System for detection of myocardial infarction based on diffusion speckle

Abstract

The application provides a myocardial infarction detection system based on diffusion speckle, and relates to the field of wearable health detection.The system comprises a laser for exciting a laser signal;an optical fiber probe connected with the laser through a multimode optical fiber for guiding the laser signal to a to-be-detected object and collecting a reflected light signal of the to-be-detected object;a camera connected with the optical fiber probe through a multimode optical fiber for obtaining a diffusion speckle image based on the reflected light signal;and a processing device electrically connected with the camera for obtaining an initial blood perfusion index signal and an initial pulse wave signal based on the diffusion speckle image, reconstructing the initial blood perfusion index signal and the initial pulse wave signal respectively to obtain a target blood perfusion index signal and a target pulse wave signal, and performing myocardial infarction detection based on the target blood perfusion index signal and the target pulse wave signal.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wearable health detection, in particular to a myocardial infarction detection system based on diffusion speckle. BACKGROUND

[0002] Myocardial infarction (MI) is a serious cardiovascular disease caused by acute obstruction of coronary arteries, leading to myocardial ischemia, hypoxia, and even necrosis. It is extremely harmful, not only causing acute symptoms such as chest pain, dyspnea, and arrhythmia, but also possibly causing cardiogenic shock and cardiac arrest in severe cases. Therefore, early detection and warning of myocardial infarction is of great significance.

[0003] Currently, real-time detection functions of wearable devices can timely detect potential risk signals such as abnormal electrocardiogram and heart rate variability, thereby improving the prevention and control level of cardiovascular diseases. However, there are still many problems and limitations in the early detection and warning of myocardial infarction. First, the detection accuracy of the device is limited, especially in complex environments or user activity states, the electrocardiogram signal is easily disturbed by noise, which may cause false positives or false negatives. Second, the data processing algorithm is not mature, and the AI (Artificial Intelligence) model relied on by most devices still has a high false positive rate in identifying specific electrocardiogram features of myocardial infarction. SUMMARY

[0004] Based on the above problems, the present application provides a myocardial infarction detection system based on diffusion speckle, comprising:

[0005] a laser for exciting a laser signal; an optical fiber probe connected to the laser through a multimode optical fiber for guiding the laser signal to a to-be-detected object and collecting a reflected light signal of the to-be-detected object; a camera connected to the optical fiber probe through a multimode optical fiber for obtaining a diffusion speckle image based on the reflected light signal; and a processing device electrically connected to the camera for obtaining an initial blood perfusion index signal and an initial pulse wave signal based on the diffusion speckle image, the processing device performing signal reconstruction on the initial blood perfusion index signal and the initial pulse wave signal respectively to obtain a target blood perfusion index signal and a target pulse wave signal, and performing myocardial infarction detection based on the target blood perfusion index signal and the target pulse wave signal.

[0006] According to the embodiments of the present application, the processing device is configured to perform empirical mode decomposition on any one of the initial blood perfusion index signal and the initial pulse wave signal to obtain a plurality of first modal components; perform screening on the plurality of first modal components based on frequency domain kurtosis and energy proportion to obtain a plurality of second modal components; perform variational mode decomposition on the plurality of second modal components to obtain a plurality of third modal components; and perform signal reconstruction based on the plurality of third modal components to obtain the target blood perfusion index signal and the target pulse wave signal.

[0007] According to an embodiment of the present application, the processing device is further configured to inject Gaussian noise into the initial signal based on the plurality of noise coefficients to obtain a plurality of signals to be decomposed; perform empirical mode decomposition on the signals to be decomposed to obtain a plurality of initial modal components of the target order; and obtain a first modal component of the signal to be decomposed based on an average value of the plurality of initial modal components to obtain a plurality of first modal components.

[0008] According to an embodiment of the present application, the processing device is further configured to calculate a frequency domain kurtosis and an energy proportion of each of the plurality of first modal components; and select, from the plurality of first modal components, a modal component whose frequency domain kurtosis is greater than a first preset value and whose energy proportion is greater than a second preset value to obtain a plurality of second modal components.

[0009] According to an embodiment of the present application, the processing device is further configured to perform spectral peak search based on the plurality of second modal components to obtain a plurality of peak frequencies; perform clustering based on the plurality of peak frequencies to obtain a center frequency; and perform variational mode decomposition on each of the plurality of second modal components based on the center frequency to obtain a plurality of third modal components.

[0010] According to an embodiment of the present application, the processing device is further configured to accumulate the plurality of third modal components to obtain a target blood perfusion index signal and the target pulse wave signal.

[0011] According to an embodiment of the present application, the processing device is further configured to perform joint feature extraction on the target blood perfusion index signal and the target pulse wave signal to obtain a correlation feature; and perform myocardial infarction detection based on the correlation feature.

[0012] According to an embodiment of the present application, the processing device is further configured to divide the target blood perfusion index signal into a plurality of first sub-signals and divide the target pulse wave signal into a plurality of second sub-signals based on a preset window and a preset step size; perform correlation calculation based on the plurality of first sub-signals and the plurality of second sub-signals to obtain a first-order correlation coefficient matrix; perform normalization processing on the first-order correlation coefficient matrix to obtain a second-order correlation coefficient matrix; and perform matrix multiplication on the first-order correlation coefficient matrix and the second-order correlation coefficient matrix to obtain the correlation feature.

[0013] According to an embodiment of the present application, the processing device is further configured to perform correlation calculation on the first sub-signals and the second sub-signals corresponding to the same window to obtain a plurality of low-order frequency components; and obtain the first-order correlation coefficient matrix based on the plurality of low-order frequency components.

[0014] According to an embodiment of the present application, the processing device is further configured to split the correlation feature to obtain a plurality of feature blocks; encode each of the plurality of feature blocks to obtain a plurality of bottleneck features; and input the plurality of bottleneck features into a classifier to obtain a myocardial infarction detection result.

[0015] The application realizes the simultaneous detection of blood perfusion index signals and pulse wave signals based on the diffusion speckle principle, and performs myocardial infarction detection based on the reconstructed two signals. On the one hand, the multi-modal detection provides more dimensional information for the application; on the other hand, the signal reconstruction process significantly improves the signal-to-noise ratio of the signal and enhances the signal feature recognition, thereby reducing the signal interference caused by human body activities and external environmental factors. Therefore, the precision of the myocardial infarction detection system provided by the application is improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present application will become more apparent from the following description of embodiments of the present application, taken in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A principle diagram of a myocardial infarction detection system based on diffusion speckle according to an embodiment of the present application is shown.

[0018] Figure 2 An initial signal processing flowchart according to an embodiment of the present application is shown.

[0019] Figure 3 A flowchart of a correlation feature extraction method according to an embodiment of the present application is shown.

[0020] Figure 4 A principle diagram of obtaining a myocardial infarction detection result from a correlation feature according to an embodiment of the present application is shown.

[0021] Figure 5 A myocardial infarction detection flowchart according to an embodiment of the present application is shown.

[0022] Figure 6 Initial blood perfusion signals and initial pulse wave signals of rabbits measured in an experiment according to an embodiment of the present application are shown.

[0023] Figure 7 A plurality of first modal components obtained based on the initial blood perfusion signals and the initial pulse wave signals of rabbits in an experiment according to an embodiment of the present application are shown.

[0024] Figure 8 A plurality of second modal components obtained based on the frequency domain kurtosis and energy proportion method in an experiment according to an embodiment of the present application are shown.

[0025] Figure 9 A plurality of third modal components obtained in an experiment according to an embodiment of the present application are shown.

[0026] Figure 10 A reconstructed signal obtained in an experiment according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to specific embodiments and drawings.

[0028] The terms used herein are merely used to describe specific embodiments, and are not intended to limit the present application. The terms "include", "contain" and the like used herein indicate the presence of the described features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0029] All terms used herein, including technical and scientific terms, have meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the present specification, and should not be interpreted in an idealized or overly formal manner.

[0030] Traditional myocardial infarction detection devices only analyze pulse wave signals, such as detecting pulse wave amplitude, waveform symmetry, etc., but these features often cannot fully reflect the complex morphology of the cardiovascular system, especially the changes in microcirculation and hemodynamics.

[0031] Therefore, based on the principle of diffuse speckle, the present application simultaneously measures blood perfusion signals and pulse wave signals, and combines the two signals to more comprehensively depict the dynamic response of the cardiovascular system. Blood perfusion signals can reflect key physiological parameters such as microcirculation state, vascular elasticity and blood flow resistance, while pulse wave signals can reflect blood volume changes and heart pumping function. The combined analysis of the two improves the accuracy of myocardial infarction detection.

[0032] Figure 1 A schematic diagram of a diffuse speckle-based myocardial infarction detection system according to an embodiment of the present application is shown.

[0033] As shown in Figure 1 The diffuse speckle-based myocardial infarction detection system can include a laser 10, a fiber probe 20, a camera 30 and a processing device 40.

[0034] The laser 10 is used to excite a laser signal; the fiber probe 20 is connected to the laser through a multi-mode optical fiber, and is used to direct the laser signal to the object to be measured and collect the reflected light signal of the object to be measured; the camera 30 is connected to the fiber probe through a multi-mode optical fiber, and is used to obtain a diffuse speckle image based on the reflected light signal; and the processing device 40 is electrically connected to the camera, and is used to obtain an initial blood perfusion index signal and an initial pulse wave signal based on the diffuse speckle image. The processing device 40 respectively reconstructs the initial blood perfusion index signal and the initial pulse wave signal to obtain a target blood perfusion index signal and a target pulse wave signal, and performs myocardial infarction detection based on the target blood perfusion index signal and the target pulse wave signal.

[0035] According to an embodiment of the present application, the laser 10 can be a near-infrared semiconductor laser. The light emission of the near-infrared semiconductor laser is based on the stimulated radiation of a semiconductor PN junction (Positive-Negative Junction). When a forward bias is applied to the PN junction of the laser, the external current will cause the holes in the P region and the electrons in the N region to migrate to the active layer in the middle. In the active layer, the number of high-energy level electrons is much greater than the number of low-energy level holes. At this time, the high-energy level electrons will jump to the low-energy level under the excitation of external photons or spontaneous emission photons of themselves, and release energy to form stimulated radiation photons. These photons are reflected and amplified in the resonant cavity of the laser, and finally form a near-infrared laser with good monochromaticity and strong directivity, which is emitted from the output end of the resonant cavity.

[0036] The laser emitted by the laser 10 is further precisely guided to the object to be measured 50 by the optical fiber probe 20, wherein the object to be measured can be human tissue. The optical fiber probe 20 is usually composed of a core and a cladding. When the near-infrared laser emitted by the laser 10 is incident to the interface between the core and the cladding at an angle smaller than the critical angle, the light will be totally reflected at the interface. This total reflection will continue to occur along the length direction of the optical fiber, so that the optical signal is almost losslessly transmitted from the incident end to the human tissue to be measured, thereby avoiding the diffusion or absorption of the light in the transmission process. Similarly, the reflected light signal after interacting with the object to be measured 50 will also be collected by the optical fiber probe according to the same total reflection principle, and is conducted to the camera 30 through the multimode optical fiber.

[0037] According to an embodiment of the present application, the camera 30 can be a CCD (Charge-coupled Device) camera. When the reflected light signal conducted through the multimode optical fiber irradiates the photosensitive cell array of the CCD, the photosensitive cell converts the photons into photo-generated charges proportional to the light intensity through the photoelectric effect. The bright and dark particle characteristics of the speckle will correspondingly form the charge distribution difference of different pixel positions. Subsequently, under the control of the driving circuit, these photo-generated charges are sequentially transferred to the register along the vertical and horizontal directions. The charges transferred to the signal amplifier are amplified, and then converted into digital signals by the analog-to-digital converter, and then arranged to generate a digital image, i.e., a diffuse speckle image.

[0038] The diffuse speckle image is further transmitted to the processing device 40. Based on the diffuse speckle image, the processing device 40 obtains an initial blood perfusion index signal and an initial pulse wave signal through image processing and calculation.

[0039] According to the principle of diffuse speckle, the speckle contrast ratio reflects the blood flow perfusion index (BFI) signal, and the pulse wave signal (PPG) can be represented by the average intensity of speckles. The expressions of the initial blood flow perfusion index signal B(t) and the initial pulse wave signal P(t) are shown in formula (1) and formula (2) respectively:

[0040] (1)

[0041] (2)

[0042] wherein is the standard deviation of the pixel intensity in the diffuse speckle region, is the average value of the standard deviation of the pixel intensity in the diffuse speckle region.

[0043] Since the diffuse speckle image is easily affected by the uneven intensity distribution of the multimode optical fiber, tissue scattering noise and human motion artifacts in the actual imaging process, the processing device 40 will further reconstruct the initial blood flow perfusion index signal and the initial pulse wave signal. Finally, based on the target blood flow perfusion index signal and the target pulse wave signal obtained by reconstruction, myocardial infarction detection is performed.

[0044] Based on the principle of diffuse speckle, the present application realizes the simultaneous detection of blood flow perfusion index signal and pulse wave signal, and performs myocardial infarction detection based on the two signals after reconstruction. On the one hand, multi-modal detection provides more dimensional information for the present application; on the other hand, the signal reconstruction process significantly improves the signal-to-noise ratio of the signal and enhances the feature recognition degree of the signal, thereby reducing the signal interference caused by human body activity and external environmental factors. Therefore, the precision of the myocardial infarction detection system provided by the present application is improved.

[0045] Figure 2 An initial signal processing flowchart according to an embodiment of the present application is shown.

[0046] As shown in Figure 2 , the processing flow of the initial signal includes operations S210-S240.

[0047] In operation S210, for any one of the initial blood flow perfusion index signal and the initial pulse wave signal, the initial signal is subjected to empirical mode decomposition to obtain a plurality of first modal components.

[0048] In operation S220, based on the frequency domain kurtosis and energy proportion, the plurality of first modal components are screened to obtain a plurality of second modal components.

[0049] In operation S230, variational mode decomposition is performed on multiple second mode components to obtain multiple third mode components.

[0050] In operation S240, signal reconstruction is performed based on multiple third-mode components to obtain the target blood perfusion index signal and the target pulse wave signal.

[0051] The process of obtaining the first mode component includes the following steps: Gaussian noise is injected into the initial signal based on multiple noise figures to obtain multiple signals to be decomposed; empirical mode decomposition is performed on the signals to be decomposed to obtain multiple initial mode components of the target order; the first mode component of the signal to be decomposed is obtained based on the average value of the multiple initial mode components, so as to obtain multiple first mode components.

[0052] The following will take the processing of the initial blood perfusion index signal B(t) as an example to describe in detail the process of obtaining the first modal component corresponding to B(t).

[0053] First, Q pre-generated Gaussian noises are injected into the initial blood perfusion index signal B(t), resulting in Q signals to be decomposed. For the i-th signal B(t) to be decomposed... i (t), whose expression is shown in formula (3):

[0054] (3)

[0055] In the formula, It is zero-mean Gaussian noise. , This represents the noise figure.

[0056] Subsequently, Empirical Mode Decomposition (EMD) is performed on each noisy signal to obtain multiple initial mode components of the target order, where the j-th initial mode component is denoted as... ,extract The average value of the first initial modal components is taken as the first modal component. Its expression is shown in formula (4):

[0057] (4)

[0058] In the formula, Q is the number of signal groups to be decomposed. This indicates that the residual signal is subjected to the first... Extraction of the initial mode. The initial pulse wave signal P(t) is processed in the same way as described above to obtain the first mode component corresponding to P(t).

[0059] To accurately identify effective signal components and efficiently eliminate noise interference, this application uses a frequency domain kurtosis and energy ratio method to screen the first mode components. The specific steps are as follows: Calculate the frequency domain kurtosis and energy ratio of multiple first mode components; screen mode components with a frequency domain kurtosis greater than a first preset value and an energy ratio greater than a second preset value from the multiple first mode components to obtain multiple second mode components.

[0060] First, based on the frequency domain kurtosis method, a sliding window function is used to filter the first mode component. A sliding time window of appropriate length and step size is set for the first mode component, and the window slides successively along the signal time axis, dividing the long-time signal into several short-time signal segments. Then, the original time-domain first mode component signal is transformed to the frequency domain through a short-time Fourier transform to obtain the power spectral density corresponding to each frequency point. Subsequently, the kurtosis value of each frequency point or frequency interval is calculated. Kurtosis is a statistical measure of the degree to which a signal deviates from a normal distribution. If the signal component conforms to the distribution of stationary Gaussian noise, its kurtosis value is close to 3, while the signal component containing effective information exhibits a kurtosis value much greater than 3. Therefore, by setting a reasonable first preset value, frequency intervals with kurtosis values ​​higher than the first preset value are selected. These intervals are the key frequency bands containing effective signal characteristics. Frequency domain kurtosis... The expression is shown in formula (5):

[0061] (5)

[0062] In the formula, Initial blood perfusion index signal The short-time Fourier transform, This represents the expected value within a time window.

[0063] The energy proportion method involves time-frequency conversion or decomposition of the original first-mode component signal to obtain several signal components representing different frequencies. Then, the energy of each component is calculated, and the ratio of that component's energy to the total energy of the original signal is determined—the energy proportion. Finally, based on a set second preset value, components with energy proportions higher than this value are selected. These components contain the main information from the original signal, while components with low energy proportions are mostly noise or redundant information, thus achieving accurate extraction of effective signal components. Specifically, in the characteristic frequency band... Energy percentage The expression is shown in formula (6):

[0064] (6)

[0065] In the formula, Sampling frequency, power spectral density The estimation is performed using Welch's method, and the calculation formula is as follows:

[0066] (7)

[0067] wherein, is a window function, is a segment number, and H refers to the length of the window function .

[0068] The first modal component corresponding to the initial blood perfusion index signal and the initial pulse wave signal is screened according to the screening method, to obtain a second modal component.

[0069] Based on the plurality of second modal components, a spectral peak search is performed to obtain a plurality of peak frequencies; based on the plurality of peak frequencies, clustering is performed to obtain a center frequency; and based on the center frequency, variational modal decomposition is performed on the plurality of second modal components, respectively, to obtain a plurality of third modal components.

[0070] According to an embodiment of the present application, to further extract the effective signal, a spectral peak search is performed on the second modal component screened by the above-mentioned double preset values to obtain a series of peak frequencies M). Secondly, K-means method is used to cluster , to obtain the center frequency information K), The expression of which is shown in formula (8) :

[0071] (8)

[0072] wherein, represents a K-means clustering operation, represents the number of cluster centers.

[0073] Finally, based on the center frequency, variational modal decomposition is performed on the second modal component to extract a third modal component containing the effective signal.

[0074] The processing device 40 accumulates the plurality of third modal components to obtain a target blood perfusion index signal and a target pulse wave signal. The expression of the target blood perfusion signal is shown in formula (9) :

[0075] (9)

[0076] wherein, D is the number of third modal components containing the effective signal.

[0077] Joint feature extraction is performed on the target blood perfusion index signal and the target pulse wave signal to obtain a correlation feature; and based on the correlation feature, myocardial infarction detection is performed.

[0078] The correlation feature extraction step is as follows. Based on a preset window and a preset step, the target blood perfusion index signal is divided into a plurality of first sub-signals, and the target pulse wave signal is divided into a plurality of second sub-signals; correlation calculation is performed based on the plurality of first sub-signals and the plurality of second sub-signals to obtain a first-order correlation coefficient matrix; the first-order correlation coefficient matrix is normalized to obtain a second-order correlation coefficient matrix; and the first-order correlation coefficient matrix and the second-order correlation coefficient matrix are multiplied to obtain a correlation feature.

[0079] The first-order correlation coefficient matrix acquisition step is as follows. The first sub-signals and the second sub-signals corresponding to the same window are subjected to correlation calculation to obtain low-order frequency components; and based on the plurality of low-order frequency components, a first-order correlation coefficient matrix is obtained.

[0080] Figure 3 A flowchart of a correlation feature extraction method according to an embodiment of the present application is shown. As shown in FIG. 1, first, a sliding window correlation method is applied to the target blood perfusion index signal and the target pulse wave signal respectively, the target blood perfusion index signal and the target pulse wave signal are divided into a plurality of time windows to obtain a plurality of sub-signals. The preset window length Figure 3 represents a complete pulse period, and a one-minute signal is intercepted to obtain segmented signals, wherein The expression of is shown in equation (10):

[0081] (10)

[0082] In the formula, T is the total length of the original signal, is the preset step of each sliding window, is the integer part, wherein the sub-signals of the target blood perfusion index signal after division are first sub-signals, and the signals of the target pulse wave signal after division are second sub-signals. The nth segment of the first sub-signals is represented as , and the nth segment of the second sub-signals is represented as .

[0083] Subsequently, the correlation between the target blood perfusion index signal and the target pulse wave signal is quantified based on Pearson correlation calculation. First, the low-order frequency components (Lower Order Frequency Component, LoFC) of the first sub-signals and the second sub-signals corresponding to the same window are calculated, and the low-order frequency components are calculated according to equation (11):

[0084] (11)

[0085] wherein and They are respectively and The mean.

[0086] Calculate according to the formula respectively The LoFC of the segment signal yields the first-order correlation coefficient matrix as shown in formula (12):

[0087] (12)

[0088] matrix The Middle Column vectors are represented as To each The Middle Columns and After performing Z-score normalization on the signal, the correlation is calculated to obtain... The expression is shown in formula (13):

[0089] (13)

[0090] in and They are respectively and The mean of the correlation coefficients is obtained. Correspondingly, the second-order correlation coefficient matrix (14) is obtained:

[0091] (14)

[0092] Finally, the first-order correlation coefficient matrix is ​​then... and second-order correlation coefficient matrix Perform matrix multiplication to obtain the correlation features (15):

[0093] (15)

[0094] According to an embodiment of this application, the processing device 40 is further configured to segment the relevant features to obtain multiple feature blocks; encode the multiple feature blocks to obtain multiple bottleneck features; and input the multiple bottleneck features into a classifier to obtain the myocardial infarction detection result.

[0095] Figure 4 A schematic diagram illustrating the principle of obtaining myocardial infarction detection results from correlation features according to an embodiment of this application is shown.

[0096] like Figure 4As shown, in order to reduce the data dimension, first, the correlation feature is divided and projected into the feature space to obtain a plurality of feature blocks. After passing through the encoder, it is encoded into a bottleneck feature and further input into the classifier. Among them, the bottleneck feature is a low-dimensional, highly condensed core feature vector obtained by the encoder gradually reducing the dimension and information compression of the input feature block. In the encoding process of the bottleneck feature, the encoder will automatically remove the redundant information in the original feature, and only keep the most critical and representative information for the subsequent task.

[0097] The classifier mainly includes a Dropout layer, a fully connected layer and an output layer, wherein the Dropout layer can avoid network overfitting. After inputting the bottleneck feature into the classifier, it is first transmitted into the fully connected layer, and the feature is preliminarily integrated and the more discriminative intermediate feature is extracted through linear transformation and nonlinear activation function; then it enters the Dropout layer, and in the training stage, part of the neurons are randomly turned off according to the preset probability to avoid overfitting caused by the network's excessive dependence on specific neurons; then the feature processed by Dropout is transmitted into the subsequent fully connected layer, and the feature is further integrated and the dimension is adjusted; finally, it enters the output layer, outputs the myocardial infarction detection result, and completes the whole process from feature input to detection result output.

[0098] Figure 5 A myocardial infarction detection flowchart according to an embodiment of the application is shown.

[0099] As shown in Figure 5 After the processing device collects the initial blood perfusion index signal and the initial pulse wave signal, Gaussian noise is injected into the initial signal (i.e. the initial blood perfusion index signal and the initial pulse wave signal) and empirical mode decomposition is performed to obtain a plurality of first modal components IMF1(t), IMF2(t)…IMF n (t). Subsequently, the first modal signal is double-preset value screened based on the frequency domain kurtosis and energy proportion method to obtain a second modal component. Then, the third modal component is obtained by performing variational mode decomposition on the second modal component. The third modal component is reconstructed and the correlation feature is extracted, and finally, the myocardial infarction detection result is obtained based on the correlation feature.

[0100] To verify the effectiveness of the myocardial infarction detection system based on diffusion speckle of the application, the following rabbit myocardial infarction experimental model was performed:

[0101] The experiment employed coronary artery ligation to simulate the pathological process of myocardial ischemia and infarction. New Zealand white rabbits weighing 2.5-3.5 kg were selected as experimental animals, as their cardiac anatomy is similar to that of humans, especially the distribution of the left anterior descending coronary artery (LAD), facilitating surgical manipulation and making them sensitive to myocardial ischemia. Before the experiment, the rabbits were fasted for 12 hours, and anesthesia was administered via the marginal ear vein. After complete anesthesia, they were fixed to the operating table. An incision was made in the 3rd-4th intercostal space on the left side of the sternum, the pericardium was carefully cut, and the heart was removed and flushed with heparinized saline to prevent thrombosis. Subsequently, the middle segment of the LAD was ligated with silk sutures to block blood flow, inducing myocardial ischemia and infarction. Postoperatively, the heart was returned to the thoracic cavity, the incision was sutured, and vital signs such as heart rate, blood pressure, and respiration were closely monitored. After the experiment, the rabbits were euthanized, and cardiac tissue was harvested for pathological analysis to determine the extent of infarction and to assess the degree of myocardial damage by detecting serum myocardial enzyme levels.

[0102] Figure 6 The initial blood perfusion signal and initial pulse wave signal of the rabbit measured in an experiment according to an embodiment of this application are shown. Figure 7 The illustration shows multiple first mode components obtained based on the initial blood perfusion signal and initial pulse wave signal of a rabbit in an experiment according to an embodiment of this application. Figure 6 Empirical mode decomposition is performed on the two signals to obtain, as follows: Figure 7 The first modal component 1, the first modal component 2, and the first modal component 3 are shown.

[0103] Figure 8 The illustration shows multiple second-mode components obtained by screening based on frequency domain kurtosis and energy proportion in an experiment according to an embodiment of this application. The multiple first-mode components were then screened according to the principle of frequency domain kurtosis > 1 and energy proportion > 0.8, resulting in the following... Figure 8 The second mode component 1, second mode component 2, and second mode component 3 are shown.

[0104] Figure 9 The diagram illustrates multiple third mode components obtained in an experiment according to an embodiment of this application. Variational mode decomposition is performed on the aforementioned multiple second mode components to obtain, as shown below... Figure 9 The third mode component 1 and the third mode component 2 are shown.

[0105] Figure 10 The reconstructed signal obtained in an experiment according to an embodiment of this application is shown. Signal reconstruction based on the aforementioned third mode component yields the following result: Figure 10 The reconstructed signal is shown.

[0106] It can be seen that the signal reconstruction method of this application can significantly improve the signal-to-noise ratio and obtain blood flow pulse wave characteristics more clearly.

[0107] Finally, the initial blood perfusion index and initial pulse wave signal of normal animals (17) and myocardial infarction animals (13) were obtained by using animal models respectively, and the signals before and after signal reconstruction were used as the input signals of the discrimination model for myocardial infarction discrimination. The results are shown in Table 1

[0108] Table 1

[0109]

[0110] From the experimental results, it can be seen that the use of reconstructed signals can improve the discrimination accuracy of myocardial infarction animals.

[0111] The myocardial infarction detection system based on diffusion speckle provided by the present application simultaneously obtains blood perfusion index signals and pulse wave signals, more comprehensively characterizes the dynamic response of the cardiovascular system, and significantly improves the myocardial infarction detection accuracy. In addition, the initial blood perfusion index signal and the initial pulse wave signal are reconstructed, which reduces the signal interference caused by the displacement of skin, muscle and bone due to the physical activity of the subject, as well as the interference caused by the fluctuation of environmental light, further improving the myocardial infarction detection accuracy.

[0112] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A myocardial infarction detection system based on diffusion speckle, comprising: a laser for exciting a laser signal; an optical fiber probe connected with the laser through a multimode optical fiber for guiding the laser signal to a to-be-detected object and collecting a reflected light signal of the to-be-detected object; a camera connected with the optical fiber probe through a multimode optical fiber for obtaining a diffusion speckle image based on the reflected light signal; and a processing device electrically connected with the camera for obtaining an initial blood perfusion index signal and an initial pulse wave signal based on the diffusion speckle image, reconstructing the initial blood perfusion index signal and the initial pulse wave signal to obtain a target blood perfusion index signal and a target pulse wave signal, extracting a correlation feature based on the target blood perfusion index signal and the target pulse wave signal, and detecting myocardial infarction based on the correlation feature; wherein the processing device is specifically configured to: divide the target blood perfusion index signal into a plurality of first sub-signals and divide the target pulse wave signal into a plurality of second sub-signals based on a preset window and a preset step; and perform correlation calculation based on the plurality of first sub-signals and the plurality of second sub-signals to obtain a first-order correlation coefficient matrix; perform normalization processing on the first-order correlation coefficient matrix to obtain a second-order correlation coefficient matrix; and perform matrix multiplication on the first-order correlation coefficient matrix and the second-order correlation coefficient matrix to obtain the correlation feature.

2. The system of claim 1, wherein, The processing device is configured to: perform empirical mode decomposition on any one of the initial blood perfusion index signal and the initial pulse wave signal to obtain a plurality of first modal components; select a plurality of second modal components from the plurality of first modal components based on frequency domain kurtosis and energy proportion; perform variational mode decomposition on the plurality of second modal components to obtain a plurality of third modal components; reconstruct the target blood perfusion index signal and the target pulse wave signal based on the plurality of third modal components.

3. The system of claim 2, wherein, The processing device is configured to: inject Gaussian noise into the initial signal based on a plurality of noise coefficients to obtain a plurality of decomposed signals; perform empirical mode decomposition on the decomposed signals to obtain a plurality of initial modal components of a target order; obtain a first modal component of the decomposed signal based on an average value of the plurality of initial modal components to obtain a plurality of first modal components.

4. The system of claim 2, wherein, The processing device is configured to: respectively calculate the frequency domain kurtosis and the energy proportion of the plurality of first modal components; select modal components with the frequency domain kurtosis greater than a first preset value and the energy proportion greater than a second preset value from the plurality of first modal components to obtain a plurality of second modal components.

5. The system of claim 2, wherein, The processing device is configured to: perform spectral peak search based on the plurality of second modal components to obtain a plurality of peak frequencies; perform clustering based on the plurality of peak frequencies to obtain a center frequency; respectively perform variational mode decomposition on the plurality of second modal components based on the center frequency to obtain a plurality of third modal components.

6. The system of claim 2, wherein, The processing device is configured to: accumulate the third modal components to obtain the target blood perfusion index signal and the target pulse wave signal.

7. The system of claim 1, wherein, The processing device is configured to: correlate the first sub-signal and the second sub-signal corresponding to the same window to obtain low-order frequency components; obtain the first-order correlation coefficient matrix based on the low-order frequency components.

8. The system of claim 1, wherein, The processing device is configured to: segment the correlation features to obtain feature blocks; encode the feature blocks to obtain bottleneck features; input the bottleneck features into a classifier to obtain a myocardial infarction detection result.

Images