Ultrasonic image correction method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present invention provide an ultrasonic image correction method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring a reference ultrasonic image sequence collected at at least one reference position in a blood vessel, a reference ultrasonic image corresponding to each reference position including a reference ultrasonic image collected within at least one cardiac cycle, and each cardiac cycle comprising a reference cardiac state and at least one non-reference cardiac state; for each non-reference cardiac state, on the basis of the reference ultrasonic image sequence, calculating a change coefficient of blood vessel morphology of the blood vessel in the non-reference cardiac state relative to blood vessel morphology in the reference cardiac state to obtain a blood vessel morphology change coefficient; acquiring a target ultrasonic image sequence; and on the basis of the blood vessel morphology change coefficient, transforming blood vessel morphology in a target ultrasonic image in the target ultrasonic image sequence. The solution can reduce cardiac motion artifacts.

Description

Ultrasonic image correction method and device, electronic device and storage medium Technical Field

[0001] The present invention relates to the technical field of ultrasonic image processing, and in particular to an ultrasonic image correction method, an ultrasonic image correction device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Intravascular ultrasound (IVUS) imaging is a catheter-based imaging technique that provides real-time cross-sectional images of blood vessels. During IVUS imaging, the alternating dilation and contraction of the vascular lumen during the cardiac cycle, as well as the pulsatile blood flow within the lumen, cause the transducer located at the catheter tip of the ultrasound device to displace longitudinally along the long axis of the lumen, and the angle of the catheter relative to the lumen also changes. Furthermore, the vascular diameter exhibits characteristic variations during the cardiac cycle. These factors combine to produce periodic variations in the grayscale characteristics of a series of cross-sectional images (i.e., ultrasound images) acquired during continuous catheter withdrawal. This phenomenon is known as motion artifact, which is caused by the cardiac cycle. Motion artifact manifests as a jagged edge of the vessel wall in long-axis images and as a misalignment of the lumen cross-section between adjacent frames in cross-sectional images. Motion artifact is a major factor affecting the visual quality of IVUS images, the accuracy of vascular morphological parameter measurements, and the accuracy of three-dimensional vascular reconstruction.

[0003] Therefore, an ultrasonic image correction solution is urgently needed to solve the above technical problems.

[0004] Summary of the Invention

[0005] The present invention is proposed in view of the above problems. The present invention provides an ultrasonic image correction method, an ultrasonic image correction device, an electronic device, and a computer-readable storage medium.

[0006] According to one aspect of the present invention, a method for correcting an ultrasonic image is provided, comprising: acquiring a sequence of reference ultrasonic images acquired by an ultrasonic device at at least one reference position within a blood vessel, wherein the reference ultrasonic images corresponding to each reference position in the sequence of reference ultrasonic images include reference ultrasonic images acquired by the ultrasonic device for the reference position within at least one cardiac cycle, wherein each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state; for each of the at least one non-reference cardiac state, calculating, based on the reference ultrasonic image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state, and obtaining a vascular morphology variation coefficient corresponding to the non-reference cardiac state; acquiring a sequence of target ultrasonic images acquired by the ultrasonic device during a retraction process; and for each of the at least one non-reference cardiac state, transforming, based on the vascular morphology variation coefficient corresponding to the non-reference cardiac state, the vascular morphology in the target ultrasonic image corresponding to the non-reference cardiac state in the target ultrasonic image sequence, so as to perform motion artifact correction on the target ultrasonic image sequence.

[0007] Exemplarily, the reference ultrasound image sequence includes at least one group of reference ultrasound images, each group of reference ultrasound images corresponds to a unique cardiac cycle and a unique reference position; wherein, based on the reference ultrasound image sequence, a vascular morphology variation coefficient of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state is calculated to obtain the vascular morphology variation coefficient corresponding to the non-reference cardiac state, including: for each group of reference ultrasound images in the reference ultrasound image sequence, a variation coefficient of the vascular morphology of the blood vessel in the first reference ultrasound image relative to the vascular morphology of the blood vessel in the second reference ultrasound image is calculated to obtain the sub-vascular morphology corresponding to the group of reference ultrasound images The variation coefficient is as follows: the first reference ultrasound image is a reference ultrasound image corresponding to the non-reference cardiac state in the group of reference ultrasound images, and the second reference ultrasound image is a reference ultrasound image corresponding to the reference cardiac state in the group of reference ultrasound images; when there are multiple groups of at least one group of reference ultrasound images, the sub-vessel morphology variation coefficients corresponding to the at least one group of reference ultrasound images are averaged to obtain the vessel morphology variation coefficient corresponding to the non-reference cardiac state; wherein, when there are only one group of at least one group of reference ultrasound images, the vessel morphology variation coefficient corresponding to the non-reference cardiac state is the sub-vessel morphology variation coefficient corresponding to the group of reference ultrasound images.

[0008] Exemplarily, the vascular morphology variation coefficient includes a rotational and translational variation coefficient of the blood vessel, wherein calculating the variation coefficient of the vascular morphology of the blood vessel in the first reference ultrasonic image relative to the vascular morphology of the blood vessel in the second reference ultrasonic image to obtain the sub-vascular morphology variation coefficient corresponding to the group of reference ultrasonic images includes: detecting feature points on the blood vessels respectively contained in the first reference ultrasonic image and the second reference ultrasonic image; matching the feature points on the blood vessels respectively contained in the first reference ultrasonic image and the second reference ultrasonic image; and calculating the rotational and translational variation coefficient of the blood vessel in the first reference ultrasonic image relative to the blood vessel in the second reference ultrasonic image based on the mutually matched feature points as the sub-vascular morphology variation coefficient corresponding to the group of reference ultrasonic images.

[0009] Exemplarily, the vascular morphology variation coefficient includes a rotational and translational variation coefficient of the blood vessel, wherein the variation coefficient of the vascular morphology of the blood vessel in the first baseline ultrasound image relative to the vascular morphology of the blood vessel in the second baseline ultrasound image is calculated to obtain the sub-vascular morphology variation coefficient corresponding to the group of baseline ultrasound images, including: detecting the lumen contours on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; determining the position of the contour center of gravity of the lumen contours on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; and calculating the rotational and translational variation coefficient of the blood vessel in the first baseline ultrasound image relative to the blood vessel in the second baseline ultrasound image based on the positions of the contour center of gravity corresponding to each of the first baseline ultrasound image and the second baseline ultrasound image, as the sub-vascular morphology variation coefficient corresponding to the group of baseline ultrasound images.

[0010] Exemplarily, the blood vessel morphology variation coefficient includes one or more of the following: a diameter variation coefficient of the lumen diameter of the blood vessel and an area variation coefficient of the lumen area of ​​the blood vessel.

[0011] Exemplarily, the number of cardiac cycles in at least one cardiac cycle is multiple and / or the number of reference positions in at least one reference position is multiple.

[0012] Exemplarily, for each of at least one non-baseline cardiac state, based on a baseline ultrasound image sequence, a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state is calculated to obtain a vascular morphology change coefficient corresponding to the non-baseline cardiac state, including: for each of at least one non-baseline cardiac state, based on a baseline ultrasound image corresponding to the non-baseline cardiac state and a baseline ultrasound image corresponding to the baseline cardiac state in a baseline ultrasound image sequence, a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state is calculated to obtain a vascular morphology change coefficient corresponding to the non-baseline cardiac state.

[0013] Exemplarily, for each non-baseline cardiac state of at least one non-baseline cardiac state, before calculating, based on a baseline ultrasound image sequence, a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the coefficient of change of the vascular morphology corresponding to the non-baseline cardiac state, the method further includes: acquiring an electrocardiogram signal acquired synchronously with the baseline ultrasound image sequence; and determining, based on the electrocardiogram signal, a baseline ultrasound image in the baseline ultrasound image sequence corresponding to each of the multiple cardiac states.

[0014] Exemplarily, for each of at least one non-baseline cardiac state, the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence is transformed based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state to perform motion artifact correction on the target ultrasound image sequence, including: for each of at least one non-baseline cardiac state, based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state, determining an inverse transformation coefficient; and transforming the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence based on the inverse transformation coefficient to perform motion artifact correction on the target ultrasound image sequence.

[0015] Exemplarily, for each non-baseline cardiac state of at least one non-baseline cardiac state, before calculating, based on a baseline ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state, the method further includes: determining the baseline cardiac state based on user input information.

[0016] Exemplarily, the at least one reference position includes an examination start point within the blood vessel and / or an examination end point within the blood vessel.

[0017] According to another aspect of the present invention, an ultrasonic image correction device is also provided, comprising: a first acquisition module for acquiring a reference ultrasonic image sequence acquired by an ultrasonic device at at least one reference position in a blood vessel, wherein the reference ultrasonic image corresponding to each reference position in the reference ultrasonic image sequence includes a reference ultrasonic image acquired by the ultrasonic device for the reference position within at least one cardiac cycle, wherein each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state; and a calculation module for calculating, for each non-reference cardiac state in the at least one non-reference cardiac state, a reference ultrasonic image corresponding to the non-reference cardiac state in the reference ultrasonic image sequence. and a baseline ultrasound image corresponding to a baseline cardiac state, calculating a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the vascular morphology change coefficient corresponding to the non-baseline cardiac state; a second acquisition module, for acquiring a target ultrasound image sequence acquired by the ultrasound device during the retraction process; a correction module, for transforming the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence for each non-baseline cardiac state in at least one non-baseline cardiac state based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state, so as to perform motion artifact correction on the target ultrasound image sequence.

[0018] According to another aspect of the present invention, an electronic device is provided, including a processor and a memory, wherein a computer program / instruction is stored in the memory, and the processor executes the computer program / instruction to implement the above-mentioned ultrasonic image correction method.

[0019] According to yet another aspect of the present invention, a computer-readable storage medium is provided, storing a computer program / instruction, which implements the above-mentioned ultrasound image correction method when executed by a processor.

[0020] According to the ultrasonic image correction method, ultrasonic image correction device, electronic device, and computer-readable storage medium of embodiments of the present invention, for each of at least one non-baseline cardiac state, a coefficient of variation of the vascular morphology in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state is calculated based on a baseline ultrasonic image sequence to obtain the vascular morphology variation coefficient corresponding to the non-baseline cardiac state. Subsequently, based on the vascular morphology variation coefficient corresponding to the non-baseline cardiac state, the vascular morphology in a target ultrasonic image sequence corresponding to the non-baseline cardiac state is transformed to normalize the vascular morphology in the non-baseline cardiac state to that in the baseline cardiac state, thereby performing motion artifact correction on the target ultrasonic image sequence. This scheme can reduce imaging errors caused by cardiac motion during intravascular ultrasound imaging and effectively reduce cardiac motion artifacts, such as "zigzag" artifacts formed in the longitudinal direction of the intravascular ultrasound image. This optimizes the visual quality of the intravascular ultrasound image and helps improve the accuracy of subsequent processing based on the intravascular ultrasound image, such as three-dimensional vascular reconstruction. In addition, the target ultrasound image sequence can be acquired during the pullback process and then corrected using the ultrasound image correction method, thereby avoiding affecting the efficiency of normal examination.

[0021] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features, and advantages of the present invention will become more apparent through a more detailed description of the embodiments of the present invention with reference to the accompanying drawings. The accompanying drawings are provided to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and are not intended to limit the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

[0023] FIG1 shows a schematic flow chart of an ultrasonic image correction method according to an embodiment of the present invention;

[0024] FIG2 shows a curve showing changes in lumen area of ​​a blood vessel along a cardiac cycle according to an embodiment of the present invention;

[0025] FIG3 shows a schematic block diagram of an ultrasonic image correction device according to an embodiment of the present invention; and

[0026] FIG4 shows a schematic block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the present invention more apparent, exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present invention.

[0028] To address the above technical issues, the present invention provides an ultrasonic image correction method. FIG1 illustrates a schematic flow chart of an ultrasonic image correction method 100 according to one embodiment of the present invention. As shown in FIG1 , ultrasonic image correction method 100 includes steps S110, S120, S130, and S140.

[0029] Step S110, obtaining a reference ultrasound image sequence acquired by an ultrasound device at at least one reference position in a blood vessel, wherein the reference ultrasound image corresponding to each reference position in the reference ultrasound image sequence includes a reference ultrasound image acquired by the ultrasound device for the reference position within at least one cardiac cycle, and each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state.

[0030] For example, an IVUS ultrasound device can be used to capture ultrasound images within a blood vessel, such as the coronary arteries and veins of the heart. The ultrasound transducer in the ultrasound device is positioned at the tip of a catheter. During the ultrasound image acquisition process, the catheter in the ultrasound device can be positioned at any location within the blood vessel to capture ultrasound images at that location. In an embodiment of the present invention, the catheter of the ultrasound device can be placed at a reference location within the blood vessel, and then the catheter is controlled to remain stationary to capture ultrasound images over at least one complete cardiac cycle. The reference location can be any location within the blood vessel, such as the starting point (distal end of the vessel examination site), the end point (proximal end of the vessel examination site), or any intermediate location (a location between the distal and proximal ends of the vessel examination site) during an ultrasound examination. There can be one or more reference locations. For each reference location, an ultrasound image (referred to herein as a reference ultrasound image) is captured at that location over at least one cardiac cycle while the catheter remains stationary, obtaining a series of reference ultrasound images corresponding to that reference location. For ease of description, the series of reference ultrasound images corresponding to each reference location can be referred to as a reference ultrasound image subsequence. A reference ultrasound image sequence can include at least one reference ultrasound image subsequence corresponding to each reference location. The number of cardiac cycles corresponding to any two different reference positions may be the same or different. It should be noted that the proximal end may be the end close to the operator, and the distal end may be the end far from the operator.

[0031] Each cardiac cycle within at least one cardiac cycle can include multiple different cardiac states. Each cardiac state corresponds to a specific moment or time period within the cardiac cycle, such as the end-diastole or early-systole of a blood vessel. Within a set of reference ultrasound images corresponding to the same reference location and the same cardiac cycle, each frame of the reference ultrasound image can correspond to a cardiac state. That is, there are as many reference ultrasound image frames as there are cardiac states in a cardiac cycle. In other words, the cardiac cycle is divided into as many cardiac states as there are frames acquired within the cardiac cycle. In some cases, multiple reference ultrasound image frames can correspond to a single cardiac state. In one embodiment, a cardiac cycle can include multiple wavebands, such as the P wave, Q wave, R wave, S wave, and T wave, each of which can correspond to smaller wavebands, such as a start and end point. Exemplarily, each cardiac state within a cardiac cycle can be (or correspond to) any moment within any waveband within the cardiac cycle, such as the end of the P wave or the start of the Q wave. In this case, reference ultrasound images can be collected separately for several bands that are considered as cardiac states within the cardiac cycle or for specific moments within several bands that are considered as cardiac states. It is more desirable that the duration of each cardiac cycle can be divided evenly into the time interval between adjacent frames, so that each cardiac state can be matched more accurately with each frame. However, even if the duration of each cardiac cycle cannot be divided evenly into the time interval between adjacent frames, it will not have much impact on the matching relationship between cardiac states and frames. For example, assuming that a cardiac cycle is 0.8 seconds, and a cardiac cycle is set to contain 10 cardiac states, then a frame can be collected every 0.08 seconds (the frames collected at the beginning or end can be excluded from the current cardiac cycle), or a frame can be collected every 0.075 seconds, etc.

[0032] For each reference position, the reference ultrasound image subsequence corresponding to the reference position may include multiple frames of reference ultrasound images. For example, for any reference position X, a 100-frame ultrasound examination video (i.e., a reference ultrasound image subsequence) may be acquired, the video containing 100 reference ultrasound images, and the 100 reference ultrasound images are sorted according to the frame acquisition order of the ultrasound video. These 100 reference ultrasound images may serve as the reference ultrasound image subsequence corresponding to the current reference position. For example, the sequence number of the first frame of the reference ultrasound image may be 001, the sequence number of the second frame of the reference ultrasound image may be 002, and so on, the sequence number of the 100th frame of the reference ultrasound image may be 100. The number of reference ultrasound images contained in the reference ultrasound image subsequences corresponding to any two different reference positions may be the same or different. For example, if reference ultrasound images within 10 cardiac cycles are collected at the reference position X, and the number of cardiac states contained in each cardiac cycle is equal to 10, then in the above 100 frames of reference ultrasound images, each cardiac state can correspond to one frame of reference ultrasound image, and one cardiac cycle contains 10 reference ultrasound images.

[0033] The multiple cardiac states may include a baseline cardiac state and at least one non-baseline cardiac state. The baseline cardiac state may be any one of the multiple cardiac states and may be set as needed, and the present invention is not limited thereto. For example, the baseline cardiac state may be a T wave. Non-baseline cardiac states are cardiac states other than the baseline cardiac state during the cardiac cycle. In the embodiment described above where each cardiac cycle includes 10 cardiac states, the number of non-baseline cardiac states is equal to 9.

[0034] Step S120, for each non-baseline cardiac state of at least one non-baseline cardiac state, based on the baseline ultrasound image sequence, calculate the change coefficient of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtain the vascular morphology change coefficient corresponding to the non-baseline cardiac state.

[0035] For example, the vascular morphology variation coefficient corresponding to a non-baseline cardiac state can be calculated based on a sequence of baseline ultrasound images within the same cardiac cycle. For example, the variation coefficient of the vascular morphology of a blood vessel in a non-baseline cardiac state relative to the vascular morphology in a baseline cardiac state within the same cardiac cycle is calculated to obtain the vascular morphology variation coefficient corresponding to the non-baseline cardiac state. Determining the vascular morphology variation coefficient based on ultrasound images within the same cardiac cycle can narrow the comparison range, avoid fluctuation errors between different cardiac cycles, and improve the accuracy of the vascular morphology variation coefficient. In other embodiments, the vascular morphology variation coefficient corresponding to a non-baseline cardiac state can also be calculated based on a sequence of baseline ultrasound images within different cardiac cycles. The specific implementation method can refer to the implementation method within the same cardiac cycle and will not be described in detail. This method calculates the vascular morphology variation coefficient corresponding to the non-baseline cardiac state without requiring multiple acquisitions of ultrasound images within the baseline cardiac state, which can shorten measurement and calculation time and improve overall efficiency.

[0036] For example, assume that reference ultrasound images are acquired within a cardiac cycle at a certain reference position to obtain a reference ultrasound image sequence. This reference ultrasound image sequence may include 10 reference ultrasound images, namely, reference ultrasound images 001 to 010. Furthermore, assume that the cardiac state corresponding to reference ultrasound image 005 is the reference cardiac state, and the cardiac states corresponding to the other nine reference ultrasound images are non-reference cardiac states. For each of the at least one non-reference cardiac state, a variation coefficient of the vascular morphology in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state may be calculated based on the reference ultrasound image corresponding to the non-reference cardiac state (e.g., reference ultrasound image 001) and reference ultrasound image 005 corresponding to the reference cardiac state in the reference ultrasound image sequence, thereby obtaining a vascular morphology variation coefficient corresponding to the non-reference cardiac state. In this way, nine vascular morphology variation coefficients may be determined for each of the nine non-reference cardiac states. When baseline ultrasound images are acquired over multiple cardiac cycles for multiple reference positions and / or for at least one of all reference positions, multiple sub-vessel morphological variation coefficients corresponding to each non-reference cardiac state can be calculated based on each set of baseline ultrasound images (corresponding to a unique reference position and a unique cardiac cycle). For example, if there are three sets of baseline ultrasound images, then for each non-reference cardiac state, there are also three corresponding sub-vessel morphological variation coefficients. The sub-vessel morphological variation coefficients corresponding to each non-reference cardiac state can then be averaged to obtain the vessel morphological variation coefficient corresponding to each non-reference cardiac state. The vessel morphological variation coefficient can be used to characterize the morphological variation of a vessel in a non-reference cardiac state relative to the baseline cardiac morphology. Exemplarily, the vessel morphological variation coefficient may include one or more of the following: a diameter variation coefficient of the vessel's lumen diameter, an area variation coefficient of the vessel's lumen area, and a rotational-translational variation coefficient of the vessel. For example, if the vascular morphology change coefficient includes the area change coefficient of the lumen area, that is, the vascular morphology change includes the change in the lumen area, then, for example, the ratio between the lumen area of ​​the blood vessel in the above-mentioned reference ultrasound image 001 and the lumen area of ​​the blood vessel in the reference ultrasound image 005 can be calculated as the change coefficient of the vascular morphology of the blood vessel in the non-reference cardiac state corresponding to the reference ultrasound image 001 relative to the vascular morphology in the reference cardiac state corresponding to the reference ultrasound image 005.

[0037] In one embodiment, a baseline cardiac state may be determined based on user input or other information before step S120, and then a vascular morphology variation coefficient corresponding to each non-baseline cardiac state may be determined in step S120. In step S140, vascular morphology transformation may be performed on target ultrasound images corresponding to each of the non-baseline cardiac states based on the vascular morphology variation coefficients under the various non-baseline cardiac states, thereby achieving motion artifact correction.

[0038] Step S130 : acquiring a target ultrasound image sequence acquired by the ultrasound device during the retraction process.

[0039] Exemplarily, the ultrasound device can first be sent to the distal end of the inspection site in the blood vessel (i.e., the inspection starting point), and then retracted by a stepper motor or manual operation. This retraction process can be, for example, a retraction process in a normal intravascular ultrasound examination. During the retraction process, an ultrasound examination video stacked by IVUS cross-sectional images can be obtained. The ultrasound examination video may include multiple frames, each frame may correspond to an ultrasound image, and then multiple frames of ultrasound images may be obtained based on the obtained ultrasound examination video as target ultrasound images. The ultrasound examination video can be regarded as a target ultrasound image sequence. Therefore, the target ultrasound image sequence may include multiple frames, each frame may correspond to a target ultrasound image.

[0040] For example, a processor in an apparatus for implementing the ultrasound image correction method 100 may acquire a target ultrasound image sequence acquired by the ultrasound device during a pullback process.

[0041] Step S140, for each non-baseline cardiac state of at least one non-baseline cardiac state, based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state, transform the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence to perform motion artifact correction on the target ultrasound image sequence.

[0042] Exemplarily, based on the vascular morphology variation coefficients of blood vessels in a non-baseline cardiac state, the vascular shapes in target ultrasound images corresponding to the non-baseline cardiac state in the target ultrasound image sequence can be transformed, such that the vascular morphology in the non-baseline cardiac state approaches that in the baseline cardiac state, or in other words, the vascular morphology in the non-baseline cardiac state is as consistent as possible with that in the baseline cardiac state. This allows the vascular morphology in each cardiac state to be normalized to that in the baseline cardiac state, thereby correcting motion artifacts in the target ultrasound image sequence. Exemplarily, when transforming the vascular morphology, the transformation can be performed according to inverse transformation coefficients, which can be determined based on the vascular morphology variation coefficients. Subsequently, the vascular morphology of the blood vessels in the target ultrasound images corresponding to the non-baseline cardiac state in the target ultrasound image sequence can be transformed according to the inverse transformation coefficients (which can also be understood as an inverse transformation from the non-baseline cardiac state to the baseline cardiac state).

[0043] According to an embodiment of the present invention, for each of at least one non-baseline cardiac state, a variation coefficient of the vascular morphology in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state is calculated based on a baseline ultrasonic image corresponding to the non-baseline cardiac state and a baseline ultrasonic image corresponding to the baseline cardiac state in a baseline ultrasonic image sequence, thereby obtaining a vascular morphology variation coefficient corresponding to the non-baseline cardiac state. Subsequently, based on the vascular morphology variation coefficient corresponding to the non-baseline cardiac state, the vascular morphology in a target ultrasonic image sequence corresponding to the non-baseline cardiac state is transformed to normalize the vascular morphology in the non-baseline cardiac state to that in the baseline cardiac state, thereby performing motion artifact correction on the target ultrasonic image sequence. This approach can reduce imaging errors caused by cardiac motion during intravascular ultrasound imaging and effectively reduce cardiac motion artifacts, such as "zigzag" artifacts formed in the longitudinal direction of the intravascular ultrasound image. This can optimize the visual quality of the intravascular ultrasound image and help improve the accuracy of subsequent processing based on the intravascular ultrasound image, such as three-dimensional vascular reconstruction. In addition, the target ultrasound image sequence can be acquired during the pullback process and then corrected using the ultrasound image correction method, thereby avoiding affecting the efficiency of normal examination.

[0044] The blood vessels included in the reference ultrasound image sequence and the blood vessels included in the target ultrasound image sequence can be different blood vessels of the same subject, the same blood vessel of the same subject, or the same blood vessel of different subjects. Furthermore, it should be noted that the execution order of the steps shown in FIG1 is merely an example, and the present invention is not limited to the order shown in FIG1 . For example, step S110 can be executed before, after, or simultaneously with step S130, and step S120 can be executed before, after, or simultaneously with step S130.

[0045] Illustratively, the blood vessel morphology variation coefficient may include one or more of the following: a diameter variation coefficient of the lumen diameter of the blood vessel, an area variation coefficient of the lumen area of ​​the blood vessel, and a rotational translation variation coefficient of the blood vessel.

[0046] In one embodiment, the lumen diameter of a blood vessel can be represented by the shortest lumen diameter across the center of the lumen or by the longest lumen diameter across the center of the lumen. The diameter variation coefficient represents the change in the size of the lumen diameter. The lumen area of ​​a blood vessel can be represented by the area surrounded by the innermost boundary of the lumen (blood vessel, thrombus or tissue). The area variation coefficient represents the change in the size of the lumen area. The rotational translation variation coefficient of a blood vessel can be obtained by calculating the rotation angle and translation orientation of the center of mass, center of gravity or characteristic points on the lumen of the blood vessel.

[0047] According to the above technical solution, the blood vessel morphology change coefficient is obtained through the diameter change coefficient of the blood vessel lumen diameter and / or the area change coefficient of the lumen area and / or the rotation and translation change coefficient. This can determine the morphology change of the blood vessel more simply and quickly with less calculation.

[0048] Exemplarily, the reference ultrasound image sequence may include at least one set of reference ultrasound images, each set of reference ultrasound images corresponds to a unique cardiac cycle and a unique reference position, and each set of reference ultrasound images may include at least two frames of reference ultrasound images. Exemplarily, calculating, based on a sequence of reference ultrasound images, a vascular morphology variation coefficient of a blood vessel in a non-reference cardiac state relative to the vascular morphology in a reference cardiac state to obtain the vascular morphology variation coefficient corresponding to the non-reference cardiac state may include: for each set of reference ultrasound images in the sequence of reference ultrasound images, calculating a variation coefficient of the vascular morphology of a blood vessel in a first reference ultrasound image relative to the vascular morphology of a blood vessel in a second reference ultrasound image to obtain a sub-vessel morphology variation coefficient corresponding to the set of reference ultrasound images, wherein the first reference ultrasound image is a reference ultrasound image in the set of reference ultrasound images corresponding to the non-reference cardiac state, and the second reference ultrasound image is a reference ultrasound image in the set of reference ultrasound images corresponding to the reference cardiac state; when there are multiple sets of at least one set of reference ultrasound images, averaging the sub-vessel morphology variation coefficients corresponding to the at least one set of reference ultrasound images (averaging may also be replaced by other methods such as weighted summing) to obtain the vascular morphology variation coefficient corresponding to the non-reference cardiac state; wherein, when there is only one set of at least one reference ultrasound image, the vascular morphology variation coefficient corresponding to the non-reference cardiac state is the sub-vessel morphology variation coefficient corresponding to the set of reference ultrasound images.

[0049] In one embodiment, the reference ultrasound image sequence may include one or more groups of reference ultrasound images. Each group of reference ultrasound images corresponds to a unique cardiac cycle and a unique reference position. For example, assuming that the number of reference positions is one, and the cardiac cycles corresponding to the reference position are N, where N≥2, the reference ultrasound image sequence may include N groups of reference ultrasound images. For another example, assuming that the number of reference positions is M, where M≥2, and each reference position corresponds to 1 cardiac cycle, the reference ultrasound image sequence may include M groups of reference ultrasound images. For another example, assuming that the number of reference positions is M, and each reference position corresponds to N cardiac cycles, where M≥2 and N≥2, the reference ultrasound image sequence may include M×N groups of reference ultrasound images. Each group of reference ultrasound images may include at least two frames of reference ultrasound images, namely, a first reference ultrasound image corresponding one-to-one to each non-reference cardiac state and a second reference ultrasound image corresponding to the reference cardiac state.

[0050] Step S120 may include the following operations: for each set of reference ultrasound images in the reference ultrasound image sequence, a variation coefficient of the vascular morphology in each first reference ultrasound image in the set of reference ultrasound images relative to the vascular morphology in the second reference ultrasound image may be calculated. For example, if the vascular morphology variation coefficient of a vessel is calculated based on the vessel's lumen diameter, then for each non-reference cardiac state, the ratio between the lumen diameter of the vessel in the first reference ultrasound image corresponding to the non-reference cardiac state and the lumen diameter of the vessel in the second reference ultrasound image in the set of reference ultrasound images may be calculated as the sub-vessel morphology variation coefficient corresponding to the non-reference cardiac state. If the vascular morphology variation coefficient of a vessel is calculated based on the vessel's lumen area or other parameters, the above-described method for calculating the sub-vessel morphology variation coefficient based on lumen diameter may be used, and for the sake of brevity, this method will not be further described here. If there are multiple sets of at least one reference ultrasound image, for example, three sets of reference ultrasound images, the sub-vessel morphology variation coefficients corresponding to the three sets of reference ultrasound images may be averaged to obtain the vascular morphology variation coefficient corresponding to the non-reference cardiac state. It is understood that if the number of reference ultrasound images is one group, the sub-vessel morphology variation coefficients corresponding to the group of reference ultrasound images can be directly used as the vessel morphology variation coefficients. For each non-reference cardiac state, the corresponding vessel morphology variation coefficient can be determined using the above method.

[0051] Figure 2 shows a curve showing the change in lumen area of ​​a blood vessel over the cardiac cycle according to one embodiment of the present invention. The abscissa of Figure 2 represents the frame number (i.e., the frame sequence number). In the embodiment shown in Figure 2, reference ultrasound images are acquired at three reference locations within the blood vessel, with 90 consecutive frames of reference ultrasound images acquired at each reference location. Curves A, B, and C respectively represent the relationship between the lumen area of ​​the blood vessel in the ultrasound images acquired at the three reference locations and the change in the cardiac cycle. An asterisk (*) indicates that the current location is the end of the T wave, and a plus sign (+) indicates that the current location is the beginning of the QRS complex. The interval between two asterisks (*) represents one cardiac cycle, or the interval between two plus signs (+) represents one cardiac cycle. Within a complete cardiac cycle, the corresponding electrocardiogram (ECG) signal may include a P wave, a QRS wave, and a T wave. The P wave represents atrial electrical activity, the QRS wave represents electrical activity generated during ventricular depolarization and excitation, and the T wave represents the process of cardiac repolarization. The ratio of the lumen area of ​​a blood vessel in the first reference ultrasound image to the lumen area of ​​a blood vessel in the second reference ultrasound image can be represented by the slope between the two points corresponding to the two reference ultrasound image frames on the curve in Figure 2 . Referring to Figure 2 , assuming that each cardiac cycle corresponds to 25 frames and that the reference cardiac state is the T wave, the remaining 24 frames correspond to 24 non-reference cardiac states. In this case, for each cardiac cycle on the three curves A, B, and C, the ratio of the lumen area corresponding to the 24 reference ultrasound images to the lumen area corresponding to the reference ultrasound image at the T wave can be taken as the sub-vessel morphological variation coefficient. The determined sub-vessel morphological variation coefficients can then be averaged to obtain the vascular morphological variation coefficients corresponding to the 24 non-reference cardiac states.

[0052] According to the above technical solution, the reference ultrasound images corresponding to each non-reference cardiac state are compared with the reference ultrasound images corresponding to the reference cardiac state in the same group of reference ultrasound images to calculate the sub-vessel morphological change coefficients corresponding to the group of reference ultrasound images. By comparing the sub-vessel morphological change coefficients with high granularity, the accurate vascular morphological change coefficients corresponding to the non-reference cardiac state can be obtained, so that accurate and reliable artifact correction can be performed on the ultrasound image sequence. In addition, when there are multiple groups of at least one group of reference ultrasound images, the sub-vessel morphological change coefficients corresponding to the at least one group of reference ultrasound images are averaged to accurately obtain the vascular morphological change coefficients, and thus accurately obtain the changes in the reference ultrasound images, so as to ensure the accuracy of motion artifact correction.

[0053] Exemplarily, the vascular morphology variation coefficient may include a rotational and translational variation coefficient of the blood vessel, wherein calculating the variation coefficient of the vascular morphology of the blood vessel in the first baseline ultrasonic image relative to the vascular morphology of the blood vessel in the second baseline ultrasonic image to obtain the sub-vascular morphology variation coefficient corresponding to the group of baseline ultrasonic images includes: detecting feature points on the blood vessels respectively contained in the first baseline ultrasonic image and the second baseline ultrasonic image; matching the feature points on the blood vessels respectively contained in the first baseline ultrasonic image and the second baseline ultrasonic image; and calculating the rotational and translational variation coefficient of the blood vessel in the first baseline ultrasonic image relative to the blood vessel in the second baseline ultrasonic image based on the mutually matched feature points as the sub-vascular morphology variation coefficient corresponding to the group of baseline ultrasonic images.

[0054] In one embodiment, the vascular morphology variation coefficient may include the rotational and translational variation coefficient of the vascular. In this case, the rotational and translational variation coefficient of the vascular in the first reference ultrasound image relative to the vascular in the second reference ultrasound image can be determined by the rotation angle and / or translation orientation between the mutually matching feature points in the two frames of reference ultrasound images, as the above-mentioned sub-vascular morphology variation coefficient. Specifically, the feature points on the vascular vessels contained in each of the first and second reference ultrasound images can be detected. The feature points can be any suitable one or more pixel points in the reference ultrasound image, such as pixel points where the pixel value changes dramatically. For example, the feature points can be points with large curvature on the vascular lumen in the reference ultrasound image. Feature point recognition can be achieved by algorithms such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF). Subsequently, the feature points of the two frames of reference ultrasound images can be matched. For example, feature point matching algorithms such as Brute-Force (BF) and Fast Library for Approximate Nearest Neighbors (FLANN) can be used to match feature points on blood vessels contained in the first and second reference ultrasound images. Based on the positions of the matching feature points in each image, a transformation matrix is ​​calculated for the blood vessels in the first reference ultrasound image relative to the matching feature points in the second reference ultrasound image. This transformation matrix can represent the relative rotation angle and translation orientation of the matching feature points in the two reference ultrasound images. This transformation matrix is ​​used as the sub-vessel morphology change coefficient corresponding to the set of reference ultrasound images.

[0055] According to the above technical solution, based on the matching feature points in the first and second reference ultrasound images, the rotational and translational variation coefficients of the blood vessels in the first reference ultrasound image relative to the blood vessels in the second reference ultrasound image are calculated to obtain the vascular morphology variation coefficient. Using the rotational and translational variation coefficients as the vascular morphology variation coefficients can avoid distortion of the calculated vascular morphology variation coefficients when the ultrasound device's catheter is located within a stenotic lesion within the blood vessel, thereby improving the accuracy of the calculated vascular morphology variation coefficients. Furthermore, the solution for determining the rotational and translational variation coefficients based on matching feature points has a high accuracy rate.

[0056] Exemplarily, the vascular morphology variation coefficient may include a rotational and translational variation coefficient of the blood vessel, wherein the variation coefficient of the vascular morphology of the blood vessel in the first baseline ultrasound image relative to the vascular morphology of the blood vessel in the second baseline ultrasound image is calculated to obtain the sub-vascular morphology variation coefficient corresponding to the group of baseline ultrasound images, including: detecting the lumen contours on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; determining the position of the contour center of gravity of the lumen contours on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; and calculating the rotational and translational variation coefficient of the blood vessel in the first baseline ultrasound image relative to the blood vessel in the second baseline ultrasound image based on the positions of the contour center of gravity corresponding to the first baseline ultrasound image and the second baseline ultrasound image, as the sub-vascular morphology variation coefficient corresponding to the group of baseline ultrasound images.

[0057] In one embodiment, the vascular morphological variation coefficient may include the rotational and translational variation coefficient of the vessel. In this case, the rotational and translational variation coefficient of the vessel in the first reference ultrasound image relative to the vessel in the second reference ultrasound image can be determined by the rotation angle and / or translational orientation between the contour centroids or centers of gravity in the two reference ultrasound images, and used as the above-mentioned sub-vessel morphological variation coefficient. Specifically, the lumen contours of the vessels contained in each of the first and second reference ultrasound images can be detected. Exemplarily, an image segmentation network can be used to detect the lumen contours. The image segmentation network may include, but is not limited to, one or more of the following: Fully Convolutional Networks (FCNs), U-nets, DeepLab series, V-nets, etc. Optionally, the lumen contours of the vessels contained in each of the first and second reference ultrasound images can be obtained through morphological operations. Exemplarily, the positions of the contour centroids of the lumen contours of the vessels contained in each of the first and second reference ultrasound images can be determined by calculating the moments of the images formed by the lumen contours. For example, an image coordinate system can be established by using the lower left corner vertex on the image as the origin, the direction passing through the origin and parallel to the horizontal direction as the image coordinate X-axis, and the direction passing through the origin and perpendicular to the X-axis as the image coordinate Y-axis. The position of the contour center of gravity can be represented by the pixel coordinates corresponding to the center of gravity on the image. Based on the positions of the contour center of gravity corresponding to the first and second reference ultrasound images, the rotation angle and translation orientation of the center of gravity of the blood vessel in the first reference ultrasound image relative to the center of gravity of the blood vessel in the second reference ultrasound image are calculated as the sub-vessel morphological change coefficient corresponding to the set of reference ultrasound images.

[0058] According to the above technical solution, based on the positions of the corresponding contour centroids of the first and second reference ultrasound images, the rotational and translational variation coefficients of the blood vessels in the first reference ultrasound image relative to the blood vessels in the second reference ultrasound image are calculated to obtain the vascular morphology variation coefficient. Using the rotational and translational variation coefficients as the vascular morphology variation coefficients can avoid distortion of the calculated vascular morphology variation coefficients when the ultrasound device catheter is located within a stenotic lesion within the blood vessel, thereby improving the accuracy of the calculated vascular morphology variation coefficients. Furthermore, determining the rotational and translational variation coefficients based on contour centroids requires less computational effort and therefore offers higher computational efficiency.

[0059] In one embodiment, step S140 may include the following operation: calculating inverse transformation coefficients based on the vascular morphology change coefficients corresponding to the non-baseline cardiac state. For example, in the embodiment where the vascular morphology change coefficients are rotational and translational change coefficients, the inverse transformation coefficients may be the inverse transformation matrix of the aforementioned transformation matrix. Subsequently, the vascular morphology of the blood vessels in the target ultrasound image may be transformed based on the inverse transformation coefficients to perform motion artifact correction on the target ultrasound image.

[0060] Exemplarily, the number of cardiac cycles in at least one cardiac cycle is multiple and / or the number of reference positions in at least one reference position is multiple.

[0061] As described above, in one embodiment, ultrasound images over multiple cardiac cycles may be acquired at the same reference position to form a reference ultrasound image sequence. Alternatively, ultrasound images over one cardiac cycle may be acquired at multiple reference positions to form a reference ultrasound image sequence. Alternatively, reference ultrasound images over multiple cardiac cycles may be acquired at multiple reference positions to form a reference ultrasound image sequence.

[0062] According to the above technical solution, a reference ultrasound image sequence is obtained based on multiple cardiac cycles and / or multiple reference positions, so that the acquired vascular morphology is more comprehensive, and therefore the calculated vascular morphology change parameters are more accurate.

[0063] Exemplarily, for each of at least one non-baseline cardiac state, based on a baseline ultrasound image sequence, calculating a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the vascular morphology change coefficient corresponding to the non-baseline cardiac state may include: for each of at least one non-baseline cardiac state, based on a baseline ultrasound image corresponding to the non-baseline cardiac state and a baseline ultrasound image corresponding to the baseline cardiac state in a baseline ultrasound image sequence, calculating a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the vascular morphology change coefficient corresponding to the non-baseline cardiac state.

[0064] According to the above technical solution, a reference ultrasound image corresponding to a non-reference cardiac state and a reference ultrasound image corresponding to a reference cardiac state are compared, and a coefficient of variation of the vascular morphology of the blood vessels in the non-reference cardiac state is calculated. That is, the coefficient of variation is determined based on the reference cardiac state, which can accurately evaluate the degree of influence of the non-reference cardiac state on the artifact, thereby facilitating motion artifact correction of the ultrasound image.

[0065] Exemplarily, for each non-baseline cardiac state of at least one non-baseline cardiac state, before calculating, based on a baseline ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state, the method may further include: acquiring an electrocardiogram signal acquired synchronously with the baseline ultrasound image sequence; and determining, based on the electrocardiogram signal, a baseline ultrasound image in the baseline ultrasound image sequence corresponding to each of the multiple cardiac states.

[0066] The image acquisition device (which may include an ultrasonic transducer) in the IVUS ultrasound device can be connected to the ECG signal acquisition device and connected in series to the same processor. The image acquisition device and ECG signal acquisition device in the IVUS ultrasound device can also be connected to the same processor or to different processors (in which case, the different processors can communicate with each other in real time over a network). In one embodiment, before step S120, a reference ultrasound image corresponding to each cardiac state can be determined from the reference ultrasound image sequence. For example, when acquiring the reference ultrasound image, the ECG signal can be acquired synchronously. For example, a synchronization signal can be used to synchronize the reference ultrasound image and the ECG signal. The processor can determine the start time of each cardiac state in real time based on the ECG signal. For example, the reference ultrasound image can be identified in real time based on the real-time acquired ECG signal. In this way, each frame of the reference ultrasound image acquired by the image acquisition device in the IVUS ultrasound device can be identified with a specific moment in the cardiac cycle and the cardiac state corresponding to the frame of the reference ultrasound image. In this way, the reference ultrasound image corresponding to each of the multiple cardiac states in the reference ultrasound image sequence can be determined based on the ECG signal. Optionally, after the ECG signal and the reference ultrasound image are acquired, the processor may determine the start time of each cardiac state based on the waveform of the ECG signal, and further determine the reference ultrasound image corresponding to each cardiac state.

[0067] According to the above technical solution, based on electrocardiogram signals acquired synchronously with the reference ultrasound image sequence, a reference ultrasound image corresponding to each of multiple cardiac states in the reference ultrasound image sequence is determined. This ensures a relatively accurate correspondence between the reference ultrasound image and the cardiac state, further reducing errors in motion artifact correction for the target ultrasound image.

[0068] Exemplarily, for each of at least one non-baseline cardiac state, based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state, the vascular morphology in the target ultrasonic image corresponding to the non-baseline cardiac state in the target ultrasonic image sequence is transformed to perform motion artifact correction on the target ultrasonic image sequence, which may include: for each of at least one non-baseline cardiac state, based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state, determining an inverse transformation coefficient; and transforming the vascular morphology in the target ultrasonic image corresponding to the non-baseline cardiac state in the target ultrasonic image sequence based on the inverse transformation coefficient to perform motion artifact correction on the target ultrasonic image sequence.

[0069] The embodiment of transforming the vascular morphology in the target ultrasound image by using the inverse transformation coefficients to perform motion artifact correction on the target ultrasound image sequence has been described above, and will not be repeated here.

[0070] According to the above technical solution, motion artifact correction is performed one by one based on non-reference cardiac states, which can more specifically eliminate motion artifacts in each non-reference motion state, thereby further reducing the error of motion artifact correction for the target ultrasound image.

[0071] Exemplarily, before calculating, for each of at least one non-baseline cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state based on a baseline ultrasound image sequence, and obtaining the coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state, the method may further include: determining the baseline cardiac state based on user input information.

[0072] The device for implementing the ultrasound image correction method 100 may include an input device. By way of example and not limitation, the input device may include one or more of a keyboard, a mouse, a microphone, a trackball, a touch screen, and the like. User input information may include text information and / or audio information, and the like. For example, through the input device, the user may input the cardiac state "end diastole" as the reference cardiac state. For another example, different cardiac states have one-to-one corresponding identifiers, where end diastole may correspond to the letter A, early systole may correspond to the letter B, and end systole may correspond to the letter C. The user inputs "A" through the input device to indicate that the reference cardiac state is end diastole.

[0073] According to the above technical solution, the baseline cardiac state is determined based on the user input information, which can flexibly adapt to different application scenarios and meet the examination needs of different users.

[0074] Exemplarily, the baseline cardiac state can also be obtained by calculation by the device for implementing the ultrasound image correction method 100. For example, the electrocardiogram signal of the subject is obtained, and based on the electrocardiogram signal, waveform amplitude characteristics of different cardiac states corresponding to different time periods of the same cardiac cycle are analyzed to determine the waveform amplitude change. The cardiac state with a waveform amplitude change less than a set amplitude change threshold and a duration greater than a set time period threshold is determined as the baseline cardiac state. In this way, a cardiac state that is in a stable state and lasts for a sufficiently long time can be used as the baseline cardiac state, thereby improving the image quality and stability of the baseline ultrasound image in the baseline cardiac state.

[0075] For example, the at least one reference position may include an examination start point within the blood vessel and / or an examination end point within the blood vessel.

[0076] In one embodiment, the at least one reference position may be the examination start point (e.g., distal end of the examination site) and / or the examination end point (e.g., proximal end of the examination site) within the blood vessel. Because the vascular morphology at these two positions is more continuous and stable, ultrasound image deviations caused by changes in catheter position due to heartbeats can be reduced. Of course, the at least one reference position may also include other positions, such as any one or more positions between the examination start point and the examination end point.

[0077] According to another aspect of the present invention, an ultrasonic image correction device is also provided. FIG3 shows a schematic block diagram of an ultrasonic image correction device 300 according to one embodiment of the present invention. As shown in FIG3 , the device 300 may include a first acquisition module 310, a calculation module 320, a second acquisition module 330, and a correction module 340.

[0078] The first acquisition module 310 is used to acquire a reference ultrasound image sequence acquired by an ultrasound device at at least one reference position within a blood vessel. The reference ultrasound image corresponding to each reference position in the reference ultrasound image sequence includes a reference ultrasound image acquired by the ultrasound device for the reference position within at least one cardiac cycle. Each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state.

[0079] A calculation module 320 is configured to calculate, for each of at least one non-baseline cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state based on a baseline ultrasound image sequence, to obtain a vascular morphology variation coefficient corresponding to the non-baseline cardiac state.

[0080] The second acquisition module 330 is configured to acquire a target ultrasound image sequence acquired by the ultrasound device during the retraction process.

[0081] The correction module 340 is configured to transform, for each of at least one non-baseline cardiac state, the vascular morphology in a target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence based on a vascular morphology change coefficient corresponding to the non-baseline cardiac state, so as to perform motion artifact correction on the target ultrasound image sequence.

[0082] Exemplarily, the reference ultrasound image sequence includes at least one set of reference ultrasound images, each set of reference ultrasound images corresponding to a unique cardiac cycle and a unique reference position. The calculation module 320 may include a first calculation submodule and an averaging submodule. The first calculation submodule is configured to, for each set of reference ultrasound images in the reference ultrasound image sequence, calculate a variation coefficient of the vascular morphology of a blood vessel in the first reference ultrasound image relative to the vascular morphology of a blood vessel in a second reference ultrasound image, thereby obtaining a sub-vessel morphology variation coefficient corresponding to the set of reference ultrasound images. The first reference ultrasound image is a reference ultrasound image in the set of reference ultrasound images corresponding to the non-reference cardiac state, and the second reference ultrasound image is a reference ultrasound image in the set of reference ultrasound images corresponding to the reference cardiac state. The averaging submodule is configured to, when there are multiple sets of at least one set of reference ultrasound images, average the sub-vessel morphology variation coefficients corresponding to each of the at least one set of reference ultrasound images to obtain a vascular morphology variation coefficient corresponding to the non-reference cardiac state. When there is only one set of at least one reference ultrasound image, the vascular morphology variation coefficient corresponding to the non-reference cardiac state is the sub-vessel morphology variation coefficient corresponding to the set of reference ultrasound images.

[0083] Exemplarily, the vascular morphology variation coefficient includes a rotational and translational variation coefficient of the vascular image, wherein the first calculation submodule may include a first detection unit, a matching unit, and a first calculation unit. The first calculation submodule may specifically include: a first detection unit for detecting feature points on the vascular image contained in each of the first and second reference ultrasound images; a matching unit for matching the feature points on the vascular image contained in each of the first and second reference ultrasound images; and a first calculation unit for calculating, based on the matched feature points, the rotational and translational variation coefficient of the vascular image in the first reference ultrasound image relative to the vascular image in the second reference ultrasound image, as the sub-vascular morphology variation coefficient corresponding to the set of reference ultrasound images.

[0084] Exemplarily, the blood vessel morphology variation coefficient includes the rotational and translational variation coefficient of the blood vessel, wherein the first calculation submodule may specifically include: a second detection unit, used to detect the lumen contours on the blood vessels respectively contained in the first reference ultrasound image and the second reference ultrasound image; a determination unit, used to determine the position of the contour center of gravity of the lumen contours on the blood vessels respectively contained in the first reference ultrasound image and the second reference ultrasound image; a second calculation unit, used to calculate the rotational and translational variation coefficient of the blood vessel in the first reference ultrasound image relative to the blood vessel in the second reference ultrasound image based on the positions of the contour center of gravity corresponding to the first reference ultrasound image and the second reference ultrasound image, as the sub-blood vessel morphology variation coefficient corresponding to the group of reference ultrasound images.

[0085] Exemplarily, the blood vessel morphology variation coefficient includes one or more of the following: a diameter variation coefficient of the lumen diameter of the blood vessel and an area variation coefficient of the lumen area of ​​the blood vessel.

[0086] Exemplarily, the number of cardiac cycles in at least one cardiac cycle is multiple and / or the number of reference positions in at least one reference position is multiple.

[0087] Illustratively, the calculation module 320 may include a second calculation submodule configured to calculate, for each of the at least one non-baseline cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state based on a reference ultrasound image corresponding to the non-baseline cardiac state and a reference ultrasound image corresponding to the reference cardiac state in the reference ultrasound image sequence, thereby obtaining a coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state.

[0088] Exemplarily, the ultrasonic image correction apparatus 300 may further include a third acquisition module and a first determination module. The third acquisition submodule is configured to acquire an electrocardiogram (ECG) signal acquired synchronously with the reference ultrasound image sequence before the calculation module 320 calculates, based on the reference ultrasound image sequence, for each of at least one non-reference cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state, and obtains the vascular morphology variation coefficient corresponding to the non-reference cardiac state; and the first determination module is configured to determine, based on the ECG signal, a reference ultrasound image corresponding to each of the multiple cardiac states in the reference ultrasound image sequence, before the calculation module 320 calculates, based on the reference ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state, and obtains the vascular morphology variation coefficient corresponding to the non-reference cardiac state.

[0089] Exemplarily, the correction module 340 may include a determination submodule and a transformation submodule. The determination submodule is configured to determine, for each of at least one non-baseline cardiac state, an inverse transformation coefficient based on a vascular morphology change coefficient corresponding to the non-baseline cardiac state; and the transformation submodule is configured to transform, based on the inverse transformation coefficient, the vascular morphology in a target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence, to perform motion artifact correction on the target ultrasound image sequence.

[0090] Exemplarily, the ultrasonic image correction apparatus 300 may further include a second determination module. The second determination module is configured to determine the baseline cardiac state based on user input information before the calculation module 320 calculates, for each of the at least one non-baseline cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state based on the baseline ultrasonic image sequence, and obtains the coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state.

[0091] Exemplarily, the at least one reference position includes an examination start point within the blood vessel and / or an examination end point within the blood vessel.

[0092] Those skilled in the art can understand the implementation of the ultrasonic image correction device and its beneficial effects by reading the above description of the ultrasonic image correction method. For the sake of brevity, they will not be described here in detail.

[0093] According to yet another aspect of the present invention, an electronic device is also provided. Figure 4 shows a schematic block diagram of an electronic device according to an embodiment of the present invention. As shown in the figure, the electronic device 400 includes a processor 410 and a memory 420. The memory 420 stores a computer program / instruction, which, when executed by the processor 410, is used to execute the above-described ultrasound image correction method.

[0094] In one embodiment, the computer program / instructions are configured to, when executed by the processor 410, perform the following steps: acquiring a sequence of reference ultrasound images acquired by an ultrasound device at at least one reference position within a blood vessel, wherein the reference ultrasound images corresponding to each reference position in the sequence of reference ultrasound images include reference ultrasound images acquired by the ultrasound device for the reference position within at least one cardiac cycle, wherein each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state; for each of the at least one non-reference cardiac state, calculating, based on the sequence of reference ultrasound images, a coefficient of variation of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state, thereby obtaining a vascular morphology variation coefficient corresponding to the non-reference cardiac state; acquiring a sequence of target ultrasound images acquired by the ultrasound device during a pullback process; and for each of the at least one non-reference cardiac state, transforming, based on the vascular morphology variation coefficient corresponding to the non-reference cardiac state, the vascular morphology in the target ultrasound images corresponding to the non-reference cardiac state in the sequence of target ultrasound images, thereby performing motion artifact correction on the sequence of target ultrasound images.

[0095] Exemplarily, the reference ultrasound image sequence includes at least one group of reference ultrasound images, each group of reference ultrasound images corresponds to a unique cardiac cycle and a unique reference position; wherein the computer program / instructions executed by the processor 410 when running the computer program / instructions include the steps of: calculating, for each group of reference ultrasound images in the reference ultrasound image sequence, a vascular morphology variation coefficient of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state, and obtaining a vascular morphology variation coefficient corresponding to the non-reference cardiac state; and a sub-vessel morphology change coefficient corresponding to a quasi-ultrasound image, wherein the first reference ultrasound image is a reference ultrasound image corresponding to the non-reference cardiac state in the group of reference ultrasound images, and the second reference ultrasound image is a reference ultrasound image corresponding to the reference cardiac state in the group of reference ultrasound images; when there are multiple groups of at least one group of reference ultrasound images, the sub-vessel morphology change coefficients corresponding to the at least one group of reference ultrasound images are averaged to obtain the vessel morphology change coefficient corresponding to the non-reference cardiac state; wherein, when there are only one group of at least one group of reference ultrasound images, the vessel morphology change coefficient corresponding to the non-reference cardiac state is the sub-vessel morphology change coefficient corresponding to the group of reference ultrasound images.

[0096] Exemplarily, the vascular morphology variation coefficient includes the rotational and translational variation coefficient of the blood vessel, wherein the computer program / instructions used by the processor 410 when executed to execute the step of "calculating the variation coefficient of the vascular morphology of the blood vessel in the first baseline ultrasound image relative to the vascular morphology of the blood vessel in the second baseline ultrasound image, and obtaining the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images" include: detecting feature points on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; matching the feature points on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; and calculating the rotational and translational variation coefficient of the blood vessel in the first baseline ultrasound image relative to the blood vessel in the second baseline ultrasound image based on the mutually matched feature points, as the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images.

[0097] Exemplarily, the vascular morphology variation coefficient includes the rotational and translational variation coefficient of the blood vessel, wherein the computer program / instructions used by the processor 410 to execute the step of "calculating the variation coefficient of the vascular morphology of the blood vessel in the first baseline ultrasound image relative to the vascular morphology of the blood vessel in the second baseline ultrasound image, and obtaining the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images" include: detecting the lumen contours of the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; determining the position of the contour center of gravity of the lumen contours of the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; and calculating the rotational and translational variation coefficient of the blood vessel in the first baseline ultrasound image relative to the blood vessel in the second baseline ultrasound image based on the positions of the contour center of gravity corresponding to the first baseline ultrasound image and the second baseline ultrasound image, as the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images.

[0098] Exemplarily, the blood vessel morphology variation coefficient includes one or more of the following: a diameter variation coefficient of the lumen diameter of the blood vessel and an area variation coefficient of the lumen area of ​​the blood vessel.

[0099] Exemplarily, the number of cardiac cycles in at least one cardiac cycle is multiple and / or the number of reference positions in at least one reference position is multiple.

[0100] Exemplarily, the computer program / instructions executed by the processor 410 when running include the steps of "for each non-baseline cardiac state among at least one non-baseline cardiac state, calculating, based on a baseline ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining a vascular morphology variation coefficient corresponding to the non-baseline cardiac state" including: for each non-baseline cardiac state among at least one non-baseline cardiac state, calculating, based on a baseline ultrasound image corresponding to the non-baseline cardiac state and a baseline ultrasound image corresponding to the baseline cardiac state in a baseline ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining a vascular morphology variation coefficient corresponding to the non-baseline cardiac state.

[0101] Exemplarily, before the computer program / instructions are executed by the processor 410 to perform the step of "for each non-baseline cardiac state in at least one non-baseline cardiac state, based on the baseline ultrasound image sequence, calculating the coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the coefficient of change of the vascular morphology corresponding to the non-baseline cardiac state", the computer program / instructions can also be used by the processor 410 to perform the following when running: acquiring an electrocardiogram signal acquired synchronously with the baseline ultrasound image sequence; and determining, based on the electrocardiogram signal, a baseline ultrasound image in the baseline ultrasound image sequence corresponding to each of the multiple cardiac states.

[0102] Exemplarily, the computer program / instructions executed by the processor 410 when running include the steps of: for each non-baseline cardiac state among at least one non-baseline cardiac state, transforming the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state, so as to perform motion artifact correction on the target ultrasound image sequence. The steps include: for each non-baseline cardiac state among at least one non-baseline cardiac state, determining the inverse transformation coefficient based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state; and transforming the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence based on the inverse transformation coefficient, so as to perform motion artifact correction on the target ultrasound image sequence.

[0103] Exemplarily, before the computer program / instructions are executed by the processor 410 to perform the step of "for each non-baseline cardiac state in at least one non-baseline cardiac state, calculating, based on the baseline ultrasound image sequence, a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, to obtain a coefficient of change of the vascular morphology corresponding to the non-baseline cardiac state", the computer program / instructions can also be used by the processor 410 to perform the following when running: determining the baseline cardiac state based on user input information.

[0104] Exemplarily, the at least one reference position includes an examination start point within the blood vessel and / or an examination end point within the blood vessel.

[0105] According to another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program / instructions are stored. When executed, the computer program / instructions are used to perform the above-described ultrasound image correction method. The computer-readable storage medium may include, for example, a storage component of a tablet computer, a hard disk of a personal computer, an erasable programmable read-only memory (EPROM), a compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above-described storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0106] In one embodiment, the computer program / instructions, when run, are configured to: acquire a sequence of reference ultrasound images acquired by an ultrasound device at at least one reference position within a blood vessel, wherein the reference ultrasound images corresponding to each reference position in the sequence of reference ultrasound images include reference ultrasound images acquired by the ultrasound device for the reference position within at least one cardiac cycle, wherein each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state; for each of the at least one non-reference cardiac state, calculate, based on the sequence of reference ultrasound images, a coefficient of variation of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state, thereby obtaining a vascular morphology variation coefficient corresponding to the non-reference cardiac state; acquire a sequence of target ultrasound images acquired by the ultrasound device during a pullback process; and for each of the at least one non-reference cardiac state, transform, based on the vascular morphology variation coefficient corresponding to the non-reference cardiac state, the vascular morphology in the target ultrasound image corresponding to the non-reference cardiac state in the sequence of target ultrasound images, thereby performing motion artifact correction on the sequence of target ultrasound images.

[0107] Exemplarily, the reference ultrasound image sequence includes at least one group of reference ultrasound images, each group of reference ultrasound images corresponds to a unique cardiac cycle and a unique reference position; wherein the step of "calculating, based on the reference ultrasound image sequence, a vascular morphology variation coefficient of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state, and obtaining the vascular morphology variation coefficient corresponding to the non-reference cardiac state" performed by the computer program / instructions when running includes: for each group of reference ultrasound images in the reference ultrasound image sequence, calculating a vascular morphology variation coefficient of the vascular morphology of the blood vessel in the first reference ultrasound image relative to the vascular morphology of the blood vessel in the second reference ultrasound image, and obtaining a vascular morphology variation coefficient corresponding to the group of reference ultrasound images; The sub-vessel morphology change coefficient corresponding to the image is obtained, wherein the first reference ultrasound image is the reference ultrasound image corresponding to the non-reference cardiac state in the group of reference ultrasound images, and the second reference ultrasound image is the reference ultrasound image corresponding to the reference cardiac state in the group of reference ultrasound images; when the number of at least one group of reference ultrasound images is multiple, the sub-vessel morphology change coefficients corresponding to the at least one group of reference ultrasound images are averaged to obtain the vessel morphology change coefficient corresponding to the non-reference cardiac state; wherein, when the number of at least one group of reference ultrasound images is one, the vessel morphology change coefficient corresponding to the non-reference cardiac state is the sub-vessel morphology change coefficient corresponding to the group of reference ultrasound images.

[0108] Exemplarily, the vascular morphology variation coefficient includes the rotational and translational variation coefficient of the blood vessel, wherein the computer program / instructions used to execute the step of "calculating the variation coefficient of the vascular morphology of the blood vessel in the first baseline ultrasound image relative to the vascular morphology of the blood vessel in the second baseline ultrasound image, and obtaining the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images" when running include: detecting feature points on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; matching the feature points on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; and calculating the rotational and translational variation coefficient of the blood vessel in the first baseline ultrasound image relative to the blood vessel in the second baseline ultrasound image based on the mutually matched feature points, as the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images.

[0109] Exemplarily, the vascular morphology variation coefficient includes the rotational and translational variation coefficient of the blood vessel, wherein the step of "calculating the variation coefficient of the vascular morphology of the blood vessel in the first baseline ultrasound image relative to the vascular morphology of the blood vessel in the second baseline ultrasound image, and obtaining the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images" executed by the computer program / instructions during execution includes: detecting the lumen contours on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; determining the position of the contour center of gravity of the lumen contours on the blood vessels respectively contained in the first baseline ultrasound image and the second baseline ultrasound image; and calculating the rotational and translational variation coefficient of the blood vessel in the first baseline ultrasound image relative to the blood vessel in the second baseline ultrasound image based on the positions of the contour center of gravity corresponding to the first baseline ultrasound image and the second baseline ultrasound image, as the sub-vessel morphology variation coefficient corresponding to the group of baseline ultrasound images.

[0110] Exemplarily, the blood vessel morphology variation coefficient includes one or more of the following: a diameter variation coefficient of the lumen diameter of the blood vessel and an area variation coefficient of the lumen area of ​​the blood vessel.

[0111] Exemplarily, the number of cardiac cycles in at least one cardiac cycle is multiple and / or the number of reference positions in at least one reference position is multiple.

[0112] Exemplarily, the step of "for each non-baseline cardiac state among at least one non-baseline cardiac state, calculating, based on a baseline ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining a vascular morphology variation coefficient corresponding to the non-baseline cardiac state" executed by the computer program / instructions when running includes: for each non-baseline cardiac state among at least one non-baseline cardiac state, calculating, based on a baseline ultrasound image corresponding to the non-baseline cardiac state and a baseline ultrasound image corresponding to the baseline cardiac state in a baseline ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining a vascular morphology variation coefficient corresponding to the non-baseline cardiac state.

[0113] Exemplarily, before the computer program / instructions are used to execute the step of "for each non-baseline cardiac state in at least one non-baseline cardiac state, based on the baseline ultrasound image sequence, calculating the coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, and obtaining the coefficient of change of the vascular morphology corresponding to the non-baseline cardiac state" when running, the computer program / instructions can also be used to execute the following when running: acquiring an electrocardiogram signal acquired synchronously with the baseline ultrasound image sequence; and determining, based on the electrocardiogram signal, a baseline ultrasound image in the baseline ultrasound image sequence corresponding to each of the multiple cardiac states.

[0114] Exemplarily, the steps of "for each non-baseline cardiac state among at least one non-baseline cardiac state, transforming the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state, so as to perform motion artifact correction on the target ultrasound image sequence" performed by the computer program / instructions when running include: for each non-baseline cardiac state among at least one non-baseline cardiac state, determining an inverse transformation coefficient based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state; and transforming the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence based on the inverse transformation coefficient, so as to perform motion artifact correction on the target ultrasound image sequence.

[0115] Exemplarily, before the computer program / instructions are used to execute the step of "for each non-baseline cardiac state in at least one non-baseline cardiac state, calculating, based on a baseline ultrasound image sequence, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state, to obtain a coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state" when running, the computer program / instructions may also be used to execute, when running: determining the baseline cardiac state based on user input information.

[0116] Exemplarily, the at least one reference position includes an examination start point within the blood vessel and / or an examination end point within the blood vessel.

[0117] A person skilled in the art can understand the specific implementation scheme of the ultrasonic image correction device, electronic device and computer-readable storage medium by reading the above description of the ultrasonic image correction method. For the sake of brevity, it is not repeated here.

[0118] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely illustrative and are not intended to limit the scope of the present invention. Various changes and modifications may be made therein by those skilled in the art without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as claimed in the appended claims.

[0119] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0120] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units described is merely a logical functional division. In actual implementation, other division methods may be used. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not implemented.

[0121] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0122] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this approach to the present invention should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More precisely, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0123] It will be understood by those skilled in the art that, except where mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus disclosed herein may be combined in any combination. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature providing the same, equivalent, or similar purpose.

[0124] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0125] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some modules in the ultrasonic image correction device according to an embodiment of the present invention. The present invention may also be implemented as a device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0126] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for correcting an ultrasonic image, comprising: Acquire a reference ultrasound image sequence acquired by an ultrasound device at at least one reference position in a blood vessel, wherein the reference ultrasound image corresponding to each reference position in the reference ultrasound image sequence includes a reference ultrasound image acquired by the ultrasound device for the reference position in at least one cardiac cycle, each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state; For each of the at least one non-baseline cardiac state, based on the base line ultrasound image sequence, calculating a coefficient of change of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the base line cardiac state, and obtaining a coefficient of change of the vascular morphology corresponding to the non-baseline cardiac state; Acquire a target ultrasound image sequence acquired by the ultrasound device during the withdrawal process; For each of the at least one non-baseline cardiac state, the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence is transformed based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state to perform motion artifact correction on the target ultrasound image sequence.

2. The method of claim 1, wherein: The reference ultrasound image sequence includes at least one group of reference ultrasound images, each group of reference ultrasound images corresponds to a unique cardiac cycle and a unique reference position; wherein, The step of calculating the vascular morphology variation coefficient of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state based on the reference ultrasonic image sequence to obtain the vascular morphology variation coefficient corresponding to the non-reference cardiac state includes: For each group of reference ultrasonic images in the reference ultrasonic image sequence, calculating a variation coefficient of the vascular morphology of the blood vessel in a first reference ultrasonic image relative to the vascular morphology of the blood vessel in a second reference ultrasonic image, and obtaining a sub-vessel morphology variation coefficient corresponding to the group of reference ultrasonic images, wherein the first reference ultrasonic image is a reference ultrasonic image in the group of reference ultrasonic images corresponding to the non-reference cardiac state, and the second reference ultrasonic image is a reference ultrasonic image in the group of reference ultrasonic images corresponding to the reference cardiac state; When the number of the at least one group of reference ultrasound images is plural, averaging the sub-vessel morphology change coefficients corresponding to the at least one group of reference ultrasound images to obtain the vessel morphology change coefficient corresponding to the non-reference cardiac state; Wherein, when the number of the at least one group of reference ultrasound images is one group, the blood vessel morphology change coefficient corresponding to the non-reference cardiac state is the sub-blood vessel morphology change coefficient corresponding to the group of reference ultrasound images.

3. The method of claim 2, wherein: The blood vessel morphology variation coefficient includes the rotation and translation variation coefficient of the blood vessel, wherein: The step of calculating the variation coefficient of the vascular morphology of the blood vessel in the first reference ultrasonic image relative to the vascular morphology of the blood vessel in the second reference ultrasonic image to obtain the variation coefficient of the sub-vessel morphology corresponding to the group of reference ultrasonic images includes: detecting feature points on the blood vessel respectively contained in the first reference ultrasonic image and the second reference ultrasonic image; The first reference ultrasonic image and the second reference ultrasonic image respectively contain the blood vessels. Matching of feature points; Based on the mutually matched feature points, a rotational translational variation coefficient of the blood vessel in the first reference ultrasonic image relative to the blood vessel in the second reference ultrasonic image is calculated as a sub-blood vessel morphology variation coefficient corresponding to the set of reference ultrasonic images.

4. The method of claim 2, wherein: The blood vessel morphology variation coefficient includes the rotation and translation variation coefficient of the blood vessel, wherein: The step of calculating the variation coefficient of the vascular morphology of the blood vessel in the first reference ultrasonic image relative to the vascular morphology of the blood vessel in the second reference ultrasonic image to obtain the variation coefficient of the sub-vessel morphology corresponding to the group of reference ultrasonic images includes: Detecting a lumen contour on the blood vessel respectively included in the first reference ultrasonic image and the second reference ultrasonic image; Determine the position of the contour centroid of the lumen contour on the blood vessel contained in the first reference ultrasonic image and the second reference ultrasonic image respectively; Based on the positions of the contour centroids corresponding to the first reference ultrasonic image and the second reference ultrasonic image, the rotational translational variation coefficient of the blood vessel in the first reference ultrasonic image relative to the blood vessel in the second reference ultrasonic image is calculated as the sub-vessel morphology variation coefficient corresponding to the group of reference ultrasonic images.

5. The method of claim 2, wherein: The blood vessel morphology variation coefficient includes one or more of the following: a diameter variation coefficient of the lumen diameter of the blood vessel and an area variation coefficient of the lumen area of ​​the blood vessel.

6. The method according to any one of claims 1 to 5, wherein: The number of cardiac cycles in the at least one cardiac cycle is plural and / or the number of reference positions in the at least one reference position is plural.

7. The method according to any one of claims 1 to 5, wherein: The step of calculating, for each of the at least one non-reference cardiac state, a change coefficient of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state based on the reference ultrasound image sequence, and obtaining the vascular morphology change coefficient corresponding to the non-reference cardiac state comprises: For each of the at least one non-baseline cardiac state, based on a baseline ultrasound image corresponding to the non-baseline cardiac state in the baseline ultrasound image sequence and a baseline ultrasound image corresponding to the baseline cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state is calculated to obtain the coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state.

8. The method according to any one of claims 1 to 5, wherein: Before calculating, for each of the at least one non-baseline cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state based on the baseline ultrasound image sequence, and obtaining the coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state, the method further comprises: Acquire an electrocardiogram signal acquired synchronously with the reference ultrasound image sequence; A reference ultrasound image corresponding to each of the plurality of cardiac states in the reference ultrasound image sequence is determined based on the electrocardiographic signal.

9. The method according to any one of claims 1 to 5, wherein: For each of the at least one non-reference cardiac state, based on the vascular morphology change coefficient corresponding to the non-reference cardiac state, transforming the vascular morphology in the target ultrasonic image corresponding to the non-reference cardiac state in the target ultrasonic image sequence to perform motion artifact correction on the target ultrasonic image sequence, comprising: For each of the at least one non-reference cardiac state, determining an inverse transformation coefficient based on a vascular morphology change coefficient corresponding to the non-reference cardiac state; The blood vessel morphology in the target ultrasound image corresponding to the non-reference cardiac state in the target ultrasound image sequence is transformed based on the inverse transformation coefficients to perform motion artifact correction on the target ultrasound image sequence.

10. The method according to any one of claims 1 to 5, wherein: Before calculating, for each of the at least one non-baseline cardiac state, a coefficient of variation of the vascular morphology of the blood vessel in the non-baseline cardiac state relative to the vascular morphology in the baseline cardiac state based on the baseline ultrasound image sequence, and obtaining the coefficient of variation of the vascular morphology corresponding to the non-baseline cardiac state, the method further comprises: Based on user input information, the reference cardiac state is determined.

11. The method according to any one of claims 1 to 5, wherein: The at least one reference position includes an examination start point in the blood vessel and / or an examination end point in the blood vessel.

12. An ultrasonic image correction device, comprising: A first acquisition module is configured to acquire a reference ultrasound image sequence acquired by an ultrasound device at at least one reference position in a blood vessel, wherein the reference ultrasound image corresponding to each reference position in the reference ultrasound image sequence includes a reference ultrasound image acquired by the ultrasound device for the reference position in at least one cardiac cycle, each cardiac cycle includes multiple cardiac states, and the multiple cardiac states include a reference cardiac state and at least one non-reference cardiac state; a calculation module, configured to calculate, for each of the at least one non-reference cardiac state, a change coefficient of the vascular morphology of the blood vessel in the non-reference cardiac state relative to the vascular morphology in the reference cardiac state based on the reference ultrasound image sequence, and obtain a vascular morphology change coefficient corresponding to the non-reference cardiac state; A second acquisition module is used to acquire a target ultrasound image sequence acquired by the ultrasound device during the withdrawal process; A correction module is used for transforming the vascular morphology in the target ultrasound image corresponding to the non-baseline cardiac state in the target ultrasound image sequence based on the vascular morphology change coefficient corresponding to the non-baseline cardiac state for each non-baseline cardiac state of the at least one non-baseline cardiac state, so as to perform motion artifact correction on the target ultrasound image sequence.

13. An electronic device, comprising a processor and a memory, wherein a computer program / instruction is stored in the memory, and the processor executes the computer program / instruction to implement the ultrasonic image correction method according to any one of claims 1 to 11.

14. A computer-readable storage medium storing a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the ultrasonic image correction method according to any one of claims 1 to 11.

Images