A cardiovascular disease detection method based on image analysis

Abstract

The present invention discloses a cardiovascular disease detection method based on image analysis, which specifically relates to the technical field of cardiovascular disease detection; by evaluating the uniformity of microbubble distribution at the blood vessel branch and the degree of development of myocardial tissue lesions, it is judged whether further detection is needed. If further detection is needed, photoacoustic imaging technology is used to evaluate the detection accuracy of microcalcifications in the cardiovascular system by analyzing the saturation degree of the photoacoustic signal and combining it with a nonlinear signal demodulation algorithm. By analyzing the influence of the arrangement direction of cardiovascular tissue fibers on the propagation path of the optical signal, the degree of abnormal fiber structure in the lesion area is evaluated. The degree of myocardial tissue lesions, the accuracy of microcalcification detection, and the degree of abnormal fiber structure are comprehensively analyzed to evaluate the severity of cardiovascular disease, and to determine whether clinical intervention measures are needed, so as to achieve early diagnosis and accurate evaluation of cardiovascular disease and improve diagnostic efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of cardiovascular disease detection, and more specifically, to a cardiovascular disease detection method based on image analysis. Background Art

[0002] Traditional cardiovascular disease detection methods, such as electrocardiogram, ultrasound imaging, magnetic resonance imaging or CT scan, have limitations in early lesion detection and identification of microscopic tissue structural abnormalities, and it is difficult to accurately quantify abnormal myocardial fiber arrangement, microcalcifications and the degree of lesion development.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a cardiovascular disease detection method based on image analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A cardiovascular disease detection method based on image analysis comprises the following steps:

[0007] The uniformity of microbubble distribution at the vascular branches was evaluated by analyzing the flow path of microbubble angiography in ultrasound images;

[0008] Analyze the myocardial tissue shear wave propagation images obtained in ultrasonic shear wave elastography to evaluate the development of myocardial tissue lesions;

[0009] Based on the uniformity of microbubble distribution at the vascular branches and the degree of progression of myocardial tissue lesions, determine whether further testing is needed;

[0010] When further testing is needed: by analyzing the saturation of the photoacoustic imaging signal and applying a nonlinear signal demodulation algorithm, the accuracy of detecting micro-calcifications in the cardiovascular system can be evaluated; by analyzing the effect of the fiber arrangement direction of the cardiovascular tissue on the propagation path of the optical signal, the degree of abnormality of the fiber structure in the lesion area can be evaluated;

[0011] A comprehensive analysis is conducted on the degree of development of myocardial tissue lesions, the accuracy of detecting microcalcifications in the cardiovascular system, and the degree of abnormality of the fiber structure in the lesion area to assess the severity of cardiovascular disease and determine whether clinical intervention measures are needed.

[0012] In a preferred embodiment, the uniformity of microbubble distribution at the vascular branch is evaluated by analyzing the flow path of microbubble angiography in the ultrasound image, specifically:

[0013] Acquire ultrasound image data and extract microbubble signals in continuous time series;

[0014] Perform temporal and spatial registration on the extracted microbubble signals to correct the image offset caused by the cardiac cycle;

[0015] The morphological segmentation algorithm is used to separate the blood vessel branch area from the background area;

[0016] Calculate the distribution density of microbubble signals in the vascular branch area and evaluate the uniformity of microbubble distribution in the vascular branch: The calculation formula of the uniformity coefficient is: ;in, is the uniformity coefficient; is the average microbubble distribution density of all sub-areas; For the The density of microbubbles in each sub-region; is the total number of all sub-regions.

[0017] In a preferred embodiment, the myocardial tissue shear wave propagation image obtained in ultrasonic shear wave elastography is analyzed to evaluate the development degree of myocardial tissue lesions, specifically:

[0018] A high-frequency ultrasound probe is used to acquire image sequences of shear wave propagation in myocardial tissue;

[0019] The shear wave velocity is calculated by measuring the propagation time and distance of the shear wave in different myocardial tissue regions;

[0020] Based on the relationship between shear wave velocity and myocardial tissue elastic modulus, the degree of myocardial lesions is assessed.

[0021] In a preferred embodiment, based on the uniformity of microbubble distribution at the vascular branch and the degree of development of myocardial tissue lesions, it is determined whether further testing is needed, specifically:

[0022] Preset the uniformity coefficient threshold and compare the uniformity coefficient with the uniformity coefficient threshold:

[0023] When the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, it indicates that the uniformity of microbubble distribution at the blood vessel branch is high;

[0024] When the uniformity coefficient is less than the uniformity coefficient threshold, it indicates that the uniformity of microbubble distribution at the blood vessel branch is low;

[0025] Preset the development coefficient threshold and compare the development coefficient with the development coefficient threshold:

[0026] When the development coefficient is greater than the development coefficient threshold, it indicates that the development degree of the myocardial tissue lesions is fast;

[0027] When the development coefficient is less than or equal to the development coefficient threshold, it indicates that the development degree of myocardial tissue lesions is low;

[0028] When the uniformity coefficient is less than the uniformity coefficient threshold and the development coefficient is greater than the development coefficient threshold, it is determined that further detection is required; otherwise, it is determined that no further detection is required.

[0029] In a preferred embodiment, the saturation degree of the photoacoustic imaging signal is analyzed and a nonlinear signal demodulation algorithm is applied to evaluate the accuracy of detecting microcalcifications in the cardiovascular system, specifically:

[0030] Acquire intracardiac photoacoustic signals and perform preliminary denoising preprocessing;

[0031] Monitor the saturation distortion signal appearing in the photoacoustic signal;

[0032] Apply nonlinear signal demodulation algorithm to reconstruct the saturated distorted signal;

[0033] Perform time-frequency analysis on the reconstructed signal to extract high-confidence features;

[0034] Based on the high confidence features, the accuracy coefficient is calculated.

[0035] In a preferred embodiment, the abnormal degree of the fiber structure in the lesion area is evaluated by analyzing the influence of the fiber arrangement direction of the cardiovascular tissue on the propagation path of the optical signal, specifically:

[0036] Collect cardiovascular tissue optical signal data and record signal distribution at different incident angles;

[0037] Analyze the attenuation intensity of optical signals in different fiber directions;

[0038] Extracting the angular distribution characteristics of the optical signal propagation path;

[0039] Calculate the degree of deviation between the angular distribution characteristics of the optical signal propagation path and the standard fiber distribution to evaluate the degree of abnormal fiber structure in the lesion area: The calculation formula for the deviation coefficient is: ;in, is the coefficient of deviation; is the deviation degree function; is the standard fiber distribution function.

[0040] In a preferred embodiment, the degree of development of myocardial tissue lesions, the accuracy of detection of microcalcifications in cardiovascular tissues, and the degree of abnormal fiber structure in the lesion area are comprehensively analyzed to assess the severity of cardiovascular disease and determine whether clinical intervention measures are needed, specifically:

[0041] The normalized development coefficient, accuracy coefficient, and deviation coefficient are calculated to obtain the severity coefficient. The calculation formula is: ;in, is the severity coefficient; is the coefficient of deviation; is the development coefficient; is the accuracy coefficient;

[0042] Preset the severity coefficient threshold and compare the severity coefficient with the severity coefficient threshold:

[0043] When the severity coefficient is greater than the severity coefficient threshold, it indicates that the severity of cardiovascular disease is high and clinical intervention measures are required;

[0044] When the severity coefficient is less than or equal to the severity coefficient threshold, it indicates that the severity of the cardiovascular disease is low and no clinical intervention is required.

[0045] Technical effects and advantages of a cardiovascular disease detection method based on image analysis of the present invention:

[0046] The functional status of vascular branches is evaluated by the uniformity of microbubble distribution; the degree of development of myocardial tissue lesions is analyzed by shear wave propagation images; microcalcifications are accurately detected by nonlinear demodulation of the saturation degree of photoacoustic signals; and the degree of fiber abnormality is further evaluated by combining the influence of fiber arrangement direction on the propagation path of optical signals. This multi-level comprehensive analysis method can significantly improve the detection sensitivity and specificity of cardiovascular diseases and provide a reliable basis for the quantitative assessment of the severity of cardiovascular diseases. At the same time, through the comprehensive evaluation of multi-dimensional parameters, it can effectively determine whether clinical intervention measures are needed, optimize the diagnostic process, reduce the risk of missed diagnosis, and provide strong support for the early prevention, diagnosis and precision treatment of cardiovascular diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a schematic diagram of a cardiovascular disease detection method based on image analysis according to the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0049] Figure 1 The present invention provides a cardiovascular disease detection method based on image analysis, which comprises the following steps:

[0050] The uniformity of microbubble distribution at the vascular branches was evaluated by analyzing the flow path of microbubble angiography in ultrasound images;

[0051] Analyze the myocardial tissue shear wave propagation images obtained in ultrasonic shear wave elastography to evaluate the development of myocardial tissue lesions;

[0052] Based on the uniformity of microbubble distribution at the vascular branches and the degree of progression of myocardial tissue lesions, determine whether further testing is needed;

[0053] When further testing is needed: by analyzing the saturation of the photoacoustic imaging signal and applying a nonlinear signal demodulation algorithm, the accuracy of detecting micro-calcifications in the cardiovascular system can be evaluated; by analyzing the effect of the fiber arrangement direction of the cardiovascular tissue on the propagation path of the optical signal, the degree of abnormality of the fiber structure in the lesion area can be evaluated;

[0054] A comprehensive analysis is conducted on the degree of development of myocardial tissue lesions, the accuracy of detecting microcalcifications in the cardiovascular system, and the degree of abnormality of the fiber structure in the lesion area to assess the severity of cardiovascular disease and determine whether clinical intervention measures are needed.

[0055] Specifically, the uniformity of microbubble distribution at the vascular branch is evaluated by analyzing the flow path of microbubble angiography in ultrasound images, including:

[0056] Ultrasonic image data is collected through ultrasonic image acquisition equipment to extract microbubble signals in continuous time series: the ultrasonic image acquisition equipment includes a high-resolution two-dimensional ultrasonic probe that can perform real-time imaging in blood vessels and capture the dynamic process of microbubbles flowing in blood vessels. Microbubble angiography is a technology that uses the scattering characteristics of ultrasonic signals in microbubbles to enhance vascular imaging by injecting contrast agents containing gas microbubbles.

[0057] The image acquisition process of microbubble angiography relies on the ability of the ultrasound probe to transmit and receive ultrasound signals. After the probe transmits an ultrasound pulse, the ultrasound wave will be reflected back when it encounters microbubbles and received by the probe. The reflected signal of the microbubble is different from the signal of the surrounding tissue, which can effectively improve the imaging quality of blood vessels, especially in deeper vascular structures. The collected data includes information such as the location, movement trajectory, and echo intensity of the microbubbles.

[0058] Image data is stored in matrix form, denoted as , indicating that in the time frame , pixel position The grayscale intensity of the image, Represents the time frame sequence index, which represents the time sequence of image acquisition. is the image pixel coordinate, indicating the two-dimensional spatial position in the ultrasound image. In each time frame, the echo intensity of the microbubble signal is recorded. The echo intensity is calculated from the ultrasound amplitude reflected by the contrast microbubble and is defined as: ;in, Indicated in time frame , pixel position The microbubble signal intensity at represents the amplitude of the ultrasonic signal reflected by the microbubbles in the ultrasound image. It is the calibration coefficient of the ultrasonic image acquisition device, which is used to adjust the proportional relationship between the image grayscale intensity and the true ultrasonic echo amplitude. It can be preset or automatically calibrated according to different ultrasonic image acquisition devices and imaging conditions.

[0059] Perform temporal and spatial registration of the extracted microbubble signals to correct image deviation caused by the cardiac cycle: Since the contraction and relaxation of the heart caused by the cardiac cycle will lead to dynamic changes in the geometric structure of the blood vessels, it is necessary to perform spatial and temporal registration of the images in the continuous time series to eliminate the influence of cardiac motion on image stability.

[0060] To achieve spatial correction, a phase-correlation-based image registration method is used. First, the cross-correlation function between consecutive time frames is calculated: ;in, Pixel offset The mutual correlation coefficient below reflects the matching degree of two frames of images; It is the pixel offset between two adjacent frames of images, which is used to correct the change of spatial position; For the time frame The pixel intensity value after the shift.

[0061] Shift all time frame images by pixel Perform spatial translation compensation to complete spatial registration.

[0062] For time registration, the signal change rate between consecutive time frames is calculated to correct the periodic fluctuation of the signal caused by the cardiac cycle. Normalized time signal difference is introduced: ;in, is the time registration difference coefficient, which is used to measure the degree of signal change in adjacent time frames; Indicated in time frame , pixel position The gray intensity of the image; if If it is greater than the set threshold (such as 10% of the peak value of the cardiac cycle signal), it is determined to be an image offset caused by the cardiac cycle, and the time axis alignment is adjusted.

[0063] The morphological segmentation algorithm is used to separate the vascular branch area from the background area: After completing the time and space registration, the vascular branch area needs to be identified. Gaussian smoothing is performed on the ultrasound image to reduce noise interference: ;in, is the gray value of the image after Gaussian smoothing; is the standard deviation of the Gaussian kernel, indicating the degree of smoothness and controlling the blurriness of the filter; is the pixel coordinate of the center of the image, which is used to determine the center position of the Gaussian kernel.

[0064] Adopt adaptive threshold segmentation algorithm to segment blood vessel area. Define pixel gray intensity threshold , binarization is performed according to the pixel gray intensity threshold to obtain the vascular area mask :

[0065] ; When the gray value of the image after Gaussian smoothing is greater than or equal to the pixel gray intensity threshold, the pixel is marked as 1 (vascular branch area), otherwise it is marked as 0 (background area).

[0066] Calculate the distribution density of microbubble signals in the vascular branch area and evaluate the uniformity of microbubble distribution in the vascular branch: Calculate the distribution density of microbubble signals based on the identified vascular branch area. Divide the vascular branch area into different sub-areas, and the pixel set of each sub-area is , microbubble signal intensity , distribution density Calculated as: ;in, For the The density of microbubbles in each sub-region; For the The pixel set of a sub-region represents the set of all pixel points in the region; For the The total number of pixels in a sub-region, indicating the number of pixels in the region.

[0067] Based on the microbubble distribution density in the sub-region, the uniformity coefficient of microbubble distribution in the vascular branch region is calculated: ;in, is the uniformity coefficient; is the average microbubble distribution density of all sub-areas; For the The density of microbubbles in each sub-region; is the total number of all sub-regions.

[0068] The larger the uniformity coefficient, the more uniform the distribution of microbubble signals in the vascular branch area, and the more consistent the concentration of microbubbles in the vascular branch area, indicating that the blood flow dynamics are relatively stable, and there is no obvious deviation or unevenness in the distribution of microbubbles in the vascular branch, which can better reflect the state of blood flow in the blood vessels and the flow path of microbubbles. The uniform distribution of microbubble signals helps to improve the quality of imaging, making the image enhancement effect clearer and more stable, and helps to more accurately identify potential lesion areas.

[0069] Specifically, the myocardial tissue shear wave propagation images obtained in ultrasonic shear wave elastography are analyzed to evaluate the development of myocardial tissue lesions, including:

[0070] Use a high-frequency ultrasound probe to obtain an image sequence of shear wave propagation in myocardial tissue: Use a high-frequency ultrasound probe to perform ultrasonic shear wave elastography of myocardial tissue. A short-term high-intensity sound beam is applied to a specific section of the chest wall to stimulate shear waves, and the tissue movement caused by shear wave propagation is recorded.

[0071] Image data is stored in a three-dimensional matrix, defined as: , for the time , spatial location The ultrasonic image pixel intensity value at represents the grayscale intensity of the reflected signal; represents an image sequence index, which represents ultrasound image frames in different imaging planes or different sampling batches; represents the time frame index, which indicates the time series of image acquisition; are pixel coordinates in three-dimensional space, representing the horizontal position, vertical position, and depth direction in the image respectively.

[0072] The shear wave localization algorithm based on phase coherence is used to identify and track the propagation path of the shear wave in the myocardial tissue: the acquired image sequence is subjected to shear wave detection, and the shear wave detection algorithm based on phase coherence is used to enhance the recognizability of the shear wave signal in the myocardial tissue.

[0073] Calculate the phase coherence coefficient: ;in, For in time , spatial location The phase coherence coefficient at is used to evaluate the stability of the ultrasonic signal and the clarity of the shear wave front; Indicates Frame image corresponding to pixels The instantaneous phase angle at , in radians; is an imaginary unit; Indicates the total number of time frames used to compute the coherence.

[0074] When the phase coherence coefficient is greater than the set threshold, it is determined to be a shear wave propagation path.

[0075] The shear wave velocity is calculated by measuring the propagation time and distance of the shear wave in different myocardial tissue areas: based on the identified shear wave propagation path, the relationship between the position of the wavefront and time is extracted, and the propagation velocity of the shear wave is calculated.

[0076] The shear wave velocity calculation formula is: ;in, is the shear wave propagation velocity, which indicates the propagation rate of the shear wave in the myocardial tissue; is the shear wave front in the time interval The propagation distance within is in meters; is the time interval for the shear wave front to propagate, in seconds.

[0077] Based on the relationship between shear wave velocity and myocardial tissue elastic modulus, the degree of myocardial lesions is evaluated: there is the following relationship between shear wave propagation velocity and myocardial tissue elastic modulus: ;in, is the Young's modulus of myocardial tissue; Myocardial tissue density.

[0078] In order to evaluate the degree of myocardial lesions, the coefficient of variation of the elastic modulus was calculated, and the calculation formula was: ;in, is the coefficient of variation of elastic modulus; is the standard deviation of elastic modulus; is the average value of the elastic modulus.

[0079] According to the coefficient of variation of shear wave propagation velocity and elastic modulus, the development coefficient is calculated as follows: ;in, is the development coefficient; is the coefficient of variation of elastic modulus; is the shear wave propagation velocity; are the weight coefficients of shear wave propagation velocity and elastic modulus variation coefficient, respectively.

[0080] The larger the development coefficient, the faster the myocardial lesions develop. A larger severity coefficient indicates that there are obvious abnormalities in the elastic modulus distribution of myocardial tissue. For example, a significant increase in the elastic modulus may correspond to a fibrotic or sclerotic area, reflecting an increase in myocardial tissue stiffness, which is usually related to the progression of diseases such as myocardial remodeling, myocardial fibrosis, and heart failure. At the same time, an increase in the development coefficient may also reflect the presence of a staggered distribution of local high-hardness and low-hardness areas, which means that there are complex lesions inside the myocardial tissue.

[0081] Specifically, based on the uniformity of microbubble distribution at the vascular branches and the degree of progression of myocardial tissue lesions, it is determined whether further testing is needed, including:

[0082] Preset the uniformity coefficient threshold and compare the uniformity coefficient with the uniformity coefficient threshold:

[0083] When the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, it indicates that the uniformity of microbubble distribution at the blood vessel branch is high;

[0084] When the uniformity coefficient is less than the uniformity coefficient threshold, it indicates that the uniformity of the microbubble distribution at the blood vessel branch is low.

[0085] Preset the development coefficient threshold and compare the development coefficient with the development coefficient threshold:

[0086] When the development coefficient is greater than the development coefficient threshold, it indicates that the development degree of the myocardial tissue lesions is fast and the myocardial tissue is in a pathological state;

[0087] When the development coefficient is less than or equal to the development coefficient threshold, it indicates that the development degree of the myocardial tissue lesions is low and the myocardial tissue is in a normal state.

[0088] When the uniformity coefficient is less than the uniformity coefficient threshold and the development coefficient is greater than the development coefficient threshold, it is determined that further detection is required; otherwise, it is determined that no further detection is required.

[0089] Specifically, by analyzing the saturation of photoacoustic imaging signals and applying nonlinear signal demodulation algorithms, the accuracy of detecting microcalcifications in cardiovascular tissues is evaluated, including:

[0090] Acquire the photoacoustic signal in the cardiovascular system and perform preliminary denoising preprocessing: The photoacoustic signal in the cardiovascular system is collected by photoacoustic imaging equipment. When the photoacoustic signal propagates in the cardiovascular tissue, it will be interfered by noise, including system noise and environmental noise. To ensure the high-quality acquisition of the photoacoustic signal, a bandwidth optimization filter is used to select the frequency domain range of the photoacoustic signal, and a multi-layer low-pass filter is used to eliminate high-frequency noise components. In the signal time domain, a processing method based on an adaptive filtering algorithm is used to attenuate possible artifacts. Assume that the collected signal is a function , the signal after denoising can be expressed as: ;in, represents the photoacoustic signal after denoising preprocessing; represents the original acquired photoacoustic signal; represents the environmental noise signal component; Represents the system noise signal component, which comes from the electronic noise inside the photoacoustic imaging device; is the time variable.

[0091] Monitor the saturation distortion signal in the photoacoustic signal: In the photoacoustic signal acquisition, the saturation phenomenon is mainly due to the nonlinear response of the receiving end caused by the high-energy laser pulse. The dynamic threshold method is used to detect the saturation area of ​​the photoacoustic signal. Implement partitioned recording. The saturation zone can be defined by the following formula: ;in, Represents the set of detected saturation time periods, including the set of all time points that meet the saturation conditions; is the time threshold.

[0092] During the detection process, the saturation distortion signal is distinguished from the normal signal, which are and ;in, Indicates a saturated distorted signal that requires nonlinear correction; Indicates a normal signal where saturation has not occurred.

[0093] Apply nonlinear signal demodulation algorithm to reconstruct saturated distorted signal: For signal distortion in saturation area, nonlinear signal demodulation algorithm is used to correct it. According to the signal model of saturation area, nonlinear relationship is established: ;in, represents a true signal; represents the linear gain coefficient; Represents the nonlinear distortion coefficient, which indicates the contribution of second harmonic distortion.

[0094] Minimize the objective function by iteratively :

[0095] , constantly adjusting the real signal The value of the iterative minimization objective function is minimized. When the value of the iterative minimization objective function converges to the minimum value, the real signal The optimal estimate of is the reconstructed signal ,Right now ;in, To minimize the objective function.

[0096] Perform time-frequency analysis on the reconstructed signal to extract high-confidence features: , short-time Fourier transform is used to analyze its time-frequency characteristics, the formula is as follows:

[0097] ;in, is the time-frequency distribution result of the reconstructed signal, represents the reconstruction signal; is the window function; is a time variable, representing the central time point in the short-time Fourier transform; is a frequency variable, which represents the frequency distribution of the reconstructed signal in the time-frequency plane; Is an imaginary unit.

[0098] Through time-frequency analysis, the local energy distribution of the signal can be extracted, and a set of feature vectors can be constructed based on the signal amplitude and frequency distribution. The main goal of feature extraction is to locate the high energy peak of the calcification area and reduce the influence of background interference signals.

[0099] Based on the high confidence features, calculate the accuracy coefficient: based on the feature vector , and the standard template vector of the calcification signal Perform cosine similarity matching and calculate the accuracy coefficient. The accuracy coefficient calculation formula is: ;in, is the accuracy coefficient; is the number of features that were successfully matched; is the total number of features.

[0100] The larger the accuracy coefficient, the more accurate the detection results of cardiovascular microcalcifications analyzed by photoacoustic imaging signals. During the photoacoustic signal analysis process, the degree of saturation reflects the nonlinear distortion that may exist at the signal receiving end. After correcting the saturated signal through a nonlinear signal demodulation algorithm, signal features that are closer to the real thing can be extracted. The accuracy coefficient is calculated by comparing the degree of feature matching between the reconstructed signal and the calcification standard template signal. The closer the value is to 1, the higher the signal matching degree is, that is, the detected calcification target is more consistent with the calcification distribution characteristics in the real tissue. A larger accuracy coefficient means a higher recognition accuracy of the calcification area.

[0101] Specifically, by analyzing the effect of the fiber arrangement direction of cardiovascular tissue on the propagation path of the optical signal, the abnormal degree of the fiber structure in the lesion area is evaluated, including:

[0102] Collecting cardiovascular tissue optical signal data and recording signal distribution at different incident angles: Using high-resolution optical imaging equipment to collect optical signals from cardiovascular tissue samples, the equipment emits optical signals with controllable incident angles to analyze the effect of fiber direction on the light propagation path. ( The light intensity distribution is recorded using a light detector on the back or side of the sample. ;in, The incident angle is At the coordinate The optical signal intensity distribution at Indicates Sub-light signal incident angle; is the initial intensity of the light source; The incident angle is The light attenuation coefficient when Represents the optical signal from the light source to the detection point in the plane coordinate system propagation distance.

[0103] Analyze the attenuation intensity of the optical signal in different fiber directions: After recording the distribution of multiple incident angle signals, analyze the attenuation of the optical signal along the fiber direction and perpendicular to the fiber direction to quantify the impact of different fiber directions on light propagation. Calculate the attenuation intensity of the optical signal , defined as: ;in, The incident angle is The attenuation intensity of the optical signal; The incident angle is Next, coordinates The optical signal intensity recorded at Represents the straight-line distance that light travels.

[0104] Extract the angular distribution characteristics of the optical signal propagation path: In order to quantify the propagation path characteristics of the optical signal inside the tissue, the signal propagation angular distribution characteristics are extracted based on the attenuation intensity of the optical signal. Define the signal propagation path angular distribution function :

[0105] ;in, is the angle distribution function; Angular variation of the direction of signal propagation.

[0106] Calculate the deviation between the angular distribution characteristics of the optical signal propagation path and the standard fiber distribution to assess the degree of abnormal fiber structure in the lesion area: standard fiber distribution function It can be measured by healthy tissue samples and define the degree of deviation function for: ;in, is the deviation degree function; is the standard fiber distribution function.

[0107] The larger the deviation coefficient, the more obvious the abnormality of the fiber structure of cardiovascular tissue. The fiber direction of normal cardiovascular tissue usually has a more consistent light signal propagation path, and its attenuation and direction distribution are relatively regular; while abnormal cardiovascular tissue may cause the light propagation path to be dispersed or the light attenuation to be uneven, making the angle distribution deviate more obviously from the standard template. Therefore, the larger the deviation coefficient, the more irregular the fiber arrangement is, which can be used as a quantitative indicator to evaluate the area of ​​cardiovascular disease, which is helpful for auxiliary diagnosis and early disease screening.

[0108] Specifically, the degree of development of myocardial tissue lesions, the accuracy of detection of microcalcifications in the cardiovascular system, and the degree of abnormal fiber structure in the lesion area are comprehensively analyzed to assess the severity of cardiovascular disease and determine whether clinical intervention measures are needed, including:

[0109] The development coefficient corresponding to the development degree of myocardial tissue lesions, the accuracy coefficient corresponding to the detection accuracy of cardiovascular microcalcifications, and the deviation coefficient corresponding to the abnormal degree of fiber structure in the lesion area are normalized respectively, and the normalized development coefficient, accuracy coefficient, and deviation coefficient are calculated to obtain the severity coefficient. The calculation formula is: ;in, is the severity coefficient; is the coefficient of deviation; is the development coefficient; is the accuracy coefficient.

[0110] Preset the severity coefficient threshold and compare the severity coefficient with the severity coefficient threshold:

[0111] When the severity coefficient is greater than the severity coefficient threshold, it indicates that the severity of cardiovascular disease is high and clinical intervention measures are required; clinical intervention measures include advanced imaging examinations (such as high-resolution magnetic resonance imaging, computed tomography), interventional treatments (such as stent implantation, angioplasty) or drug treatments (such as anti-fibrotic drugs, anti-inflammatory drugs). In addition, it is necessary to develop personalized treatment plans for patients to prevent further progression of cardiovascular disease and the occurrence of potential complications;

[0112] When the severity coefficient is less than or equal to the severity coefficient threshold, it indicates that the severity of the cardiovascular disease is low and no clinical intervention is required.

[0113] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0114] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0115] Those of ordinary skill in the art will appreciate that the modules 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. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0118] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0120] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0121] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0122] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cardiovascular disease detection method based on image analysis, characterized in that: The steps include: The uniformity of microbubble distribution at the vascular branches was evaluated by analyzing the flow path of microbubble angiography in ultrasound images; Analyze the myocardial tissue shear wave propagation images obtained in ultrasonic shear wave elastography to evaluate the development of myocardial tissue lesions; Based on the uniformity of microbubble distribution at the vascular branches and the degree of progression of myocardial tissue lesions, determine whether further testing is needed; When further testing is needed: by analyzing the saturation of the photoacoustic imaging signal and applying a nonlinear signal demodulation algorithm, the accuracy of detecting micro-calcifications in the cardiovascular system can be evaluated; by analyzing the effect of the fiber arrangement direction of the cardiovascular tissue on the propagation path of the optical signal, the degree of abnormality of the fiber structure in the lesion area can be evaluated; A comprehensive analysis is conducted on the degree of development of myocardial tissue lesions, the accuracy of detecting microcalcifications in the cardiovascular system, and the degree of abnormality of the fiber structure in the lesion area to assess the severity of cardiovascular disease and determine whether clinical intervention measures are needed.

2. A cardiovascular disease detection method based on image analysis according to claim 1, characterized in that: The uniformity of microbubble distribution at the vascular branch was evaluated by analyzing the flow path of microbubble angiography in ultrasound images, specifically: Acquire ultrasound image data and extract microbubble signals in continuous time series; Perform temporal and spatial registration on the extracted microbubble signals to correct the image offset caused by the cardiac cycle; The morphological segmentation algorithm is used to separate the blood vessel branch area from the background area; Calculate the distribution density of microbubble signals in the vascular branch area and evaluate the uniformity of microbubble distribution in the vascular branch: The calculation formula of the uniformity coefficient is: ;in, is the uniformity coefficient; is the average microbubble distribution density of all sub-areas; For the The density of microbubbles in each sub-region; is the total number of all sub-regions.

3. A cardiovascular disease detection method based on image analysis according to claim 2, characterized in that: The myocardial tissue shear wave propagation images obtained in ultrasonic shear wave elastography were analyzed to evaluate the development of myocardial tissue lesions, specifically: A high-frequency ultrasound probe is used to acquire image sequences of shear wave propagation in myocardial tissue; The shear wave velocity is calculated by measuring the propagation time and distance of the shear wave in different myocardial tissue regions; Based on the relationship between shear wave velocity and myocardial tissue elastic modulus, the degree of myocardial lesions is assessed.

4. A cardiovascular disease detection method based on image analysis according to claim 3, characterized in that: Based on the uniformity of microbubble distribution at the vascular branches and the degree of progression of myocardial tissue lesions, it is determined whether further testing is needed, specifically: Preset the uniformity coefficient threshold and compare the uniformity coefficient with the uniformity coefficient threshold: When the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, it indicates that the uniformity of microbubble distribution at the blood vessel branch is high; When the uniformity coefficient is less than the uniformity coefficient threshold, it indicates that the uniformity of microbubble distribution at the blood vessel branch is low; Preset the development coefficient threshold and compare the development coefficient with the development coefficient threshold: When the development coefficient is greater than the development coefficient threshold, it indicates that the development degree of the myocardial tissue lesions is fast; When the development coefficient is less than or equal to the development coefficient threshold, it indicates that the development degree of myocardial tissue lesions is low; When the uniformity coefficient is less than the uniformity coefficient threshold and the development coefficient is greater than the development coefficient threshold, it is determined that further detection is required; otherwise, it is determined that no further detection is required.

5. A cardiovascular disease detection method based on image analysis according to claim 4, characterized in that: By analyzing the saturation of photoacoustic imaging signals and applying nonlinear signal demodulation algorithms, the accuracy of detecting microcalcifications in cardiovascular tissues was evaluated. Specifically: Acquire intracardiac photoacoustic signals and perform preliminary denoising preprocessing; Monitor the saturation distortion signal appearing in the photoacoustic signal; Apply nonlinear signal demodulation algorithm to reconstruct the saturated distorted signal; Perform time-frequency analysis on the reconstructed signal to extract high-confidence features; Based on the high confidence features, the accuracy coefficient is calculated.

6. A cardiovascular disease detection method based on image analysis according to claim 5, characterized in that: By analyzing the influence of the fiber arrangement direction of cardiovascular tissue on the propagation path of optical signals, the abnormal degree of fiber structure in the lesion area is evaluated, specifically: Collect cardiovascular tissue optical signal data and record signal distribution at different incident angles; Analyze the attenuation intensity of optical signals in different fiber directions; Extracting the angular distribution characteristics of the optical signal propagation path; Calculate the degree of deviation between the angular distribution characteristics of the optical signal propagation path and the standard fiber distribution to evaluate the degree of abnormal fiber structure in the lesion area: The calculation formula for the deviation coefficient is: ;in, is the coefficient of deviation; is the deviation degree function; is the standard fiber distribution function.

7. A cardiovascular disease detection method based on image analysis according to claim 6, characterized in that: Comprehensively analyze the development of myocardial tissue lesions, the accuracy of detecting microcalcifications in the cardiovascular system, and the abnormality of the fiber structure in the lesion area to assess the severity of cardiovascular disease and determine whether clinical intervention measures are needed, specifically: The normalized development coefficient, accuracy coefficient, and deviation coefficient are calculated to obtain the severity coefficient. The calculation formula is: ;in, is the severity coefficient; is the coefficient of deviation; is the development coefficient; is the accuracy coefficient; Preset the severity coefficient threshold and compare the severity coefficient with the severity coefficient threshold: When the severity coefficient is greater than the severity coefficient threshold, it indicates that the severity of cardiovascular disease is high and clinical intervention measures are required; When the severity coefficient is less than or equal to the severity coefficient threshold, it indicates that the severity of the cardiovascular disease is low and no clinical intervention is required.

Images