Pre-period shrinkage determination device, pre-period shrinkage determination method, and pre-period shrinkage determination program

Abstract

In order to determine the presence or absence of pre-constriction with high accuracy on the basis of an image of a heart, a pre-constriction determination device (1) is provided with: an acquisition unit (101) that acquires a signal waveform indicating a time-series change in the area of each ventricle and each atrium region in the image of the heart; and a determination unit (104) that determines whether or not there is a pre-period contraction by comparing the time interval from the point in time when the area indicated by the signal waveform reaches the reference value to the point in time when the area reaches the reference value again with a predetermined threshold value.

Description

Technical Field

[0001] This invention relates to a technique for determining the presence or absence of premature contractions based on images of the heart. Background Technology

[0002] The technique of determining the left-right and atrioventricular relationships of the heart from dynamic ultrasound images is widely used. For example, Patent Document 1 discloses an ultrasound diagnostic device that determines a group of boundary positions in multiple heart chambers from a dynamic ultrasound image, and obtains the boundary positions of multiple heart chambers covering an area spanning at least one heartbeat based on the tracking results of the group of boundary positions.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2022-149097 Summary of the Invention

[0006] (a) Technical problems to be solved

[0007] Previously, electrocardiography (ECG) was primarily used for the diagnosis of arrhythmias. However, it was sometimes difficult to determine whether the arrhythmia was premature contraction, leaving room for improvement in accuracy. Furthermore, premature contractions are a type of arrhythmia that cause abnormal stimulation to the heart, adding a contraction-induced pulsation in addition to the standard beat. One aspect of this invention aims to determine the presence or absence of premature contractions with high precision based on cardiac imaging.

[0008] (II) Technical Solution

[0009] To address the aforementioned issues, one aspect of the present invention provides a premature contraction determination apparatus comprising: an acquisition unit that acquires a signal waveform generated by analyzing images of the heart, representing a time-series change in the area of ​​at least one region among the left atrium, left ventricle, right atrium, and right ventricle; and a determination unit that determines whether a premature contraction is present by comparing a time interval from the moment when the area represented by the signal waveform becomes a reference value set based on the displacement of the signal waveform to the moment when the area represented by the signal waveform again becomes the reference value with a predetermined threshold.

[0010] Furthermore, one aspect of the premature contraction determination method of the present invention is a premature contraction determination method executed by one or more information processing devices, comprising: an acquisition step of acquiring a signal waveform representing a time-series change in the area of ​​at least one region of the left atrium, left ventricle, right atrium, and right ventricle, generated by analyzing images of the heart; and a determination step of determining whether it is a premature contraction by comparing a time interval from the moment when the area shown by the signal waveform becomes a reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform becomes the reference value again with a predetermined threshold.

[0011] The various embodiments of the preterm contraction determination device of the present invention can also be implemented by a computer. In this case, by making the computer operate as each part (software element) of the preterm contraction determination device, the control program of the preterm contraction determination device implemented by the computer, and the computer-readable recording medium on which the control program is recorded, also fall within the scope of the present invention.

[0012] (III) Beneficial Effects

[0013] According to one aspect of the present invention, it is possible to determine with high precision whether premature contractions are present based on images of the heart. Attached Figure Description

[0014] Figure 1 This is a block diagram illustrating an example of the main structure of a pre-contraction determination device according to an embodiment of the present invention.

[0015] Figure 2 This diagram illustrates an example of detecting different regions of the left atrium, left ventricle, right atrium, and right ventricle based on ultrasound images of the heart.

[0016] Figure 3 This is a diagram showing an example of a signal waveform used to determine premature contraction.

[0017] Figure 4 This is a diagram illustrating how to set the baseline and threshold values.

[0018] Figure 5 This is a flowchart illustrating an example of a premature contraction determination method according to an embodiment of the present invention. Detailed Implementation

[0019] [Structure of the Premature Contraction Detection Device 1]

[0020] based on Figure 1The structure of a premature contraction determination device 1 according to one embodiment of the present invention will be described. The premature contraction determination device 1 has the function of determining the presence or absence of premature contractions based on an image of the heart, and will be described in detail below. According to the premature contraction determination device 1, compared with the method of determining the presence or absence of premature contractions using an electrocardiogram, a more accurate determination result can be output.

[0021] Figure 1 This is a block diagram illustrating an example of the main structure of the pre-term contraction determination device 1. As shown, the pre-term contraction determination device 1 includes a processor 10, a memory 11, and a storage device 12. The pre-term contraction determination device 1 can be a personal computer, a server, or a workstation. The processor 10 loads the pre-term contraction determination program stored in the storage device 12 into the memory 11 and executes it, thereby functioning as each of the units from the acquisition unit 101 to the output control unit 106, which will be described later.

[0022] The processor 10 can be implemented using logic circuits (hardware) formed on integrated circuits (IC chips) or software. In the case of software implementation, the processor 10 can be configured as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a combination thereof. Furthermore, in this case, the software is pre-stored in the storage device 12. Then, the processor 10 reads the software into the memory 11 and executes it.

[0023] Both memory 11 and storage device 12 are storage devices for various data used by the storage period shrinkage 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. As memory 11, for example, high-speed access memory such as SDRAM (Synchronous Dynamic Random Access Memory) can be used. As storage device 12, for example, HDD (Hard Disk Drive), SSD (Solid State Drive), SD (Secure Digital) card, or eMMC (embedded Multi-Media Controller) can be used.

[0024] Furthermore, the premature contraction determination device 1 includes an input IF unit 13 and an output IF unit 14 as interfaces (IF) with external devices. The input IF unit 13 is an interface for receiving input signals from input devices such as keyboards and mice. The output IF unit 14 is an interface for outputting the determination result of whether premature contraction exists to an external device. For example, a display device can be connected to the output IF unit 14 to display the determination result of whether premature contraction exists.

[0025] The processor 10 performs the functions of the acquisition unit 101, the specific component removal unit 102, the reference value setting unit 103, the determination unit 104, the threshold setting unit 105, and the output control unit 106 by executing the pre-contraction determination program.

[0026] The acquisition unit 101 acquires a signal waveform representing the time-series change in the area of ​​at least one region among the left atrium, left ventricle, right atrium, and right ventricle contained in an image of the heart. Furthermore, the "signal waveform" is data representing the time-series change in the area of ​​the aforementioned region. Details regarding the image of the heart, the area of ​​each region, and the signal waveform will be described later.

[0027] The specific component removal unit 102 performs a process of removing specific frequency components from the signal waveform acquired by the acquisition unit 101. Details will be described later. For example, the specific component removal unit 102 may also remove high-frequency and low-frequency components from the signal waveform by providing it to a low-pass filter and a high-pass filter.

[0028] The reference value setting unit 103 sets a reference value based on the displacement of the signal waveform acquired by the acquisition unit 101. Additionally, the threshold setting unit 105 sets a threshold (prescribed threshold) for determining whether premature contractions are present. The method for setting the threshold and reference value will be described later.

[0029] The determination unit 104 determines whether premature contraction has occurred. Specifically, during this determination, the determination unit 104 first determines a time interval, which is the time interval from the moment when the area of ​​the signal waveform acquired by the acquisition unit 101 reaches a reference value set by the reference value setting unit 103 until the area of ​​the signal waveform reaches the reference value again. Then, the determination unit 104 determines whether premature contraction has occurred by comparing the determined time interval with a threshold set by the threshold setting unit 105. Details of this determination will be described later.

[0030] The output control unit 106 causes various output devices to output the determination result of the determination unit 104. For example, when a display device is connected via the output IF unit 14, the output control unit 106 can also cause the display device to output the determination result. Of course, the output method is arbitrary, and the determination result of the determination unit 104 can be output through display output, sound output, print output, or combinations thereof.

[0031] As described above, the premature contraction determination device 1 includes an acquisition unit 101 that acquires a signal waveform generated by analyzing images of the heart, representing a time-series change in the area of ​​at least one region among the left atrium, left ventricle, right atrium, and right ventricle. Furthermore, the premature contraction determination device 1 includes a determination unit 104 that compares the time interval from the moment when the area shown by the signal waveform reaches a reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform again reaches the reference value with a predetermined threshold. Thus, the determination unit 104 determines whether a premature contraction has occurred.

[0032] The inventors of this application have discovered that, in the case of premature contractions, a characteristic change occurs in the time interval from the moment when the area shown in the aforementioned signal waveform becomes a reference value to when it becomes a reference value again. Therefore, it is possible to determine with high precision whether a premature contraction has occurred based on an image of the heart.

[0033] [Analysis of images related to the heart]

[0034] As described above, the premature contraction determination device 1 uses a signal waveform generated by analyzing images of the heart, which represents the time-series change in the area of ​​at least one region of the left atrium, left ventricle, right atrium, and right ventricle, to determine whether premature contractions are present.

[0035] Here, based on Figure 2 The analysis of the heart image used to generate the above signal waveform is explained. Figure 2 This diagram illustrates an example of examining different regions of the left atrium, left ventricle, right atrium, and right ventricle using ultrasound images of the heart. More specifically... Figure 2 Image A1 shown is an ultrasound image of the heart, and image A2 is superimposed on this ultrasound image to represent the detection results of each region. Furthermore, an ultrasound image is an image formed by imaging the reflected waves of ultrasound waves emitted towards the heart and its surroundings, reflected from the surface of the heart, etc.; it can also be called an echo image.

[0036] The heart is visualized in the area slightly below the center in image A1, allowing for visual confirmation of its shape and the division of its interior into multiple regions. Thus, in the ultrasound image, the two ventricles and two atria of the heart can be visually identified as closed regions. Therefore, by analyzing the ultrasound image, it is possible to detect the regions of the left atrium, left ventricle, right atrium, and right ventricle.

[0037] For example, machine learning can be performed using teacher data containing labels for the left atrium, left ventricle, right atrium, and right ventricle in ultrasound images of the heart, labeled as positive resolution data. These labels can also be called annotations. Thus, a detection model capable of detecting different regions based on ultrasound images of the heart can be constructed. For example, by constructing a detection model using a convolutional neural network, high-precision region detection can be achieved.

[0038] Figure 2 Image A2 shows the detection results using this detection model. The detected regions R1 to R4 are the regions detected as the right ventricle, left ventricle, left atrium, and right atrium, respectively. Furthermore, by detecting each region, the area of ​​each region can be numerically represented. For example, the area of ​​a region can also be represented by the number of pixels it contains.

[0039] [Regarding the generation of signal waveforms and the removal of specific components from signal waveforms]

[0040] By performing region detection as described above on multiple ultrasound images constituting a time series, a signal waveform representing the time-series change in the area of ​​a region can be generated. For example, frame images constituting an ultrasound image can be extracted from the ultrasound image, which is a dynamic image, and region detection can be performed on each frame image to generate a signal waveform. Figure 3 An example of a signal waveform generated in this way is shown.

[0041] Figure 3 This is a diagram illustrating an example of a signal waveform used to determine premature contraction. More specifically, in Figure 3 In section B1, for each region of the right ventricle, left ventricle, left atrium, and right atrium, a signal waveform representing the time-series change in the number of pixels contained in that region is shown. Furthermore, the horizontal axis (time) is in seconds.

[0042] As shown in B1, the number of pixels, i.e., the area, of each region increases and decreases repeatedly at the same period. However, for example, around 2.5 to 3.0 seconds, the periodic increasing and decreasing pattern becomes disordered. This disorder in the increasing and decreasing pattern is caused by cardiac arrhythmia. Therefore, by detecting the disorder in the periodic increasing and decreasing pattern, cardiac arrhythmia can be detected. Furthermore, according to the premature contraction determination device 1, the presence or absence of premature contraction can be determined with high precision based on the increasing and decreasing pattern of such signal waveform.

[0043] Here, it is possible to directly use a signal waveform like B1 to determine whether premature contraction exists, but it is also possible to use a signal waveform in which a specific frequency component has been removed by the specific component removal unit 102 to determine whether premature contraction exists. In this case, the determination unit 104 determines the aforementioned time interval in the signal waveform in which the specific frequency component has been removed. As a result, an appropriate time interval can be determined, thereby improving the determination accuracy.

[0044] exist Figure 3 Figure B2 shows the signal waveform obtained by removing specific frequency components from the signal waveform shown in Figure B1. More specifically, B2 shows the signal waveform after removing the low-frequency component (containing DC and trend components of the waveform signal) and the high-frequency component (containing noise components). By removing the low-frequency component, as shown in the figure, the center value of the signal waveform's displacement can be set to zero, resulting in a waveform representing an increase or decrease in area. Furthermore, by removing the high-frequency component, a smooth waveform with noise components removed, as shown in the figure, can be obtained.

[0045] Furthermore, the center value of the displacement of a signal waveform is the average of the area covered by the signal waveform at each moment. For example, if it is a 10-second signal waveform, then the average of the total area covered by the signal waveform is the center value of the displacement.

[0046] Here, if the overall size of the heart reflected in the image that forms the basis of the signal waveform is constant, then by subtracting the center value of the displacement from the area values ​​at each moment in the signal waveform, the center value of the displacement can be set to zero, resulting in a waveform representing the increase or decrease in area. However, when the overall size of the heart reflected in the image that forms the basis of the signal waveform changes over time, setting the center value of the displacement to zero during the subtraction process fails to yield a suitable waveform representing the increase or decrease in area. An example of this is when the imaging device moves during imaging.

[0047] Therefore, as described above, the specific component removal unit 102 preferably removes low-frequency components from the waveform signal. In this case, the determination unit 104 determines the time interval in the signal waveform after removing the low-frequency components. Since the trend component, such as the time-varying change in the size of the whole heart reflected in the image, is contained in the low-frequency component, according to the above structure, such trend component can also be removed, making the center value of the displacement zero, and obtaining a proper waveform representing the increase or decrease in area.

[0048] Furthermore, the specific component removal unit 102 can also remove high-frequency components as described above. By removing high-frequency components, a smooth waveform with noise components removed can be obtained, which can improve the determination accuracy of the determination unit 104. In addition, the specific component removal unit 102 can also smooth the signal waveform by means of moving average or the like, and the same effect can be obtained in this case.

[0049] [Methods for setting baseline and threshold values]

[0050] based on Figure 4 The methods for setting the baseline and threshold values ​​are explained. Figure 4 This is a diagram illustrating how to set the baseline and threshold values. Furthermore, Figure 4 The signal waveform G1 shown is for Figure 3 The waveform is one of the four signal waveforms shown in B1, and a portion of it is amplified.

[0051] As described above, the determination unit 104 determines a time interval, which is the time interval from the moment when the area shown by the signal waveform becomes a reference value set based on the displacement of the signal waveform until the area shown by the signal waveform becomes the reference value again. The reference value set by the reference value setting unit 103 is used to determine this time interval.

[0052] As long as it is within the range of signal waveform displacement, the reference value setting unit 103 can set any reference value. For example, the reference value setting unit 103 can also set the center value of the displacement in the signal waveform as the reference value. Figure 4 The reference value in the diagram is 0, represented by line segment L. Furthermore, as mentioned above, the center value of the signal waveform's displacement is the average value or trend component of the overall signal. Based on this structure, an appropriate time interval can be determined, thus improving the accuracy of the judgment.

[0053] Alternatively, the reference value can be predetermined to be 0. In this case, the reference value setting unit 103 can be omitted, and the presence or absence of premature contraction can be determined using the signal waveform after the low-frequency components have been removed by the specific component removal unit 102. Alternatively, for example, the acquisition unit 101 can also acquire the signal waveform after the low-frequency components have been removed, in which case the specific component removal unit 102 can also be omitted.

[0054] Thus, when the reference value is set to 0, low-frequency components containing DC and trend components need to be removed from the signal waveform beforehand. Alternatively, without removing low-frequency components, the reference value setting unit 103 may use the peak value (the point where the area value increases or decreases) as the reference point instead of the 0 point. In this case, the determination unit 104 determines the time interval between reference points and determines whether premature contraction occurs based on the determined time interval. Furthermore, to avoid incorrectly setting the increase or decrease in area value caused by noise as the peak value, it is preferable to smooth the waveform signal beforehand by removing high-frequency components, etc.

[0055] When the reference value setting unit 103 sets the reference value as described above, the determination unit 104 determines the time interval, which is the time interval from the moment when the area shown by the signal waveform becomes the reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform becomes the reference value again.

[0056] For example, in Figure 4 In the case of signal waveform G1, the determination unit 104 determines the time interval t1 from point P1 to point P2, the time interval t2 from point P2 to point P3, the time interval t3 from point P3 to point P4, the time interval t4 from point P4 to point P5, and the time interval t5 from point P5 to point P6. The same applies to points P6 and beyond.

[0057] The threshold setting unit 105 can also set the threshold based on the representative value of each time interval determined in this way. By setting the threshold based on the representative value of each time interval, appropriate judgments can be made that take into account differences caused by individual differences in the variation pattern in the signal waveform, physical conditions, etc. In addition, the representative value is simply a value that represents each determined time interval. For example, the median value or average value of each determined time interval can also be used as the representative value. If the median value or average value of the time interval is multiplied by 2, it becomes a value that is approximately equal to the pulse.

[0058] For example, the threshold setting unit 105 can set the value obtained by adding a predetermined value to the representative value as the threshold, or it can set the value obtained by subtracting a predetermined value from the representative value as the threshold. For example, the threshold setting unit 105 can also set the value obtained by adding 0.2 seconds to the representative value, or the value obtained by subtracting 0.2 seconds from the representative value, as the threshold. In addition, for example, the threshold setting unit 105 can set the value that is larger than a predetermined multiple of the representative value as the threshold, or it can set the value that is smaller than a predetermined multiple of the representative value as the threshold.

[0059] When a threshold is set for a value larger than the representative value, if the determined time intervals include time intervals above the threshold, the determination unit 104 determines that it is a premature contraction. On the other hand, when a threshold is set for a value smaller than the representative value, if the determined time intervals include time intervals below the threshold, the determination unit 104 determines that it is a premature contraction.

[0060] Alternatively, the threshold setting unit 105 may set a threshold larger than the representative value and a threshold smaller than the representative value, respectively. In this case, the determination unit 104 can determine that it is premature contraction as long as the determined time intervals include at least one of the time intervals with a threshold greater than the representative value and a time interval with a threshold less than the representative value.

[0061] [Method for Determining Premature Contraction]

[0062] based on Figure 5 The method for determining premature contraction in this embodiment will be explained. Figure 5 This is a flowchart illustrating an example of the premature contraction determination method of this embodiment.

[0063] In S1 (acquisition step), the acquisition unit 101 acquires a signal waveform generated by analyzing an image of the heart, representing the time-series change of the area of ​​at least one region among the left atrium, left ventricle, right atrium, and right ventricle over a specified period. For example, the acquisition unit 101 may also acquire a signal waveform input via the input IF unit 13. Furthermore, examples of acquiring signal waveforms corresponding to the left atrium, left ventricle, right atrium, and right ventricle will be described below.

[0064] In S2, the specific component removal unit 102 removes specific frequency components from the signal waveform acquired in S1. For example, as described above, the specific component removal unit 102 can also remove high-frequency components using a low-pass filter and low-frequency components using a high-pass filter. This processing is performed on each signal waveform corresponding to the left atrium, left ventricle, right atrium, and right ventricle, respectively. The processing in S3 to S5 is the same.

[0065] In S3, the reference value setting unit 103 sets a reference value based on the displacement of the signal waveform from which specific frequency components have been removed in S2. For example, the reference value setting unit 103 may also set the center value of the displacement in the signal waveform as the reference value. In addition, if the center value of the displacement of the signal waveform is zero due to the removal of low-frequency components in S2, the reference value may be preset to zero, and the processing in S3 may be omitted.

[0066] In S4, the determination unit 104 determines a time interval, which is the time interval from the moment when the area of ​​the signal waveform to which a specific frequency component has been removed in S2 becomes a reference value set in S3 until the area of ​​the signal waveform becomes a reference value again. This process is performed on the entire signal waveform over a specified period, and multiple time intervals are determined.

[0067] In S5, the threshold setting unit 105 sets a threshold for determining whether premature contractions have occurred based on each time interval determined in S4. For example, the threshold setting unit 105 may also set the threshold based on a representative value of each time interval determined in S4. Alternatively, the threshold setting unit 105 may set at least one of a threshold larger than the representative value and a threshold smaller than the representative value.

[0068] In step S6 (determination step), the determination unit 104 determines whether a premature contraction is occurring by comparing the time interval determined in step S4 with the threshold set in step S5. This determination is performed separately for the left atrium, left ventricle, right atrium, and right ventricle, obtaining a determination for whether a premature contraction occurs in each of these regions. Therefore, it is possible not only to determine whether a premature contraction exists, but also to determine in which region of the heart the premature contraction occurs.

[0069] Here, the determination unit 104 may also make a final determination on whether it is a pre-term contraction based on the determination results for each of the multiple regions. For example, if the determination result for at least one of the multiple regions is a pre-term contraction, the determination unit 104 may also set the final determination result as a pre-term contraction. Alternatively, for example, the determination unit 104 may set the final determination result for these regions as a pre-term contraction only if the determination results for the multiple regions are pre-term contractions and are consistent.

[0070] Alternatively, the determination unit 104 can determine only the left and right atria or only the left and right ventricles, instead of all four regions. Alternatively, the determination unit 104 can determine only any one of the four regions.

[0071] In S7, the output control unit 106 causes the designated output device to output the determination result of S6, thereby Figure 5 The processing ends. Alternatively, the result can be stored in storage device 12 without being output, and the processing can then end.

[0072] As described above, the premature contraction determination method of this embodiment includes an acquisition step (S1), which acquires a signal waveform generated by analyzing images of the heart, representing the time-series change of the area of ​​at least one region among the left atrium, left ventricle, right atrium, and right ventricle. Furthermore, the premature contraction determination method includes a determination step (S6). In this determination step, the time interval from the moment when the area shown by the signal waveform becomes a reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform again becomes the reference value is compared with a predetermined threshold. Therefore, whether or not premature contraction occurs is determined in the determination step. Thus, the presence or absence of premature contraction can be determined with high accuracy.

[0073] [Variation Example]

[0074] The execution entities of each process described in the above embodiments are arbitrary and not limited to the examples above. That is, by using multiple information processing devices capable of communicating with each other, a pre-term contraction determination system with the same function as the pre-term contraction determination device 1 can be constructed. For example, by using... Figure 1 The processor 10 contains blocks distributed across multiple information processing devices, enabling the construction of a pre-term contraction determination system with the same functions as the pre-term contraction determination device 1.

[0075] For example, in Figure 5 In the pre-term contraction determination method shown, the execution subject of each step can be an information processing device (pre-term contraction determination device 1) or multiple information processing devices.

[0076] Furthermore, a premature contraction determination system, including an imaging device or image generation device, an information processing device, and a premature contraction determination device 1, is also included within the scope of this invention. The imaging device captures an image of the heart, and the image generation device generates an image of the heart. The information processing device analyzes the captured or generated image to generate the aforementioned signal waveform. The premature contraction determination device 1 uses the generated signal waveform to determine whether premature contractions are present. Additionally, this premature contraction determination system may also include an output device that outputs the determination result of whether premature contractions are present.

[0077] [Software-based implementation example]

[0078] As described above, the function of the pre-term contraction determination device 1 can be realized through the pre-term contraction determination program, which enables the computer to function as the pre-term contraction determination device 1 and to function as each control block of the device.

[0079] The above procedure can also be recorded on one or more non-transitory, computer-readable recording media. This recording medium may or may not be included with the pre-expiration shrinkage determination device 1. In the latter case, the above procedure can also be supplied to the pre-expiration shrinkage determination device 1 via any wired or wireless transmission medium.

[0080] Furthermore, some or all of the functions of the pre-contraction determination device 1 can also be implemented through logic circuits. For example, it can be formed as... Figure 1 The integrated circuits of the logic circuits that function the various control blocks shown (each part included in the processor 10) are also included within the scope of this invention. Furthermore, the functions of the aforementioned control blocks can also be implemented, for example, using a quantum computer.

[0081] This invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims. Embodiments obtained by appropriately combining the various technical means disclosed in the above embodiments are also included within the technical scope of this invention.

[0082] [Summarize]

[0083] The premature contraction determination device of Embodiment 1 of the present invention comprises: an acquisition unit that acquires a signal waveform generated by analyzing an image of the heart, representing a time-series change in the area of ​​at least one of the left atrium, left ventricle, right atrium, and right ventricle; and a determination unit that determines whether a premature contraction is present by comparing a time interval from the moment when the area shown by the signal waveform becomes a reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform again becomes the reference value with a predetermined threshold.

[0084] The premature contraction determination device of the present invention in embodiment 2 may also include, in embodiment 1 above, a specific component removal unit that removes low-frequency components from the signal waveform, and the determination unit determines the time interval in the signal waveform after the low-frequency components have been removed.

[0085] The premature contraction determination device of the present invention in Method 3 can also be, in Method 1 or 2 above, the reference value is the center value of the displacement in the signal waveform.

[0086] The premature contraction determination device of the present invention in embodiment 4 may also be, in any of the embodiments 1 to 3 above, a value set based on a representative value of the time interval.

[0087] The premature contraction determination method of Embodiment 5 of the present invention is a premature contraction determination method executed by one or more information processing devices, comprising: an acquisition step of acquiring a signal waveform representing the time-series change of the area of ​​at least one of the left atrium, left ventricle, right atrium, and right ventricle, generated by analyzing images of the heart; and a determination step of determining whether it is a premature contraction by comparing the time interval from the moment when the area shown by the signal waveform becomes a reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform becomes the reference value again with a predetermined threshold.

[0088] A pre-term contraction determination procedure is provided to enable a computer to function as a pre-term contraction determination device according to any one of the above-described methods 1 to 4, wherein the pre-term contraction determination procedure enables the computer to function as both the acquisition unit and the determination unit.

[0089] Explanation of reference numerals in the attached figures

[0090] Pre-contraction determination device

[0091] 101 Acquisition Department

[0092] 102 Specific Component Removal Section

[0093] 104 Judgment Department

[0094] S1 Acquisition Steps

[0095] S6 Judgment Step

Claims

1. A device for determining premature contraction, characterized in that, have: The acquisition unit acquires a signal waveform representing the time-series variation of the area of ​​at least one region among the left atrium, left ventricle, right atrium, and right ventricle, generated by analyzing images of the heart; and The determination unit determines whether it is premature contraction by comparing the time interval from the moment when the area shown by the signal waveform becomes a reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform becomes the reference value again with a predetermined threshold.

2. The device for determining premature contraction according to claim 1, characterized in that, It also includes a specific component removal unit, which removes the low-frequency components of the signal waveform. The determination unit determines the time interval from the signal waveform after removing low-frequency components.

3. The device for determining premature contraction according to claim 1 or 2, characterized in that, The reference value is the center value of the displacement in the signal waveform.

4. The device for determining premature contraction according to claim 1 or 2, characterized in that, The specified threshold is a value set based on a representative value of the time interval.

5. A method for determining premature contraction, which is a method for determining premature contraction executed by one or more information processing devices, characterized in that, include: The acquisition step involves acquiring a signal waveform representing the time-series variation of the area of ​​at least one region among the left atrium, left ventricle, right atrium, and right ventricle, generated by analyzing images of the heart; and The determination step involves comparing the time interval from the moment when the area shown by the signal waveform becomes a reference value set based on the displacement of the signal waveform to the moment when the area shown by the signal waveform becomes the reference value again with a predetermined threshold to determine whether it is premature contraction.

6. A procedure for determining premature contraction, characterized in that, The computer is configured to function as the pre-term contraction determination device as described in claim 1, and the pre-term contraction determination program is configured to function as both the acquisition unit and the determination unit.

Images