Arrhythmia type determination device, arrhythmia type determination method, arrhythmia type determination program

Abstract

The type of premature contraction can be accurately determined from images of the heart. [Solution] The arrhythmia type determination device includes an acquisition unit that acquires a target signal waveform including at least one of the following pairs, generated by analyzing images of the subject's heart: a pair of signal waveforms showing the time-series change in the area of ​​the left atrium region and a pair of signal waveforms showing the time-series change in the area of ​​the left ventricle region, and a pair of signal waveforms showing the time-series change in the area of ​​the right atrium region and a pair of signal waveforms showing the time-series change in the area of ​​the right ventricle region; and a determination unit that determines the type of premature contraction the subject is suffering from based on the target signal waveform during the period of interest in which premature contractions occur in the subject's heart.

Description

[TECHNICAL FIELD]

[0001] The present invention relates to a technology for determining the type of arrhythmia. [BACKGROUND ART]

[0002] Technologies for grasping the relationship between the left and right sides of the heart and the relationship between the atria and ventricles from ultrasonic diagnostic moving images of the heart are widely used. For example, Patent Document 1 discloses an ultrasonic diagnostic apparatus that identifies boundary position groups in a plurality of heart cavities in an ultrasonic moving image, and acquires boundary positions of the plurality of heart cavities over a section of at least one heartbeat or more based on a tracking result of the boundary position group. [PRIOR ART DOCUMENT] [PATENT DOCUMENT]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2022-149097 [SUMMARY OF THE INVENTION] [Problem to be Solved by the Invention]

[0004] Conventionally, electrocardiography is mainly used for arrhythmia diagnosis, but there are cases where it is difficult to determine the type of premature contraction that has occurred, and there has been room for improvement in terms of determination accuracy. Note that premature contraction is a type of arrhythmia, in which an abnormal stimulus occurs in the heart, and a beat due to additional contraction is added in addition to the normal beat.

[0005] An object of one aspect of the present invention is to accurately determine the type of premature contraction from an image obtained by photographing the heart. [Means for Solving the Problem]

[0006] An arrhythmia type determination device according to one aspect of the present invention includes: an acquisition unit that acquires a target signal waveform including at least one of the following pairs, generated by analyzing an image of the heart of a subject: a pair of signal waveforms showing a time-series change in the area of ​​the left atrium region and a pair of signal waveforms showing a time-series change in the area of ​​the left ventricle region, and a pair of signal waveforms showing a time-series change in the area of ​​the right atrium region and a pair of signal waveforms showing a time-series change in the area of ​​the right ventricle region; and a determination unit that determines the type of premature contraction the subject is suffering from based on the target signal waveform during a period of interest in which premature contractions occur in the heart of the subject.

[0007] An arrhythmia type determination method according to one aspect of the present invention is an arrhythmia type determination method performed by one or more information processing devices, comprising: an acquisition step of acquiring a target signal waveform that includes at least one of the following pairs, generated by analyzing an image of the heart of a subject: a signal waveform showing a time-series change in the area of ​​the left atrium region and a signal waveform showing a time-series change in the area of ​​the left ventricle region, and a pair showing a time-series change in the area of ​​the right atrium region and a time-series change in the area of ​​the right ventricle region; and a determination step of determining the type of premature contraction that the subject is suffering from, based on the target signal waveform during a period of interest in which premature contractions occur in the heart of the subject.

[0008] Each aspect of the present invention may be implemented by a computer, in which case a control program for an arrhythmia type determination device that enables the implementation of the arrhythmia type determination device by a computer, by operating the computer as each part (software element) of the arrhythmia type determination device, and a computer-readable recording medium on which the program is recorded also fall within the scope of the present invention. [Effects of the Invention]

[0009] According to one aspect of the present invention, the type of premature contraction can be accurately determined from an image of the heart. [Brief explanation of the drawing]

[0010] [Figure 1]This figure shows an example configuration of an arrhythmia type determination system according to one embodiment of the present invention. [Figure 2] This figure shows an example of detecting the left atrium, left ventricle, right atrium, and right ventricle regions from a cardiac ultrasound image. [Figure 3] This figure shows an example of detecting the left atrium, left ventricle, right atrium, and right ventricle regions from ultrasound images of a subject who does not suffer from arrhythmia. [Figure 4] This figure shows an example of a target signal waveform that includes the period during which ventricular premature contractions (PVCs) occur. [Figure 5] This figure shows an example of a target signal waveform that includes the period during which supraventricular premature contractions (PACs) occur. [Figure 6] This is a block diagram showing an example of the main components of an arrhythmia type determination device according to Embodiment 1 of the present invention. [Figure 7] This diagram illustrates an example of a process for detecting increasing and decreasing periods from a pair of atrial and ventricular waveforms. [Figure 8] This flowchart shows an example of the processing flow performed by an arrhythmia type determination device. [Figure 9] This is a block diagram showing an example of the main components of an arrhythmia type determination device according to Embodiment 2 of the present invention. [Figure 10] This figure shows an example comparing the shapes of the atrial waveform and the ventricular waveform for a single beat. [Figure 11] This figure shows another example comparing the shapes of the atrial and ventricular waveforms for a single beat. [Figure 12] This flowchart shows an example of the processing flow performed by an arrhythmia type determination device. [Figure 13] This is a block diagram showing an example of the main components of an arrhythmia type determination device according to Embodiment 3 of the present invention. [Figure 14] This figure shows how the absence of ventricular contraction corresponding to atrial contraction was detected from a pair of atrial and ventricular waveforms. [Figure 15] This flowchart shows an example of the processing flow performed by an arrhythmia type determination device. [Figure 16] It is a block diagram showing an example of the main configuration of an arrhythmia type determination apparatus according to Embodiment 4 of the present invention. MODES FOR CARRYING OUT THE INVENTION

[0011] Embodiment 1 Hereinafter, one embodiment of the present invention will be described in detail.

[0012] (Overview of Arrhythmia Type Determination Apparatus 1) The arrhythmia type determination apparatus 1 according to one embodiment of the present invention determines the type of premature contraction that a subject patient suffers from based on a target signal waveform in a target period in which premature contraction occurs in the heart of the subject patient. Here, the target signal waveform is a target signal waveform generated by analyzing an image of the heart of the subject patient, and includes at least one of the following sets (1) and (2). · (1) A set of a signal waveform (left atrial waveform) indicating a time-series change in the area of a left atrial region and a signal waveform (left ventricular waveform) indicating a time-series change in the area of a left ventricular region. · (2) A set of a signal waveform (right atrial waveform) indicating a time-series change in the area of a right atrial region and a signal waveform (right ventricular waveform) indicating a time-series change in the area of a right ventricular region.

[0013] Hereinafter, the term "atrial waveform" is intended to mean a signal waveform indicating a time-series change in the area of an atrial region, without particularly limiting whether it is the left atrium or the right atrium. Further, hereinafter, the term "ventricular waveform" is intended to mean a signal waveform indicating a time-series change in the area of a ventricular region, without particularly limiting whether it is the left ventricle or the right ventricle.

[0014] Premature contractions (PVCs) are arrhythmias in which the heart contracts prematurely, deviating from its normal rhythm, due to abnormal electrical impulses in the heart. They occur as occasional rapid beats mixed in with a normal, regular pulse. The main types of premature contractions are ventricular premature contractions (PVCs) and supraventricular premature contractions (PACs). PVCs are premature contractions in which the ventricles are activated before a normal heartbeat occurs due to abnormal electrical impulses in the ventricles, resulting in a contraction that deviates from the normal rhythm. PACs, on the other hand, are premature contractions in which the atria are activated before a normal heartbeat occurs due to abnormal electrical impulses in an abnormal location, resulting in a contraction that deviates from the normal rhythm.

[0015] The inventors have found that the type of premature contraction occurring in a heart can be accurately determined based on a signal waveform showing the time-series change in the area of ​​at least one of the regions of the left atrium, left ventricle, right atrium, and right ventricle contained in an image of the heart. The arrhythmia type determination device 1 can accurately determine the type of premature contraction occurring in a subject's heart from an image of the subject's heart.

[0016] The subject may be an animal with a heart or its fetus. For example, the subject may be a human fetus. In this case, the area of ​​each atrium and ventricle may be calculated based on ultrasound images of the fetus, which include multiple frames. The fetal heart is visible in the ultrasound images of the fetus, and the area of ​​each region of the fetal heart can be calculated from these ultrasound images. The process of calculating the area of ​​each region of the heart from ultrasound images will be explained later with specific examples.

[0017] (Configuration of the arrhythmia type determination system 100) First, the configuration of an arrhythmia type determination system 100, including an arrhythmia type determination device 1 according to one embodiment of the present invention, will be described with reference to Figure 1. Figure 1 is a diagram showing an example of the configuration of the arrhythmia type determination system 100. The arrhythmia type determination system 100 may include an imaging device 2, an image analysis device 3, a premature contraction detection device 4, an arrhythmia type determination device 1, and a display device 6.

[0018] [Imaging device 2] The imaging device 2 may be an ultrasound imaging device capable of non-invasively imaging the inside of the subject's body. That is, the input image captured by the imaging device 2 may be an ultrasound image such as an echo image for tomographic imaging. The imaging device 2 may be connected to the image analysis device 3 in a communicative manner, as shown in the figure, in which case the image analysis device 3 may directly acquire the input image from the imaging device 2. The input image may be stored in an image management device (not shown) in association with subject information for each subject (e.g., electronic medical record information), in which case the arrhythmia type determination device 1 only needs to acquire the input image from the image management device.

[0019] [Image analysis device 3] Image analysis device 3 detects the left atrium, left ventricle, right atrium, and right ventricle regions of the subject's heart as captured in the input image. Image analysis device 3 also calculates the area of ​​each detected region and generates a target signal waveform that shows the time-series change in the area of ​​each region.

[0020] The image analysis device 3 may be installed in the facility where the imaging device 2 is installed (for example, a medical facility), or it may be installed in a remote location. If installed in a remote location, the image analysis device 3 can acquire input images via communication over a communication network such as the Internet.

[0021] Here, the process of detecting the regions corresponding to each atrium and ventricle of the heart from the input image will be explained based on Figure 2. Figure 2 shows an example of detecting the regions of the left atrium, left ventricle, right atrium, and right ventricle from an ultrasound image of the heart. Image A1 in Figure 2 is an ultrasound image of the heart, and image A2 shows the detection results for each region R1 to R4 superimposed on the ultrasound image.

[0022] In image A1, the heart is visible in the area slightly below the center, and its external shape and the division of its interior into multiple compartments can be seen. Thus, in ultrasound images, each of the two ventricles and each of the two atria of the heart can be seen as a closed region. Therefore, by analyzing ultrasound images of the heart, it is possible to detect the left atrium, left ventricle, right atrium, and the respective regions R1-R4 of the right ventricle.

[0023] For example, machine learning can be performed using training data in which regions corresponding to the left atrium, left ventricle, right atrium, and right ventricle of the heart, as seen in cardiac ultrasound images, are labeled as ground truth data. These labels can also be called annotations. Through such machine learning, it is possible to construct a learning model capable of detecting the regions R1-R4 of the left atrium, left ventricle, right atrium, and right ventricle from cardiac ultrasound images. For example, by constructing a learning model using a convolutional neural network and using that model, highly accurate region detection becomes possible.

[0024] Image A2 in Figure 2 shows the results of detection using this learning model. The detected regions R1 to R4 are the right ventricle, left ventricle, left atrium, and right atrium, respectively. By detecting each region R1 to R4, it becomes possible to calculate the area of ​​each region R1 to R4.

[0025] For example, the area of ​​each detected region R1 to R4 can be represented by the number of pixels contained in each region R1 to R4. By calculating the area of ​​each region R1 to R4 of the left atrium, left ventricle, right atrium, and right ventricle of the subject's heart in each frame of the ultrasound image, a target signal waveform showing the time-series change of the area of ​​each region R1 to R4 can be obtained. Figure 3 shows an example of detecting the left atrium, left ventricle, right atrium, and right ventricle from an ultrasound image of the heart of a subject without arrhythmia. In the case of a heart without arrhythmia, as shown in Figure 3, the area of ​​each atrium and each ventricle increases and decreases in a nearly constant period. Furthermore, the heart rhythm is reproduced in which the area of ​​the ventricle decreases when the area of ​​the atrial region increases, and the area of ​​the ventricle decreases when the area of ​​the atrial region decreases.

[0026] [Premature contraction detection device 4] The premature contraction detection device 4 uses the target signal waveform acquired from the image analysis device 3 to detect the period of interest during which premature contractions such as PVCs and PACs occur in the heart of the subject. Here, it is desirable that the length of the period of interest be longer than the period corresponding to a predetermined number of beats (for example, 3 or more). For example, the period of interest may be 3 seconds (corresponding to 8 to 10 beats), 5 seconds (corresponding to 12 to 15 beats), or 10 seconds (corresponding to 24 to 30 beats).

[0027] For example, the premature contraction detection device 4 may detect the period of interest by performing the following steps (a) and (b). Step (a): The time interval from the point in time when the area shown in the target signal waveform reaches a reference value set based on the displacement of the target signal waveform until the area shown in the target signal waveform next reaches the reference value is compared with a predetermined threshold for determining the presence or absence of premature contraction. Here, the reference value may be any value within the range in which the target signal waveform is displaced, for example, it may be the center value of the displacement in the target signal waveform. • Process (b): The period of interest is detected based on the comparison results obtained in process (a).

[0028] If a period of interest is detected in the target signal waveform acquired from the image analysis device 3, the premature contraction detection device 4 may output period of interest information, indicating the position of the period of interest in the target signal waveform, along with the target signal waveform, to the arrhythmia type determination device 1, which will be described later. In this case, the arrhythmia type determination device 1 determines the type of premature contraction the subject is suffering from based on the waveform in the period of interest identified by the period of interest information in the target signal waveform acquired from the premature contraction detection device 4.

[0029] Alternatively, if the premature contraction detection device 4 detects a period of interest in the target signal waveform acquired from the image analysis device 3, it may extract a partial waveform corresponding to the period of interest (i.e., the target signal waveform during the period of interest) from the target signal waveform and output it to the arrhythmia type determination device 1, which will be described later. The extracted partial waveform includes one or more periods containing the waveform that formed the basis for determining that a premature contraction has occurred. In this case, the arrhythmia type determination device 1 determines the type of premature contraction the subject is suffering from based on the partial waveform acquired from the premature contraction detection device 4.

[0030] The premature contraction detection device 4 is not limited to the configuration shown in Figure 1. For example, the premature contraction detection device 4 may be configured to acquire, in addition to the target signal waveform acquired from the image analysis device 3, pulse data measured during the acquisition of the input image used to generate the target signal waveform, and electrocardiogram data recording the heartbeat of the subject. In this case, the premature contraction detection device 4 may detect the period of interest by applying known detection criteria based on at least one of the pulse wave data and the electrocardiogram. For example, if the period of interest is detected from the subject's electrocardiogram, the premature contraction detection device 4 may extract the target signal waveform of the subject during the detected period of interest from the target signal waveform and output it to the arrhythmia type determination device 1, which will be described later.

[0031] The premature contraction detection device 4 may be connected to the image analysis device 3 in a communication manner, as shown in the figure. In this case, the premature contraction detection device 4 may directly acquire the target signal waveform from the image analysis device 3. The target signal waveform generated by the image analysis device 3 may be stored, for example, on a portable recording medium. In this case, the premature contraction detection device 4 can read the target signal waveform from the recording medium. Alternatively, the target signal waveform generated by the image analysis device 3 may be stored in an arbitrary storage device (not shown) in association with the target subject information for each target subject. In this case, the premature contraction detection device 4 can acquire the target signal waveform from the storage device.

[0032] The premature contraction detection device 4 may be installed in the same facility as the image analysis device 3 (for example, a medical facility), or it may be installed in a remote location. If installed in a remote location, the premature contraction detection device 4 can acquire the target signal waveform generated by the image analysis device 3 via communication over a communication network such as the Internet.

[0033] The configuration may include having another computer perform some of the processing performed by the premature contraction detection device 4. In other words, the processing performed by the premature contraction detection device 4 may be performed by one or more information processing devices. Alternatively, the premature contraction detection device 4 may also have the functions of the image analysis device 3. For example, if the premature contraction detection device 4 also has the functions of the image analysis device 3, the image analysis device 3 is omitted from the components of the arrhythmia type determination system 100.

[0034] In the following explanation, we will describe an example configuration in which the arrhythmia type determination device 1 acquires a partial waveform (i.e., the target signal waveform during the period of interest) extracted by the premature contraction detection device 4, and determines the type of premature contraction occurring in the subject's heart based on the target signal waveform. In the following, when "target signal waveform" is used, it refers to the target signal waveform during the period of interest, and includes a pair of atrial and ventricular waveforms, for example, at least one of the pairs (1) and (2) below. (1) A pair of left atrial waveforms and left ventricular waveforms. (2) A pair of right atrial waveforms and right ventricular waveforms.

[0035] [Arrhythmia Type Determination Device 1] Figure 4 shows an example of a target signal waveform including the period in which ventricular premature contractions (PVCs) occur, with PVCs occurring in periods P1 and P2. On the other hand, Figure 5 shows an example of a target signal waveform including the period in which supraventricular premature contractions (PACs) occur, with PACs occurring in periods P3 to P6. Here, PVCs are premature contractions in which the ventricles are activated before a normal heartbeat occurs due to abnormal electrical stimulation generated in the ventricles, resulting in a contraction that deviates from the normal contraction rhythm. PACs, on the other hand, are premature contractions in which the atria are activated before a normal heartbeat occurs due to electrical stimulation generated in an abnormal location, resulting in a contraction that deviates from the normal contraction rhythm.

[0036] The inventors found that there is a clear difference in the target signal waveform between cases where PVC occurs in the target subject's heart and cases where PAC occurs in the target subject's heart.

[0037] For example, in the target signal waveform shown in Figure 3, during periods when the area shown in the atrial waveform is increasing, the area shown in the ventricular waveform is always decreasing, and during periods when the area shown in the atrial waveform is decreasing, the area shown in the atrial waveform is always increasing. In contrast, in the target signal waveform shown in Figure 4 (especially during periods P1 and P2), there are periods when both the area shown in the atrial waveform and the area shown in the ventricular waveform increase (hereinafter referred to as the increasing period), and periods when both the area shown in the atrial waveform and the area shown in the ventricular waveform decrease (hereinafter referred to as the decreasing period). On the other hand, in the target signal waveform shown in Figure 5, there are no increasing or decreasing periods.

[0038] Furthermore, in the target signal waveform shown in Figure 3, the similarity between the shape of the atrial waveform corresponding to one heartbeat in the atrial waveform and the shape of the ventricular waveform corresponding to the same heartbeat in the ventricular waveform is always high, and the similarity never falls below a predetermined standard value. In contrast, in the target signal waveform shown in Figure 4 (especially in periods P1 and P2), the similarity between the shape of the atrial waveform and the shape of the ventricular waveform often falls below a predetermined standard value. On the other hand, in the target signal waveform shown in Figure 5, even in periods P3 to P6, the similarity between the shape of the atrial waveform and the shape of the ventricular waveform rarely falls below a predetermined standard value.

[0039] Furthermore, in the target signal waveform shown in Figure 3, when the atria contract, the ventricles always contract afterward, and when the ventricles contract, the atria always contract afterward. In contrast, in the target signal waveform shown in Figure 4 (especially during periods P1 and P2), there is a loss of ventricular contraction corresponding to atrial contraction, and a loss of atrial contraction corresponding to ventricular contraction. On the other hand, in the target signal waveform shown in Figure 5, even during periods P3 to P6, there is no loss of ventricular contraction corresponding to atrial contraction, and no loss of atrial contraction corresponding to ventricular contraction.

[0040] The inventors discovered that they could accurately determine the type of premature contractions occurring in the subject's heart based on the target signal waveform. The arrhythmia type determination device 1 uses the target signal waveform to determine the type of premature contractions the subject is experiencing. Compared to determining the type of premature contractions using an electrocardiogram, the arrhythmia type determination device 1 can output a more accurate determination result.

[0041] The arrhythmia type determination device 1 may be connected to the premature contraction detection device 4 in a communicative manner, as shown in the figure. In this case, the arrhythmia type determination device 1 may directly acquire the target signal waveform from the premature contraction detection device 4. Alternatively, the arrhythmia type determination device 1 may be connected to the image analysis device 3 and the premature contraction detection device 4 in a communicative manner. In this case, the arrhythmia type determination device 1 may acquire the target signal waveform from the image analysis device 3 and acquire the period of interest information from the premature contraction detection device 4.

[0042] The target signal waveform may be stored, for example, on a portable recording medium. In this case, the arrhythmia type determination device 1 simply reads the target signal waveform from the recording medium. Alternatively, the target signal waveform may be stored in a memory device (not shown) in association with the subject information for each subject. In this case, the arrhythmia type determination device 1 simply acquires the target signal waveform from the memory device.

[0043] The arrhythmia type determination device 1 may be installed in a facility where the premature contraction detection device 4 is installed (for example, a medical facility), or it may be installed in a remote location. If installed in a remote location, the arrhythmia type determination device 1 can acquire the target signal waveform from the premature contraction detection device 4 via communication over a communication network such as the Internet.

[0044] The arrhythmia type determination device 1 may be configured to have a part of its processing performed by another computer. In other words, the processing performed by the arrhythmia type determination device 1 may be performed by one or more information processing devices.

[0045] The arrhythmia type determination device 1 may also have the function of the premature contraction detection device 4. For example, if the arrhythmia type determination device 1 also has the function of the premature contraction detection device 4, the premature contraction detection device 4 is omitted from the components of the arrhythmia type determination system 100. Alternatively, the arrhythmia type determination device 1 may also have the function of the image analysis device 3 and the premature contraction detection device 4. For example, if the arrhythmia type determination device 1 also has the function of the image analysis device 3 and the premature contraction detection device 4, the image analysis device 3 and the premature contraction detection device 4 are omitted from the components of the arrhythmia type determination system 100.

[0046] [Display device 6] The display device 6 is a device capable of displaying various information output from the arrhythmia type determination device 1. In addition to the various information output from the arrhythmia type determination device 1, the display device 6 may also display input images output from the imaging device 2, target signal waveforms output from the premature contraction detection device 4, etc.

[0047] (Configuration of arrhythmia type determination device 1) Next, the configuration of the arrhythmia type determination device 1 according to one embodiment of the present invention will be described with reference to Figure 6. Figure 6 is a block diagram showing an example of the main components of the arrhythmia type determination device 1. In the following description, the arrhythmia type determination device 1, which has a function to determine the type of premature contraction that the subject is suffering from from the target signal waveform acquired from the premature contraction detection device 4, will be used as an example.

[0048] As shown in the figure, the arrhythmia type determination device 1 is, for example, a computer equipped with a processor 10, memory 11, and storage device 12. The arrhythmia type determination device 1 may also be a personal computer, a server, or a workstation. The processor 10 functions as each of the parts from the acquisition unit 101 to the output control unit 106, which will be described later, by loading the arrhythmia type determination program 121 stored in the storage device 12 into the memory 11 and executing it.

[0049] The processor 10 can be implemented by logic circuits (hardware) formed on an integrated circuit (IC chip), or by software. When implemented by software, the processor 10 may be composed of, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a combination of these. In this case, the software is stored in the storage device 12. The processor 10 then loads the software into memory 11 and executes it.

[0050] Memory 11 and storage device 12 are both storage devices that store various data used by the arrhythmia type determination device 1. Memory 11 is a storage device that can write and read data at a higher speed than storage device 12. Storage device 12 has a larger data storage capacity than memory 11. For memory 11, a high-speed access memory such as SDRAM (Synchronous Dynamic Random-Access Memory) can be used. For storage device 12, an HDD (Hard Disk Drive), SSD (Solid-State Drive), SD (Secure Digital) card, or eMMC (embedded Multi-Media Controller) can be used.

[0051] Furthermore, the arrhythmia type determination device 1 is equipped with an input IF unit 13 and an output IF unit 14 as interfaces (IFs) with external devices. The input IF unit 13 is an interface for receiving input signals from input devices such as keyboards and mice, and for acquiring various information and data from external devices. For example, the input IF unit 13 can be connected to a premature contraction detection device 4, and the input IF unit 13 can be used as an interface for acquiring target signal waveforms, etc., from the premature contraction detection device 4. The output IF unit 14 is an interface for outputting the determination result of the type of premature contraction, etc., to an external device. For example, the output IF unit 14 can be connected to a display device, and the determination result of the type of premature contraction, etc., can be displayed on the display device.

[0052] The processor 10 functions as an acquisition unit 101, a period detection unit 102, a determination unit 105, and an output control unit 106, respectively, by executing an arrhythmia type determination program 121 to acquire the target signal waveform from the premature contraction detection device 4.

[0053] The period detection unit 102 detects increasing and decreasing periods in the acquired target signal waveform. More specifically, the period detection unit 102 calculates corrected atrial and ventricular waveforms by removing noise from the atrial and ventricular waveforms, respectively. Known filtering methods such as moving average filters, Fast Fourier Transform (FFT) filters, and Gaussian filters can be applied to remove noise.

[0054] The period detection unit 102 then detects as an increase period a period during which both the area shown in the corrected atrial waveform and the area shown in the corrected ventricular waveform increase for a predetermined time or longer during the period of interest. The period detection unit 102 also detects as a decrease period a period during which both the area shown in the corrected atrial waveform and the area shown in the corrected ventricular waveform decrease for a predetermined time or longer during the period of interest.

[0055] Figure 7 illustrates an example of a process for detecting increasing and decreasing periods from a set of atrial and ventricular waveforms. In Figure 7, periods P7 and P8 represent periods in which premature contractions occur. In Figure 7, the values ​​on the vertical axis represent the magnitude of area changes in the atrium and ventricle regions during systole and diastole.

[0056] In the upper panel of Figure 7, the dashed line represents the left ventricular waveform of the target signal waveform, and the solid line is the corrected ventricular waveform obtained by removing noise from the left ventricular waveform. The upper panel of Figure 7 also superimposes a binarized graph of the increase / decrease pattern of the area shown by the corrected ventricular waveform, obtained by assigning "1" when the area of ​​the corrected ventricular waveform increases and "-1" when the area decreases. On the other hand, in the lower panel of Figure 7, the dashed line represents the left atrial waveform of the target signal waveform, and the solid line is the corrected atrial waveform obtained by removing noise from the left atrial waveform.

[0057] Furthermore, the lower part of Figure 7 also superimposes a binarized graph of the increase and decrease patterns of the left atrial waveform area, obtained by assigning "1" when the area transitions from a minimum to a maximum and "-1" when the area transitions from a maximum to a minimum. Here, maxima and maximae in the left atrial waveform area that occur in a time shorter than a predetermined time (e.g., 0.1 seconds) are ignored.

[0058] The period detection unit 102 detects, for example, the periods indicated by thick lines with the white circles and white triangles shown in the upper part of Figure 7 as increasing and decreasing periods, based on the corrected ventricular waveform shown in the upper part of Figure 7 and the corrected atrial waveform shown in the lower part of Figure 7.

[0059] Alternatively, the period detection unit 102 may detect periods of increase and decrease based on the general increase and decrease patterns of the atrial and ventricular waveforms of the target signal waveform. For example, the period detection unit 102 may create a graph (lower part of Figure 7) that binarizes the increase and decrease pattern of the area shown by the left atrial waveform, and then create a graph for the left ventricular waveform as well, and detect periods of increase and decrease by comparing these graphs.

[0060] The determination unit 105 determines the type of premature contraction the subject is suffering from based on the target signal waveform. Specifically, the determination unit 105 determines the type of premature contraction the subject is suffering from based on the detection status of the increasing period and the decreasing period. That is, the determination unit 105 determines that the subject is suffering from PVC if either the increasing period or the decreasing period is detected during the period of focus, and determines that the subject is suffering from PAC if neither the increasing period nor the decreasing period is detected during the period of focus. For example, as shown in Figure 7, if both the increasing period and the decreasing period are detected from the target signal waveform, the determination unit 105 determines that the premature contraction the subject is suffering from is PVC. On the other hand, if neither the increasing period nor the decreasing period is detected from the target signal waveform, the determination unit 105 determines that the premature contraction the subject is suffering from is PAC.

[0061] Returning to Figure 3, the output control unit 106 causes the determination result from the determination unit 105 to be output to various output devices. For example, if a display device 6 is connected via the output IF unit 14, the output control unit 106 may display the determination result on the display device 6. The manner in which the determination result is output is arbitrary, and the output control unit 106 may output the determination result by display output, audio output, print output, or a combination thereof.

[0062] (Processing performed by arrhythmia type determination device 1) Next, the processing performed by the arrhythmia type determination device 1 (arrhythmia type determination method) will be explained using Figure 8. Figure 8 is a flowchart showing an example of the processing flow performed by the arrhythmia type determination device 1.

[0063] First, the acquisition unit 101 acquires the target signal waveform (step S1: acquisition step). Next, the period detection unit 102 detects increasing and decreasing periods during the period of interest in which premature contractions occur. Then, the determination unit 105 determines that if increasing and decreasing periods are detected (YES in step S2), the premature contractions affecting the subject are PVCs (step S3: determination step). On the other hand, if increasing and decreasing periods are not detected (NO in step S2), the determination unit 105 determines that the premature contractions affecting the subject are PACs (step S4: determination step). The output control unit 106 outputs the determination result from the determination unit 105 to an output device (e.g., display device 6) (step S5: output step).

[0064] With the above configuration, the arrhythmia type determination device 1 can accurately determine the type of premature contractions the subject is suffering from from images of the subject's heart. For example, the arrhythmia type determination device 1 can estimate with high accuracy whether the type of premature contractions in a fetus is "PVC" or "PAC".

[0065] [Embodiment 2] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0066] The arrhythmia type determination device 1 according to the above embodiment is configured to determine the type of premature contraction the subject is suffering from based on whether or not an increasing period in which both the atrial and ventricular waveforms increase, and a decreasing period in which both the atrial and ventricular waveforms decrease, are detected in the target signal waveform. On the other hand, the arrhythmia type determination device 1a according to this embodiment is configured to determine the type of premature contraction the subject is suffering from based on the similarity of the shapes of one or more atrial and ventricular waveforms corresponding to each heartbeat of the subject's heart, from the target signal waveform.

[0067] Similar to the embodiment described above, the following description will use an arrhythmia type determination device 1a as an example, which has the function of determining the type of premature contraction the subject is suffering from from a target signal waveform acquired from the premature contraction detection device 4. However, the arrhythmia type determination device 1a may also have the functions of the image analysis device 3 and the premature contraction detection device 4. In this case, the arrhythmia type determination device 1a can generate a target signal waveform from an input image acquired from the imaging device 2 and determine the type of premature contraction the subject is suffering from.

[0068] In the following explanation, we will describe an example configuration in which the arrhythmia type determination device 1a acquires a partial waveform (i.e., the target signal waveform during the period of interest) extracted by the premature contraction detection device 4, and determines the type of premature contraction occurring in the subject's heart based on the target signal waveform.

[0069] (Configuration of arrhythmia type determination device 1a) The configuration of the arrhythmia type determination device 1a according to one embodiment of the present invention will be described with reference to Figure 9. Figure 9 is a block diagram showing an example of the main components of the arrhythmia type determination device 1a.

[0070] As shown in the figure, the arrhythmia type determination device 1a is, for example, a computer equipped with a processor 10a, memory 11, and storage device 12. The arrhythmia type determination device 1a may also be a personal computer, a server, or a workstation. The processor 10a functions as each of the parts from the acquisition unit 101 to the output control unit 106, which will be described later, by loading the arrhythmia type determination program 121a stored in the storage device 12 into the memory 11 and executing it.

[0071] The processor 10a can be implemented by logic circuits (hardware) formed on an integrated circuit (IC chip), or by software. When implemented by software, the processor 10a may be configured as a CPU, a GPU, or a combination of these. In this case, the software is stored in the storage device 12. The processor 10a then loads the software into memory 11 and executes it.

[0072] The processor 10a functions as an acquisition unit 101, a similarity calculation unit 103, a determination unit 105a, and an output control unit 106, respectively, by executing the arrhythmia type determination program 121a.

[0073] The similarity calculation unit 103 calculates the similarity by comparing the shapes of the atrial waveform and the ventricular waveform during the period of interest.

[0074] More specifically, the similarity calculation unit 103 first calculates corrected atrial and ventricular waveforms by removing noise from the atrial and ventricular waveforms, respectively. Known filtering methods such as moving average filters, FFT filters, and Gaussian filters can be applied to remove noise.

[0075] Next, the similarity calculation unit 103 obtains multiple single-beat atrial waveforms corresponding to each heartbeat of the subject's heart from the corrected atrial waveforms during the period of interest. The similarity calculation unit also obtains multiple single-beat ventricular waveforms corresponding to each heartbeat of the subject's heart from the corrected ventricular waveforms during the period of interest.

[0076] To obtain a single-beat atrial waveform, the similarity calculation unit 103 may detect the point in time when the atrium transitions from systole to diastole (the minimum point in the atrial waveform) from the corrected atrial waveform and divide the atrial waveform at these points. On the other hand, to obtain a single-beat ventricular waveform, the similarity calculation unit 103 may detect the point in time when the ventricle transitions from systole to diastole (the minimum point in the ventricular waveform) from the corrected ventricular waveform and divide the ventricular waveform at these points.

[0077] The similarity calculation unit 103 may be configured to obtain a single-beat atrial waveform and a single-beat ventricular waveform by detecting an arbitrary point in time that marks the boundary of each heartbeat from the corrected atrial waveform and the corrected ventricular waveform, and dividing the atrial waveform and ventricular waveform. For example, when obtaining a single-beat atrial waveform from the corrected atrial waveform, the similarity calculation unit 103 may be configured to detect the point in time when the area of ​​the atrial region in the corrected atrial waveform reaches a predetermined value during diastole. In this case, the similarity calculation unit 103 obtains the waveform from the point in time when the area of ​​the atrial region reaches a predetermined value during diastole to the point in time when the area of ​​the atrial region reaches a predetermined value during the next diastole as a single-beat atrial waveform. The similarity calculation unit 103 can similarly obtain a single-beat ventricular waveform from the corrected ventricular waveform.

[0078] The similarity calculation unit 103 may use a learning model such as a convolutional neural network to detect the point in time that marks the boundary between each atrial beat from the corrected atrial waveform. Such a learning model can be constructed, for example, by machine learning using training data in which the sample atrial waveform of the sample subject is used as the explanatory variable and the point in time that marks the boundary between each atrial beat in the sample atrial waveform is used as the objective variable. Similarly, the similarity calculation unit 103 may use a learning model such as a convolutional neural network to detect the point in time that marks the boundary between each ventricular beat from the corrected ventricular waveform. Such a learning model can be constructed, for example, by machine learning using training data in which the sample ventricular waveform of the sample subject is used as the explanatory variable and the point in time that marks the boundary between each ventricular beat in the sample ventricular waveform is used as the objective variable.

[0079] Next, the similarity calculation unit 103 normalizes the amplitudes of the acquired single-beat atrial waveforms and single-beat ventricular waveforms, and calculates the similarity by comparing the shapes of the normalized single-beat atrial waveforms with the shapes of the normalized single-beat ventricular waveforms.

[0080] For example, if the atrium is in systole, the corresponding ventricle is in diastole, and if the ventricle is in systole, the corresponding atrium is in diastole. Therefore, the similarity calculation unit 103 inverts either the one-beat atrial waveform or the one-beat ventricular waveform in the direction of increasing or decreasing area without changing its shape, and compares the shape of the one-beat atrial waveform with the shape of the one-beat ventricular waveform corresponding to that one-beat atrial waveform to calculate the similarity.

[0081] Figures 10 and 11 show examples comparing the shapes of individual atrial waveforms extracted from the atrial and ventricular waveforms of target signal waveforms from different subjects, respectively, with the shapes of the corresponding individual ventricular waveforms. In Figures 10 and 11, the dashed lines represent individual ventricular waveforms extracted from the right ventricular waveform, and the solid lines represent individual atrial waveforms extracted from the right atrial waveform. For example, in the example shown in Figure 10, the shapes of each individual atrial waveform are quite similar to the shapes of the corresponding individual ventricular waveforms. In such cases, the similarity calculated by the similarity calculation unit 103 is high. On the other hand, in the example shown in Figure 11, the similarity between the shapes of each individual atrial waveform and the shapes of the corresponding individual ventricular waveforms is lower than in the example shown in Figure 10. In such cases, the similarity calculated by the similarity calculation unit 103 is low.

[0082] The determination unit 105a determines the type of premature contraction the subject is suffering from based on the target signal waveform. Specifically, the determination unit 105a determines the type of premature contraction the subject is suffering from based on the calculated similarity. More specifically, the determination unit 105a may determine the type of premature contraction the subject is suffering from based on the result of comparing the similarity during the observation period with a predetermined reference value that can distinguish between the similarity when PVC occurs and the similarity when PAC occurs. That is, if the similarity during the observation period is less than or equal to the predetermined reference value, the determination unit 105a may determine that the subject is suffering from PVC, and if the similarity during the observation period is higher than the predetermined reference value, the determination unit 105a may determine that the subject is suffering from PAC. For example, the determination unit 105a determines that the type of premature contraction the subject is suffering from is PAC based on the similarity between the shape of the one-beat atrial waveform and the shape of the one-beat ventricular waveform shown in Figure 10. On the other hand, the determination unit 105a determines that the type of premature contraction the subject is suffering from is PVC based on the similarity between the shape of the atrial waveform and the ventricular waveform shown in Figure 11.

[0083] (Processing performed by arrhythmia type determination device 1a) Next, the processing performed by the arrhythmia type determination device 1a (arrhythmia type determination method) will be explained using Figure 12. Figure 12 is a flowchart showing an example of the processing flow performed by the arrhythmia type determination device 1a.

[0084] First, the acquisition unit 101 acquires the target signal waveform (Step S1: Acquisition step). Next, the similarity calculation unit 103 compares the shape of the atrial waveform and the shape of the ventricular waveform during the period of interest in which premature contractions occur and calculates the similarity (Step S2a). Then, the determination unit 105 determines that the premature contractions affected by the subject are PVCs if the calculated similarity is below a predetermined standard value (YES in Step S2b) (Step S3: Determination step). On the other hand, if the calculated similarity is below a predetermined standard value (NO in Step S2b), the determination unit 105 determines that the premature contractions affected by the subject are PACs (Step S4: Determination step). The output control unit 106 outputs the determination result from the determination unit 105 to an output device (for example, a display device 6) (Step S5: Output step).

[0085] With the above configuration, the arrhythmia type determination device 1a can accurately determine the type of premature contractions the subject is suffering from from images of the subject's heart. For example, the arrhythmia type determination device 1 can estimate with high accuracy whether the type of premature contractions in a fetus is "PVC" or "PAC".

[0086] [Embodiment 3] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0087] The arrhythmia type determination device 1b according to this embodiment is configured to determine the type of premature contraction that the subject is suffering from based on the presence or absence of (1) a deletion of ventricular contraction corresponding to atrial contraction and (2) a deletion of atrial contraction corresponding to ventricular contraction from the target signal waveform.

[0088] Similar to the embodiment described above, the following description will use an arrhythmia type determination device 1b as an example, which has the function of determining the type of premature contraction the subject is suffering from from a target signal waveform acquired from the premature contraction detection device 4. However, the arrhythmia type determination device 1b may also have the functions of the image analysis device 3 and the premature contraction detection device 4. In this case, the arrhythmia type determination device 1b generates a target signal waveform from the input image acquired from the imaging device 2 and determines the type of premature contraction the subject is suffering from.

[0089] In the following explanation, we will describe an example configuration in which the arrhythmia type determination device 1b acquires a partial waveform (i.e., the target signal waveform during the period of interest) extracted by the premature contraction detection device 4, and determines the type of premature contraction occurring in the subject's heart based on the target signal waveform.

[0090] (Configuration of arrhythmia type determination device 1b) The configuration of the arrhythmia type determination device 1b according to one embodiment of the present invention will be described with reference to Figure 13. Figure 13 is a block diagram showing an example of the main components of the arrhythmia type determination device 1b.

[0091] As shown in the figure, the arrhythmia type determination device 1b is, for example, a computer equipped with a processor 10b, memory 11, and storage device 12. The arrhythmia type determination device 1b may also be a personal computer, a server, or a workstation. The processor 10b functions as each of the parts from the acquisition unit 101 to the output control unit 106, which will be described later, by loading the arrhythmia type determination program 121b stored in the storage device 12 into the memory 11 and executing it.

[0092] The processor 10b can be implemented by logic circuits (hardware) formed on an integrated circuit (IC chip), or by software. When implemented by software, the processor 10b may be configured as a CPU, a GPU, or a combination of these. In this case, the software is stored in the storage device 12. The processor 10b then loads the software into memory 11 and executes it.

[0093] The processor 10b functions as an acquisition unit 101, a deletion detection unit 104, a determination unit 105b, and an output control unit 106, respectively, by executing the arrhythmia type determination program 121b.

[0094] The deletion detection unit 104 detects deletions of ventricular contractions shown in the ventricular waveform that correspond to atrial contractions shown in the atrial waveform during the period of interest, and deletions of atrial contractions shown in the atrial waveform that correspond to ventricular contractions shown in the ventricular waveform. Alternatively, the deletion detection unit 104 may detect deletions of ventricular dilation shown in the ventricular waveform that correspond to atrial dilation shown in the atrial waveform during the period of interest, and deletions of atrial dilation shown in the atrial waveform that correspond to ventricular dilation shown in the ventricular waveform. The following description will use an example of a configuration in which the deletion detection unit 104 detects deletions of atrial and ventricular contractions.

[0095] An example of the processing performed by the deletion detection unit 104 will be explained using Figure 14. Figure 14 shows how the deletion of ventricular contraction corresponding to atrial contraction is detected from a pair of atrial and ventricular waveforms. In Figure 14, the values ​​on the vertical axis represent the magnitude of the area change in each region of the atrial and ventricular heart during contraction and diastole. To detect the deletion to be detected, the deletion detection unit 104 first detects the point in the target signal waveform where the atrial heart transitions from systole to diastole (a minimum point in the atrial waveform, represented by a black circle in Figure 14), and the point in the target signal waveform where the ventricle transitions from systole to diastole (a minimum point in the ventricular waveform, represented by a black star in Figure 14).

[0096] For example, the deletion detection unit 104 detects that in Figure 14, among the sequence of "black circle → black star → black circle → ..." over time, there is a sequence of "black circle → black circle →" (white arrow around 5 seconds), and that the black star that should be there is missing. In other words, in the example shown in Figure 14, there is a deletion of the ventricular contraction shown in the ventricular waveform that corresponds to the atrial contraction shown in the atrial waveform.

[0097] The determination unit 105b determines the type of premature contraction (PVC) the subject is suffering from based on the target signal waveform. Specifically, the determination unit 105b determines the type of PVC the subject is suffering from based on whether a deletion of ventricular contraction corresponding to atrial contraction was detected during the observation period, or whether a deletion of atrial contraction corresponding to ventricular contraction was detected. More specifically, if a deletion of atrial contraction corresponding to ventricular contraction is detected during the observation period, the determination unit 105b determines that the subject is suffering from PVC. On the other hand, if a deletion of ventricular contraction corresponding to atrial contraction is detected during the observation period, the determination unit 105b determines that the subject is suffering from PAC. For example, from the example shown in Figure 14, the determination unit 105b determines that the subject is suffering from PAC.

[0098] The deletion detection unit 104 may also identify the time of each atrial contraction shown in the atrial waveform and the time of each ventricular contraction shown in the ventricular waveform based on the time information corresponding to time V1 and time V2, respectively. In this case, the deletion detection unit 104 may be configured to calculate any of the following (i) to (iv) and to detect at least one of an abnormality in the timing of atrial contraction or an abnormality in the timing of ventricular contraction. (i) The time between contractions of the atria. (ii) The time between contractions of the ventricles. (iii) The time between the contraction of the atrium and the subsequent contraction of the ventricle. (iv) The time between the contraction of the ventricle and the next contraction of the atrium.

[0099] For example, the times t1 to t5 shown in Figure 14 represent the time between the first and next atrial contractions. Times t1, t2, and t5 are approximately 0.4 seconds, while time t3 is approximately 0.25 seconds and time t4 is approximately 0.65 seconds. In other words, the deletion detection unit 104 detects an abnormality in the timing of atrial contractions from the example shown in Figure 14. In this case, the determination unit 105b may determine that the subject has PAC based on the detection of an abnormality in the timing of atrial contractions.

[0100] Alternatively, the deletion detection unit 104 may be capable of detecting both deletions of ventricular and atrial contractions, and abnormalities in the timing of atrial and ventricular contractions. This configuration allows for more accurate determination of the type of premature contractions the subject is experiencing. (Processing performed by arrhythmia type determination device 1b) Next, the processing performed by the arrhythmia type determination device 1b (arrhythmia type determination method) will be explained using Figure 15. Figure 15 is a flowchart showing an example of the processing flow performed by the arrhythmia type determination device 1b.

[0101] First, the acquisition unit 101 acquires the target signal waveform (step S1: acquisition step). Next, the deletion detection unit 104 detects (1) deletions of ventricular contractions corresponding to atrial contractions and (2) deletions of atrial contractions corresponding to ventricular contractions during the period of interest in which premature contractions occur (step S2c).

[0102] The determination unit 105b determines that (1) if a deletion of ventricular contraction corresponding to atrial contraction is detected (YES in step S2d), the type of premature contraction the subject is suffering from is PVC (step S3: determination step).

[0103] On the other hand, the determination unit 105b determines that if (1) no deletion of ventricular contraction corresponding to atrial contraction is detected (NO in step S2d), and (2) a deletion of atrial contraction corresponding to ventricular contraction is detected (YES in step S2e), the type of premature contraction the subject is experiencing is PAC (step S4: determination step). If the result is NO in step S2d and NO in step S2e, the determination unit 105b determines that the type of premature contraction the subject is experiencing is a premature contraction that does not fall under either PVC or PAC (step S4a: determination step). In step S4a, the determination unit 105b may output that the type of premature contraction the subject is experiencing cannot be determined.

[0104] Then, the output control unit 106 causes the determination result (or a message indicating that determination is not possible) from the determination unit 105a to be output to the output device (for example, the display device 6) (step S5: output step).

[0105] With the above configuration, the arrhythmia type determination device 1a can more accurately estimate the type of tachyarrhythmia the subject is suffering from from an image of the subject's heart. For example, the arrhythmia type determination device 1 can estimate with high accuracy whether the type of premature contraction in the fetus is "PVC" or "PAC".

[0106] [Embodiment 4] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0107] The arrhythmia type determination device 1c according to this embodiment is equipped with all of the period detection unit 102, similarity calculation unit 103, and deletion detection unit 104 described in Embodiment 1 above, and is configured to determine the type of premature contraction that the subject is suffering from from the target signal waveform using each of its respective functions.

[0108] Similar to the embodiment described above, the following description will use an arrhythmia type determination device 1c as an example, which has the function of determining the type of premature contraction the subject is suffering from based on the target signal waveform acquired from the premature contraction detection device 4. However, the arrhythmia type determination device 1c may also have the functions of the image analysis device 3 and the premature contraction detection device 4. In this case, the arrhythmia type determination device 1c generates a target signal waveform from the input image acquired from the imaging device 2 and determines the type of premature contraction the subject is suffering from.

[0109] (Configuration of arrhythmia type determination device 1c) The configuration of the arrhythmia type determination device 1c according to one embodiment of the present invention will be described with reference to Figure 16. Figure 16 is a block diagram showing an example of the main components of the arrhythmia type determination device 1c.

[0110] As shown in the figure, the arrhythmia type determination device 1c is, for example, a computer equipped with a processor 10c, memory 11, and storage device 12. The arrhythmia type determination device 1c may also be a personal computer, server, or workstation. The processor 10c functions as each part from the acquisition unit 101 to the output control unit 106, which will be described later, by loading the arrhythmia type determination programs 121, 121a, and 121b stored in the storage device 12 into the memory 11 and executing them.

[0111] The processor 10c can be implemented by logic circuits (hardware) formed on an integrated circuit (IC chip), or by software. When implemented by software, the processor 10c may be composed of a CPU, a GPU, or a combination of these. In this case, the software is stored in the storage device 12. The processor 10c then loads the software into memory 11 and executes it.

[0112] The processor 10c functions as an acquisition unit 101, a period detection unit 102, a similarity calculation unit 103, a deletion detection unit 104, a determination unit 105c, and an output control unit 106, respectively, by executing arrhythmia type determination programs 121, 121a, and 121b to acquire the target signal waveform from the premature contraction detection device 4.

[0113] According to this configuration, the determination unit 105c may determine the type of premature contraction the subject is suffering from by the three processes described in Embodiments 1 to 3 above, and output three determination results.

[0114] Alternatively, the determination unit 105c may be configured to output a single determination result regarding the type of premature contraction (PVC) affected by the subject, based on the degree of agreement of the three determination results. This makes it possible to more accurately determine the type of PVC affected by the subject. For example, the determination unit 105c may be configured to output a single determination result regarding the type of PVC affected by the subject, based on a majority vote of the three determination results. That is, if two of the three determination results determine PAC and one determines PVC, the determination unit 105c may output a single determination result stating that the type of PVC affected by the subject is PAC. In this case, it is preferable that the determination unit 105c also outputs information regarding the possibility that the type of PVC affected by the subject could have been determined, and the basis for that determination, along with the determination result. This allows medical professionals to confirm the correctness of the type of PVC affected by the subject, as determined by the arrhythmia type determination device 1c.

[0115] In this embodiment, an arrhythmia type determination device 1c comprising all three components—a period detection unit 102, a similarity calculation unit 103, and a deletion detection unit 104—has been described. However, the configuration of the arrhythmia type determination device 1c is not limited to this. For example, the arrhythmia type determination device 1c may comprise only the period detection unit 102 and the similarity calculation unit 103, or only the period detection unit 102 and the deletion detection unit 104, or only the similarity calculation unit 103 and the deletion detection unit 104.

[0116] [Examples of implementation using software] The functions of the arrhythmia type determination devices 1, 1a, 1b, and 1c (hereinafter referred to as "devices") are programs that cause a computer to function as the device, and these programs can be realized by programs that cause a computer to function as each control block of the device (in particular, each part included in processors 10, 10a, 10b, and 10c).

[0117] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., memory) as hardware for executing the program. By executing the program using this control device and storage device, the functions described in each of the embodiments are realized.

[0118] The above program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the above device. In the latter case, the program may be supplied to the above device via any wired or wireless transmission medium.

[0119] Furthermore, some or all of the functions of each of the above control blocks can also be realized by logic circuits. For example, an integrated circuit in which logic circuits functioning as each of the above control blocks are formed is also included in the scope of the present invention. In addition, it is also possible to realize the functions of each of the above control blocks by, for example, a quantum computer.

[0120] Furthermore, each process described in the above embodiments may be performed by AI (Artificial Intelligence). In this case, the AI ​​may operate on the control device described above, or it may operate on other devices (for example, an edge computer or a cloud server).

[0121] The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

[0122] 〔summary〕 An arrhythmia type determination device according to embodiment 1 of the present invention includes: an acquisition unit that acquires a target signal waveform including at least one of the following pairs, generated by analyzing an image of the heart of a subject: a pair of signal waveforms showing a time-series change in the area of ​​the left atrium region and a pair of signal waveforms showing a time-series change in the area of ​​the left ventricle region, and a pair of signal waveforms showing a time-series change in the area of ​​the right atrium region and a pair of signal waveforms showing a time-series change in the area of ​​the right ventricle region; and a determination unit that determines the type of premature contraction the subject is suffering from based on the target signal waveform during a period of interest in which premature contractions occur in the heart of the subject.

[0123] An arrhythmia type determination device according to embodiment 2 of the present invention, in embodiment 1 above, the target signal waveform includes an atrial waveform showing a time-series change in the area of ​​the left atrium or the right atrium region, and a ventricular waveform showing a time-series change in the area of ​​the left ventricle or the right ventricle region, and further comprises a period detection unit that detects an increase period in which both the area shown in the atrial waveform and the area shown in the ventricular waveform increase during the period of interest, and a decrease period in which both the area shown in the atrial waveform and the area shown in the ventricular waveform decrease, and the determination unit may determine the type of premature contraction that the subject is suffering from based on the detection status of the increase period and the decrease period during the period of interest.

[0124] In the arrhythmia type determination device according to embodiment 3 of the present invention, in embodiment 2 above, the period detection unit calculates corrected atrial waveforms and corrected ventricular waveforms obtained by removing noise from the atrial waveform and the ventricular waveform, respectively, and in the period of interest, detects as the increase period a period in which the area shown in the corrected atrial waveform and the area shown in the corrected ventricular waveform both increase for a predetermined time or longer, and in the period of interest, detects as the decrease period a period in which the area shown in the corrected atrial waveform and the area shown in the corrected ventricular waveform both decrease for a predetermined time or longer.

[0125] In the arrhythmia type determination device according to embodiment 4 of the present invention, in embodiment 2 or 3 above, the determination unit may determine that the subject suffers from ventricular premature contractions if either the increasing period or the decreasing period is detected during the attention period, and determine that the subject suffers from supraventricular premature contractions if neither the increasing period nor the decreasing period is detected during the attention period.

[0126] An arrhythmia type determination device according to embodiment 5 of the present invention, in any of embodiments 1 to 4 above, further comprises a similarity calculation unit that calculates similarity by comparing the shape of the atrial waveform and the shape of the ventricular waveform during the attention period, wherein the target signal waveform includes an atrial waveform showing a time-series change in the area of ​​the left atrium or the right atrium region, and a ventricular waveform showing a time-series change in the area of ​​the left ventricle or the right ventricle region, and the determination unit may determine the type of premature contraction that the subject is suffering from based on the similarity.

[0127] In the arrhythmia type determination device according to embodiment 6 of the present invention, in embodiment 5, the similarity calculation unit calculates corrected atrial waveforms and corrected ventricular waveforms obtained by removing noise from the atrial waveform and the ventricular waveform, respectively; obtains a plurality of single-beat atrial waveforms corresponding to each heartbeat of the subject's heart from the corrected atrial waveform during the period of interest; obtains a plurality of single-beat ventricular waveforms corresponding to each heartbeat of the subject's heart from the corrected ventricular waveform during the period of interest; normalizes the amplitudes of the obtained plurality of single-beat atrial waveforms and the plurality of single-beat ventricular waveforms; and calculates the similarity by comparing the shape of the normalized plurality of single-beat atrial waveforms with the shape of the plurality of single-beat ventricular waveforms.

[0128] In the arrhythmia type determination device according to embodiment 7 of the present invention, in embodiment 5 or 6 above, the determination unit may determine that the subject suffers from ventricular premature contractions if the similarity is less than or equal to a predetermined standard value during the observation period, and determine that the subject suffers from supraventricular premature contractions if the similarity is higher than the predetermined standard value during the observation period.

[0129] An arrhythmia type determination device according to embodiment 8 of the present invention, in any of embodiments 1 to 7 above, further comprises a deletion detection unit that detects deletions of ventricular contractions shown in the ventricular waveform corresponding to atrial contractions shown in the atrial waveform and deletions of atrial contractions shown in the atrial waveform corresponding to ventricular contractions shown in the ventricular waveform during the observation period, and deletions of atrial contractions shown in the atrial waveform corresponding to ventricular contractions shown in the ventricular waveform during the observation period, wherein the determination unit may determine the type of premature contraction the subject is suffering from based on whether a deletion of ventricular contractions corresponding to atrial contractions or a deletion of atrial contractions corresponding to ventricular contractions is detected during the observation period.

[0130] In the arrhythmia type determination device according to embodiment 9 of the present invention, in embodiment 8 above, the determination unit may determine that the subject suffers from ventricular premature contractions if a deletion of atrial contraction corresponding to ventricular contraction is detected during the observation period, and determine that the subject suffers from supraventricular premature contractions if a deletion of ventricular contraction corresponding to atrial contraction is detected during the observation period.

[0131] An arrhythmia type determination method according to aspect 10 of the present invention is an arrhythmia type determination method performed by one or more information processing devices, comprising: an acquisition step of acquiring a target signal waveform that includes at least one of the following pairs, generated by analyzing an image of the heart of a subject: a pair of signal waveforms showing a time-series change in the area of ​​the left atrium region and a pair of signal waveforms showing a time-series change in the area of ​​the left ventricle region, and a pair of time-series changes in the area of ​​the right atrium region and a pair of time-series changes in the area of ​​the right ventricle region; and a determination step of determining the type of premature contraction that the subject is suffering from, based on the target signal waveform during a period of interest in which premature contractions occur in the heart of the subject.

[0132] The arrhythmia type determination program according to aspect 11 of the present invention is an arrhythmia type determination program for causing a computer to function as an arrhythmia type determination device according to any of aspects 1 to 9 above, and is an arrhythmia type determination program for causing a computer to function as the acquisition unit and the determination unit. [Explanation of symbols]

[0133] 1, 1a, 1b, 1c Arrhythmia type determination device 10, 10a, 10b, 10c processors 101 Acquisition Department 102 Period detection unit 103 Similarity calculation unit 104 Deletion detection unit 105, 105a, 105b, 105c Judgment section 121, 121a, 121b Arrhythmia Type Determination Program

Claims

1. An acquisition unit acquires target signal waveforms that include at least one of the following pairs, generated by analyzing images of the heart of a target subject: a pair of signal waveforms showing the time-series change in the area of ​​the left atrium region and a pair of signal waveforms showing the time-series change in the area of ​​the left ventricle region, and a pair of signal waveforms showing the time-series change in the area of ​​the right atrium region and a pair of signal waveforms showing the time-series change in the area of ​​the right ventricle region. A determination unit that determines the type of premature contraction the subject is suffering from, based on the target signal waveform during the period of interest in which premature contractions occur in the subject's heart, An arrhythmia type determination device equipped with the following features.

2. The target signal waveform includes an atrial waveform showing the time-series change in the area of ​​the left atrium or the right atrium, and a ventricular waveform showing the time-series change in the area of ​​the left ventricle or the right ventricle. The system further includes a period detection unit that detects periods of increase in which both the area shown in the atrial waveform and the area shown in the ventricular waveform increase, and periods of decrease in which both the area shown in the atrial waveform and the area shown in the ventricular waveform decrease, during the aforementioned period of focus. The determination unit, Based on the detection status of the increase period and the decrease period during the aforementioned observation period, the type of premature contraction that the subject is suffering from is determined. The arrhythmia type determination device according to claim 1.

3. The aforementioned period detection unit, Corrected atrial and ventricular waveforms are calculated by removing noise from the atrial and ventricular waveforms, respectively. During the aforementioned period of attention, the period in which both the area shown in the corrected atrial waveform and the area shown in the corrected ventricular waveform increase for a predetermined time or longer is detected as the increase period. During the aforementioned period of attention, the period in which both the area shown in the corrected atrial waveform and the area shown in the corrected ventricular waveform decrease for a predetermined time or longer is detected as the decrease period. The arrhythmia type determination device according to claim 2.

4. The determination unit, If either the increase period or the decrease period is detected during the aforementioned observation period, the subject is determined to be suffering from ventricular premature contractions. If neither the aforementioned increase period nor the aforementioned decrease period is detected during the aforementioned observation period, the subject is determined to be suffering from supraventricular premature contractions. The arrhythmia type determination device according to claim 2 or 3.

5. The target signal waveform includes an atrial waveform showing the time-series change in the area of ​​the left atrium or the right atrium, and a ventricular waveform showing the time-series change in the area of ​​the left ventricle or the right ventricle. The system further includes a similarity calculation unit that calculates the degree of similarity by comparing the shape of the atrial waveform and the shape of the ventricular waveform during the aforementioned period of interest, The determination unit, Based on the similarity, the type of premature contraction that the subject is suffering from is determined. The arrhythmia type determination device according to claim 1.

6. The similarity calculation unit, Corrected atrial and ventricular waveforms are calculated by removing noise from the atrial and ventricular waveforms, respectively. From the corrected atrial waveform during the period of interest, multiple single-beat atrial waveforms corresponding to each heartbeat of the subject's heart are obtained; from the corrected ventricular waveform during the period of interest, multiple single-beat ventricular waveforms corresponding to each heartbeat of the subject's heart are obtained; The amplitudes of the acquired single-beat atrial waveforms and the multiple single-beat ventricular waveforms are normalized. The similarity is calculated by comparing the shapes of the multiple normalized single-beat atrial waveforms with the shapes of the multiple single-beat ventricular waveforms. The arrhythmia type determination device according to claim 5.

7. The determination unit, If the similarity is below a predetermined threshold during the aforementioned observation period, the subject is determined to be suffering from ventricular premature contractions. If the similarity is higher than the predetermined standard value during the aforementioned observation period, the subject is determined to be suffering from supraventricular premature contractions. The arrhythmia type determination device according to claim 5 or 6.

8. The target signal waveform includes an atrial waveform showing the time-series change in the area of ​​the left atrium or the right atrium, and a ventricular waveform showing the time-series change in the area of ​​the left ventricle or the right ventricle. The system further includes a deletion detection unit that detects deletions of ventricular contractions shown in the ventricular waveform that correspond to atrial contractions shown in the atrial waveform, and deletions of atrial contractions shown in the atrial waveform that correspond to ventricular contractions shown in the ventricular waveform, during the aforementioned period of interest. The determination unit, During the aforementioned observation period, the type of premature contraction the subject is suffering from is determined based on whether a deletion of ventricular contraction corresponding to atrial contraction is detected, or whether a deletion of atrial contraction corresponding to ventricular contraction is detected. The arrhythmia type determination device according to claim 1.

9. The determination unit, If a deficit in atrial contraction corresponding to ventricular contraction is detected during the aforementioned observation period, the subject is determined to be suffering from ventricular premature contractions. If a deletion of ventricular contraction corresponding to atrial contraction is detected during the aforementioned observation period, the subject is determined to be suffering from supraventricular premature contractions. The arrhythmia type determination device according to claim 8.

10. A method for determining the type of arrhythmia, which is performed by one or more information processing devices, Acquisition step of acquiring target signal waveforms that include at least one of the following pairs, generated by analyzing images of the heart of the target subject: a pair of signal waveforms showing the time-series change in the area of ​​the left atrium region and a pair of signal waveforms showing the time-series change in the area of ​​the left ventricle region, and a pair of signal waveforms showing the time-series change in the area of ​​the right atrium region and a pair of signal waveforms showing the time-series change in the area of ​​the right ventricle region; A determination step to determine the type of premature contraction the subject is suffering from, based on the target signal waveform during the period of interest in which premature contractions occur in the subject's heart; A method for determining the type of arrhythmia, including the type of arrhythmia.

11. An arrhythmia type determination program for causing a computer to function as an arrhythmia type determination device according to claim 1, wherein the arrhythmia type determination program causes a computer to function as the acquisition unit and the determination unit.

Images