CN112215836A

CN112215836A - Carotid plaque detection method and device based on medical ultrasonic image

Info

Publication number: CN112215836A
Application number: CN202011140586.3A
Authority: CN
Inventors: 李振洲; 刘欣; 吴欣殷; 黄珊珊; 陈胜华; 关晓韵; 林晓君
Original assignee: Shenzhen Second Peoples Hospital
Current assignee: Shenzhen Second Peoples Hospital
Priority date: 2020-10-22
Filing date: 2020-10-22
Publication date: 2021-01-12

Abstract

The application provides a carotid artery plaque detection method and a carotid artery plaque detection device based on a medical ultrasonic image, wherein the method comprises the following steps: establishing a corresponding relation between characteristic parameters in a carotid artery medical ultrasonic image of a patient and a perfusion mode of a new blood vessel in a carotid artery plaque by utilizing the self-learning capability of an artificial neural network; acquiring current characteristic parameters of a medical ultrasonic image corresponding to the current carotid artery of a patient; determining a current carotid artery plaque neovascular perfusion mode corresponding to the current characteristic parameters according to the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque. The capability of extracting effective characteristics of the neural network is improved, the personnel cost required by detection is reduced, and the accuracy is high.

Description

Carotid plaque detection method and device based on medical ultrasonic image

Technical Field

The application relates to the field of medical detection, in particular to a carotid artery plaque detection method and device based on a medical ultrasonic image.

Background

Transient Ischemic Attack (TIA) is a transient and reversible neurologic deficit syndrome and also an important risk factor for cerebral infarction. Research shows that the incidence rate of TIA postcerebral infarction is as high as 8.0-10.5%. The carotid artery is the main blood vessel for supplying blood to the brain, and the atherosclerotic plaque of the carotid artery is one of the main causes for TIA and cerebral infarction. Recent studies indicate that the carotid plaque neovascular perfusion pattern is also one of the independent risk factors for TIA patients to relapse or develop ischemic stroke.

In the existing clinical detection, at least two ultrasonic diagnosticians with high annual capital need to perform plaque enhancement and grading judgment on the obtained ultrasonic contrast images to accurately obtain the diagnosis result of the carotid plaque neovascular perfusion mode, so that the required personnel cost is huge and the time consumption is too long; moreover, due to the artificial judgment process, individual subjective judgment factors are easily introduced, so that the accuracy of the judgment result is reduced.

Disclosure of Invention

In view of the above, the present application is proposed to provide a method and apparatus for carotid artery plaque detection based on medical ultrasound images that overcomes or at least partially solves the above problems, comprising:

a carotid artery plaque detection method based on medical ultrasonic images comprises the following steps:

establishing a corresponding relation between characteristic parameters in a carotid artery medical ultrasonic image of a patient and a perfusion mode of a new blood vessel in a carotid artery plaque by utilizing the self-learning capability of an artificial neural network;

acquiring current characteristic parameters of a medical ultrasonic image corresponding to the current carotid artery of a patient;

determining a current carotid artery plaque neovascular perfusion mode corresponding to the current characteristic parameters according to the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque.

Further, the air conditioner is provided with a fan,

the characteristic parameters comprise: the image characteristic and/or the medical history characteristic and/or a one-dimensional or more than two-dimensional array consisting of characteristics extracted from the image characteristic and the medical history characteristic according to a set rule; wherein the content of the first and second substances,

the image features include: plaque location, plaque size, plaque internal echogenic features, plaque surface morphology, intimal echogenic discontinuities or surface ulcerations, eccentricity index, plaque thickness, contralateral intimal thickness, presence of liquefied components inside, and intensity grading of contrast agent enhancement inside carotid plaque;

the medical history characteristics comprise: hypertension, diabetes, hyperlipidemia, smoking history, family history of cerebral apoplexy, and compliance with drug administration;

and/or the presence of a gas in the gas,

the corresponding relation comprises: a functional relationship; the characteristic parameter is an input parameter of the functional relationship, and the perfusion mode of the new blood vessel in the carotid plaque is an output parameter of the functional relationship;

determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the current characteristic parameters, further comprising:

and when the corresponding relation comprises a functional relation, inputting the current characteristic parameter into the functional relation, and determining the output parameter of the functional relation as the current perfusion mode of the new vessels in the carotid plaque.

Further, the step of establishing a correspondence between the characteristic parameters in the medical ultrasound image of carotid artery and the perfusion pattern of the new blood vessel in the carotid artery plaque comprises:

acquiring sample data for establishing a corresponding relation between the characteristic parameters and a perfusion mode of a new blood vessel in the carotid plaque;

analyzing the characteristics and the rules of the characteristic parameters, and determining the network structure and the network parameters of the artificial neural network according to the characteristics and the rules;

training and testing the network structure and the network parameters by using the sample data, and determining the corresponding relation between the characteristic parameters and the perfusion mode of the new vessels in the carotid plaque.

Further, the step of obtaining sample data for establishing a correspondence between the characteristic parameter and a perfusion pattern of a new vessel within the carotid plaque comprises:

collecting the characteristic parameters of the patient for different patterns of neovascular perfusion in carotid plaques and the patterns of neovascular perfusion in carotid plaques;

analyzing the characteristic parameters, and selecting data related to the perfusion mode of the new vessels in the carotid plaque as the characteristic parameters by combining prestored expert experience information;

and taking the perfusion mode of the new blood vessel in the carotid plaque and the data pair formed by the selected characteristic parameters as sample data.

Further, the air conditioner is provided with a fan,

the Network structure comprises at least one of a Faster R-CNN Network, an FPN Network, an SqeezeNet Network, a VGG model, a GoogleNet Network, a ResNet Network and a Network-In-Network model;

and/or the presence of a gas in the gas,

the network parameters comprise: at least one of the number of dense blocks, the number of output layers, the number of convolution layers, the number of deconvolution layers, the number of transition layers, the initial weight, and the offset value.

Further, the air conditioner is provided with a fan,

training the network structure and the network parameters, including:

selecting a part of data in the sample data as a training sample, inputting the characteristic parameters in the training sample into the network structure, and training through an activation function of the network structure and the network parameters to obtain an actual training result;

determining whether an actual training error between the actual training result and a corresponding carotid plaque neovascular perfusion pattern in the training sample satisfies a preset training error;

determining that the training of the network structure and the network parameters is completed when the actual training error meets the preset training error;

and/or the presence of a gas in the gas,

testing the network structure and the network parameters, comprising:

selecting another part of data in the sample data as a test sample, inputting the characteristic parameters in the test sample into the trained network structure, and testing by using the activation function and the trained network parameters to obtain an actual test result;

determining whether an actual test error between the actual test result and a corresponding carotid intra-plaque neovascular perfusion pattern in the test sample satisfies a set test error;

and when the actual test error meets the set test error, determining that the test on the network structure and the network parameters is finished.

Further, the air conditioner is provided with a fan,

training the network structure and the network parameters, further comprising:

when the actual training error does not meet the set training error, updating the network parameters through an error energy function of the network structure;

retraining through the activation function of the network structure and the updated network parameters until the retrained actual training error meets the set training error;

and/or the presence of a gas in the gas,

testing the network structure and the network parameters, further comprising:

and when the actual test error does not meet the set test error, retraining the network structure and the network parameters until the retrained actual test error is slower than the set test error.

A carotid plaque detection apparatus based on medical ultrasound images, comprising:

the establishing module is used for establishing a corresponding relation between characteristic parameters in a carotid artery medical ultrasonic image of a patient and a perfusion mode of a new blood vessel in a carotid artery plaque by utilizing the self-learning capability of the artificial neural network;

the acquisition module is used for acquiring the current characteristic parameters of the medical ultrasonic image corresponding to the current carotid artery of the patient;

the determining module is used for determining a current carotid artery plaque neogenesis blood vessel perfusion mode corresponding to the current characteristic parameter through the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque.

An apparatus comprising a processor, a memory and a computer program stored on the memory and being executable on the processor, the computer program, when executed by the processor, implementing the steps of the method for carotid artery plaque detection based on medical ultrasound images as described above.

A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for carotid artery plaque detection based on medical ultrasound images as described above.

The application has the following advantages:

in the embodiment of the application, the self-learning capability of the artificial neural network is utilized to establish the corresponding relation between the characteristic parameters in the carotid artery medical ultrasonic image of the patient and the perfusion mode of the new vessels in the carotid artery plaques; acquiring current characteristic parameters of a medical ultrasonic image corresponding to the current carotid artery of a patient; determining a current carotid artery plaque neovascular perfusion mode corresponding to the current characteristic parameters according to the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque. The capability of extracting effective features of the neural network is improved, the attention to useful features is enhanced, the attention to useless features is reduced, and the detection precision of the detection network is improved; the personnel cost required by detection is reduced, the consumed time is short, and the accuracy is high.

Drawings

In order to more clearly illustrate the technical solutions of the present application, the drawings needed to be used in the description of the present application will be briefly introduced below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive labor.

Fig. 1 is a flowchart illustrating steps of a carotid artery plaque detection method based on medical ultrasound images according to an embodiment of the present application;

fig. 2 is a schematic diagram illustrating intra-plaque contrast enhancement grading of a carotid artery plaque detection method based on a medical ultrasound image according to an embodiment of the present application;

fig. 3 is a ROC graph of a Logistic regression model of a carotid artery plaque detection method based on a medical ultrasound image according to an embodiment of the present application;

fig. 4 is a block diagram illustrating a carotid artery plaque detection device based on a medical ultrasound image according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Referring to fig. 1, a carotid artery plaque detection method based on a medical ultrasound image provided by an embodiment of the application is shown, including:

s110, establishing a corresponding relation between characteristic parameters in a carotid artery medical ultrasonic image of a patient and a perfusion mode of a new blood vessel in a carotid artery plaque by utilizing the self-learning capability of an artificial neural network;

s120, obtaining the current characteristic parameters of the medical ultrasonic image corresponding to the current carotid artery of the patient;

s130, determining a current carotid artery plaque neogenesis blood vessel perfusion mode corresponding to the current characteristic parameters through the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque.

In the embodiment of the application, the self-learning capability of the artificial neural network is utilized to establish the corresponding relation between the characteristic parameters in the carotid artery medical ultrasonic image of the patient and the perfusion mode of the new vessels in the carotid artery plaque; acquiring current characteristic parameters of a medical ultrasonic image corresponding to the current carotid artery of a patient; determining a current carotid artery plaque neovascular perfusion mode corresponding to the current characteristic parameters according to the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque. The capability of extracting effective features of the neural network is improved, the attention to useful features is enhanced, the attention to useless features is reduced, and the detection precision of the detection network is improved; the personnel cost required by detection is reduced, the consumed time is short, and the accuracy is high.

Next, the carotid artery plaque detection method based on the medical ultrasound image in the present exemplary embodiment will be further described.

As described in the above step S110, the self-learning capability of the artificial neural network is utilized to establish the corresponding relationship between the characteristic parameters in the medical ultrasound image of carotid artery of the patient and the perfusion pattern of the new vessels in the carotid artery plaque.

For example: and analyzing the display state rule of the characteristic parameters in the carotid artery medical ultrasonic image of the patient corresponding to the perfusion mode of the new blood vessel in the carotid artery plaque by utilizing an artificial neural network algorithm, and finding the mapping rule between the characteristic parameters in the carotid artery medical ultrasonic image of the patient and the perfusion mode of the new blood vessel in the carotid artery plaque through the self-learning and self-adaptive characteristics of the artificial neural network.

For example: the artificial neural network algorithm can be used for collecting characteristic parameters in carotid artery medical ultrasonic images of a plurality of different volunteers (including but not limited to one or more of the following ages, sexes, medical histories and the like, wherein the medical histories include but are not limited to hypertension, diabetes, hyperlipidemia, smoking history, family history of cerebral apoplexy and medication compliance), selecting the characteristic parameters in the carotid artery medical ultrasonic images of a plurality of volunteers and a neovascular perfusion mode in carotid artery plaques as sample data, learning and training the neural network, and fitting the neural network with the relationship between the characteristic parameters in the carotid artery medical ultrasonic images and the perfusion patterns of the neovascularization in the carotid artery plaques by adjusting the network structure and the weights among network nodes, so that the neural network can accurately fit the corresponding relationship between the characteristic parameters in the carotid artery medical ultrasonic images and the perfusion patterns of the neovascularization in the carotid artery plaques of different patients.

In one embodiment, the characteristic parameters include: the image characteristic and/or the medical history characteristic and/or a one-dimensional or more than two-dimensional array consisting of characteristics extracted from the image characteristic and the medical history characteristic according to a set rule;

optionally, the image feature includes: plaque location, plaque size, plaque internal echogenic features, plaque surface morphology, intimal echogenic discontinuities or surface ulcerations, eccentricity index, plaque thickness, contralateral intimal thickness, presence of liquefied components inside, and intensity grading of contrast agent enhancement inside carotid plaque;

referring to fig. 2, it should be noted that the intensity grading of contrast agent enhancement inside carotid plaque includes: 1A: level 0, no enhancement; 1B: grade 1, adventitia enhancement, no enhancement in plaque; 1C: grade 2, small amount of scattered spots in the plaque are enhanced in a punctiform manner; 1D: level 3, linear reinforcement extending into plaque; 1E: and 4, diffuse enhancement in the plaque (the area indicated by the arrow in the figure is the plaque, the left side is the image before enhancement, and the right side is the image after enhancement).

Optionally, the medical history characteristics include: hypertension, diabetes, hyperlipidemia, smoking history, family history of cerebral apoplexy, and compliance with drug administration;

in the medical history characteristics, the expression of the characteristics can be 'whether the patient has hypertension' as an expression form, and the expression of the characteristics is 'whether the patient has hypertension' or 'does not have hypertension', taking the hypertension as an example;

the expression of the characteristic of the compliance of taking the medicine can be 'good' or 'bad', and the expression of the characteristic can be 'good compliance of taking the medicine' or 'bad compliance of taking the medicine'.

As an example, carotid plaque patients who had TIA were collected with inclusion criteria at stroke base of second national hospital, shenzhen, 2014 12, 2014, 1 month by 2014. Inclusion criteria were: (ii) meeting the latest TIA definition proposed by the american stroke association in 2009, typical clinical symptoms generally last <1h due to transient onset neurological deficit from focal cerebral and retinal ischemia, with no evidence of acute infarction; routine ultrasonic examination shows that carotid plaque exists, and the plaque thickness is more than or equal to 2.5 mm; age >45 years. Exclusion criteria: the history of cerebrovascular diseases such as cerebral infarction, cerebral hemorrhage and the like; consciousness disorder exists or the examination cannot be matched; ③ severe infection, heart and lung insufficiency, liver and kidney insufficiency, respiratory failure or malignant tumor; fourthly, the strong echo is mainly or uniformly used inside the plaque; plaque ultrasonic imaging is not carried out; sixthly, losing the visit.

The final inclusion of 61 patients, 28 men and 33 women, aged 48-88 years, averaged (67.2 + -10.8 years). 41 cases of combined hypertension, 34 cases of diabetes, 21 cases of hyperlipidemia, 19 cases of smoking history, 20 cases of stroke family history and 21 cases of poor compliance of taking medicines. During the follow-up period, 9 patients had ischemic stroke and 16 patients had TIA. The follow-up time is more than or equal to 18 months.

A Siemens Acuson S2000 color Doppler ultrasonic diagnostic instrument and a 9L4 broadband linear array probe with the frequency of 7-14 MHz are adopted, and Contrast Pulse Sequence (CPS) software is matched. The patient lies on the examination bed with the head biased to the opposite side, and the neck of the examined side is fully exposed. Longitudinal and transverse scanning is carried out along the common carotid artery from bottom to top, and the plaque position, the size and the internal echo characteristics of the carotid arteries at two sides are observed. Selecting plaque with thickness of 2.5mm or more at the beginning of common carotid artery or internal carotid artery, and selecting the largest plaque if there are multiple plaques. And evaluating two-dimensional ultrasonic characteristics of the target plaque, comparing the echo inside the plaque with the echo of the ipsilateral sternocleidomastoid muscle, and dividing the echo into 3 types of low echo, equal echo and mixed echo. Plaque size was measured and the presence or absence of unstable features was observed: irregular surface morphology, intimal echo discontinuity or surface ulceration, eccentricity index (plaque thickness/contralateral endoblast thickness) >2, appearance of fluid components inside, etc.

CEUS was performed on target plaques. After the images were satisfactory, the CEUS program was selected and the Cadence imaging mode was entered, with a mechanical index of 0.2. 2.5mm of the SonoVue suspension is injected into the median vein of the left elbow by a bolus injection, and then 5ml of physiological saline is injected rapidly. And (5) timing and recording images when the medicine is injected, and observing the filling process of the contrast agent in the lumen and the plaque. If a dynamic point-like strong echo or high echo signal is found in the interior or the edge of the plaque, the contrast agent enhanced echo is judged to be visible in the plaque. Referring to the classification method of Liveren and the like, the strength of contrast agent enhancement in the carotid plaque after radiography is classified into 0-4 grades. Level 0: no enhancement; level 1: the adventitia is strengthened, and the plaque is not strengthened; and 2, stage: small amount of scattered spot-like reinforcement in the plaque; and 3, level: the linear reinforcement extends into the plaque; 4, level: the mass within the plaque was increased diffusely (FIG. 2). Enhanced grading of plaques was judged collectively by 2 senior sonographers.

After ultrasound examination, patients routinely manage vascular risk factors such as hypertension, diabetes, hyperlipidemia, etc. Follow-up 1 time every 3 months to know the patient's medication compliance, whether there is recurrent TIA or ischemic stroke, follow-up at least 18 months. The compliance of taking medicine is judged by the proportion of the number of days of taking medicine in compliance with the medical advice of the patient to the total follow-up days, 80 percent of the total follow-up days of taking medicine in compliance with the medical advice is good, and otherwise, the compliance is poor. After the initial symptom signs are completely recovered, new persistent neurological impairment appears again, and the patient has imaging evidence and is defined as ischemic stroke; the new neurological deficit was completely restored within 1h, defined as a recurrent TIA. The occurrence of ischemic stroke or recurrent TIA during follow-up was defined as recurrent group, and vice versa as non-recurrent group.

SPSS17.0 statistical analysis software was used. Count data are expressed as frequency and percentage (%) and comparisons between groups are by X²And (6) checking. The data are expressed in x + -s and the comparison between the two groups is performed using independent sample t-test. And analyzing risk factors of TIA recurrence or ischemic stroke by adopting multivariate Logistic regression. And (3) evaluating the effectiveness of the Logistic regression model for diagnosing recurrent TIA or ischemic stroke by adopting an ROC curve. P<A difference of 0.05 is statistically significant.

It should be noted that, by analyzing the collected parameters of 61 patients (25 patients in the recurrent group and 36 patients in the non-recurrent group), it was found that the difference between the age and the sex of the two groups of patients was not statistically significant (P > 0.05); the incidence rate of hypertension, diabetes, hyperlipidemia, smoking history, family history of cerebral apoplexy and medication compliance show statistical significance (P is less than 0.05), and the specific data are shown in tables 1 and 2. Thus, age and gender are not included as features in the methods of the invention.

Group of	Age (year of old)	Sex (male/female, example)	Hypertension (with/without, example)	Diabetes mellitus (with/without, case)
					Recurrent group (n is 25)	70.8±10.3	11/14	21/4	20/5
Group of recurrent diseases (n ═ 36)	65.8±10.1	17/19	20/16	14/22
					t or X²Value of	1.882	0.062	5.417	10.108
P value	0.065	0.804	0.020	0.001

TABLE 1

TABLE 2

In plaque detection of 61 patients, 22 cases of equal-echo plaque, 18 cases of low-echo plaque and 21 cases of mixed-echo plaque are detected. Maximum plaque thickness (3.2 mm 0.7). The 25 plaques are characterized by irregular surface morphology or ulcer, eccentricity index of >2, and unstable internal liquefied components. CEUS: 18 cases of 0-level enhancement, 7 cases of 1-level enhancement, 12 cases of 2-level enhancement, 15 cases of 3-level enhancement and 9 cases of 4-level enhancement. The two-dimensional ultrasonic plaque stability characteristics and the CEUS enhanced intensity level between the recurrent group and the non-recurrent group have statistical significance (P is less than 0.05, and shown in a table 3).

TABLE 3

Whether TIA recurs or cerebral ischemic stroke occurs is used as a dependent variable, indexes with statistical significance of difference (hypertension, diabetes, hyperlipidemia, smoking history, cerebral stroke family history, drug taking compliance, two-dimensional ultrasonic plaque stability characteristic and CEUS characteristic are used as independent variables to carry out Logistic regression analysis, see table 4, the obtained regression constant is-6.965, the hypertension, the diabetes, the drug taking compliance, the two-dimensional ultrasonic plaque stability characteristic and the CEUS characteristic are independent risk factors for predicting TIA recurrences or cerebral ischemic stroke of patients, after the traditional risk factors are corrected, plaque CEUS 3-4 grade enhancement is an independent risk factor (P <0.01) of recurrent TIA OR ischemic stroke, the intensity of the recurrent disease is judged according to the OR value, and the CEUS characteristic, the hypertension, the drug compliance, the hyperglycemia and the two-dimensional ultrasonic plaque stability characteristic are arranged.

P(Y)＝exp(-6.965+3.146X1+2.080X2+2.238X3+1.945X4+3.167X5)/[1+exp(-6.965+3.146X1+2.080X2+2.238X3+1.945X4+3.167X5)]。

The Logistic regression model was used to evaluate the efficacy of diagnosing recurrent TIA or ischemic stroke using the ROC curve (figure 2) with an area under the ROC curve of 0.881[ 95% CI (0.797, 0.964), P <0.05 ].

TABLE 4

In an embodiment, the correspondence includes: and (4) functional relation.

Preferably, the characteristic parameter is an input parameter of the functional relationship, and the perfusion mode of the new blood vessel in the carotid plaque is an output parameter of the functional relationship;

therefore, the flexibility and convenience of determining the perfusion mode of the new vessels in the current carotid plaque can be improved through the corresponding relations in various forms.

Such as: the features extracted by the traditional convolution are processed by two paths: the first path automatically acquires the importance degree of each feature channel in a learning mode through two operations of compressing and exciting the feature map, promotes useful features according to the importance degree of the feature channels, and inhibits features with small influence on the current task. Wherein the compression operation is implemented using global average pooling; the excitation operation is realized by adopting two layers of full-connection layers, a Relu activation function layer is connected behind the first layer of full-connection layer, a Sigmoid activation function layer is connected behind the second layer of full-connection layer, and the weight is normalized to be 0-1. And the second path compresses the characteristic channels by adopting 1 × 1 convolution and 3 × 3 convolution, and normalizes the weight corresponding to the spatial information to be between 0 and 1 through a Sigmoid activation function layer and fuses. By the network structure, useful spatial information of a network model is enhanced and useless spatial information is weakened in the dimension of the spatial information. And (3) convolution is carried out by adopting 1 × 1 and 3 × 3 to acquire spatial information with different weights through different receptive fields. In the process of extracting image features, feature information is obtained by using convolution kernels with different sizes and different receptive fields and is fused, the utilization rate of spatial information is improved, prediction is carried out from feature maps with small, medium and large resolution scales, the feature information is fully utilized, and the performance of a network model is improved; the weight factors and the balance factors are added into the loss functions of the classification of the positive samples and the background samples, so that the number of the positive samples and the negative samples is balanced, the model is more concerned about samples which are difficult to classify and easy to separate, overfitting is effectively prevented, and the performance of the classification model is improved.

In an embodiment, the specific process of establishing the correspondence between the characteristic parameters in the medical ultrasound image of carotid artery and the perfusion pattern of the new vessels in the carotid artery plaque in step S110 can be further explained in conjunction with the following description.

The following steps are described: acquiring sample data for establishing a corresponding relation between the characteristic parameters and a perfusion mode of a new blood vessel in the carotid plaque;

in an advanced embodiment, the specific process of obtaining sample data for establishing the correspondence between the characteristic parameters and the perfusion pattern of the new vessels in the carotid plaque may be further described in conjunction with the following description.

The following steps are described: collecting the characteristic parameters of the patient for different patterns of neovascular perfusion in carotid plaques and the patterns of neovascular perfusion in carotid plaques;

for example: data collection: collecting characteristic parameters of patients with different medical history conditions and corresponding perfusion modes of new vessels in carotid plaques; collecting characteristic parameters of patients of different ages and corresponding perfusion modes of new vessels in carotid plaque; and collecting characteristic parameters of patients of different genders and corresponding perfusion modes of new vessels in carotid artery plaques.

Therefore, the operation data are collected through multiple ways, the quantity of the operation data is increased, the learning capacity of the artificial neural network is improved, and the accuracy and the reliability of the determined corresponding relation are improved.

The following steps are described: analyzing the characteristic parameters, and selecting data related to the perfusion mode of the new blood vessels in the carotid plaque as the characteristic parameters by combining with prestored expert experience information (for example, selecting the characteristic parameters influencing the perfusion mode of the new blood vessels in the carotid plaque as input parameters, and using designated parameters as output parameters);

for example: characteristic parameters in the relevant data of the diagnosed volunteers are used as input parameters, and the carotid artery plaque neovascular perfusion mode in the relevant data is used as output parameters.

The following steps are described: and taking the perfusion mode of the new blood vessel in the carotid plaque and the data pair formed by the selected characteristic parameters as sample data.

For example: and using part of the obtained input and output parameter pairs as training sample data and using part of the obtained input and output parameter pairs as test sample data.

Therefore, the collected characteristic parameters are analyzed and processed to obtain sample data, the operation process is simple, and the reliability of the operation result is high.

The following steps are described: analyzing the characteristics and the rules of the characteristic parameters, and determining the network structure and the network parameters of the artificial neural network according to the characteristics and the rules;

for example: according to the data characteristics and the rules thereof which have influence on the perfusion mode of the new vessels in the carotid plaque by different medical histories, the basic structure of the network, the number of input and output nodes of the network, the number of hidden layers of the network, the number of hidden nodes, the initial weight of the network and the like can be preliminarily determined.

Preferably, the network structure comprises: at least one of a Faster R-CNN network, an FPN network, an AlexNet network, a SqeezeNet network, a VGG model, a GoogleNet network, a ResNet network, and a deep feature enhancement network.

Preferably, the network parameters include: at least one of a number of dense blocks, a number of output layers, a number of convolution layers, a number of deconvolution layers, a number of transition layers, a feature enhancement layer, an initial weight, and an offset value.

Referring to fig. 3, as an example, a specific structure of the artificial neural network includes: the method comprises the steps of firstly containing 2 layers of convolution layers of 3 x 3, then 4 three-dimensional residual blocks, wherein each residual block is connected with a pooling layer for down-sampling, and each residual block consists of 3 residual units. In order to improve the detection accuracy of the network model for the nodes, the feature map after the down-sampling of the fourth layer is up-sampled twice, and the feature map obtained by the up-sampling is transversely connected with the down-sampling feature map with the corresponding size, so as to fully utilize the feature information.

Optionally, the specific process of training the network structure and the network parameters in "using the sample data to train and test the network structure and the network parameters and determine the corresponding relationship between the characteristic parameters and the perfusion pattern of the new vessels in the carotid plaque" may be further explained in conjunction with the following description.

Selecting a part of data in the sample data as a training sample, inputting the characteristic parameters in the training sample into the network structure, and training through the network structure and the network parameters to obtain an actual training result; determining whether an actual training error between the actual training result and a corresponding carotid plaque neovascular perfusion pattern in the training sample satisfies a preset training error; determining that the training of the network structure and the network parameters is completed when the actual training error meets the preset training error;

more optionally, training the network structure and the network parameters further includes:

when the actual training error does not meet the set training error, updating the network parameters through an error energy function of the network structure; retraining through the activation function of the network structure and the updated network parameters until the retrained actual training error meets the set training error;

for example: and if the test error meets the requirement, finishing the network training test.

Therefore, the reliability of the network structure and the network parameters is further verified by using the test sample for testing the network structure and the network parameters obtained by training.

Optionally, the specific process of testing the network structure and the network parameters in the step of training and testing the network structure and the network parameters and determining the corresponding relationship between the characteristic parameters and the perfusion pattern of the new vessels in the carotid plaque may be further explained in conjunction with the following description.

Selecting another part of data in the sample data as a test sample, inputting the characteristic parameters in the test sample into the trained network structure, and testing by using the activation function and the trained network parameters to obtain an actual test result; determining whether an actual test error between the actual test result and a corresponding carotid intra-plaque neovascular perfusion pattern in the test sample satisfies a set test error; and when the actual test error meets the set test error, determining that the test on the network structure and the network parameters is finished.

As described in the above step S120, obtaining the current characteristic parameters of the current carotid artery of the patient;

as described in step S130 above, the current perfusion pattern of the new blood vessel in the carotid artery plaque corresponding to the current characteristic parameter is determined through the corresponding relationship.

For example: characteristic parameters in a carotid artery medical ultrasound image of a patient are identified in real time.

Therefore, the current carotid artery plaque neogenesis blood vessel perfusion mode of the carotid artery is effectively identified according to the current characteristic parameters based on the corresponding relation, so that accurate judgment basis is provided for diagnosis of doctors, and the judgment result is good in accuracy.

In an alternative example, the determining the current perfusion pattern of the carotid artery plaque corresponding to the characteristic parameter in step S130 may include: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque.

In an optional example, the determining the current perfusion pattern of the carotid artery plaque corresponding to the characteristic parameter in step S130 may further include: when the corresponding relation can comprise a functional relation, inputting the current characteristic parameter into the functional relation, and determining the output parameter of the functional relation as the current perfusion mode of the new vessels in the carotid plaque.

Therefore, the current carotid artery plaque neogenesis blood vessel perfusion mode is determined according to the current characteristic parameters based on the corresponding relation or the functional relation, the determination mode is simple and convenient, and the reliability of the determination result is high.

In an alternative embodiment, the method may further include: a process of verifying whether the current intra-carotid plaque neovascular perfusion pattern coincides with an actual intra-carotid plaque neovascular perfusion pattern.

Optionally, a verification result that the current carotid plaque neovascular perfusion mode is not consistent with the actual carotid plaque neovascular perfusion mode may be received, and/or when it is determined that there is no feature parameter in the correspondence that is the same as the current feature parameter, at least one maintenance operation of updating, correcting, and relearning the correspondence may be performed.

For example: the device can not know the actual perfusion mode of the new blood vessel in the carotid plaque, and needs the feedback operation of a doctor, namely, if the device intelligently judges the perfusion mode of the new blood vessel in the carotid plaque, the doctor can know the mode by the device through the operation feedback that the doctor does not accord with the actual state.

Verifying whether the current intra-carotid-plaque neovascular perfusion pattern matches the actual intra-carotid-plaque neovascular perfusion pattern (e.g., displaying the actual intra-carotid-plaque neovascular perfusion pattern via an AR display module to verify whether the determined current intra-carotid-plaque neovascular perfusion pattern matches the actual intra-carotid-plaque neovascular perfusion pattern).

And when the current carotid plaque neovascular perfusion mode is not consistent with the actual carotid plaque neovascular perfusion mode and/or the corresponding relation does not have the characteristic parameter which is the same as the current characteristic parameter, performing at least one maintenance operation of updating, correcting and relearning on the corresponding relation.

For example: and determining the current perfusion mode of the new vessels in the carotid plaque according to the maintained corresponding relation and the current characteristic parameters. For example: and determining the perfusion mode of the new blood vessel in the carotid artery plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship after maintenance as the current perfusion mode of the new blood vessel in the carotid artery plaque.

Therefore, the accuracy and the reliability of determining the perfusion mode of the new blood vessel in the carotid plaque can be improved by maintaining the corresponding relation between the determined characteristic parameters and the perfusion mode of the new blood vessel in the carotid plaque.

Half of the collected data is imported into the artificial neural network of the method for learning and training, and the other half of the collected data is used as the detection data of the model, so that the accuracy of the result obtained by the method can reach more than 95% by comparing with the actual result.

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

Referring to fig. 4, a carotid artery plaque detection device based on medical ultrasound images provided by an embodiment of the application is shown, which includes:

the establishing module 410 is used for establishing the corresponding relation between the characteristic parameters in the carotid artery medical ultrasonic image of the patient and the perfusion mode of the new vessels in the carotid artery plaques by utilizing the self-learning capability of the artificial neural network;

an obtaining module 420, configured to obtain a current characteristic parameter of a medical ultrasound image corresponding to a current carotid artery of a patient;

a determining module 430, configured to determine, according to the correspondence, a current carotid artery plaque neovascular perfusion mode corresponding to the current characteristic parameter; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque.

In one embodiment, the characteristic parameters include: the motion mode which is extracted according to a set rule in the interest area image sequence and is used for representing each pixel; wherein the content of the first and second substances,

and/or the presence of a gas in the gas,

In one embodiment, the establishing module 410 includes:

the acquisition submodule is used for acquiring sample data for establishing a corresponding relation between the characteristic parameters and a perfusion mode of a new blood vessel in the carotid plaque;

the analysis submodule is used for analyzing the characteristics and the rules of the characteristic parameters and determining the network structure and the network parameters of the artificial neural network according to the characteristics and the rules;

and the training submodule is used for training and testing the network structure and the network parameters by using the sample data, and determining the corresponding relation between the characteristic parameters and the perfusion mode of the new vessels in the carotid plaque.

In one embodiment, the obtaining sub-module includes:

a collection sub-module for collecting the characteristic parameters of the patient for different patterns of neovascular perfusion in carotid plaques and the patterns of neovascular perfusion in carotid plaques;

the analysis submodule is used for analyzing the characteristic parameters and selecting data related to a perfusion mode of a new blood vessel in the carotid plaque as the characteristic parameters by combining prestored expert experience information;

and the sample data generation submodule is used for taking the perfusion mode of the new blood vessel in the carotid plaque and the data pair formed by the selected characteristic parameters as sample data.

In one embodiment of the present invention, the substrate is,

and/or the presence of a gas in the gas,

In one embodiment of the present invention, the substrate is,

the training submodule includes:

a training result generation submodule, configured to select a part of the sample data as a training sample, input the feature parameters in the training sample to the network structure, and perform training through an activation function of the network structure and the network parameters to obtain an actual training result;

a training result error judgment submodule for determining whether an actual training error between the actual training result and a perfusion mode of a new blood vessel in a corresponding carotid plaque in the training sample meets a preset training error;

a training completion determination submodule configured to determine that the training of the network structure and the network parameters is completed when the actual training error satisfies the preset training error;

and/or the presence of a gas in the gas,

a test sub-module for testing the network structure and the network parameters, the test sub-module comprising:

a test result generation submodule, configured to select another part of the sample data as a test sample, input the feature parameter in the test sample into the trained network structure, and perform a test with the activation function and the trained network parameter to obtain an actual test result;

the test result error judgment submodule is used for determining whether the actual test error between the actual test result and the corresponding carotid plaque neovascular perfusion mode in the test sample meets the set test error;

and the test completion judging submodule is used for determining that the test on the network structure and the network parameters is completed when the actual test error meets the set test error.

In one embodiment of the present invention, the substrate is,

the training submodule further comprises:

the network parameter updating submodule is used for updating the network parameters through an error energy function of the network structure when the actual training error does not meet the set training error;

the first retraining submodule is used for retraining through the network structure and the updated network parameters until the retrained actual training error meets the set training error;

and/or the presence of a gas in the gas,

the test submodule further comprises:

and the second retraining submodule is used for retraining the network structure and the network parameters when the actual test error does not meet the set test error until the retrained actual test error is slower than the set test error.

Referring to fig. 5, a computer device of a carotid artery plaque detection method based on a medical ultrasound image of the present invention is shown, which may specifically include the following:

the computer device 12 described above is embodied in the form of a general purpose computing device, and the components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, and a processor or local bus 18 using any of a variety of bus 18 architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus 18, micro-channel architecture (MAC) bus 18, enhanced ISA bus 18, audio Video Electronics Standards Association (VESA) local bus 18, and Peripheral Component Interconnect (PCI) bus 18.

Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (commonly referred to as "hard drives"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, with the program modules 42 configured to carry out the functions of embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, camera, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, computer device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN)), a Wide Area Network (WAN), and/or a public network (e.g., the Internet) via network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be appreciated that although not shown in FIG. 5, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

The processing unit 16 executes programs stored in the system memory 28 to execute various functional applications and data processing, such as implementing the method for detecting carotid artery plaque based on medical ultrasound images provided by the embodiment of the present invention.

That is, the processing unit 16 implements, when executing the program,: establishing a corresponding relation between characteristic parameters in a carotid artery medical ultrasonic image of a patient and a perfusion mode of a new blood vessel in a carotid artery plaque by utilizing the self-learning capability of an artificial neural network; acquiring current characteristic parameters of a medical ultrasonic image corresponding to the current carotid artery of a patient; determining a current carotid artery plaque neovascular perfusion mode corresponding to the current characteristic parameters according to the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque.

In an embodiment of the present invention, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for detecting carotid artery plaque based on medical ultrasound images as provided in all embodiments of the present application:

that is, the program when executed by the processor implements: establishing a corresponding relation between characteristic parameters in a carotid artery medical ultrasonic image of a patient and a perfusion mode of a new blood vessel in a carotid artery plaque by utilizing the self-learning capability of an artificial neural network; acquiring current characteristic parameters of a medical ultrasonic image corresponding to the current carotid artery of a patient; determining a current carotid artery plaque neovascular perfusion mode corresponding to the current characteristic parameters according to the corresponding relation; specifically, determining a current carotid intra-plaque neovascular perfusion pattern corresponding to the characteristic parameter comprises: and determining the neovascular perfusion mode in the carotid plaque corresponding to the characteristic parameter which is the same as the current characteristic parameter in the corresponding relationship as the current neovascular perfusion mode in the carotid plaque.

Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer-readable storage medium or a computer-readable signal medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPOM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.

The method and the device for detecting carotid artery plaque based on medical ultrasound images provided by the application are described in detail above, and specific examples are applied in the text to explain the principle and the implementation of the application, and the description of the above embodiments is only used to help understand the method and the core idea of the application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A carotid artery plaque detection method based on medical ultrasonic images is characterized by comprising the following steps:

2. The method of claim 1,

and/or the presence of a gas in the gas,

3. The method of claim 1, wherein the step of establishing a correspondence between characteristic parameters in the medical ultrasound images of carotid arteries and perfusion patterns of new vessels in carotid plaques comprises:

4. The method according to claim 3, wherein the step of obtaining sample data for establishing a correspondence between the characteristic parameter and a perfusion pattern of the neovasculature within the carotid plaque comprises:

5. The method of claim 4,

and/or the presence of a gas in the gas,

6. The method according to any one of claims 3 to 5,

training the network structure and the network parameters, including:

and/or the presence of a gas in the gas,

testing the network structure and the network parameters, comprising:

7. The method of claim 6,

training the network structure and the network parameters, further comprising:

and/or the presence of a gas in the gas,

testing the network structure and the network parameters, further comprising:

8. A carotid plaque detection device based on medical ultrasound images, comprising:

9. An apparatus comprising a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program when executed by the processor implementing the method of any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.