Methods for estimating ventricular volumes

Abstract

The present invention provides a method for estimating ventricular volume, comprising: obtaining a left ventricular mask image corresponding to a cardiac ultrasound image, wherein the left ventricular mask image is a binary image; finding three reference point pixels in the left ventricular mask image, wherein each reference point pixel has a first value, each reference point pixel is surrounded by N surrounding pixels, and the plurality of surrounding pixels of each reference point pixel include N1 first surrounding pixels having the first value and N2 second surrounding pixels having a second value; estimating a left ventricular volume corresponding to the cardiac ultrasound image based on the plurality of reference point pixels. In this way, the left ventricular volume can be automatically estimated with better efficiency without manually marking the apex and the mitral valves on both sides.

Description

Technical Field

[0001] The present invention relates to a medical image evaluation method, and in particular to a method for estimating ventricular volume. Background Art

[0002] In the prior art, there are many documents that estimate the ventricular volume in cardiac ultrasound images based on the Simpson's rule. Generally speaking, before using the Simpson's rule, three specific reference points must be found in the cardiac ultrasound image, and these reference points correspond to the apex and the mitral valves on both sides. After finding the above reference points, the Simpson's rule can be applied to estimate the ventricular volume.

[0003] However, the reference points generally need to be manually marked on the cardiac ultrasound image by relevant medical professionals, and currently there is no relevant technology for automatically marking the reference points. Summary of the invention

[0004] In view of this, the present invention provides a method for estimating ventricular volume, which can be used to solve the above technical problems.

[0005] The present invention provides a method for estimating ventricular volume, which is suitable for an electronic device, comprising: obtaining a left ventricular mask image corresponding to a cardiac ultrasound image, wherein the left ventricular mask image is a binary image; finding three reference point pixels in the left ventricular mask image, wherein each reference point pixel has a first value, each reference point pixel is surrounded by N surrounding pixels, and the multiple surrounding pixels of each reference point pixel include N1 first surrounding pixels with the first value and N2 second surrounding pixels with a second value; estimating a left ventricular volume corresponding to the cardiac ultrasound image based on the multiple reference point pixels. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The accompanying drawings are included to provide a further understanding of the present invention and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments of the present invention and together with the description serve to explain the principles of the present invention.

[0007] Figure 1 is a schematic diagram of an electronic device according to an embodiment of the present invention;

[0008] Figure 2 is a flowchart of a method for estimating ventricular volume according to an embodiment of the present invention;

[0009] Figure 3 is an application scenario diagram according to an embodiment of the present invention;

[0010] Figure 4is a schematic diagram illustrating how to find first, second and third reference point pixels based on distances between reference point pixels according to an embodiment of the present invention;

[0011] Figure 5A is based on Figure 3 The diagram shows a schematic diagram of finding the reference point pixel corresponding to the apex of the heart;

[0012] Figure 5B is based on Figure 5A The diagram shows a schematic diagram of finding the reference point pixel corresponding to the left mitral valve;

[0013] Figure 5C is based on Figure 5B The diagram shows a schematic diagram of finding the reference point pixel corresponding to the right mitral valve;

[0014] Figure 6 is a flowchart of a method for assisting in assessing cardiac motion status according to an embodiment of the present invention;

[0015] Fig. 7A is an application scenario diagram according to an embodiment of the present invention;

[0016] Figure 7B is based on Fig. 7A Another application scenario diagram is shown in the figure. DETAILED DESCRIPTION

[0017] Reference will now be made in detail to exemplary embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Whenever possible, the same reference numerals are used in the drawings and the description to refer to the same or like parts.

[0018] Please refer to Figure 1 , which is a schematic diagram of an electronic device according to an embodiment of the present invention. In different embodiments, the electronic device 100 is, for example, various computer devices, smart devices and / or handheld devices, but is not limited thereto.

[0019] like Figure 1 As shown, the electronic device 100 includes a storage circuit 102 and a processor 104. The storage circuit 102 is, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk or other similar devices or a combination of these devices, and can be used to record multiple program codes or modules.

[0020] The processor 104 is coupled to the memory circuit 102 and may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, a controller, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), any other type of integrated circuit, a state machine, an Advanced RISC Machine (ARM) based processor, and the like.

[0021] In an embodiment of the present invention, the processor 104 can access the modules and program codes recorded in the storage circuit 102 to implement the method for estimating ventricular volume proposed by the present invention, the details of which are described as follows.

[0022] Please refer to Figure 2 and Figure 3 ,in Figure 2 is a flowchart of a method for estimating ventricular volume according to an embodiment of the present invention. Figure 3 is an application scenario diagram according to an embodiment of the present invention. The method of this embodiment can be performed by Figure 1 The electronic device 100 is executed as follows: Figure 1 The components shown and Figure 3 Scenario description Figure 2 Details of each step.

[0023] First, in step S210, the processor 104 may obtain a left ventricle mask image 31 corresponding to the cardiac ultrasound image 30, wherein the left ventricle mask image 31 is a binary image. In an embodiment of the present invention, the processor 104 may, for example, input the cardiac ultrasound image 30 (which is, for example, an apical view of A2C (apical two chamber) or A4C ​​(apical four chamber)) into a pre-trained machine learning model, so that the machine learning model outputs a corresponding binary image as the left ventricle mask image 31 in response to the cardiac ultrasound image 30.

[0024] In one embodiment, in order to enable the above-mentioned machine learning model to have the above-mentioned capabilities, the designer can input various cardiac ultrasound images with image regions of ventricles marked as training data into the machine learning model during the training of the machine learning model. In this way, the machine learning model can learn the features of the image regions corresponding to the ventricles, and then when an unknown cardiac ultrasound image is obtained, the image region corresponding to the ventricles can be correspondingly identified therein. Afterwards, the machine learning model can set all pixels in the image region corresponding to the ventricles to a first value (e.g., 255), and set all pixels in the image region not corresponding to the ventricles to a second value (e.g., 0), so as to generate a corresponding binary image, but is not limited thereto.

[0025] Afterwards, in step S220 , the processor 104 may find three reference point pixels 311 ˜ 313 in the left ventricle mask image 31 .

[0026] In the embodiment of the present invention, each reference point pixel 311-313 may have a first value (e.g., 255). In addition, each reference point pixel 311-313 may be surrounded by N (e.g., 8) surrounding pixels, and the surrounding pixels of each reference point pixel 311-313 may include N1 (e.g., 3) first surrounding pixels having the first value and N2 (e.g., 5) second surrounding pixels having the second value (e.g., 0), wherein N, N1, and N2 are positive integers.

[0027] In one embodiment, among the surrounding pixels of the reference point pixel 311, the first surrounding pixels (ie, the pixels located in the range 311a) are arranged in a straight line, and the second surrounding pixels (ie, the pixels located in the range 311b) are arranged in a C shape.

[0028] In one embodiment, among the surrounding pixels of the reference point pixel 312, the first surrounding pixels (ie, the pixels located in the range 312a) are arranged in an L shape, and the second surrounding pixels (ie, the pixels located in the range 312b) are arranged in an L shape.

[0029] In one embodiment, among the surrounding pixels of the reference point pixel 313, the first surrounding pixels (ie, the pixels located in the range 313a) are arranged in an L shape, and the second surrounding pixels (ie, the pixels located in the range 313b) are arranged in an L shape.

[0030] In an embodiment of the present invention, since the reference point pixels 311~313 are individually unique in the left ventricle mask image 31, the processor 104 can examine each pixel in the left ventricle mask image 31 one by one, and define the three pixels that meet the above conditions (for example, including three first surrounding pixels with a first value and five second surrounding pixels with a second value among the eight surrounding pixels, and having the first value) as reference point pixels 311~313.

[0031] Then, in step S230, the processor 104 may estimate the left ventricular volume corresponding to the cardiac ultrasound image 30 based on the reference point pixels 311-313. In one embodiment, the processor 104 may estimate the distances between the reference point pixels 311-313, and accordingly find the first reference point pixel, the second reference point pixel, and the third reference point pixel corresponding to the apex, the first mitral valve (e.g., the left mitral valve), and the second mitral valve (e.g., the right mitral valve) in the reference point pixels 311-313. Then, the processor 104 may apply the Simpson formula based on the first reference point pixel, the second reference point pixel, and the third reference point pixel to estimate the left ventricular volume corresponding to the cardiac ultrasound image 30.

[0032] Please refer to Figure 4 , which is a schematic diagram of finding the first, second and third reference point pixels based on the distance between reference point pixels according to an embodiment of the present invention. Generally speaking, the distance between the left and right mitral valves should be smaller than the distance between the apex and any mitral valve. Therefore, the processor 104 can find the first, second and third reference point pixels corresponding to the apex, the first mitral valve and the second mitral valve respectively from the reference point pixels 311-313 based on this principle.

[0033] exist Figure 4 In the figure, there may be a first distance D1 between the reference point pixel 311 and the reference point pixel 312, a second distance D2 between the reference point pixel 311 and the reference point pixel 313, and a third distance D3 between the reference point pixel 312 and the reference point pixel 313.

[0034] exist Figure 4 In the scenario, in response to determining that the first distance D1 and the second distance D2 are both greater than the third distance D3 , the processor may define the reference point pixels 311 ˜ 313 as the first, second, and third reference point pixels, respectively.

[0035] In another embodiment, in response to determining that the second distance D2 and the third distance D3 are both greater than the first distance D1, the processor 104 may define the reference point pixel 313, the reference point pixel 311, and the reference point pixel 312 as the first, second, and third reference point pixels, respectively. In addition, in yet another embodiment, in response to determining that the first distance D1 and the third distance D3 are both greater than the second distance D2, the processor 103 may define the reference point pixel 312, the reference point pixel 311, and the reference point pixel 313 as the first, second, and third reference point pixels, respectively.

[0036] In addition, if the cardiac ultrasound image 30 is determined to be an apical view, then the one with the highest height among the three reference point pixels found should correspond to the apex. Figure 4In the embodiment, the processor 104 may directly define the reference point pixel 311 with the highest height as the first reference point pixel corresponding to the apex, and define the remaining reference point pixels 312 and 313 as the second and third reference point pixels corresponding to the mitral valve, respectively, but is not limited thereto.

[0037] Afterwards, the processor 104 may apply the Simpson's formula based on the first, second and third reference point pixels to estimate the left ventricular volume corresponding to the cardiac ultrasound image 30 , and the details thereof may be referred to the related prior art documents and will not be elaborated herein.

[0038] In addition, to improve the efficiency of finding the reference point pixels 311-313, the processor 104 may further FIG. 5A to FIG. 5C The mechanism shown is used to find the reference point pixels 311-313.

[0039] Please refer to Figure 5A , which is based on Figure 3 The figure shows a schematic diagram of finding the reference point pixel corresponding to the apex of the heart. As described above, if the cardiac ultrasound image 30 is determined to be an apex view, then the one with the highest height among the three found reference point pixels should correspond to the apex of the heart.

[0040] Based on this, starting from the highest pixel column in the left ventricle mask image 31, the processor 104 may scan down column by column to find a pixel that meets the above conditions (for example, including 3 first surrounding pixels with the first value and 5 second surrounding pixels with the second value among the 8 surrounding pixels, and having the first value). Figure 5A When a pixel meeting the above conditions is found, the processor 104 can directly define the pixel as the reference point pixel 311 corresponding to the apex of the heart and pause the scan.

[0041] Please refer to Figure 5B , which is based on Figure 5A The figure shows a schematic diagram of finding the reference point pixel corresponding to the left mitral valve. When the cardiac ultrasound image 30 is determined to be an apical view, the leftmost lower one of the three found reference point pixels should correspond to the left mitral valve.

[0042] Based on this, starting from the lowest pixel column in the left ventricle mask image 31, the processor 104 may scan from left to right column by column to find a pixel that meets the above conditions (for example, including 3 first surrounding pixels with the first value and 5 second surrounding pixels with the second value among the 8 surrounding pixels, and having the first value). Figure 5B When a pixel meeting the above conditions is found, the processor 104 can directly define the pixel as the reference point pixel 312 corresponding to the left mitral valve and suspend the scanning process.

[0043] Please refer to Figure 5C , which is based on Figure 5B The figure shows a schematic diagram of finding the reference point pixel corresponding to the right mitral valve. When the cardiac ultrasound image 30 is determined to be an apical view, the rightmost lower one of the three reference point pixels found should correspond to the right mitral valve.

[0044] Based on this, starting from the lowest pixel column in the left ventricle mask image 31, the processor 104 may scan from right to left column by column to find a pixel that meets the above conditions (for example, including 3 first surrounding pixels with the first value and 5 second surrounding pixels with the second value among the 8 surrounding pixels, and having the first value). Figure 5C In the process, when a pixel that meets the above conditions is found, the processor 104 may first determine whether this pixel has been defined as another reference point pixel (e.g., reference point pixel 312). If not, the processor 104 may directly define this pixel as the reference point pixel 313 corresponding to the right mitral valve, and suspend the scanning process. On the other hand, if this pixel has been defined as another reference point pixel (e.g., reference point pixel 312), the processor 104 may first ignore this pixel and continue to scan upwards to find another pixel that meets the above conditions. When another pixel that meets the above conditions is found, the processor 104 may directly define the other pixel as the reference point pixel 313 corresponding to the right mitral valve, and suspend the scanning process.

[0045] In other embodiments, the processor 104 may also use other methods to find the reference point pixels 311-313 in the left ventricle mask image 31, and is not limited to FIG. 5A to FIG. 5C The way of teaching.

[0046] As can be seen from the above, the method for estimating ventricular volume proposed by the present invention can obtain a left ventricular mask image corresponding to the left ventricular ultrasound, and then find 3 pixels that meet specific conditions (for example, including 3 first surrounding pixels with a first value and 5 second surrounding pixels with a second value among 8 surrounding pixels, and having the first value) as reference point pixels corresponding to the apex and the mitral valves on both sides. After that, the left ventricular volume can be estimated based on the multiple reference point pixels. In this way, the present invention can automatically estimate the left ventricular volume with better efficiency without manually marking the apex and the mitral valves on both sides.

[0047] In other embodiments, the present invention further proposes a method for assisting in assessing cardiac motion state, which can determine whether the heart is in an abnormal motion state based on the change in left ventricular volume. In an embodiment of the present invention, the processor 104 can access the modules and program codes recorded in the storage circuit 102 to implement the method for assisting in assessing cardiac motion state proposed by the present invention, and the details are described as follows.

[0048] Please refer to Figure 6 , which is a flowchart of a method for assisting in assessing cardiac motion status according to an embodiment of the present invention. The method of this embodiment can be performed by Figure 1 The electronic device 100 is executed as follows: Figure 1 Description of components shown Figure 6 Details of each step.

[0049] First, in step S610 , the processor 104 may obtain a plurality of consecutive cardiac ultrasound images corresponding to a heart (eg, the heart of a patient), and estimate a plurality of left ventricular volumes corresponding to the plurality of cardiac ultrasound images.

[0050] In one embodiment, the processor 104 may first obtain the above cardiac ultrasound images and determine whether each cardiac ultrasound image belongs to the apical view (e.g., A2C or A4C). In one embodiment, the processor 104 may determine whether each cardiac ultrasound image belongs to the apical view based on the technology described in the document "Guidelines for Performing a Comprehensive Transthoracic Echocardiographic Examination in Adults: Recommendations from the American Society of Echocardiography", so the relevant details can be referred to the above document and will not be further described here.

[0051] In response to determining that each cardiac ultrasound image belongs to the apical view, the processor 104 may extract a left ventricle mask image corresponding to the left ventricle of the heart from each cardiac ultrasound image, and estimate the left ventricle volume corresponding to the cardiac ultrasound image accordingly.

[0052] In one embodiment, the processor 104 may, for example, input each cardiac ultrasound image into the aforementioned machine learning model, wherein the machine learning model may output a corresponding left ventricle mask image in response to each cardiac ultrasound image.

[0053] In an embodiment of the present invention, for each left ventricle mask image, the processor 104 may be based on Figures 2 to 5C The corresponding left ventricular volume is estimated by the mechanism taught, so its details are not repeated here.

[0054] To facilitate the explanation of the concept of the present invention, the following will be supplemented with Fig. 7A To further explain, Fig. 7A is an application scenario diagram according to an embodiment of the present invention. Fig. 7A In the example, the continuous left ventricular volumes obtained in step S610 can be shown as Fig. 7AA graph 700 of left ventricular volume changes is shown.

[0055] Afterwards, in step S620 , the processor 104 may find a plurality of specific extreme values ​​711 ˜ 715 in the plurality of left ventricular volumes, and estimate a plurality of time differences T1 ˜ T4 between the plurality of specific extreme values ​​711 ˜ 715 accordingly.

[0056] In one embodiment, the processor 104 may, for example, use a plurality of specific left ventricular volumes corresponding to EDV in the above-mentioned left ventricular volumes as the plurality of specific extreme values, but is not limited thereto. By definition, each EDV should correspond to the maximum left ventricular volume in the heart rate cycle to which it belongs. Based on this, if the processor 104 determines that the i-th (where i is an integer) left ventricular volume in the above-mentioned left ventricular volumes is greater than the i-1th ventricular volume and the i+1th ventricular volume in the above-mentioned left ventricular volumes, the processor 104 may determine that the i-th ventricular volume should correspond to EDV, and further determine that the i-th left ventricular volume belongs to one of the above-mentioned specific extreme values.

[0057] exist Fig. 7A In this scenario, since the left ventricular volume change graph 700 can be understood to include 5 heart rate cycles, the processor 104 can find out 5 EDVs as specific extreme values ​​711-715 according to the above principle. Afterwards, the processor 104 can estimate the time differences T1-T4 between the specific extreme values ​​711-715.

[0058] Roughly speaking, assuming that the specific extreme values ​​found by the processor 104 include the 1st specific extreme value to the Kth specific extreme value (where K is an integer), the time difference between the j+1th specific extreme value and the jth specific extreme value can be defined as the jth time difference, where 1≤j≤K-1.

[0059] by Fig. 7A For example, the time difference T1 (which can be understood as the first time difference) is, for example, the time difference between the specific extreme value 711 (which can be understood as the first specific extreme value) and the specific extreme value 712 (which can be understood as the second specific extreme value). The time difference T2 (which can be understood as the second time difference) is, for example, the time difference between the specific extreme value 712 (which can be understood as the second specific extreme value) and the specific extreme value 713 (which can be understood as the third specific extreme value). The time difference T3 (which can be understood as the third time difference) is, for example, the time difference between the specific extreme value 713 (which can be understood as the third specific extreme value) and the specific extreme value 714 (which can be understood as the fourth specific extreme value). The time difference T4 (which can be understood as the fourth time difference) is, for example, the time difference between the specific extreme value 714 (which can be understood as the fourth specific extreme value) and the specific extreme value 715 (which can be understood as the fifth specific extreme value), but it is not limited thereto.

[0060] Afterwards, in step S630, the processor 104 may estimate the statistical characteristic values ​​of the multiple time differences T1-T4 (including but not limited to the average value of the time differences T1-T4) based on the multiple time differences T1-T4. In addition, the processor 104 may determine whether each time difference T1-T4 deviates from the above statistical characteristic to a preset threshold value. In different embodiments, the above preset threshold value may be set to any proportion value according to the needs of the designer, such as 5%, but is not limited thereto.

[0061] In step S640, in response to determining that at least one of the multiple time differences T1-T4 deviates from the statistical characteristic value by a preset threshold value, the processor 104 may determine that the heart is in an abnormal motion state (e.g., an arrhythmia state). On the other hand, in response to determining that none of the multiple time differences T1-T4 deviates from the statistical characteristic value by a preset threshold value, the processor 104 may determine that the heart is not in an abnormal motion state.

[0062] exist Fig. 7A In the example, assuming that the processor 104 determines that the time differences T1 to T4 do not deviate from the statistical characteristic value to reach the preset threshold value, the processor 104 can determine that the heart does not have an abnormal motion state such as arrhythmia.

[0063] Please refer to Figure 7B , which is based on Fig. 7A Another application scenario diagram is shown. In this embodiment, it is assumed that the processor 104 obtains the following according to the previous teachings: Figure 7B The left ventricular volume change diagram 700a is shown, and a plurality of specific extreme values ​​711a-715a corresponding to EDV and the corresponding time differences T1'-T4' are found therein.

[0064] exist Figure 7B In the example, assuming that the processor 104 determines that the time difference T2' in the time difference T1'-T4' deviates from the statistical characteristic value of the time difference T1'-T4' by a preset threshold value, the processor 104 may determine that the heart has an abnormal motion state (eg, an arrhythmia state), but is not limited thereto.

[0065] In an embodiment of the present invention, the processor 104 may provide the determination result of whether the heart is in an abnormal motion state to relevant medical personnel as a reference for diagnosis, but is not limited thereto.

[0066] In addition, although the left ventricular volume corresponding to EDV is used as the specific extreme value considered in the above embodiments, in other embodiments, the processor 104 may also use the left ventricular volume corresponding to ESV as the specific extreme value considered. By definition, each ESV should correspond to the smallest left ventricular volume in the heart rate cycle to which it belongs. Based on this, if the processor 104 determines that the i-th left ventricular volume among the above left ventricular volumes is smaller than the i-1-th ventricular volume and the i+1-th ventricular volume among the above left ventricular volumes, the processor 104 may determine that the i-th ventricular volume should correspond to ESV, and further determine that the i-th left ventricular volume belongs to one of the above specific extreme values.

[0067] Based on this, Figure 7B In the scenario of , the processor 104 may accordingly find out the left ventricular volume value corresponding to the ESV as the specific extreme values ​​711b-715b, and estimate the corresponding time differences T1"-T4" accordingly.

[0068] exist Figure 7B In the embodiment, assuming that the processor 104 determines that the time difference T1" in the time difference T1"~T4" deviates from the statistical characteristic value of the time difference T1"~T4" by reaching a preset threshold value, the processor 104 can determine that the heart has an abnormal movement state (for example, an arrhythmia state), and it can be used as a reference for the diagnosis of relevant medical personnel.

[0069] In some embodiments, if the relevant medical personnel is viewing the corresponding Figure 7B If the processor 104 determines that the heart system is misjudged as being in an abnormal motion state (i.e., the heart is not actually in an abnormal motion state) after viewing the cardiac ultrasound image, the relevant medical personnel may report this situation to the electronic device 100. In the embodiment of the present invention, since the misjudgment situation may be caused by the poor recognition ability of the machine learning model for the left ventricle image area, the processor 104 may retrain the machine learning model accordingly to reduce the probability of misjudgment in the future, but it is not limited to this.

[0070] In summary, the method for estimating ventricular volume proposed by the present invention can obtain a left ventricular mask image corresponding to the left ventricular ultrasound wave, and then find three pixels that meet specific conditions as reference point pixels corresponding to the apex and the mitral valves on both sides. After that, the left ventricular volume can be estimated based on the multiple reference point pixels. In this way, the present invention can automatically estimate the left ventricular volume with better efficiency without manually marking the apex and the mitral valves on both sides.

[0071] In addition, the method for assisting in assessing the cardiac motion state proposed by the present invention can find multiple specific extreme values ​​corresponding to EDV (or ESV) in multiple left ventricular volumes corresponding to multiple consecutive cardiac ultrasound images, and judge whether the heart has abnormal motion states such as arrhythmia based on the time difference between these specific extreme values. In this way, relevant medical personnel can more easily understand the condition of the heart, thereby reducing the probability of making wrong assessments (such as calculating wrong ejection fraction, etc.).

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for estimating ventricular volume, suitable for an electronic device, comprising: Obtaining a left ventricle mask image corresponding to the cardiac ultrasound image, wherein the left ventricle mask image is a binary image; Find three reference point pixels in the left ventricle mask image, wherein each of the reference point pixels has a first value, each of the reference point pixels is surrounded by N surrounding pixels, and the plurality of surrounding pixels of each of the reference point pixels include N1 first surrounding pixels having the first value and N2 second surrounding pixels having a second value, wherein N, N1 and N2 are positive integers, wherein N1 is 3, N2 is 5, the first value is 255, and the second value is 0, wherein the plurality of reference point pixels include a first reference point pixel, a second reference point pixel and a third reference point pixel, and among the plurality of surrounding pixels of the first reference point pixel, the plurality of first surrounding pixels are arranged in a straight line, and the plurality of second surrounding pixels are arranged in a C shape, and among the plurality of surrounding pixels of the second reference point pixel and the third reference point pixel, the plurality of first surrounding pixels are arranged in an L shape, and the plurality of second surrounding pixels are arranged in an L shape; The method of estimating the left ventricular volume corresponding to the cardiac ultrasound image based on the plurality of reference point pixels comprises: estimating distances between the plurality of reference point pixels, and finding out, from the plurality of reference point pixels, a first reference point pixel, a second reference point pixel, and a third reference point pixel corresponding to the apex, the first mitral valve, and the second mitral valve, respectively; The Simpson's formula is applied based on the first reference point pixel, the second reference point pixel, and the third reference point pixel to estimate the left ventricular volume corresponding to the cardiac ultrasound image.

2. The method according to claim 1, wherein the plurality of reference point pixels include a first pixel, a second pixel, and a third pixel, there is a first distance between the first pixel and the second pixel, there is a second distance between the first pixel and the third pixel, there is a third distance between the second pixel and the third pixel, and the distances between the plurality of reference point pixels are estimated, and the steps of finding the first reference point pixel, the second reference point pixel, and the third reference point pixel corresponding to the apex, the first mitral valve, and the second mitral valve, respectively, from the plurality of reference points comprises: In response to determining that the first distance and the second distance are both greater than the third distance, defining the first pixel, the second pixel, and the third pixel as the first reference point pixel, the second reference point pixel, and the third reference point pixel, respectively; In response to determining that the second distance and the third distance are both greater than the first distance, defining the third pixel, the first pixel, and the second pixel as the first reference point pixel, the second reference point pixel, and the third reference point pixel, respectively; In response to determining that both the first distance and the third distance are greater than the second distance, the second pixel, the first pixel, and the third pixel are defined as the first reference point pixel, the second reference point pixel, and the third reference point pixel, respectively.

3. A method for estimating ventricular volume, suitable for an electronic device, comprising: Obtaining a left ventricle mask image corresponding to the cardiac ultrasound image, wherein the left ventricle mask image is a binary image; Find three reference point pixels in the left ventricle mask image, wherein each of the reference point pixels has a first value, each of the reference point pixels is surrounded by N surrounding pixels, and the plurality of surrounding pixels of each of the reference point pixels include N1 first surrounding pixels having the first value and N2 second surrounding pixels having a second value, wherein N, N1 and N2 are positive integers, wherein N1 is 3, N2 is 5, the first value is 255, and the second value is 0, wherein the plurality of reference point pixels include a first reference point pixel, a second reference point pixel and a third reference point pixel, and among the plurality of surrounding pixels of the first reference point pixel, the plurality of first surrounding pixels are arranged in a straight line, and the plurality of second surrounding pixels are arranged in a C shape, and among the plurality of surrounding pixels of the second reference point pixel and the third reference point pixel, the plurality of first surrounding pixels are arranged in an L shape, and the plurality of second surrounding pixels are arranged in an L shape; The method of estimating the left ventricular volume corresponding to the cardiac ultrasound image based on the plurality of reference point pixels comprises: In response to determining that the cardiac ultrasound image is an apical view, defining one of the plurality of reference point pixels with the highest height as a first reference point pixel corresponding to the apex, and defining the other two of the plurality of reference point pixels as a second reference point pixel and a third reference point pixel corresponding to a first mitral valve and a second mitral valve, respectively; The Simpson's formula is applied based on the first reference point pixel, the second reference point pixel, and the third reference point pixel to estimate the left ventricular volume corresponding to the cardiac ultrasound image.

Images