A method, apparatus, device, and storage medium for segmenting cardiac images.

Abstract

This invention discloses a method, apparatus, device, and storage medium for segmenting cardiac images. The method includes: in response to detecting a cardiac image sequence to be processed, performing an image segmentation operation on the cardiac image sequence to obtain a first endocardial and ectopic membrane segmentation result; determining a reference cardiac image sequence based on the cardiac image sequence to be processed, and performing an image segmentation operation on the reference cardiac image sequence to obtain a second endocardial and ectopic membrane segmentation result; wherein the number of frames in the reference cardiac image sequence is the same as the number of frames in the cardiac image sequence to be processed, and the reference cardiac image sequence represents a periodic cardiac image sequence; and performing a correction operation on the first endocardial and ectopic membrane segmentation result based on the second endocardial and ectopic membrane segmentation result to obtain a target endocardial and ectopic membrane segmentation result. This invention addresses the problem of prior art failing to consider the deformation of cardiac images, thus improving the accuracy of endocardial and ectopic membrane segmentation results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a cardiac image segmentation method, device, equipment and storage medium. BACKGROUND

[0002] Coronary heart disease is a major public health problem that endangers human health, and coronary heart disease is often accompanied by myocardial microcirculation disorder, so myocardial microcirculation disorder has become a new target for the treatment of coronary artery disease today, and early detection and evaluation of myocardial microcirculation disorder is of great significance.

[0003] At present, non-invasive myocardial imaging methods are often used in clinical practice to evaluate myocardial microcirculation disorder. The principle of myocardial imaging is that after injecting ultrasound contrast agent microbubbles into peripheral veins, the microbubbles are perfused in the myocardium, and then high-energy field is triggered to destroy the microbubbles in the myocardium. The process of microbubble reperfusion is observed through cardiac images to evaluate the microcirculation state.

[0004] The segmentation of endocardium and epicardium in myocardial imaging is an important part of the evaluation of microcirculation state, but the movement of the heart will cause deformation of the cardiac image, resulting in inaccurate segmentation results of the endocardium and epicardium, which cannot meet the high-precision requirements of the medical field for the segmentation results of the endocardium and epicardium of the cardiac image. SUMMARY

[0005] The present application provides a cardiac image segmentation method, device, equipment and storage medium to solve the problem that the prior art does not consider the deformation of the cardiac image, and to improve the accuracy of the endocardium and epicardium segmentation results of the cardiac image.

[0006] According to an aspect of the present application, a cardiac image segmentation method is provided, which comprises:

[0007] In response to detecting a sequence of cardiac images to be processed, performing an image segmentation operation on the sequence of cardiac images to be processed to obtain a first endocardium and epicardium segmentation result;

[0008] Based on the sequence of cardiac images to be processed, a reference sequence of cardiac images is determined, and an image segmentation operation is performed on the reference sequence of cardiac images to obtain a second endocardium and epicardium segmentation result; wherein the sequence frame number of the reference sequence of cardiac images is the same as the sequence frame number of the sequence of cardiac images to be processed, and the reference sequence of cardiac images represents a sequence of cardiac images with periodicity;

[0009] Based on the second endocardium and epicardium segmentation result, performing a correction operation on the first endocardium and epicardium segmentation result to obtain a target endocardium and epicardium segmentation result.

[0010] According to another aspect of the present application, a cardiac image segmentation device is provided, which comprises:

[0011] a first endo-epicardium segmentation result determination module configured to, in response to detecting the to-be-processed cardiac image sequence, perform an image segmentation operation on the to-be-processed cardiac image sequence to obtain a first endo-epicardium segmentation result;

[0012] a second endo-epicardium segmentation result determination module configured to determine a reference cardiac image sequence based on the to-be-processed cardiac image sequence, and perform an image segmentation operation on the reference cardiac image sequence to obtain a second endo-epicardium segmentation result, wherein the reference cardiac image sequence has the same number of sequence frames as the to-be-processed cardiac image sequence, and the reference cardiac image sequence represents a periodic cardiac image sequence;

[0013] a target endo-epicardium segmentation result determination module configured to perform a correction operation on the first endo-epicardium segmentation result based on the second endo-epicardium segmentation result to obtain a target endo-epicardium segmentation result.

[0014] According to another aspect of the present application, an electronic device is provided, which comprises:

[0015] at least one processor; and

[0016] a memory connected to the at least one processor in communication; wherein

[0017] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the cardiac image segmentation method according to any one of the embodiments of the present application.

[0018] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the cardiac image segmentation method according to any one of the embodiments of the present application when executed by the processor.

[0019] The technical scheme of the embodiments of the present application determines a periodic reference cardiac image sequence based on a to-be-processed cardiac image sequence, and performs a correction operation on a first endo-epicardium segmentation result corresponding to the to-be-processed cardiac image sequence based on a second endo-epicardium segmentation result corresponding to the reference cardiac image sequence to obtain a target endo-epicardium segmentation result, thereby solving the problem that the prior art does not consider the periodic motion of heartbeats to cause deformation of cardiac images, improving the accuracy of endo-epicardium segmentation results, and further improving the accuracy of subsequent myocardial microcirculation disorder evaluation.

[0020] It is to be understood that the details set forth herein do not limit the scope of the embodiments of the application to the specific embodiments described. Rather, the scope of the embodiments of the application is to be defined by the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0022] Figure 1 is a flow chart of a heart image segmentation method according to the first embodiment of the present application;

[0023] Figure 2 is a schematic diagram of an endocardium and epicardium segmentation result of a heart image according to the first embodiment of the present application;

[0024] Figure 3 is a schematic diagram of a periodic heart image sequence according to the first embodiment of the present application;

[0025] Figure 4 is a flow chart of a heart image segmentation method according to the second embodiment of the present application;

[0026] Figure 5 is a structural schematic diagram of a heart image segmentation device according to the third embodiment of the present application;

[0027] Figure 6 is a structural schematic diagram of an electronic device according to the fourth embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the technical personnel in the art better understand the present application scheme, the following will combine the drawings in the embodiments of the present application, and the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described accompanying drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment one

[0031] Figure 1 is a flowchart of a heart image segmentation method according to an embodiment one of the present application. The embodiment can be applicable to the case of segmenting the endocardium and epicardium of a heart image. The method can be executed by a heart image segmentation device, which can be realized in the form of hardware and / or software, and can be configured in a terminal device. As shown in the figure, the method comprises: Figure 1

[0032] S110, in response to detecting a heart image sequence to be processed, performing an image segmentation operation on the heart image sequence to be processed to obtain a first endocardium and epicardium segmentation result.

[0033] Specifically, the heart image sequence to be processed includes at least two heart images to be processed. The acquisition device for obtaining the heart image sequence to be processed includes, but is not limited to, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, an ultrasound device, and the like.

[0034] Specifically, the image segmentation operation is performed on the at least two heart images to be processed in the heart image sequence to be processed, and correspondingly, the first endocardium and epicardium segmentation result includes a first endocardium segmentation result and a first epicardium segmentation result corresponding to the at least two heart images to be processed, respectively. The method for performing the image segmentation operation includes, but is not limited to, a neural network algorithm, a region growing algorithm, a pixel gradient segmentation method, and the like. The image segmentation method used herein is not limited.

[0035] Figure 2 ​is a schematic diagram of an endo-epicardium segmentation result of a cardiac image according to an embodiment of the present application. Specifically, the cardiac image comprises a cardiac cavity region, a myocardial region and an extra-myocardial region. The cardiac cavity region is relatively bright and constitutes a single connected domain in shape. The myocardial region is relatively dark and is a ring shape completely wrapping the cardiac cavity region. Figure 2 The inner black line of the myocardial region represents the endocardium segmentation result of the cardiac image, and the outer black line of the myocardial region represents the epicardium segmentation result of the cardiac image. Heartbeat and respiration have certain periodicity, and cardiac images at the same heartbeat phase or the same respiration phase have similarity.

[0036] S120, based on the to-be-processed cardiac image sequence, determining a reference cardiac image sequence, and performing an image segmentation operation on the reference cardiac image sequence to obtain a second endo-epicardium segmentation result.

[0037] In this embodiment, the sequence frame number of the reference cardiac image sequence is the same as that of the to-be-processed cardiac image sequence, and the reference cardiac image sequence represents a periodic cardiac image sequence. Specifically, the cardiac image sequence in each image period of the reference cardiac image sequence is the same.

[0038] In an embodiment, optionally, based on the to-be-processed cardiac image sequence, determining the reference cardiac image sequence comprises: obtaining a part of the cardiac image sequence in the to-be-processed cardiac image sequence, and determining a part of the cardiac cavity area-time sequence corresponding to the part of the cardiac image sequence; wherein the sequence frame number of the part of the cardiac image sequence is greater than or equal to 2 image periods; performing a Fourier transform operation on the part of the cardiac cavity area-time sequence to obtain an image period and a cycle number corresponding to the part of the cardiac image sequence; and determining the reference cardiac image sequence based on the part of the cardiac image sequence, the image period and the cycle number.

[0039] In an embodiment, optionally, obtaining the part of the cardiac image sequence in the to-be-processed cardiac image sequence comprises: randomly obtaining the part of the cardiac image sequence in the to-be-processed cardiac image sequence based on a preset sequence frame number. Specifically, the preset sequence frame number is the sequence frame number of the part of the cardiac image sequence, and the part of the cardiac image sequence can be any cardiac image sequence satisfying the preset sequence frame number. It should be noted that the part of the cardiac image sequence is a continuous cardiac image in the to-be-processed cardiac image sequence. For example, the part of the cardiac image sequence comprises an i-th cardiac image and an i+N-th cardiac image in the to-be-processed cardiac image sequence, where N represents the preset sequence frame number. The preset sequence frame number can be pre-set by a user according to experience, and the preset sequence frame number is greater than or equal to 2 image periods.

[0040] In another embodiment, optionally, obtaining a portion of the heart image sequence in the heart image sequence to be processed includes: determining the heart chamber area-time series to be processed corresponding to the heart image sequence to be processed based on the first endocardial segmentation result in the first endocardial segmentation result; and determining a portion of the heart image sequence to be processed based on the local maximum or local minimum value in the heart chamber area-time series to be processed.

[0041] Specifically, the unprocessed cardiac chamber area-time series characterizes the sequence of changes in cardiac chamber area over time for each cardiac image in the unprocessed cardiac image sequence. The local maximum value is the maximum cardiac chamber area within a preset time period, and the local minimum value is the minimum cardiac chamber area within a preset time period. The number of image frames corresponding to the preset time period is less than the image period.

[0042] For example, suppose the local minima of the cardiac chamber area correspond to time points t1 and t2, respectively. It's important to note that the two local minima corresponding to time points t1 and t2 are non-adjacent local minima. The cardiac image sequence within the time period t1-t2 of the cardiac image sequence to be processed is considered a partial cardiac image sequence, and the cardiac chamber area-time series within the time period t1-t2 of the cardiac chamber area-time series to be processed is considered a partial cardiac chamber area-time series.

[0043] In one embodiment, optionally, before determining a portion of the heart image sequence in the heart image sequence to be processed based on at least two local maxima or local minima in the heart cavity area-time series to be processed, the method further includes: performing a filtering operation on the heart cavity area-time series to be processed to obtain a filtered heart cavity area-time series to be processed. The advantage of this setup is that it can eliminate the influence of noise points on the recognition results.

[0044] Specifically, the number of periods satisfies the formula:

[0045]

[0046] Where S1(t) represents a partial cardiac chamber area-time series, F(k) represents the Fourier transform coefficients, ω1 represents the periodic frequency, which corresponds to the peak frequency intensity in F{S1(t)}, and Z represents the set of integers.

[0047] Specifically, the number of cycles n1 = ω1, T1 = N / n1, where N represents the number of frames in a partial cardiac image sequence. Typically, T1 is a non-integer, and the image cycle T2 is obtained by rounding T1 up or down.

[0048] In one embodiment, optionally, determining a reference cardiac image sequence based on a partial cardiac image sequence, an image period, and a number of periods includes: determining at least two cardiac image sets corresponding to the partial cardiac image sequence based on the image period and the number of periods; wherein the number of cardiac images contained in each cardiac image set is the same as the image period; determining a periodic cardiac image sequence based on each cardiac image set; wherein the number of sequence frames in the periodic cardiac image sequence is the same as the image period; and determining a reference cardiac image sequence based on the number of sequence frames corresponding to the periodic cardiac image sequence and the cardiac image sequence to be processed.

[0049] In one embodiment, optionally, determining at least two sets of cardiac images corresponding to a partial cardiac image sequence based on the image period and the number of periods includes: splitting the partial cardiac image sequence based on the image period and the number of periods to obtain at least two sets of cardiac images; wherein the number of sets of cardiac images is less than or equal to the number of periods. For example, assuming the number of frames N = 39 in the partial cardiac periodic sequence, the number of periods n1 = 4, and the image period T2 obtained by rounding up is 10, then the number of sets of cardiac images obtained by splitting is 3. Alternatively, if the image period T2 obtained by rounding down is 9, then the number of sets of cardiac images obtained by splitting is 4.

[0050] In another embodiment, optionally, determining at least two sets of heart images corresponding to a partial heart image sequence based on the image period and the number of periods includes: performing an interpolation operation on the partial heart image sequence using an interpolation function to obtain an interpolated partial heart image sequence; and splitting the interpolated partial heart image sequence into n1 sets of heart images. The number of sets of heart images is equal to the number of periods.

[0051] Specifically, the number of frames in the interpolated partial cardiac image sequence is n1T2. For example, the interpolation function is CV2.resize. For instance, assuming the number of frames in the partial cardiac cycle sequence is N = 39, the number of cycles is n1 = 4, the rounded-up image cycle T2 = 10, the number of frames in the interpolated partial cardiac cycle sequence is N' = 40, and the number of sets of the resulting cardiac images is 4. Alternatively, if the rounded-up image cycle T2 = 9, the number of frames in the interpolated partial cardiac cycle sequence is N' = 36, and the number of sets of the resulting cardiac images is 4.

[0052] In one embodiment, optionally, determining a periodic heart image sequence based on each heart image set includes: determining at least two periodic phases based on the image period; for each periodic phase, acquiring at least two heart images in each heart image set corresponding to the periodic phase; determining a periodic heart image corresponding to the periodic phase based on each heart image and preset fusion parameters, and adding the periodic heart image to the periodic heart image sequence; wherein the preset fusion parameters include pixel median or pixel average.

[0053] Each periodic phase corresponds to a heart image in the heart image set. Specifically, at least two heart images with the same periodic phase from each heart image set are subjected to pixel fusion to obtain a periodic heart image sequence, wherein the number of frames in the periodic heart image sequence is the same as the image period. Figure 3 This is a schematic diagram of a periodic cardiac image sequence according to Embodiment 1 of the present invention. Specifically, pixel fusion operations are performed on the M cardiac images corresponding to each periodic phase in the set of M cardiac images to obtain a periodic cardiac image sequence.

[0054] Specifically, the periodic cardiac image sequence is copied (n1-1) or n1 times, and then stitched together to obtain a cardiac image sequence with (n1-1)T2 or n1T2 frames. An interpolation function is then used to perform an interpolation operation on this cardiac image sequence to obtain a reference cardiac image sequence. Taking the above example, the stitched cardiac image sequence has 36 or 40 frames, while the reference cardiac image sequence has 39 frames.

[0055] For example, the methods used to perform image segmentation operations include, but are not limited to, neural network algorithms, region growing algorithms, or pixel gradient segmentation methods, etc. The image segmentation method used is not limited here.

[0056] S130. Based on the second endocardial and endocardial segmentation result, perform a correction operation on the first endocardial and endocardial segmentation result to obtain the target endocardial and endocardial segmentation result.

[0057] In one embodiment, optionally, for each frame of the heart image to be processed in the heart image sequence, a first myocardial area is determined based on the first endocardial and endocardial segmentation result corresponding to the heart image to be processed, and a second myocardial area is determined based on the second endocardial and endocardial segmentation result corresponding to the heart image to be processed. If the area difference between the first myocardial area and the second myocardial area does not meet the preset area difference range, a correction operation is performed on the first endocardial and endocardial segmentation result so that the area difference between the target myocardial area determined based on the target endocardial and endocardial segmentation result and the second myocardial area meets the preset area difference range.

[0058] The technical solution of this invention determines a periodic reference heart image sequence based on the heart image sequence to be processed, and performs a correction operation on the first endocardial and endocardial segmentation result corresponding to the heart image sequence to be processed based on the second endocardial and endocardial segmentation result corresponding to the reference heart image sequence, thereby obtaining the target endocardial and endocardial segmentation result. This solves the problem that the existing technology does not consider the deformation of the heart image caused by the periodic motion of the heartbeat, improves the accuracy of the endocardial and endocardial segmentation result, and thus improves the accuracy of subsequent assessment of myocardial microcirculation disorders.

[0059] Example 2

[0060] Figure 4 This is a flowchart of a cardiac image segmentation method according to Embodiment 2 of the present invention. This embodiment further defines the correction method for the target endocardial and endocardial segmentation results in the above embodiments. Figure 4 As shown, the method includes:

[0061] S210. In response to the detection of the cardiac image sequence to be processed, perform image segmentation operation on the cardiac image sequence to be processed to obtain the first endocardial and endocardial segmentation result.

[0062] S220. Based on the heart image sequence to be processed, determine the reference heart image sequence, and perform image segmentation operation on the reference heart image sequence to obtain the second endocardial and endocardial segmentation result.

[0063] S230. Based on the second endocardial and endocardial segmentation result, perform a correction operation on the first endocardial and endocardial segmentation result to obtain the target endocardial and endocardial segmentation result.

[0064] In one embodiment, optionally, a correction operation is performed on the first endocardial and endocardial segmentation result based on the second endocardial and endocardial segmentation result to obtain the target endocardial and endocardial segmentation result. This includes: for each frame of the heart image to be processed in the heart image sequence, determining the first endocardial and endocardial segmentation position radius corresponding to the preset detection angle based on the first endocardial and endocardial segmentation result corresponding to the heart image to be processed and the preset detection angle; determining the second endocardial and endocardial segmentation position radius corresponding to the preset detection angle based on the second endocardial and endocardial segmentation result corresponding to the heart image to be processed and the preset detection angle; if the coordinate difference between the first endocardial and endocardial segmentation position radius and the second endocardial and endocardial segmentation position radius does not meet the preset coordinate difference range, then a correction operation is performed on the first endocardial and endocardial segmentation result to obtain the target endocardial and endocardial segmentation result.

[0065] Specifically, the first and second endocardial and endocardial segmentation results corresponding to each frame of the heart image sequence to be processed are represented by polar coordinates.

[0066] Specifically, the first cardiac endocardial and endocardial segmentation results include the first endocardial segmentation result and the first cardiac ectopic model segmentation result; the second cardiac endocardial and endocardial segmentation results include the second endocardial segmentation result and the second cardiac ectopic model segmentation result; and correspondingly, the segmentation location radius of the first cardiac endocardial and endocardial segments includes the segmentation location radius r of the first endocardial segmentation. inner The radius r of the first epicardial segmentation position outer The radius of the second endocardial and endocardial segmentation location includes the radius r' of the second endocardial segmentation location. inner The radius r' of the second epicardial segmentation position outer Specifically, for each frame of the heart image sequence to be processed, based on the first endocardial segmentation result and the preset detection angle, the radius r of the first endocardial segmentation position corresponding to the preset detection angle is determined. inner And based on the second endocardial segmentation result and the preset detection angle, determine the radius r' of the second endocardial segmentation position corresponding to the preset detection angle. inner If the radius r of the first endocardial segmentation location inner Radius r' of the second endocardial segmentation location inner If the endocardial coordinate difference between the two does not meet the preset endocardial coordinate difference range, a correction operation is performed on the first endocardial segmentation result to make the radius of the target endocardial segmentation position determined based on the target endocardial segmentation result and the preset detection angle equal to the radius r' of the second endocardial segmentation position. inner The difference in endocardial coordinates between the two segments meets the preset range. Based on the first epicardial segmentation result and the preset detection angle, the radius r of the first epicardial segmentation position corresponding to the preset detection angle is determined. outer Based on the second epicardial segmentation result and the preset detection angle, the radius r' of the second epicardial segmentation position corresponding to the preset detection angle is determined. outer If the radius r of the first epicardial segmentation location outer Radius r' of the second epicardial segmentation position outer If the difference in epicardial coordinates between the two segments does not meet the preset range, a correction operation is performed on the first epicardial segmentation result to make the target epicardial segmentation position radius determined based on the target epicardial segmentation result and the preset detection angle equal to the second epicardial segmentation position radius r'. outer The difference in outer membrane coordinates between them meets the preset range of outer membrane coordinate difference.

[0067] The advantage of this setting is that it allows for fine-tuning of the first endocardial and endocardial segmentation results by targeting at least one preset detection angle corresponding to the region of interest in the myocardial region, thereby further improving the accuracy of the target endocardial and endocardial segmentation results.

[0068] S240. Obtain the current heart image to be processed from the heart image sequence to be processed.

[0069] Specifically, the following operations are performed sequentially based on each frame of the heart image sequence to be processed.

[0070] S250. Based on the target endocardial and endocardial segmentation results corresponding to the current cardiac image to be processed and the preset detection angle, determine the current myocardial thickness corresponding to the preset detection angle.

[0071] Specifically, based on the target endocardial segmentation results and the preset detection angle, the coordinates of the medial myocardial position corresponding to the preset detection angle are determined; based on the target epicardial segmentation results and the preset detection angle, the coordinates of the lateral myocardial position corresponding to the preset detection angle are determined; and based on the coordinates of the medial and lateral myocardial positions, the current myocardial thickness corresponding to the preset detection angle is determined.

[0072] S260. Determine whether the current myocardial thickness meets the preset thickness range. If yes, execute S270; otherwise, execute S280.

[0073] Specifically, the preset thickness ranges corresponding to different preset detection angles can be the same or different. The thickness of the myocardium may vary at different myocardial locations. Setting different preset thickness ranges for different preset detection angles can further improve the accuracy of the subsequent corrected segmentation results of the target endocardium and endocardium.

[0074] S270. Determine whether the thickness difference between the current myocardial thickness and the previous myocardial thickness meets the preset difference range. If yes, execute S240; otherwise, execute S280.

[0075] In this embodiment, the previous myocardial thickness is determined based on the target endocardial and endocardial segmentation results of the previous heart image adjacent to the current heart image in the heart image sequence to be processed and a preset detection angle.

[0076] The advantage of this setting is that it can detect drastic changes in myocardial thickness in the cardiac image sequence to be processed, corresponding to the preset detection angle, thereby further improving the accuracy of the subsequent corrected target endocardial and endocardial segmentation results.

[0077] S280. Correct the segmentation results of the target endocardium and endocardium to obtain the corrected segmentation results of the target endocardium and endocardium.

[0078] Specifically, based on the corrected target endocardial and endocardial segmentation results and the preset detection angle, the current myocardial thickness corresponding to the preset detection angle is determined to meet the preset thickness range. In addition, based on the corrected target endocardial and endocardial segmentation results and the preset detection angle, the thickness difference between the current myocardial thickness corresponding to the preset detection angle and the previous myocardial thickness is determined to meet the preset difference range.

[0079] It should be noted that this embodiment is illustrated by determining whether the current myocardial thickness meets the preset thickness range and whether the thickness difference between the current myocardial thickness and the previous myocardial thickness meets the preset difference range. The embodiments of the present invention also include embodiments that only determine whether the current myocardial thickness meets the preset thickness range or embodiments that only determine whether the thickness difference between the current myocardial thickness and the previous myocardial thickness meets the preset difference range, which will not be described in detail here.

[0080] Based on the above embodiments, optionally, a myocardial strength sequence corresponding to the preset detection angle is determined based on the preset detection angle and the segmentation results of the target endocardium and endocardium; wherein, the myocardial strength sequence includes the myocardial strength corresponding to the preset detection angle for each heart image to be processed in the heart image sequence to be processed; based on the myocardial strength sequence, an intensity-time fitting curve is constructed, and the microcirculation perfusion rate is determined by the intensity-time fitting curve.

[0081] Specifically, the coordinates of any point in the myocardial region within any heart image in the heart image sequence to be processed can be represented as (θ, γ, t), where θ represents the preset detection angle, γ represents the radius of any point within the annular region enclosed by the segmented endocardium and epicardium of the target myocardial region, and t represents the acquisition time of the heart image to be processed. Myocardial locations with the same positional parameters (θ, γ) at different acquisition times in the heart image sequence to be processed can be considered as the same myocardial location.

[0082] Specifically, for each cardiac image to be processed, a specific myocardial region within a preset range corresponding to a specific (θ,γ) myocardial location is selected, and the average intensity within the specific myocardial region is taken as the myocardial intensity corresponding to the specific (θ,γ).

[0083] Specifically, a smoothing operation is performed on the myocardial intensity sequence, and a fitting operation is performed on the smoothed myocardial intensity sequence based on a preset exponential function to obtain an intensity-time fitting curve. The fitting method, for example, includes, but is not limited to, the least squares method.

[0084] The preset exponential function satisfies the following formula:

[0085]

[0086] Where I(t) represents the myocardial strength at time t, A is the myocardial microcirculation perfusion intensity, τ represents the time required for the myocardial strength to rise to 63% of the stable myocardial strength, which can characterize the myocardial microcirculation perfusion rate, and B represents the minimum myocardial strength after the burst.

[0087] In another embodiment, optionally, the method further includes: constructing a bullseye diagram based on at least two preset detection angles and the microcirculation perfusion velocity corresponding to each preset detection angle.

[0088] The technical solution of this embodiment, for each frame of the heart image sequence to be processed, determines the current myocardial thickness corresponding to the preset detection angle based on the target endocardial and endocardial segmentation result and the preset detection angle. When the current myocardial thickness does not meet the preset thickness range, and / or when the thickness difference between the current myocardial thickness and the previous myocardial thickness does not meet the preset difference range, the target endocardial and endocardial segmentation result is corrected to obtain the corrected target endocardial and endocardial segmentation result. This solves the problem of low accuracy of the target endocardial and endocardial segmentation result, further improves the accuracy of the target endocardial and endocardial segmentation result, and thus improves the accuracy of subsequent assessment of myocardial microcirculation disorders.

[0089] Example 3

[0090] Figure 5 This is a schematic diagram of a heart image segmentation device according to Embodiment 3 of the present invention. Figure 5 As shown, the device includes: a first endocardial and endocardial segmentation result determination module 310, a second endocardial and endocardial segmentation result determination module 320, and a target endocardial and endocardial segmentation result determination module 330.

[0091] The first endocardial and endocardial segmentation result determination module 310 is used to perform image segmentation operation on the heart image sequence to be processed in response to the detection of the heart image sequence to be processed, and obtain the first endocardial and endocardial segmentation result.

[0092] The second endocardial and endocardial segmentation result determination module 320 is used to determine a reference heart image sequence based on the heart image sequence to be processed, and to perform image segmentation operation on the reference heart image sequence to obtain the second endocardial and endocardial segmentation result; wherein, the number of sequence frames of the reference heart image sequence is the same as the number of sequence frames of the heart image sequence to be processed, and the reference heart image sequence represents a periodic heart image sequence.

[0093] The target endocardial and endocardial segmentation result determination module 330 is used to perform a correction operation on the first endocardial and endocardial segmentation result based on the second endocardial and endocardial segmentation result to obtain the target endocardial and endocardial segmentation result.

[0094] The technical solution of this embodiment determines a periodic reference heart image sequence based on the heart image sequence to be processed, and performs a correction operation on the first endocardial and endocardial segmentation result corresponding to the heart image sequence to be processed based on the second endocardial and endocardial segmentation result corresponding to the reference heart image sequence, thereby obtaining the target endocardial and endocardial segmentation result. This solves the problem that the existing technology does not consider the deformation of the heart image caused by the periodic motion of the heartbeat, improves the accuracy of the endocardial and endocardial segmentation result, and thus improves the accuracy of subsequent assessment of myocardial microcirculation disorders.

[0095] Based on the above embodiments, optionally, the second endocardial and endocardial segmentation result determination module 320 includes:

[0096] A partial cardiac chamber area-time series determination unit is used to acquire a partial cardiac image sequence from the cardiac image sequence to be processed, and to determine the partial cardiac chamber area-time series corresponding to the partial cardiac image sequence; wherein, the number of sequence frames of the partial cardiac image sequence is greater than or equal to 2 image periods;

[0097] The image period determination unit is used to perform a Fourier transform operation on a portion of the cardiac chamber area-time series to obtain the image period and the number of periods corresponding to the portion of the cardiac image sequence.

[0098] The reference cardiac image sequence determination unit is used to determine a reference cardiac image sequence based on a partial cardiac image sequence, image period, and number of periods.

[0099] Based on the above embodiments, optionally, the reference cardiac image sequence determination unit includes:

[0100] A cardiac image set determination subunit is used to determine at least two cardiac image sets corresponding to a portion of a cardiac image sequence based on the image period and the number of periods; wherein the number of cardiac images contained in each cardiac image set is the same as the number of image periods;

[0101] A periodic cardiac image sequence determination subunit is used to determine a periodic cardiac image sequence based on each cardiac image set; wherein, the number of sequence frames of the periodic cardiac image sequence is the same as the image period;

[0102] The reference cardiac image sequence determination subunit is used to determine the reference cardiac image sequence based on the number of sequence frames corresponding to the periodic cardiac image sequence and the cardiac image sequence to be processed.

[0103] Based on the above embodiments, optionally, the subunit is determined by referring to the cardiac image sequence, specifically for:

[0104] Based on the image period, determine at least two periodic phases;

[0105] For each cycle phase, acquire at least two cardiac images from each cardiac image set that correspond to the cycle phase;

[0106] Based on each cardiac image and preset fusion parameters, a periodic cardiac image corresponding to the periodic phase is determined and added to the periodic cardiac image sequence; wherein, the preset fusion parameters include the pixel median or pixel average.

[0107] Based on the above embodiments, optionally, the target endocardial and endocardial segmentation result determination module 330 is specifically used for:

[0108] For each frame of the heart image to be processed in the heart image sequence, the radius of the first endocardial and endocardial segmentation position corresponding to the preset detection angle is determined based on the first endocardial and endocardial segmentation result and the preset detection angle.

[0109] Based on the second endocardial and endocardial segmentation results corresponding to the heart image to be processed and the preset detection angle, determine the second endocardial and endocardial segmentation position radius corresponding to the preset detection angle;

[0110] If the coordinate difference between the first and second endocardial endocardial segmentation radii does not meet the preset coordinate difference range, a correction operation is performed on the first endocardial endocardial segmentation result to obtain the target endocardial endocardial segmentation result.

[0111] Optionally, based on the above embodiments, the device further includes:

[0112] The target endocardial and endocardial segmentation result correction module is used to perform a correction operation on the first endocardial and endocardial segmentation result based on the second endocardial and endocardial segmentation result to obtain the target endocardial and endocardial segmentation result. Then, for each frame of the heart image to be processed in the heart image sequence, the module determines the current myocardial thickness corresponding to the preset detection angle based on the target endocardial and endocardial segmentation result corresponding to the current heart image to be processed and the preset detection angle.

[0113] If the current myocardial thickness does not meet the preset thickness range, the target endocardial and endocardial segmentation results are corrected to obtain corrected target endocardial and endocardial segmentation results; and / or,

[0114] If the thickness difference between the current myocardial thickness and the previous myocardial thickness does not meet the preset difference range, the target endocardial and endocardial segmentation results are corrected to obtain the corrected target endocardial and endocardial segmentation results. The previous myocardial thickness is determined based on the target endocardial and endocardial segmentation results of the previous heart image adjacent to the current heart image in the heart image sequence to be processed and the preset detection angle.

[0115] Based on the above embodiments, optionally, the apparatus further includes:

[0116] The microcirculation perfusion velocity determination module is used to perform a correction operation on the first endocardial and endocardial segmentation result based on the second endocardial and endocardial segmentation result to obtain the target endocardial and endocardial segmentation result, and then determine the myocardial strength sequence corresponding to the preset detection angle based on the preset detection angle and the target endocardial and endocardial segmentation result; wherein, the myocardial strength sequence includes the myocardial strength of each heart image to be processed in the heart image sequence to be processed corresponding to the preset detection angle respectively.

[0117] Based on the myocardial intensity sequence, an intensity-time fitting curve was constructed, and the microcirculation perfusion rate was determined using the intensity-time fitting curve.

[0118] The cardiac image segmentation apparatus provided in this embodiment of the invention can execute the cardiac image segmentation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0119] Example 4

[0120] Figure 6 This is a schematic diagram of an electronic device according to Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0121] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0122] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0123] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for segmenting cardiac images.

[0124] In some embodiments, the cardiac image segmentation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the cardiac image segmentation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the cardiac image segmentation method by any other suitable means (e.g., by means of firmware).

[0125] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), dedicated cycle products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] Computer programs for implementing the cardiac image segmentation method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0127] Example 5

[0128] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a method for segmenting a heart image, the method comprising:

[0129] In response to the detection of the cardiac image sequence to be processed, an image segmentation operation is performed on the cardiac image sequence to be processed to obtain the first endocardial and endocardial segmentation result;

[0130] Based on the cardiac image sequence to be processed, a reference cardiac image sequence is determined, and image segmentation is performed on the reference cardiac image sequence to obtain a second endocardial and endocardial segmentation result; wherein, the number of sequence frames of the reference cardiac image sequence is the same as the number of sequence frames of the cardiac image sequence to be processed, and the reference cardiac image sequence represents a periodic cardiac image sequence.

[0131] Based on the second segmentation result of the endocardium and endocardium, a correction operation is performed on the first segmentation result of the endocardium and endocardium to obtain the target segmentation result of the endocardium and endocardium.

[0132] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0134] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0135] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0136] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0137] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of segmenting a cardiac image, characterized by, The method comprises: in response to detecting a to-be-processed cardiac image sequence, performing an image segmentation operation on the to-be-processed cardiac image sequence to obtain a first endocardium and epicardium segmentation result; based on the to-be-processed cardiac image sequence, determining a reference cardiac image sequence, and performing an image segmentation operation on the reference cardiac image sequence to obtain a second endocardium and epicardium segmentation result; wherein the sequence frame number of the reference cardiac image sequence is the same as the sequence frame number of the to-be-processed cardiac image sequence, and the reference cardiac image sequence represents a periodic cardiac image sequence; based on the second endocardium and epicardium segmentation result, performing a correction operation on the first endocardium and epicardium segmentation result to obtain a target endocardium and epicardium segmentation result; the method comprises: obtaining a part of the to-be-processed cardiac image sequence and determining a part of the to-be-processed cardiac image sequence corresponding to the part of the to-be-processed cardiac image sequence; wherein the sequence frame number of the part of the to-be-processed cardiac image sequence is greater than or equal to 2 image periods; performing a Fourier transform operation on the part of the to-be-processed cardiac image sequence to obtain the image period and the number of periods corresponding to the part of the to-be-processed cardiac image sequence; based on the part of the to-be-processed cardiac image sequence, the image period and the number of periods, determining a reference cardiac image sequence; the method comprises: for each to-be-processed cardiac image in the to-be-processed cardiac image sequence, based on the first endocardium and epicardium segmentation result corresponding to the to-be-processed cardiac image and a preset detection angle, determining a first endocardium and epicardium segmentation position radius corresponding to the preset detection angle; based on the second endocardium and epicardium segmentation result corresponding to the to-be-processed cardiac image and a preset detection angle, determining a second endocardium and epicardium segmentation position radius corresponding to the preset detection angle; if the coordinate difference between the first endocardium and epicardium segmentation position radius and the second endocardium and epicardium segmentation position radius does not satisfy a preset coordinate difference range, performing a correction operation on the first endocardium and epicardium segmentation result to obtain a target endocardium and epicardium segmentation result.

2. The method of claim 1, wherein, the method comprises: based on the image period and the number of periods, determining at least two cardiac image sets corresponding to the part of the to-be-processed cardiac image sequence; wherein the number of cardiac images in each cardiac image set is the same as the image period; based on each cardiac image set, determining a periodic cardiac image sequence; wherein the sequence frame number of the periodic cardiac image sequence is the same as the image period; based on the periodic cardiac image sequence and the sequence frame number corresponding to the to-be-processed cardiac image sequence, determining a reference cardiac image sequence.

3. The method of claim 2, wherein, the method comprises: based on the image period, determining at least two periodic phases; for each periodic phase, obtaining at least two cardiac images in each cardiac image set corresponding to the periodic phase; Determine a periodic cardiac image corresponding to the periodic phase based on the cardiac images and preset fusion parameters, and add the periodic cardiac image to a periodic cardiac image sequence; wherein the preset fusion parameters include a pixel median value or a pixel average value.

4. The method of claim 1, wherein, After performing the correction operation on the first endocardial and epicardial segmentation result based on the second endocardial and epicardial segmentation result to obtain the target endocardial and epicardial segmentation result, the method further comprises: For each frame of the to-be-processed cardiac image sequence, determine a current myocardial thickness corresponding to a preset detection angle based on the target endocardial and epicardial segmentation result corresponding to the current to-be-processed cardiac image and the preset detection angle; If the current myocardial thickness does not meet a preset thickness range, correct the target endocardial and epicardial segmentation result to obtain a corrected target endocardial and epicardial segmentation result; and / or, If a thickness difference between the current myocardial thickness and a previous myocardial thickness does not meet a preset difference range, correct the target endocardial and epicardial segmentation result to obtain a corrected target endocardial and epicardial segmentation result; wherein the previous myocardial thickness is determined based on a target endocardial and epicardial segmentation result corresponding to a previous to-be-processed cardiac image adjacent to the current to-be-processed cardiac image in the to-be-processed cardiac image sequence and the preset detection angle.

5. The method of claim 1, wherein, After performing the correction operation on the first endocardial and epicardial segmentation result based on the second endocardial and epicardial segmentation result to obtain the target endocardial and epicardial segmentation result, the method further comprises: Determine a myocardial intensity sequence corresponding to the preset detection angle based on the preset detection angle and the target endocardial and epicardial segmentation result; wherein the myocardial intensity sequence contains myocardial intensities corresponding to each to-be-processed cardiac image in the to-be-processed cardiac image sequence and the preset detection angle; Based on the myocardial intensity sequence, construct an intensity-time fitting curve, and determine a microcirculation perfusion velocity based on the intensity-time fitting curve.

6. An apparatus for segmenting a cardiac image, characterized by comprising: Comprise: A first endocardial and epicardial segmentation result determination module configured to, in response to detecting a to-be-processed cardiac image sequence, perform an image segmentation operation on the to-be-processed cardiac image sequence to obtain a first endocardial and epicardial segmentation result; A second endocardial and epicardial segmentation result determination module configured to determine a reference cardiac image sequence based on the to-be-processed cardiac image sequence, and perform an image segmentation operation on the reference cardiac image sequence to obtain a second endocardial and epicardial segmentation result; wherein the reference cardiac image sequence has the same number of sequence frames as the to-be-processed cardiac image sequence, and the reference cardiac image sequence represents a periodic cardiac image sequence; A target endocardial and epicardial segmentation result determination module configured to perform a correction operation on the first endocardial and epicardial segmentation result based on the second endocardial and epicardial segmentation result to obtain a target endocardial and epicardial segmentation result; The second endocardial and epicardial segmentation result determination module comprises: A partial heart chamber area-time sequence determination unit is configured to obtain a partial heart image sequence in the to-be-processed heart image sequence and determine a partial heart chamber area-time sequence corresponding to the partial heart image sequence; wherein the sequence frame number of the partial heart image sequence is greater than or equal to two image cycles; An image cycle determination unit is configured to perform a Fourier transform operation on the partial heart chamber area-time sequence to obtain an image cycle and a cycle number corresponding to the partial heart image sequence; A reference heart image sequence determination unit is configured to determine a reference heart image sequence based on the partial heart image sequence, the image cycle and the cycle number; The target endocardium-epicardium segmentation result determination module is specifically configured to, for each to-be-processed heart image in the to-be-processed heart image sequence, determine a first endocardium-epicardium segmentation position radius corresponding to a preset detection angle based on a first endocardium-epicardium segmentation result corresponding to the to-be-processed heart image and the preset detection angle; determine a second endocardium-epicardium segmentation position radius corresponding to the preset detection angle based on a second endocardium-epicardium segmentation result corresponding to the to-be-processed heart image and the preset detection angle; if a coordinate difference between the first endocardium-epicardium segmentation position radius and the second endocardium-epicardium segmentation position radius does not satisfy a preset coordinate difference range, perform a correction operation on the first endocardium-epicardium segmentation result to obtain a target endocardium-epicardium segmentation result.

7. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the heart image segmentation method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to implement the heart image segmentation method of any one of claims 1-5 when executed.

Images