Abnormal blood flow distribution characterization method, device and equipment based on ultrasound images

Abstract

This invention discloses a method for characterizing abnormal blood flow distribution based on ultrasound images. The method includes the following steps: Step 1, acquiring an ultrasound image containing abnormal blood flow signals and preprocessing it; Step 2, extracting the abnormal blood flow signal region from the ultrasound image; Step 3, calculating the characteristic parameters of the abnormal blood flow distribution region; Step 4, using the above characteristic parameters as independent variables to establish a mathematical model between the combination of abnormal blood flow signal characteristic parameters and the abnormal blood flow distribution. This method can analyze and evaluate blood flow abnormalities, and is efficient, accurate, and scalable. Compared with traditional manual interpretation methods, this method significantly improves the efficiency and accuracy of abnormal blood flow signal evaluation and can be applied to various medical imaging technologies, showing broad application prospects.

Description

Technical Field

[0001] This invention relates to a method for characterizing abnormal blood flow distribution based on ultrasound images, belonging to the field of medical ultrasound imaging. Background Technology

[0002] Abnormal blood flow is an important physiological feature of many diseases, especially closely related to the occurrence and progression of cardiovascular diseases, tumors, and neurological disorders. Its morphological and distribution characteristics can reflect the occurrence, development, and severity of the lesion. Detection of abnormal blood flow generally employs various medical imaging methods. For example, ultrasound imaging is widely used for detecting abnormal blood flow signals due to its real-time, non-invasive, and low-cost advantages. However, traditional methods for analyzing abnormal blood flow rely heavily on manual interpretation and experience, which has the following limitations: low efficiency (manual image analysis requires a significant amount of time, making it difficult to meet the needs of large-scale screening); strong subjectivity (different doctors may have different interpretations of the same image, resulting in inconsistent and unobjective results); and difficulty in quantification (manual methods struggle to accurately quantify abnormal blood flow signals, limiting their application in disease research and efficacy evaluation).

[0003] To address the aforementioned issues, this invention proposes a method for characterizing abnormal blood flow distribution based on ultrasound images. By extracting characteristic parameters of blood flow distribution from ultrasound blood flow images and combining them with a quantitative analysis model, the degree of blood flow abnormality can be quantified efficiently and accurately, thereby precisely characterizing the abnormal blood flow distribution. Summary of the Invention

[0004] The purpose of this invention is to provide a method for characterizing abnormal blood flow distribution based on ultrasound images. By acquiring ultrasound blood flow images through ultrasound blood flow imaging, extracting characteristic parameters of blood flow distribution in the images, and establishing a relationship model between the combination of characteristic parameters and the degree of blood flow abnormality, an automated quantitative analysis and evaluation of blood flow abnormalities in the images can be achieved.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present invention provides a method for characterizing abnormal blood flow distribution based on ultrasound images, comprising the following steps:

[0007] Step 1: Acquire ultrasound images containing abnormal blood flow signals and preprocess them;

[0008] Step 2: Extract abnormal blood flow signal regions from ultrasound images;

[0009] Step 3: Calculate the characteristic parameters of the abnormal blood flow distribution area;

[0010] Step 4: Using the above characteristic parameters as independent variables, establish a mathematical model between the combination of abnormal blood flow signal characteristic parameters and the abnormal blood flow distribution.

[0011] Step 5: Analyze and quantify the abnormal blood flow signals in the image based on the mathematical model.

[0012] Furthermore, in step 1, the dynamic characteristics of blood flow are analyzed by cross-convolution between consecutive frames of ultrasound images.

[0013] Furthermore, let the two echo signals received by the system be s(t) and s(t+Δt), where t is time and Δt is the time delay, representing the time interval between the two frames; calculate the cross-convolution between these two frames:

[0014]

[0015] Where τ is the integration variable;

[0016] By analyzing the amplitude information of cross-convolution, the amplitude changes of blood flow are extracted to reflect the intensity of blood flow; by analyzing the phase information of cross-convolution results, the phase changes of blood flow are extracted to reflect the direction and velocity of blood flow.

[0017] Furthermore, in step 2, abnormal blood flow signals are extracted using an image binarization method.

[0018] Furthermore, the abnormal blood flow region is selected from the ultrasound images, including one ultrasound image parallel to the nerve and one ultrasound image perpendicular to the nerve. Then, using image binarization, pixels are divided into background or foreground based on a set threshold for each of the image's three color channels (red, green, and blue).

[0019]

[0020] Where B(i,j) represents the binarized image (0 or 1), I(i,j) is the pixel value of the original image, and [T1,T2] is a given threshold range (for each color channel), which converts the pixel values ​​of the image to 0 or 1 to extract abnormal blood flow signals.

[0021] Furthermore, in step 3, the feature parameters include: the proportion of longitudinal length, the proportion of transverse width, the proportion of abnormal blood flow signal pixels under longitudinal scanning, and the proportion of abnormal blood flow signal pixels under transverse scanning. The proportion of longitudinal length is the ratio of the longitudinal length of the abnormal blood flow signal region to the nerve thickness; the proportion of transverse width is the ratio of the transverse width of the abnormal blood flow signal region to the transverse width of the ROI region; the proportion of abnormal blood flow pixels is the ratio of the number of pixels in the abnormal blood flow signal region to the total number of pixels in the ROI region. The extracted feature parameters are normalized so that the mean of each feature value is zero and the standard deviation is 1.

[0022] Furthermore, in step 4, the extracted features—the proportion of longitudinal length (x1), the proportion of transverse width (x2), the proportion of abnormal blood flow pixels (x3), and the proportion of abnormal blood flow pixels (x4) under transverse scanning—are used as independent variables, and the degree of blood flow distribution abnormality (y) is used as the dependent variable. The model is established as follows:

[0023] y = a + b1x1 + b2x2 + b3x3 + b4x4

[0024] Where a, b1, b2, b3, b4 are model coefficients, which can be adjusted according to different application scenarios.

[0025] Furthermore, in step 5, the model established in step 4 is used to evaluate the ultrasound image containing abnormal blood flow signals to obtain quantitative results of its abnormal blood flow distribution, thereby realizing automated quantitative analysis of blood flow abnormalities. The analysis steps include normalizing the extracted feature parameter set X = [x1, x2, x3, x4] so that the mean of each feature is zero and the standard deviation is 1; determining the model coefficients; and calculating the degree of abnormality in blood flow distribution.

[0026] Furthermore, in similar analyses, for different detection objects, the ROI should be selected to have the same location, shape, and size to ensure detection consistency.

[0027] In a second aspect, the present invention provides an abnormal blood flow analysis device for ultrasound images, comprising:

[0028] The image acquisition module is used to acquire ultrasound images containing abnormal blood flow signals and preprocess them;

[0029] The image extraction module is used to extract abnormal blood flow signal regions from ultrasound images;

[0030] The model building module establishes a mathematical model between the combination of abnormal blood flow signal characteristic parameters and the abnormal blood flow distribution by calculating the characteristic parameters of the abnormal blood flow distribution area.

[0031] The image analysis module analyzes and quantifies abnormal blood flow signals in images based on mathematical models.

[0032] Thirdly, the present invention provides an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the above-described abnormal blood flow distribution characterization method.

[0033] Fourthly, the present invention provides a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the above-described abnormal blood flow distribution characterization method.

[0034] The beneficial effects of the present invention are: the method of the present invention can effectively extract the feature parameters of ultrasound blood flow images, automatically evaluate the abnormality of blood flow distribution in unknown images, significantly improve the efficiency and accuracy of abnormal blood flow signal analysis, and provide quantitative analysis results, and has wide applicability and versatility. Attached Figure Description

[0035] Figure 1 This is a flowchart illustrating the overall process of the method of this invention;

[0036] Figure 2 This is a schematic diagram of extracting abnormal blood flow signal regions under longitudinal scanning mode;

[0037] Figure 3 This is a schematic diagram of extracting abnormal blood flow signal regions under transverse scanning mode. Detailed Implementation

[0038] To provide a detailed explanation of the present invention, the specific implementation process of the present invention will now be described in detail with reference to the accompanying drawings and embodiments, thereby demonstrating the process of extracting and analyzing abnormal blood flow characteristic signals according to the present invention.

[0039] This embodiment proposes a method for characterizing abnormal blood flow distribution based on ultrasound images, and its implementation process is as follows: Figure 1 As shown.

[0040] First, images containing abnormal blood flow signals are acquired using ultrasound blood flow imaging, including one ultrasound image parallel to the nerve and one ultrasound image perpendicular to the nerve. Then, the abnormal blood flow signal region is extracted from the images using image binarization.

[0041] by Figure 2 , Figure 3 Taking ultrasound blood flow images under two scanning modes as an example Figure 2 (a) is the original ultrasound blood flow image without blood flow abnormalities under longitudinal scanning. Figure 2(c) is the original ultrasound blood flow image containing blood flow abnormalities under longitudinal scanning. Figure 2 (b) and Figure 2 (d) The corresponding binarized images after blood flow signal extraction, where the white area represents the location where blood flow abnormality occurs. Figure 3 (a) is the original ultrasound blood flow image without blood flow abnormalities under transverse scanning. Figure 3 (c) is the original ultrasound blood flow image containing blood flow abnormalities under transverse scanning. Figure 3 (b) and Figure 3 (d) The corresponding binarized images after blood flow signal extraction, where the white areas represent the locations of blood flow abnormalities. The four extracted features—the proportion of longitudinal length (x1), the proportion of transverse width (x2), the proportion of abnormal blood flow pixels (x3), and the proportion of abnormal blood flow pixels (x4) in the transverse scan—are used as independent variables, and the degree of blood flow distribution abnormality (y) is used as the dependent variable, and substituted into the model:

[0042] y = a + b1x1 + b2x2 + b3x3 + b4x4

[0043] Where a = 0.29, b1 = 3.35, b2 = 0.70, b3 = 3.71, and b4 = 0.19 are the coefficients of the model.

[0044] Finally, an image with normal blood flow was obtained. (-) =0.29, image containing blood flow abnormalities y (+) =3.55. This model can determine the presence or absence of abnormal blood flow and quantify the degree of blood flow abnormality by characterizing the abnormality degree y. The coefficients selected when forming the parameter combination can be adjusted according to specific circumstances and are not limited to the coefficients used in this embodiment.

[0045] This method can be used to analyze abnormal blood flow signal regions in ultrasound images. The extracted geometric features and model parameters can be adjusted according to specific application scenarios, and it can be widely used in fields such as medical imaging and biological research.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0047] All parts not covered in this invention are the same as or can be implemented using existing technologies.

Claims

1. A method for characterizing abnormal blood flow distribution based on ultrasound images, characterized in that, Includes the following steps: Step 1: Acquire ultrasound images containing abnormal blood flow signals and preprocess them; Step 2: Extract abnormal blood flow signal regions from ultrasound images; select abnormal blood flow regions in the ultrasound images, including one ultrasound image parallel to the nerve and one ultrasound image perpendicular to the nerve; then, using image binarization, for the three color channels of the image, divide the pixels into background or foreground according to the threshold set for each channel, i.e.: ， in, This represents the binarized image. These are the pixel values ​​of the original image. Given a threshold range, the pixel values ​​of the image are converted to 0 or 1 to extract abnormal blood flow signals; Step 3: Calculate the characteristic parameters of the abnormal blood flow distribution area; Step 4: Using the above feature parameters as independent variables, establish a mathematical model between the combination of abnormal blood flow signal feature parameters and the abnormal blood flow distribution; extract the features, and determine the proportion of longitudinal length under longitudinal section scanning. Horizontal width ratio Percentage of abnormal blood flow pixels and the percentage of abnormal blood flow pixels under transverse scanning Blood flow distribution abnormality as an independent variable As the dependent variable, the model is established as follows: ， in, These are model coefficients, which can be adjusted according to different application scenarios; Step 5: Analyze and quantify the abnormal blood flow signals in the image based on the mathematical model.

2. The method for characterizing abnormal blood flow distribution based on ultrasound images according to claim 1, characterized in that, In step 1, the dynamic characteristics of blood flow are analyzed by cross-convolution between consecutive frames of ultrasound images; the system receives two frames of echo signals. and ,in It is time. It represents the time delay, indicating the time interval between consecutive frames; calculate the cross-convolution between these two frames: ， in It is an integral variable; By analyzing the amplitude information of cross-convolution, the amplitude changes of blood flow are extracted to reflect the intensity of blood flow; by analyzing the phase information of cross-convolution results, the phase changes of blood flow are extracted to reflect the direction and velocity of blood flow.

3. The method for characterizing abnormal blood flow distribution based on ultrasound images according to claim 1, characterized in that, In step 2, abnormal blood flow signals are extracted using image binarization.

4. The method for characterizing abnormal blood flow distribution based on ultrasound images according to claim 1, characterized in that, In step 3, the feature parameters include: the proportion of longitudinal length, the proportion of transverse width, the proportion of abnormal blood flow signal pixels, and the proportion of abnormal blood flow signal pixels under transverse scanning.

5. The method for characterizing abnormal blood flow distribution based on ultrasound images according to claim 1, characterized in that, In step 5, the analysis step includes processing the extracted feature parameter set. Perform normalization to make the mean of each feature zero and the standard deviation 1; determine the model coefficients; The degree of abnormality in blood flow distribution was calculated.

6. The method for characterizing abnormal blood flow distribution based on ultrasound images according to claim 1, characterized in that, In step 5, in the analysis of similar situations, for different detection objects, the ROI should be selected with the same location, shape, and size to ensure detection consistency.

7. An abnormal blood flow analysis device for ultrasound images, characterized in that, A method for characterizing abnormal blood flow distribution as described in any one of claims 1 to 6 includes: The image acquisition module is used to acquire ultrasound images containing abnormal blood flow signals and preprocess them; The image extraction module is used to extract abnormal blood flow signal regions from ultrasound images; The model building module establishes a mathematical model between the combination of abnormal blood flow signal characteristic parameters and the abnormal blood flow distribution by calculating the characteristic parameters of the abnormal blood flow distribution area. The image analysis module analyzes and quantifies abnormal blood flow signals in images based on mathematical models.

8. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the abnormal blood flow distribution characterization method as described in any one of claims 1 to 6.

Images