Method of operation of an apparatus for digitizing the waveform images of each channel of an electrocardiogram

Abstract

A method for controlling an electronic device is disclosed. The control method comprises the steps of: identifying a target area containing an electrocardiogram within an image composed of an electrocardiogram recording sheet; identifying the number of pixels constituting a unit scale of the electrocardiogram based on the target area; and quantifying the waveform of the electrocardiogram based on calibration wave information within the image and the identified number of pixels.

Description

Technology Field

[0001] The present disclosure relates to an electrocardiogram analysis and storage technology, and more specifically, to a control method for an electronic device that extracts and stores time-series data by dividing each section of an electrocardiogram record sheet by channel. Background Technology

[0002] In the case of electrocardiogram (ECG) records measured or acquired through conventional ECG equipment, it was common for experts, such as doctors, to visually inspect them and use them for diagnosis.

[0003] However, in order to use various patient data as educational materials or training data for artificial intelligence models, or to utilize other automated diagnostic algorithms, specific devices or systems are required for data anonymization, purification, and storage.

[0004] For example, conventionally, time-series data is used when analyzing electrocardiograms with artificial intelligence models. However, since electrocardiogram data stored in hospitals is saved as images, it is necessary to quantify and utilize waveforms from the images of the electrocardiogram records. Prior art literature

[0005] Registered Patent Publication No. 10-2362679 The problem to be solved

[0006] The present disclosure provides a control method for an electronic device that analyzes and processes an image of an electrocardiogram record sheet to convert and store channel-specific waveforms into time-series data.

[0007] The purposes of the present disclosure are not limited to those mentioned above, and other purposes and advantages of the present disclosure not mentioned may be understood from the following description and will be more clearly understood from the embodiments of the present disclosure. Furthermore, it will be readily apparent that the purposes and advantages of the present disclosure can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0008] A control method for an electronic device according to one embodiment of the present disclosure comprises the steps of: the electronic device identifying a target area containing an electrocardiogram within an image composed of an electrocardiogram recording sheet; the electronic device identifying a number of pixels constituting a unit scale of the electrocardiogram based on the target area; and the electronic device quantifying a waveform of the electrocardiogram based on correction wave information within the image and the identified number of pixels.

[0009] The step of identifying the number of pixels may include: a step of obtaining a first image by extracting the R value among the R (Red), G (Green), and B (Blue) of each of the plurality of pixels included in the target area; a step of obtaining a second image by changing the R value of the pixel having the maximum R value in the first image to 0; a step of calculating a cumulative value by summing all the values ​​of the pixels in the first axis direction on the second image; a step of identifying the interval between unit scales by comparing the cumulative value in the second axis direction perpendicular to the first axis; and a step of identifying the number of pixels constituting the unit scale based on the identified interval.

[0010] At this time, the step of identifying the number of pixels can be performed by obtaining the accumulated value for each of the plurality of points along the second axis, selecting a certain number of points among the plurality of points where the difference of the accumulated value is less than a threshold and the interval is constant, and identifying the interval between the selected points as the interval between unit scales to identify the number of pixels constituting the unit scale.

[0011] Here, the step of identifying the number of pixels may involve selecting a certain number of first points among the plurality of points where the difference in the accumulated value is less than a threshold and the interval is constant, selecting a certain number of second points among the plurality of points where the difference in the accumulated value is less than a threshold and the interval is constant, and if the interval between the second points is greater than the interval between the first points, the interval between the first points may be identified as one scale interval and the interval between the second points may be identified as five scale intervals.

[0012] Meanwhile, the control method of the electronic device may include the step of obtaining a binary image by binarizing a plurality of pixels included in the target area, and the step of dividing the binary image into a plurality of waveform images based on each channel constituting the electrocardiogram. At this time, the quantification step may include the step of obtaining time-series data by quantifying each of the plurality of waveform images based on the calibration wave information and the number of identified pixels, and the step of storing the time-series data by channel.

[0013] Here, the step of dividing the binary image into a plurality of waveform images may divide the binary image into a plurality of first waveforms based on the continuity of the waveforms, and divide each of the plurality of first waveforms into a plurality of second waveforms based on vertical lines of a certain length or longer included in the binary image.

[0014] And, the step of acquiring the time series data may acquire correction wave information including a reference waveform, the time length of the reference waveform, and the magnitude of the reference waveform within the image, and based on the correction wave information and the number of identified pixels, acquire time and amplitude for each point of the waveform constituting each of the plurality of waveform images.

[0015] Meanwhile, the control method of the electronic device may include the step of the electronic device recognizing text within a region containing basic information within the image to identify the unit time length of at least one channel included in the patient information and electrocardiogram. Effects of the invention

[0016] The control method of an electronic device according to the present disclosure has the effect of accurately extracting numerical data for each point of a waveform regardless of the specifications of the electrocardiogram recording paper by preemptively identifying the number of pixels matching the scale interval. That is, electrocardiogram recording papers of various specifications can be refined and stored without restrictions. Brief explanation of the drawing

[0017] FIG. 1 is a flowchart illustrating a control method for an electronic device that extracts and stores electrocardiogram data according to one embodiment of the present disclosure, FIGS. 2a and 2b are drawings for explaining the operation of an electronic device according to one embodiment of the present disclosure extracting a target area corresponding to an electrocardiogram within an image including an electrocardiogram recording sheet, FIGS. 3a to 3e are drawings for explaining the operation of an electronic device according to one embodiment of the present disclosure identifying the number of pixels that match the scale of an electrocardiogram, FIG. 3f is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure acquiring correction wave information within an image including an electrocardiogram recording sheet, FIGS. 4a to 4e are drawings for illustrating the process of quantifying an electrocardiogram included in a target area by an electronic device according to one embodiment of the present disclosure, and FIG. 5 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present disclosure. Specific details for implementing the invention

[0018] Before specifically describing the present disclosure, the method of description in the specification and drawings is described.

[0019] First, the terms used in this specification and claims have been selected based on general terms considering their functions in the various embodiments of this disclosure. However, these terms may vary depending on the intent of those skilled in the art, legal or technical interpretations, and the emergence of new technologies. Additionally, some terms have been arbitrarily selected by the applicant. Such terms may be interpreted according to the meanings defined in this specification; in the absence of specific definitions, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant field.

[0020] In addition, the same reference numbers or symbols described in each drawing attached to this specification represent parts or components that perform substantially the same function. For convenience of explanation and understanding, the same reference numbers or symbols are used to describe different embodiments. That is, even if components having the same reference number are all depicted in multiple drawings, the multiple drawings do not imply a single embodiment.

[0021] Additionally, in this specification and claims, terms including ordinal numbers, such as "first," "second," etc., may be used to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from one another, and the meaning of the terms should not be limited by the use of such ordinal numbers. For example, the order of use or arrangement of components combined with such ordinal numbers should not be restricted by the number. If necessary, each ordinal number may be used interchangeably.

[0022] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0023] In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except where each needs to be implemented in specific individual hardware.

[0024] Furthermore, in the embodiments of the present disclosure, when a part is described as being connected to another part, this includes not only a direct connection but also an indirect connection through another medium. Additionally, the meaning that a part includes a certain component implies that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0025] FIG. 1 is a flowchart illustrating a control method for an electronic device that analyzes and stores an electrocardiogram record sheet according to one embodiment of the present disclosure.

[0026] The electronic device may correspond to a device or system including at least one computer. For example, the electronic device may correspond to various devices such as a desktop PC, tablet PC, smartphone, or server device. Additionally, the electronic device may be implemented as at least one control device or server connected to an electrocardiogram device.

[0027] The electronic device may receive images including electrocardiogram (ECG) records of various patients from at least one external device (e.g., an ECG device, a hospital server, or a user terminal including a camera). In this case, the image may be an image generated by numerically outputting the waveform of the ECG record, or it may be an image of the ECG record captured.

[0028] Through the following embodiments, the electronic device can electronically extract the patient's electrocardiogram data and store it in an optimal form.

[0029] Referring to FIG. 1, first, the electronic device can identify a target area containing an electrocardiogram within an image (S110).

[0030] At this time, the electronic device can perform preprocessing to level the image based on at least one of text, waveform, or scale included in the image. For example, the electronic device can recognize text based on character recognition technology such as OCR (Optical Character Recognition) while leveling the image based on the degree of tilt of the text. As another example, the electronic device can identify the direction of the waveform or scale and correct the image so that the identified direction becomes level.

[0031] In addition, the electronic device can extract a target region containing waveforms representing an electrocardiogram within the image.

[0032] In this regard, FIG. 2a illustrates an exemplary image (: electrocardiogram record) corresponding to a horizontally aligned state.

[0033] In one embodiment, the electronic device may extract a target area based on at least one color (e.g., RED) that matches the scale of the electrocardiogram. The scale corresponds to a dot or line representing a numerical unit associated with the waveform of the electrocardiogram within the electrocardiogram recording sheet.

[0034] Referring to the image in Fig. 2a, it is confirmed that the scale corresponds to red. In this case, the electronic device can be programmed to select pixels within the image whose R(Red) value is greater than or equal to a certain value. As a result, the electronic device can select all pixels corresponding to the scale.

[0035] However, additionally, the electronic device may perform filtering one or more times based on coordinate information for pixels whose R value is greater than or equal to a certain value. Specifically, assume a situation where the coordinates of each pixel are set according to the x-axis and y-axis within an image. Here, regarding pixels whose R value is greater than or equal to a certain value, the electronic device may group pixels with identical x values ​​by their respective x values, and pixels with identical y values ​​by their respective y values. At this time, the electronic device may exclude pixels that do not belong to either group from the selection target. Alternatively, the electronic device may exclude pixels that do not belong to either group with identical x values ​​or group with identical y values ​​from the selection target. This takes into account the characteristics of the grid that is densely and uniformly arranged in a certain direction, and has the effect of removing pixels that could be selected solely because their R value is greater than or equal to a certain value, even though they do not correspond to the grid.

[0036] And, the electronic device can extract a target area containing the selected pixels. For example, the electronic device can extract a target area of ​​a square that contains all the selected pixels and has the smallest size, but is not limited thereto. As a result, a target area (210) containing only the waveform of the electrocardiogram can be extracted as shown in FIG. 2b.

[0037] In addition, as another embodiment for extracting a target region, the electronic device can identify at least one waveform included in an image. To this end, at least one module or artificial intelligence model trained to identify waveforms may be utilized. The artificial intelligence model may be, for example, a CNN model trained to identify at least one waveform corresponding to an electrocardiogram within an image, and may be trained based on images containing waveforms of various patients and images without waveforms. In this case, the electronic device can extract a single target region containing all identified waveforms by inputting the image into the artificial intelligence model.

[0038] Meanwhile, in addition to the target area, the electronic device can obtain basic information of the electrocardiogram record contained within the image. Specifically, the electronic device can obtain patient information by recognizing text contained at a preset location (e.g., the top of the image) that matches the basic information. The patient information may include, but is not limited to, the patient's name, age, presence / severity of disease, weight, height, measurement date, etc. In a control method for an electronic device that analyzes each patient's electrocardiogram record and stores it by channel according to various embodiments of the present disclosure, the electronic device may perform anonymization by removing the patient's name, measurement date, age, etc. That is, time-series data for the electrocardiogram may be stored along with the anonymized patient information. Furthermore, the electronic device can identify the unit time length of at least one channel included in the electrocardiogram by recognizing text corresponding to the basic information.

[0039] Meanwhile, when a target area is extracted according to at least one of the embodiments described above, the electronic device can identify the number of pixels constituting a unit scale of the electrocardiogram within the target area (S120).

[0040] In this regard, FIGS. 3a to 3e are drawings for explaining the operation of an electronic device according to one embodiment of the present disclosure identifying the number of pixels that match the scale of an electrocardiogram.

[0041] Figure 3a illustrates an image area included in the target area (210) of Figure 2b.

[0042] Here, the electronic device can obtain a first image by extracting the R value among the R (Red), G (Green), and B (Blue) of each of the plurality of pixels included within the target area. Then, the electronic device can obtain a second image by changing the R value of the pixel having the maximum R value within the first image to 0. For example, if each of the R, G, and B of each pixel can have a value from 0 to 255, the pixel with an R value of 255 corresponds to a white background (where R, G, and B are all 255) from the beginning.

[0043] As a result, a second image such as Fig. 3b can be obtained. In the second image, only some pixels corresponding to the red scale are visible in red, while all other pixels that are not on the scale or were white backgrounds are changed to black.

[0044] Here, the electronic device can calculate a cumulative value by summing all the pixel values ​​in the first axis direction (e.g., x-axis or y-axis) on the second image of FIG. 3B. At this time, the electronic device can identify the interval of a unit scale by comparing the cumulative value in the second axis direction perpendicular to the first axis, and identify the number of pixels constituting the unit scale based on the identified interval.

[0045] For example, when the values ​​of pixels in the second image are summed in the x-axis direction, a cumulative value can be calculated for each y value, and as a result, a histogram such as Fig. 3c can be obtained.

[0046] Here, the electronic device acquires a cumulative value for each of multiple points along the second axis and can identify the intervals of points that have similar cumulative values ​​and are spaced at a constant interval.

[0047] Specifically, the electronic device can select a certain number (e.g., 4, 5, 8, etc.) of points among a plurality of points where the difference in accumulated value is less than a threshold and the spacing between them is constant, and identify the spacing between the selected points as the spacing between unit scales to identify the number of pixels constituting the unit scales.

[0048] For example, in FIG. 3c, the electronic device can identify the intervals between y values ​​having similar cumulative values ​​as intervals of unit scales.

[0049] In this case, the electronic device may select a certain number of first points among a plurality of points where the difference in accumulated values ​​is less than a threshold and the interval is constant, and select a certain number of second points among a plurality of points where the difference in accumulated values ​​is less than a threshold and the interval is constant. Here, the interval between the first points may be different from the interval between the second points. That is, the electronic device can identify the interval corresponding to each of the different scale units.

[0050] For example, if the interval between the second points is greater than the interval between the first points, the electronic device may identify the interval between the first points as one scale interval and the interval between the second points as five scale intervals. Here, the intervals of 'one' and 'five' may be pre-set intervals. Specifically, the electronic device may determine each interval based on the premise that the value obtained by multiplying the interval between the first points by 5 matches the interval between the second points.

[0051] As a result, the electronic device can identify intervals of one scale and five scales, respectively, as shown in Fig. 3d and Fig. 3e, and identify the number of pixels matching each interval.

[0052] Meanwhile, an electronic device according to one embodiment of the present disclosure can extract calibration wave information within an image containing an electrocardiogram recording sheet. The calibration wave information includes a reference waveform, a time length of the reference waveform, and a magnitude (amplitude) of the reference waveform.

[0053] In this regard, FIG. 3f is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure acquiring correction wave information within an image including an electrocardiogram recording sheet.

[0054] Referring to FIG. 3f, the electronic device can identify a reference waveform that matches a preset shape (a vertically elongated cap shape) and can identify the time length (e.g., 25 mm / s) and size (e.g., 10 mm / mV) of the reference waveform written at a preset position (e.g., the lower left of the target area). At this time, the time length of the correction wave information can be various values ​​other than 25 mm / s depending on the specifications of the electrocardiogram recording paper, and the size of the correction wave information can also be various values ​​other than 10 mm / mV depending on the specifications of the electrocardiogram recording paper.

[0055] Thus, once the time length and magnitude of the reference waveform are identified, the electronic device can identify the number of scale divisions corresponding to the height and width of the reference waveform, respectively, and calculate the time length and magnitude (amplitude) corresponding to the horizontal and vertical widths of each scale division, respectively.

[0056] In addition, based on the number of pixels per scale unit calculated earlier, the electronic device can calculate the time length and size corresponding to the interval between pixels. This can be used to quantify the electrocardiogram of each channel in the embodiment of FIG. 4e to be described later.

[0057] Meanwhile, if the number of pixels matching the scale interval is identified according to at least one of the embodiments described above, the electronic device can quantify the waveform of the electrocardiogram based on the calibration wave information in the image and the previously identified number of pixels (S130).

[0058] In this regard, FIGS. 4a to 4d are drawings for illustrating the process of quantifying an electrocardiogram included in a target area by an electronic device according to one embodiment of the present disclosure.

[0059] First, the electronic device can obtain a black and white image by converting the previously extracted target area into black and white. As a result, a black and white image such as Fig. 4a can be obtained.

[0060] In addition, the electronic device can binarize a black and white image to obtain a binary image such as that shown in FIG. 4b. As a specific example, the electronic device can modify pixel values ​​smaller than a certain pixel value (e.g., 100) to a maximum value (e.g., 255) and pixel values ​​smaller than a certain pixel value to a minimum value (e.g., 0: black) based on a certain pixel value.

[0061] At this time, the electronic device can remove noise by additionally changing the value of a pixel that is irrelevant to the waveform among pixels whose pixel value is not zero to zero. Specifically, the electronic device can change the value of at least one pixel to zero based on whether there is a certain number or more of pixels having a non-zero value at coordinates adjacent to each pixel having a non-zero value. For example, if there are no pixels having a non-zero value at coordinates adjacent to a specific pixel having a non-zero value, the pixel value of the aforementioned specific pixel can be changed to zero.

[0062] Here, the electronic device can divide the binary image into multiple waveform images based on each channel constituting the electrocardiogram. In this case, each channel may correspond to a respective electrocardiogram channel corresponding to standard leads (I, II, III), limb leads (aVR, aVL, aVF), chest leads (V1, V2, V3, V4, V5, V6), etc.

[0063] Specifically, the electronic device can first divide the binary image into multiple first waveforms based on the continuity of the waveforms. Referring to FIG. 4c, the waveforms having continuity were divided into four waveforms. As a result, the first waveform includes I, aVR, V1, and V4; the second waveform includes II, aVL, V2, and V5; the third waveform includes III, aVF, V3, and V6; and the fourth waveform consists of III.

[0064] Here, the electronic device can distinguish each waveform separated in FIG. 4c in detail by channel. In one embodiment, each of the plurality of first waveforms can be separated into a plurality of second waveforms based on a vertical line of a certain length or longer included in the binary image (e.g., 410 in FIG. 4d). As a result, the plurality of waveforms included in the target area can be separated by channel as shown in FIG. 4e.

[0065] If vertical lines are not present, the electronic device may utilize at least one artificial intelligence model (e.g., a CNN model) trained to distinguish waveforms by channel. To this end, the artificial intelligence model is trained based on multiple waveform images corresponding to each channel, so that the input image can be distinguished / identified as the waveform of each channel.

[0066] As shown in Fig. 4e, when multiple waveform images are acquired per channel, the electronic device can quantify and store each waveform image acquired per channel.

[0067] In this case, the electronic device can obtain time-series data by quantifying each of a plurality of waveform images based on calibration wave information and the previously identified number of pixels (: number of pixels matching the unit scale interval).

[0068] Specifically, the electronic device can acquire time and amplitude for each point of the waveform constituting each of the multiple waveform images based on calibration wave information and the previously identified number of pixels, and can store the acquired time-series data by channel. Depending on user input, the electronic device may also convert the quantified time-series data by channel into a graph.

[0069] Meanwhile, in one embodiment, the electronic device can compare the numerical time series data by channel with the standard time series data stored by channel. Here, the electronic device can compare the numerical time series data and the standard time series data by point by aligning them based on a reference point (e.g., the point where the waveform reaches maximum / minimum). At this time, the electronic device can obtain the mean or variance / standard deviation of the difference values ​​by applying all the point-by-point differences between the numerical time series data and the standard time series data. Here, if at least one of the indicators representing the difference (mean, variance, standard deviation) falls outside a threshold range, the electronic device can identify that there was an error in the pixel count identification step (S120) performed earlier.

[0070] In this case, the electronic device can re-identify the number of pixels matching the unit scale by modifying at least one parameter for the analysis of the histogram of FIG. 3c described above.

[0071] Specifically, among the multiple points in the histogram of FIG. 3c, points with a cumulative difference less than a 'threshold' and a constant interval of 'a certain number' or more were identified. The electronic device can identify points with a cumulative difference less than an 'updated threshold' and a constant interval of '(updated) a certain number' or more after updating the aforementioned 'threshold' and 'a certain number'. As a specific example, precision may be increased by decreasing the 'threshold' and increasing the 'a certain number', but is not limited thereto.

[0072] FIG. 5 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present disclosure. The electronic device (100) includes a memory (110) and a processor (120) and can perform a control method according to various embodiments described above.

[0073] The memory (110) is configured to store at least one instruction or data related to an operating system (OS) for controlling the overall operation of the components of the electronic device (100) and the components of the electronic device (100).

[0074] The memory (110) may include non-volatile memory such as ROM or flash memory, and may include volatile memory such as DRAM. Additionally, the memory (110) may include a hard disk, an SSD (Solid state drive), etc.

[0075] The memory (110) can store computer programs / software that enable the electronic device (100) to perform the various operations described above.

[0076] A processor (120) is configured to control the electronic device (100) overall. Specifically, the processor (120) can perform operations according to various embodiments of the present disclosure by being connected to memory (110) and executing at least one instruction stored in memory (110).

[0077] The processor (120) may include a general-purpose processor such as a CPU, AP, DSP (Digital Signal Processor), a graphics-dedicated processor such as a GPU, VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU. An artificial intelligence-dedicated processor may be designed with a hardware structure specialized for training or utilizing a specific artificial intelligence model.

[0078] The processor (120) can perform various operations described above by executing computer programs, etc., stored in memory (110).

[0079] Referring to FIG. 5, the electronic device (100) may further include at least one of a communication unit (130) and a user input unit (140) in addition to the memory (110) and the processor (120).

[0080] The communication unit (130) may include a circuit, module, chip, etc. for communicating with at least one external device using various wired and wireless communication methods.

[0081] The communication unit (130) may include circuits, modules, chips, etc. for communicating with at least one external device using various wired or wireless communication methods. The communication unit (140) may be connected to an external device through various networks.

[0082] Depending on the area or scale, a network may be a Personal Area Network (PAN), Local Area Network (LAN), Wide Area Network (WAN), etc., and depending on the openness of the network, it may be an Intranet, Extranet, or Internet, etc.

[0083] The communication unit (130) can be connected to external devices through various wireless communication methods such as LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th Generation) mobile communication, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), Zigbee.

[0084] Additionally, the communication unit (130) may be connected to external devices via wired communication methods such as Ethernet, an optical network, USB (Universal Serial Bus), and Thunderbolt.

[0085] In one embodiment, the electronic device (100) may transmit a computer program for performing the control method of the electronic device described above to an external device or download the computer program described above from an external device through a communication unit (130). Additionally, the electronic device (100) may perform various operations described above by interacting with one or more external devices through at least one web page or application.

[0086] The user input unit (140) is configured to receive various user commands or information. When the electronic device (100) is implemented as a terminal device such as a user, the user input unit (140) may include at least one button, touch pad, microphone, camera, etc. Alternatively, the electronic device (100) may receive user input by being connected wirelessly or via wired connection to various user input devices such as a mouse or keyboard.

[0087] Meanwhile, the various embodiments described above may be implemented by combining multiple embodiments as long as they do not conflict with one another.

[0088] Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

[0089] According to hardware implementation, the embodiments described in this disclosure 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.

[0090] In some cases, the embodiments described herein may be implemented as the processor itself. In a software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software modules. Each of the aforementioned software modules may perform one or more functions and operations described herein.

[0091] Meanwhile, computer instructions or computer programs for performing processing operations in each device according to the various embodiments of the present disclosure described above may be stored on a non-transitory computer-readable medium. When computer instructions or computer programs stored on such a non-transitory computer-readable medium are executed by a processor of a specific device, such as an electronic device, the specific device described above performs the operation of the electronic device / node according to the various embodiments described above.

[0092] Non-transient computer-readable media refers to media that store data semi-permanently and can be read by a device, unlike media that store data for a short period of time such as registers, caches, and memory. Specific examples of non-transient computer-readable media include CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, and ROMs.

[0093] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure. Explanation of the symbols

[0094] 100: Electronic device 110: Memory 120: Processor

Claims

Claim 1 A method for controlling an electronic device comprises: a step in which the electronic device identifies a target area containing an electrocardiogram within an image composed of an electrocardiogram recording sheet; a step in which the electronic device identifies the number of pixels constituting a unit scale of the electrocardiogram based on the target area; and a step in which the electronic device quantifies the waveform of the electrocardiogram based on calibration wave information within the image and the identified number of pixels; wherein the step of identifying the number of pixels comprises: a step of obtaining a first image by extracting the R value among R (Red), G (Green), and B (Blue) of each of a plurality of pixels included within the target area; a step of obtaining a second image by changing the R value of a pixel having an R value corresponding to a maximum value within the first image to 0; and a step of calculating an accumulated value by summing all the values ​​of pixels in a first axis direction on the second image. A method for controlling an electronic device, comprising the step of identifying the interval between unit scales by comparing the accumulated value in the direction of a second axis perpendicular to the first axis, and identifying the number of pixels constituting the unit scale based on the identified interval; wherein the step of quantifying the waveform of the electrocardiogram comprises obtaining a binary image by binarizing a plurality of pixels included in the target area, inputting the binary image into at least one artificial intelligence model trained to distinguish waveforms by channel, and based on the output data, dividing the binary image into a plurality of waveform images based on each channel constituting the electrocardiogram, and identifying the time and amplitude for each point constituting each of the plurality of waveform images based on the number of pixels constituting the unit scale.

Images