS. 10 is drawn based on an angle of 3.6 degrees, but is not limited thereto and the angle may be flexible depending on the judgment of medical staff or relevant personnel or for diagnostic purposes, and the number of straight lines (600) generated may be determined accordingly.

[0066] Next, the computer device (300) can calculate the intersection points (570 and 450) where the generated straight line (600) intersects the inner and outer membrane boundaries (500 and 400) (S230).

[0067] Specifically, referring to FIG. 8, the intersection point (570) where the generated straight lines (600) meet at the boundary (500) of the inner membrane and the intersection point (450) where they meet at the boundary (400) of the outer membrane can be calculated.

[0068] The intersection points (570 and 450) may be any point within the myocardial region and may be represented by spatial coordinates. Additionally, the number of intersection points (570 and 450) may vary depending on the number of predetermined angles and lines (600).

[0069] Next, the computer device (300) can calculate the thickness value of the myocardium using the distance value between the intersection points (570 and 450) where the inner and outer membrane boundaries (500 and 400) intersect (S300).

[0070] Specifically, the computing device (300) can calculate the straight-line distance value between the intersection points (570 and 450) through the internal thickness value calculation unit (320).

[0071] The computing device (300) can assist in the diagnosis of hypertrophic cardiomyopathy (HCM) by using the respective distances of multiple straight lines.

[0072] First, reference lines can be used by referring to (a) and (b) of Fig. 10. Multiple reference lines with predetermined angular intervals can be selected, and the distance from the endocardium to the epicardium can be measured through the intersection points of the straight lines that overlap with the reference lines.

[0073] Alternatively, it is also possible to diagnose the presence of HCM by using the largest value among the myocardial thicknesses measured along all straight lines. Since myocardial hypertrophy is generally diagnosed based on the thickest area, using the maximum value can be advantageous for increasing diagnostic sensitivity.

[0074] The method of using maximum values ​​can serve as a highly sensitive criterion for HCM diagnosis and can reflect even extreme localized hypertrophy of the myocardium, thereby increasing diagnostic sensitivity.

[0075] Alternatively, it is also possible to compare the distance between regions and the critical distance for diagnosis based on the regions that separate the myocardium.

[0076] For example, HCM can be diagnosed by dividing the heart into six regions according to the American Heart Association (AHA) standards and averaging the straight-line distance from the endocardium to the epicardium measured in each region. The heart muscle can be divided into 6 or 17 regions to calculate the heart muscle thickness in each region, and this value can be used to evaluate the pattern of overall heart muscle hypertrophy.

[0077] Since it allows for a comprehensive evaluation of the entire myocardium, it can provide more accurate results in the diagnosis of HCM. Therefore, by utilizing it in conjunction with the aforementioned maximum values, it is possible not only to reflect localized changes but also to evaluate overall myocardial hypertrophy.

[0078] According to the present invention, the possibility of myocardial hypertrophy can be evaluated based on myocardial thickness values ​​measured using MRI CINE images, the risk level of the patient can be analyzed, and the system can be designed to be used for customized treatment and management. The calculated myocardial thickness values ​​can be stored in a database (340) and used for more precise prediction and patient management.

[0079] For example, in the case of athlete patients, since it is important to differentiate whether myocardial hypertrophy is a physiological change caused by training or a pathological change, if a threshold is exceeded, the presence of cardiomyopathy must be confirmed through precise examination, and in some cases, restrictions on strenuous exercise may be necessary. Through this, the present invention can be utilized to protect the heart health of athletes and to determine the feasibility of safe sports activities.

[0080] The present invention can also contribute to classifying specific patient groups and comparing long-term prognoses in clinical studies by establishing diagnostic criteria utilizing threshold values. By utilizing accumulated myocardial thickness data, long-term studies and the development of risk models can be conducted, and diagnostic criteria can be optimized by performing quantitative evaluations based on various patient groups. Through this, the present invention can provide a data-driven precision medicine environment and support more systematic, patient-tailored management.

[0081] In addition, with reference to FIG. 9, it is also possible to extract a reference midpoint of a predetermined interval of the myocardial region and evaluate myocardial hypertrophy using the distance of the lines corresponding to the midpoint coordinates (700) of the reference midpoint.

[0082] The reference midpoint can be extracted through a separate neural network or calculated based on the midpoint between the endocardium and epicardium boundaries.

[0083] The computing device can calculate the distance using the intersection point of the straight line closest to the reference midpoint, and the reference midpoint (700) may be visually represented as in (a) or (b) of FIG. 10.

[0084] In addition, if the calculated myocardial thickness value deviates from a predetermined threshold, the risk of cardiomyopathy can be assessed based on the calculated thickness value.

[0085] Here, the threshold value refers to a value that can be pre-set according to the type of cardiomyopathy, the subject's genetic factors, or the history of cardiomyopathy diagnosis. For example, the threshold value for a subject without genetic factors can be set to 15 mm, and the threshold value for a subject with genetic factors can be set to 13 mm.

[0086] For the early diagnosis of cardiomegaly, the possibility of the condition may be considered if myocardial thickness exceeds a preset threshold. In the absence of genetic factors, a left ventricular wall thickness of 15 mm or greater is classified as a suspected case of cardiomegaly; in the presence of genetic factors, a thickness of 13 mm or greater requires consideration of the possibility of cardiomegaly. Specifically, for children, the presence of early cardiomegaly can be assessed by utilizing the Z-score of left ventricular wall thickness relative to body surface area. This enhances the objectivity of image interpretation and allows for effective utilization in the initial screening process.

[0087] For patients suspected of having hypertrophic cardiomyopathy without a genetic factor, regular follow-up is recommended in the 13–15 mm range, and if it is 15 mm or larger, it is advisable to perform additional tests such as genetic testing, echocardiography, and stress tests. In cases where a genetic factor is present and the threshold is exceeded, this can be used to determine early diagnosis and prophylactic treatment (e.g., administration of beta-blockers).

[0088] Additionally, the risk being evaluated can be evaluated by type of cardiomyopathy by comparing it with the average value of the thickness value in the database (340) in the risk evaluation unit (360) inside the computing device (300).

[0089] It can also be used to assess the risk of sudden cardiac death (SCD) in patients with increased calculated myocardial thickness values. For example, a left ventricular wall thickness of 30 mm or more can be assessed as having a high risk of sudden cardiac death, and a thickness of 28 mm or more can also be considered a risk factor at the clinician's discretion.

[0090] Next, the computer device (300) can visualize and provide related diagnostic information based on the evaluated risk of cardiomyopathy (S500).

[0091] Specifically, referring to Fig. 11, the diagnostic information includes information on the type and severity of cardiomyopathy and can be visualized and provided through a graphical user interface (GUI).

[0092] Here, the graphical user interface (GUI) can be provided to medical staff or personnel via monitors and touch screens to guide patients to easily understand diagnostic information and assist in diagnosis, and can also be provided directly to patients to enable them to make intuitive decisions, such as scheduling treatment.

[0093] In addition, diagnostic information provided according to the subject's age may be presented differently, for example, by increasing the font size, and may also be updated and provided at predetermined intervals.

[0094] The computing device (300) according to the above embodiment may have the feature of being able to measure the thickness of the myocardium by acquiring an image from a medical imaging device (10) to simultaneously segment the inner and outer membrane boundaries (500 and 400) of the myocardium using a learned artificial intelligence model, calculating the center point (550) of the segmented inner membrane boundary (500) to generate a straight line (600) at intervals of a predetermined angle based on the center point (550), calculating the intersection points (570 and 450) where the straight line (600) intersects the inner and outer membrane boundaries (500 and 400), and finally measuring the thickness of the myocardium by using the distance values ​​between each intersection point (570 and 450).

[0095] With reference to FIG. 12 below, a specific hardware implementation of a server as a computing device for performing the method for measuring the thickness of the myocardium according to the present embodiment will be described.

[0096] Referring to FIG. 12, in some embodiments of the present invention, the server (300) may be implemented in the form of a computing device. One or more of the modules constituting the server (300) are implemented on a general-purpose computing processor and thus may include a processor (388), an input / output I / O (382), a memory (384), an interface (386), and a bus (385). The processor (388), the input / output device (382), the memory (384), and / or the interface (386) may be coupled to each other through the bus (385). The bus (385) corresponds to a path through which data travels.

[0097] Specifically, the processor (388) may include at least one of a CPU (Central Processing Unit), MPU (Micro Processor Unit), MCU (Micro Controller Unit), GPU (Graphic Processing Unit), microprocessor, digital signal processor, microcontroller, application processor (AP), and logic elements capable of performing similar functions.

[0098] The input / output device (382) may include at least one of a keypad, a keyboard, a touchscreen, and a display device. The memory device (384) may store data and / or programs, etc.

[0099] The interface (386) can perform the function of transmitting data to a communication network or receiving data from a communication network. The interface (386) may be wired or wireless. For example, the interface (386) may include an antenna or a wired / wireless transceiver, etc. The memory (384) is a volatile operational memory for enhancing the operation of the processor (388) and protecting personal information, and may further include high-speed DRAM and / or SRAM, etc.

[0100] Additionally, the memory (384) stores programming and data configurations that provide the functions of some or all of the modules described herein. For example, it may include logic that enables the execution of selected modes of the learning method described above.

[0101] A set of instructions comprising each step of performing the above-described learning method stored in memory (384), the operation of acquiring an image of the heart using a program or a medical imaging device; the operation of simultaneously segmenting the inner and outer boundaries of the myocardium using a learned artificial intelligence model based on the acquired heart image data; the operation of calculating the center point of the segmented inner boundary, wherein the learned artificial intelligence model includes a deep learning-based neural network model; the operation of generating straight lines at predetermined angular intervals based on the center point; the operation of calculating the intersection point where each of the generated straight lines intersects the inner boundary and the outer boundary; and the operation of calculating the thickness value of the myocardium using the distance value between each calculated intersection point; the operation of the learned artificial intelligence model analyzing the acquired heart image to determine the systolic and diastolic states and then calculating the final thickness value for each state; the operation of evaluating the risk of cardiomyopathy based on the calculated thickness value when the thickness value of the myocardium deviates from a predetermined threshold value; the operation of calculating the center point of the segmented outer boundary; and the operation of related based on the evaluated risk of cardiomyopathy A computer program including actions such as visualizing and providing diagnostic information can be executed by a processor.

[0102] According to the present invention, the accuracy of thickness measurement can be improved by utilizing image processing technology and an artificial intelligence model to analyze and calculate the thickness of the myocardium.

[0103] In addition, the present invention can improve diagnostic efficiency by rapidly detecting abnormal thickness changes associated with cardiomyopathy and simplifying the diagnostic process, thereby contributing to appropriate treatment and further enabling its utilization in various medical environments.

[0104] Furthermore, the various embodiments described herein may be implemented, for example, in a recording medium readable by a computer or similar device using software, hardware, or a combination thereof.

[0105] According to hardware implementation, the embodiments described herein may be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, and other electrical units for performing functions. In some cases, the embodiments described herein may be implemented as the control module itself.

[0106] According to software implementation, embodiments such as the procedures and functions described herein may be implemented in separate software modules. Each of the software modules may perform one or more functions and operations described herein. Software code may be implemented as a software application written in a suitable programming language. The software code may be stored in a memory module and executed by a control module.

[0107] The above description is merely an illustrative explanation of the technical concept of the present invention, and those skilled in the art to which the present invention pertains will be able to make various modifications, changes, and substitutions within the scope of the essential characteristics of the present invention without departing from its nature.

[0108] Accordingly, the embodiments disclosed in this invention and the accompanying drawings are intended to illustrate, not limit, the technical concept of the invention, and the scope of the technical concept of the invention is not limited by such embodiments and accompanying drawings. The scope of protection of this invention shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of this invention.

Claims

Claim 1 A method for measuring the thickness of a myocardium performed on a computing device, comprising: a step of acquiring an image of a heart using a medical imaging device; a step of simultaneously segmenting the inner and outer boundaries of the myocardium using a learned artificial intelligence model based on the acquired heart image data; a step of calculating the center point of the segmented inner boundary, wherein the learned artificial intelligence model includes a deep learning-based neural network model; a step of generating straight lines at predetermined angular intervals based on the center point; a step of calculating the intersection points where each of the generated straight lines intersects the inner boundary and the outer boundary; and a step of calculating the thickness of the myocardium using the distance values ​​between each calculated intersection point. Claim 2 A method for measuring myocardial thickness according to claim 1, further comprising the step of the learned artificial intelligence model analyzing the acquired heart image to determine the systolic and diastolic states and then calculating a final thickness value for each state. Claim 3 A method for measuring myocardial thickness according to claim 1, characterized in that the predetermined angle interval is set as an equal interval or a variable interval adjustable according to the characteristics of the acquired cardiac image data. Claim 4 A method for measuring myocardial thickness according to claim 1, further comprising the step of evaluating the risk of cardiomyopathy based on the calculated thickness value when the thickness value of the myocardium deviates from a predetermined threshold value, wherein the risk is evaluated by comparing it with the average value of a database for the thickness value. Claim 5 A method for measuring the thickness of a myocardium according to claim 1, further comprising the step of calculating the center point of the segmented outer membrane boundary; and, if the distance value between each calculated intersection point is greater than a predetermined reference distance value, generating a straight line based on the center point of the outer membrane boundary. Claim 6 A method for measuring the thickness of the myocardium according to claim 4, further comprising the step of visualizing and providing related diagnostic information based on the evaluated risk of cardiomyopathy; wherein the diagnostic information includes information on the type and severity of cardiomyopathy and is visualized and provided through a graphical user interface (GUI). Claim 7 A computing device comprising a processor and a memory communicating with said processor, wherein the memory stores instructions that cause said processor to perform operations, said operations comprising: acquiring an image of a heart using a medical imaging device; simultaneously segmenting the inner and outer boundaries of the myocardium using a learned artificial intelligence model of the acquired heart image data; said learned artificial intelligence model including a deep learning-based neural network model; calculating the center point of the segmented inner boundary; generating straight lines at predetermined angular intervals based on said center point; calculating the intersection point where each of said generated straight lines intersects the inner boundary and the outer boundary; and calculating the thickness value of the myocardium using the distance value between each calculated intersection point. Claim 8 A computing device according to claim 7, further comprising the step of the learned artificial intelligence model analyzing the acquired heart image to determine the systolic and diastolic states and then calculating a final thickness value for each state. Claim 9 A computing device according to claim 7, characterized in that the predetermined angle interval is set as an equal interval or a variable interval adjustable according to the characteristics of the acquired cardiac image data. Claim 10 A computing device according to claim 7, further comprising an operation to evaluate the risk of cardiomyopathy based on a calculated thickness value when the thickness value of the myocardium deviates from a predetermined threshold value, wherein the risk is evaluated by comparing it with the average value of a database for the thickness value. Claim 11 A computing device according to claim 7, further comprising the operation of calculating the center point of the segmented outer membrane boundary, and characterized by generating a straight line based on the center point of the outer membrane boundary when the distance value between each calculated intersection point is greater than a predetermined reference distance value. Claim 12 A computing device according to claim 10, further comprising an operation to visualize and provide related diagnostic information based on the evaluated risk of cardiomyopathy, wherein the diagnostic information includes information on the type and severity of cardiomyopathy and is provided visualized through a graphical user interface (GUI).

Images