Auxiliary diagnosis method and system for primary liver cancer based on imaging data

Abstract

The application relates to the technical field of MRI image analysis, in particular to a primary liver cancer auxiliary diagnosis method and system based on imaging data, which comprises the following steps: acquiring MRI images in different periods, acquiring the possibility that adjacent pixel points are located in the same tissue region according to the difference between the adjacent pixel points in the MRI images, acquiring a plurality of pixel point clusters in this way, acquiring a first liver cancer factor and a second liver cancer factor of the pixel point clusters in the arterial phase MRI images according to the pixel point clusters in different MRI images, acquiring the possibility that the corresponding region of the pixel point clusters in the arterial phase MRI images is a liver cancer region according to the first liver cancer factor and the second liver cancer factor, and judging whether the corresponding region of the pixel point clusters in the arterial phase MRI images is a liver cancer region. The application can accurately extract the features of the liver cancer region by analyzing the performance of the liver cancer region in the MRI images in different periods, so as to assist in detecting liver cancer.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of MRI image analysis, in particular to a primary liver cancer auxiliary diagnosis method and system based on imaging data. BACKGROUND

[0002] Hepatocellular Carcinoma (HCC) is one of the malignant tumors with high mortality rate worldwide, and early diagnosis is crucial to improve patient survival rate. At present, MRI imaging is an important means for clinical diagnosis of liver cancer, and its multi-phase enhancement scanning (such as arterial phase, portal venous phase, equilibrium phase, and delayed phase) can dynamically reflect the blood supply characteristics of the lesion. However, the traditional diagnosis method mainly relies on the experience of doctors, and there is a high subjectivity and a risk of missed diagnosis and misdiagnosis. SUMMARY

[0003] The present application provides a primary liver cancer auxiliary diagnosis method and system based on imaging data to solve the existing problems: traditional diagnosis of primary liver cancer by MRI imaging relies on the experience of doctors and may have the risk of missed diagnosis and misdiagnosis.

[0004] The primary liver cancer auxiliary diagnosis method and system based on imaging data of the present application adopts the following technical solutions:

[0005] One embodiment of the present application provides a primary liver cancer auxiliary diagnosis method based on imaging data, which comprises the following steps:

[0006] Obtain the initial MRI image, the arterial phase MRI image, the portal venous phase MRI image, the equilibrium phase MRI image, and the delayed phase MRI image, and obtain the human body region in each MRI image;

[0007] According to the pixel points in the local range of each pixel point in the human body region, obtain the blur degree of each pixel point in the human body region; according to the gray value and blur degree of adjacent pixel points in the human body region, obtain the possibility that the adjacent pixel points are located in the same tissue region; and according to the possibility that the adjacent pixel points are located in the same tissue region, divide the human body region into several pixel point clusters;

[0008] According to the pixel point clusters in different MRI images, obtain the first abnormality degree, the second abnormality degree, the third abnormality degree, and the fourth abnormality degree of the pixel point cluster as a whole in the arterial phase MRI image; and according to the first abnormality degree, the second abnormality degree, the third abnormality degree, and the fourth abnormality degree of the pixel point cluster as a whole in the arterial phase MRI image, obtain the first liver cancer factor and the second liver cancer factor of the pixel point cluster in the arterial phase MRI image;

[0009] According to the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image, the possibility that the region corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer region is obtained, and whether the region corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer region is judged.

[0010] Preferably, the method for obtaining the blur degree of each pixel point in the human body region according to the pixel points in the local range of each pixel point in the human body region comprises the following specific method:

[0011] For any pixel point in any human body region, a local window with a size of 2 is constructed with the pixel point in the human body region as the center, so as to obtain the local window of the pixel point in the human body region; for each pixel point in the local window of the pixel point in the human body region, if the gray values of the pixel points in the eight-neighborhood of the pixel point are all less than the gray value of the pixel point, the pixel point is recorded as a maximum value point.

[0012] For each maximum value point in the local window of the pixel point in the human body region, each maximum value point in the local window of the pixel point in the human body region is connected with other maximum value points, so as to obtain a plurality of line segments of the maximum value point, and the pixel points on the line segment of the maximum value point are taken as the control points of the maximum value point; according to the distances between all maximum value points in the local window of the pixel point in the human body region and the differences in gray values between all maximum value points and their control points, the blur degree of the pixel point in the human body region is obtained, and the specific calculation formula is as follows:

[0013] ;

[0014] In the formula, Blur represents the blur degree of the pixel point in the human body region; MaxNum represents the number of maximum value points in the local window of the pixel point in the human body region; Dist represents the distance between the i th maximum value point and the j th maximum value point in the local window of the pixel point in the human body region; Num represents the number of control points of the i th maximum value point in the local window of the pixel point in the human body region; ​​​​​​​​​​ The gray value of the maximum value; The pixel point in the human body area is represented by the first pixel in the local window. The maximum value of Gray value of the control point; represents the absolute value function; represents the linear normalization function.

[0015] Preferably, the method of obtaining the possibility that adjacent pixels in the human body region are located in the same tissue region according to the grayscale values ​​and blur levels of adjacent pixels in the human body region includes the following specific methods:

[0016] For any two adjacent pixels in any human body region, the similarity between the two adjacent pixels in the human body region is obtained according to the grayscale value and blur degree of the two adjacent pixels in the human body region. The specific calculation formula is:

[0017] ;

[0018] Where, Indicates the possibility that the two adjacent pixels in the human body region are located in the same tissue region; Indicates the difference in blur degree between the two adjacent pixels in the human body area; represents the difference in grayscale values ​​between the two adjacent pixels in the human body region; represents the average value of the blur levels of the two adjacent pixels in the human body area; represents the absolute value function; Represents an exponential function with a natural constant as its base.

[0019] Preferably, the method of obtaining the first abnormality degree of the entire pixel cluster in the arterial phase MRI image includes the following specific methods:

[0020] For a human body region in any MRI image, the grayscale mean of all pixels in the human body region in the MRI image is used as the overall grayscale of the MRI image;

[0021] For any pixel cluster in the arterial phase MRI image, pixel points, and the coordinates of all MRI images are compared with the The pixel point with the same pixel points as the first The corresponding pixel point of the pixel point; The pixel point corresponding to the pixel point in the initial MRI image is The difference in grayscale value of pixels is used as the The first abnormal feature of the pixel;

[0022] Obtaining first abnormal features of all pixels in the pixel cluster in the arterial phase MRI image, and taking an average of the first abnormal features of all pixels in the pixel cluster in the arterial phase MRI image as the first abnormal feature of the entire pixel cluster in the arterial phase MRI image;

[0023] The difference between the overall grayscale difference between the initial MRI image and the arterial phase MRI image is subtracted from the first abnormal feature of the entire pixel cluster in the arterial phase MRI image to obtain the first abnormality degree of the pixel cluster in the arterial phase MRI image.

[0024] Preferably, the specific method for obtaining the second abnormality degree is:

[0025] The said The pixel point corresponding to the pixel point in the portal venous phase MRI image is the same as the pixel point in the The difference in grayscale value of pixels is used as the The second abnormal feature of the pixel;

[0026] Obtaining the second abnormality features of all pixels in the pixel cluster in the arterial phase MRI image, and taking the average of the second abnormality features of all pixels in the pixel cluster in the arterial phase MRI image as the second abnormality feature of the entire pixel cluster in the arterial phase MRI image;

[0027] The second abnormality level of the pixel cluster in the arterial phase MRI image is obtained by subtracting the difference in overall grayscale between the arterial phase MRI image and the portal venous phase MRI image from the second abnormality feature of the pixel cluster in the arterial phase MRI image.

[0028] Preferably, the specific method for obtaining the third abnormality degree is:

[0029] The said The pixel point corresponding to the pixel point in the equilibrium period MRI image is the same as the pixel point in the equilibrium period MRI image. The difference in grayscale value of pixels is used as the The third abnormal feature of the pixel;

[0030] Obtaining the third abnormal feature of all pixels in the pixel cluster in the arterial phase MRI image, and taking the average of the third abnormal features of all pixels in the pixel cluster in the arterial phase MRI image as the third abnormal feature of the entire pixel cluster in the arterial phase MRI image;

[0031] The third abnormality level of the pixel cluster in the arterial phase MRI image is obtained by subtracting the difference in overall grayscale between the arterial phase MRI image and the equilibrium phase MRI image from the overall third abnormality feature of the pixel cluster in the arterial phase MRI image.

[0032] Preferably, the specific method for obtaining the fourth abnormality degree is:

[0033] The said The pixel point in the equilibrium MRI image corresponds to the pixel point The difference in grayscale value between the corresponding pixel points in the delayed MRI image is used as the first pixel point. The fourth abnormal feature of the pixel;

[0034] Obtaining the fourth abnormality feature of all pixels in the pixel cluster in the arterial phase MRI image, and taking the average of the fourth abnormality features of all pixels in the pixel cluster in the arterial phase MRI image as the fourth abnormality feature of the entire pixel cluster in the arterial phase MRI image;

[0035] The fourth abnormality level of the pixel cluster in the arterial phase MRI image is obtained by subtracting the difference in overall grayscale between the equilibrium phase MRI image and the delayed phase MRI image from the fourth abnormality feature of the pixel cluster in the arterial phase MRI image.

[0036] Preferably, the obtaining of the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image includes the following specific methods:

[0037] For any pixel cluster in the arterial phase MRI image, the absolute value of the product of the first abnormality, the second abnormality degree, and the third abnormality degree of the pixel cluster is used as the first liver cancer factor of the pixel cluster in the arterial phase MRI image;

[0038] For any pixel cluster in the arterial phase MRI image, the pixel clusters adjacent to the pixel cluster in the arterial phase MRI image are used as the neighborhood cluster of the pixel cluster; based on the differences between the neighborhood cluster of the pixel cluster and the pixel cluster in the first abnormality degree, the second abnormality degree, and the third abnormality degree, the second liver cancer factor of the pixel cluster in the arterial phase MRI image is obtained, and the specific calculation formula is:

[0039] ;

[0040] Where, A second liver cancer factor representing the pixel cluster in the arterial phase MRI image; represents the number of neighboring clusters of the pixel cluster in the arterial phase MRI image; a difference between the neighborhood cluster of the pixel cluster and the pixel cluster in the first abnormality degree; a difference between the neighborhood cluster of the pixel cluster and the pixel cluster in the second abnormality degree; a difference between the neighborhood cluster of the pixel cluster and the pixel cluster in the third abnormality degree; a difference between the neighborhood cluster of the pixel cluster and the pixel cluster in the fourth abnormality degree; a linear normalization function.

[0041] Preferably, the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image are used to obtain the possibility that the region corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer region, and to determine whether the region corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer region, including the following specific method:

[0042] For any pixel cluster in the arterial phase MRI image, the product of the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image is normalized, and the normalized result is used as the possibility that the region corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer region;

[0043] A possibility threshold is preset For any pixel cluster in the arterial phase MRI image, if the possibility that the region corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer region is greater than or equal to the possibility threshold, then the region corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer region.

[0044] The application also provides an auxiliary diagnosis system for primary liver cancer based on imaging data, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of any one of the auxiliary diagnosis methods for primary liver cancer based on imaging data.

[0045] The embodiment of the application provides an auxiliary diagnosis system for primary liver cancer based on imaging data, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of any one of the auxiliary diagnosis methods for primary liver cancer based on imaging data.

[0046] The beneficial effects of the technical solutions of the present application are as follows: the present application collects MRI images at different periods, obtains the possibility that adjacent pixel points are located in the same tissue region according to the difference between adjacent pixel points in the MRI images, and obtains a plurality of pixel point clusters. Since the MRI images contain various tissues in the human body, accurate acquisition of the corresponding region of liver cancer in the MRI images requires that the MRI images be divided into a plurality of pixel point clusters. Since the difference within the same tissue is small, the human body region can be divided into a plurality of pixel point clusters by analyzing the difference between adjacent pixel points in the human body region.

[0047] Since the liver cancer tissue is more susceptible to the influence of the contrast agent than the normal tissue, and the liver cancer is mainly supplied by the hepatic artery, while the normal liver tissue is supplied by the portal vein and the hepatic artery, the first and second liver cancer factors of the pixel point cluster in the arterial phase MRI image are obtained according to the difference between the pixel points in the other MRI images, which are used to accurately evaluate the possibility that the corresponding region of the pixel point cluster in the arterial phase MRI image is a liver cancer region. Finally, whether the corresponding region of the pixel point cluster in the arterial phase MRI image is a liver cancer region is determined according to the possibility that the corresponding region of the pixel point cluster in the arterial phase MRI image is a liver cancer region. The present application accurately extracts the characteristics of the liver cancer region in the MRI image by comparative analysis of the MRI images at different periods, thereby improving the accuracy of auxiliary detection of liver cancer. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0049] Figure 1 The step flow chart of the present application is based on the imaging data of the primary liver cancer auxiliary diagnosis method. DETAILED DESCRIPTION

[0050] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following will combine the drawings and the preferred embodiments to specifically describe the imaging data based primary liver cancer auxiliary diagnosis method and system according to the present application, its specific implementation, structure, features and effects as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0052] The application provides a method and system for assisting diagnosis of primary liver cancer based on imaging data.

[0053] Referring to Figure 1 , a flow chart of steps of a method for assisting diagnosis of primary liver cancer based on imaging data is shown, which comprises the following steps:

[0054] Step S001: acquiring initial MRI images, arterial phase MRI images, portal vein phase MRI images, equilibrium phase MRI images and delayed phase MRI images, and acquiring human body regions in each MRI image.

[0055] It should be noted that the embodiment is a method for assisting diagnosis of primary liver cancer based on imaging data, and the specific purpose is to detect whether a patient has liver cancer through MRI images of the patient; therefore, the MRI images of the patient need to be collected first, and the background part of the MRI images also needs to be removed to avoid interference of the background region.

[0056] Specifically, the patient is laid on an MRI scanning bed, and a contrast agent is injected into the patient through intravenous injection to collect the initial MRI images, the arterial phase MRI images, the portal vein phase MRI images, the equilibrium phase MRI images and the delayed phase MRI images.

[0057] Further, the background part of each MRI image is removed through a semantic segmentation algorithm to obtain the human body region in each MRI image.

[0058] It should be noted that the initial MRI images are MRI images collected within 20 seconds after injection of the contrast agent; the arterial phase MRI images are MRI images collected within 20 to 30 seconds after injection of the contrast agent; the portal vein phase MRI images are MRI images collected within 50 to 60 seconds after injection of the contrast agent; the equilibrium phase MRI images are MRI images collected within 3 to 5 minutes after injection of the contrast agent; the delayed phase MRI images are MRI images collected within 5 to 10 minutes after injection of the contrast agent; and since the collection of the MRI images and the semantic segmentation algorithm are both known prior art, they will not be described herein.

[0059] Step S002: obtaining the blur degree of each pixel point in the human body region according to the pixel points in the local range of each pixel point in the human body region; obtaining the possibility that adjacent pixel points in the human body region are located in the same tissue region according to the gray values and blur degrees of the adjacent pixel points in the human body region; and dividing the human body region into a plurality of pixel point clusters according to the possibility that the adjacent pixel points in the human body region are located in the same tissue region.

[0060] It should be noted that the human body region in the MRI image contains various tissues in the human body. In order to accurately obtain the corresponding region of liver cancer in the MRI image, such as bones, muscles, liver, liver cancer and the like, the differences between the various tissues in the MRI image are large, and the differences within the various tissues in the MRI image are small. Therefore, the human body region can be divided into a plurality of pixel point clusters by analyzing the differences between the adjacent pixel points in the human body region, and one pixel point cluster corresponds to one tissue region.

[0061] It should be further noted that in a clear image, a sharp edge or detail will form a sparse and concentrated maximum value point, and the surrounding pixel gray values change gently; and blur will cause feature diffusion, and the maximum value points are more densely distributed, and the smooth effect of blur will cause the pixel gray values in the region between the maximum value points to be significantly reduced, forming a larger difference. Therefore, the more densely the maximum value points are and the more obvious the difference is, the more the high-frequency details of the image are weakened, and the higher the blur degree is. Therefore, the blur degree of a pixel point can be obtained based on this.

[0062] Specifically, for any pixel point in any human body region, a local window with the pixel point in the human body region as the center is constructed, and the local window of the pixel point in the human body region is obtained. The specific value of the size of the local window can be set by itself in combination with the actual situation, and the present embodiment does not make a hard requirement. In the present embodiment, the size of the local window is taken as an example for description; for the first pixel point in the local window of the pixel point in the human body region, if the gray values of the pixel points in the eight-neighbor region of the first pixel point are all less than the gray value of the first pixel point, the first pixel point is recorded as a maximum value point. For the first maximum value point in the local window of the pixel point in the human body region, a line segment is connected between the first maximum value point and each of the other maximum value points in the local window of the pixel point in the human body region, and a plurality of line segments of the first maximum value point are obtained. The pixel points located on the line segments of the first maximum value point are taken as the first maximum value point cluster.

[0063] Further, for the first maximum value point in the local window of the pixel point in the human body region, a line segment is connected between the first maximum value point and each of the other maximum value points in the local window of the pixel point in the human body region, and a plurality of line segments of the first maximum value point are obtained. The pixel points located on the line segments of the first maximum value point are taken as the first maximum value point cluster. ​​​​​​​The contrast point of the maximum point; according to the distance between all maximum points in the local window of the pixel point in the human body region and the difference in gray scale between the maximum points and their contrast points, the blur degree of the pixel point in the human body region is obtained, and the specific calculation formula is:

[0064] ;

[0065] In the formula, the blur degree of the pixel point in the human body region is represented; the number of maximum points in the local window of the pixel point in the human body region is represented; the distance between the first maximum point and the second maximum point in the local window of the pixel point in the human body region is represented; the distance between the first maximum point and the second maximum point in the local window of the pixel point in the human body region is represented; the number of contrast points of the first maximum point in the local window of the pixel point in the human body region is represented; the gray scale value of the first maximum point in the local window of the pixel point in the human body region is represented; the gray scale value of the first contrast point of the first maximum point in the local window of the pixel point in the human body region is represented; the gray scale value of the first contrast point of the first maximum point in the local window of the pixel point in the human body region is represented; the gray scale value of the first contrast point of the first maximum point in the local window of the pixel point in the human body region is represented; the gray scale value of the first contrast point of the first maximum point in the local window of the pixel point in the human body region is represented; the gray scale value of the first contrast point of the first maximum point in the local window of the pixel point in the human body region is represented; the absolute value function is represented; the linear normalization function is represented, and the specific normalization range is the gray scale value of all pixel points in all human body regions; .

[0066] It should be noted that, the density of all maximum points in the local window of the pixel point in the human body region is represented; the difference in gray scale between the pixel points and the maximum points located between the maximum points in the local window of the pixel point in the human body region is represented; since the more dense the distribution of maximum points in the local range of the pixel point and the greater the difference in gray scale between the pixel points and the maximum points, the more blurred the pixel is, and therefore the greater the value, the more blurred the pixel point in the human body region is; in this embodiment, the specific calculation process of the difference is the absolute value of the difference between two values.

[0067] ​It needs to be further explained that when the blur degree of two adjacent pixel points is large, it indicates that the high frequency information (such as edges, textures) of the region where they are located has been significantly suppressed, resulting in the original possible gray difference being reduced due to smoothing. If the difference between the gray values of the two is small, it further indicates that they originally may have similar tissue characteristics, that is, the two adjacent pixel points are more likely to be located in the same tissue region, so the similarity between the two adjacent pixel points in the human body region can be obtained according to the blur degree and the gray value of the two adjacent pixel points in the human body region.

[0068] Specifically, for any two adjacent pixel points in any human body region, the similarity between the two adjacent pixel points in the human body region is obtained according to the gray value and the blur degree of the two adjacent pixel points in the human body region. The specific calculation formula is:

[0069] ;

[0070] In the formula, represents the possibility of the two adjacent pixel points in the human body region being located in the same tissue region; represents the difference in blur degree between the two adjacent pixel points in the human body region; represents the difference in gray value between the two adjacent pixel points in the human body region; represents the average of the blur degree of the two adjacent pixel points in the human body region; represents the absolute value function; represents the exponential function with a natural constant as the base.

[0071] It needs to be noted that since the smaller the difference between the blur degree and the gray value of the two adjacent pixel points, and the larger the blur degree of the two adjacent pixel points, the more likely the two adjacent pixel points are located in the same tissue region, the value of is larger, the more likely the two adjacent pixel points in the human body region are located in the same tissue region. That is, the human body region can be divided into several tissue regions based on this.

[0072] Specifically, for any pixel point in any human body region, the similarity between the pixel point and each adjacent pixel point in the human body region is obtained, and the adjacent pixel point with the highest similarity to the pixel point in the human body region is classified into the same pixel point cluster.

[0073] Similarly, all pixel points in the human body region are classified to obtain several pixel point clusters of the human body region.

[0074] Thus, several pixel point clusters of the human body region are obtained.

[0075] Step S003: obtaining the first abnormality degree, the second abnormality degree, the third abnormality degree and the fourth abnormality degree of the pixel cluster as a whole in the arterial phase MRI image according to the pixel cluster in different MRI images; obtaining the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image according to the first abnormality degree, the second abnormality degree, the third abnormality degree and the fourth abnormality degree of the pixel cluster as a whole in the arterial phase MRI image.

[0076] It should be noted that the pixels in a pixel cluster in the MRI image are all pixels in the same tissue of the patient, and the pixels in adjacent pixel clusters in the MRI image are pixels in different tissues of the patient. In addition, the liver cancer tissue is more susceptible to the influence of the contrast agent than the normal tissue. Therefore, the abnormal features of the pixel cluster can be obtained by comparing the gray scale changes of the pixels in the pixel cluster in different MRI images, and the first liver cancer factor and the second liver cancer factor of the pixel cluster can be further obtained according to the abnormal features of the pixel cluster, which are used for subsequent evaluation of the possibility of the region corresponding to the pixel cluster being a liver cancer region.

[0077] Specifically, for a human region in any MRI image, the average gray scale of all pixels in the human region in the MRI image is taken as the overall gray scale of the MRI image.

[0078] For the first pixel in any pixel cluster in the arterial phase MRI image, all pixels with the same coordinates as the first pixel in all MRI images are taken as corresponding pixels of the first pixel. The difference in gray scale between the corresponding pixel of the first pixel in the initial MRI image and the first pixel is taken as the first abnormal feature of the first pixel.

[0079] Similarly, the first abnormal features of all pixels in the pixel cluster in the arterial phase MRI image are obtained, and the average of the first abnormal features of all pixels in the pixel cluster in the arterial phase MRI image is taken as the first abnormal feature of the pixel cluster as a whole in the arterial phase MRI image.

[0080] Further, the first abnormal feature of the pixel cluster as a whole in the arterial phase MRI image is subtracted by the difference between the overall gray scale of the initial MRI image and the arterial phase MRI image, and the result is taken as the first abnormality degree of the pixel cluster in the arterial phase MRI image. The specific calculation formula is as follows:

[0081] ​​​​​​​

[0082] wherein, represents the first abnormality degree of the pixel cluster in the arterial phase MRI image; represents the first abnormality feature of the whole pixel cluster in the arterial phase MRI image; represents the difference in overall gray scale between the initial MRI image and the arterial phase MRI image.

[0083] the difference in gray scale value between the corresponding pixel of the first pixel in the portal phase MRI image and the first pixel is taken as the second abnormality feature of the first pixel; the difference in gray scale value between the corresponding pixel of the first pixel in the equilibrium phase MRI image and the first pixel is taken as the third abnormality feature of the first pixel; Similarly, the second abnormality features of all the pixels in the pixel cluster in the arterial phase MRI image are obtained, and the mean value of the second abnormality features of all the pixels in the pixel cluster in the arterial phase MRI image is taken as the second abnormality feature of the whole pixel cluster in the arterial phase MRI image;

[0084] Further, the second abnormality feature of the whole pixel cluster in the arterial phase MRI image is subtracted by the difference in overall gray scale between the arterial phase MRI image and the portal phase MRI image, as the second abnormality degree of the pixel cluster in the arterial phase MRI image, and the specific calculation formula is:

[0085]

[0086] ;

[0087] wherein, represents the second abnormality degree of the pixel cluster in the arterial phase MRI image; represents the second abnormality feature of the whole pixel cluster in the arterial phase MRI image; represents the difference in overall gray scale between the arterial phase MRI image and the portal phase MRI image.

[0088] the difference in gray scale value between the corresponding pixel of the first pixel in the equilibrium phase MRI image and the first pixel is taken as the third abnormality feature of the first pixel; the difference in gray scale value between the corresponding pixel of the first pixel in the equilibrium phase MRI image and the first pixel is taken as the third abnormality feature of the first pixel; Similarly, the third abnormality features of all the pixels in the pixel cluster in the arterial phase MRI image are obtained, and the mean value of the third abnormality features of all the pixels in the pixel cluster in the arterial phase MRI image is taken as the third abnormality feature of the whole pixel cluster in the arterial phase MRI image;

[0089]

[0090] ​​​​Further, the third abnormality feature of the pixel cluster in the arterial phase MRI image is subtracted by the difference of the difference of the overall gray scale between the arterial phase MRI image and the equilibrium phase MRI image, as the third abnormality degree of the pixel cluster in the arterial phase MRI image, and the specific calculation formula is:

[0091] ;

[0092] In the formula, represents the third abnormality degree of the pixel cluster in the arterial phase MRI image; represents the third abnormality feature of the pixel cluster in the arterial phase MRI image as a whole; represents the difference of the overall gray scale between the arterial phase MRI image and the equilibrium phase MRI image.

[0093] The fourth abnormality feature of the first pixel point is obtained by subtracting the difference of the gray scale value between the corresponding pixel point of the first pixel point in the equilibrium phase MRI image and the corresponding pixel point of the first pixel point in the delayed phase MRI image. The fourth abnormality feature of the first pixel point is obtained by subtracting the difference of the gray scale value between the corresponding pixel point of the first pixel point in the equilibrium phase MRI image and the corresponding pixel point of the first pixel point in the delayed phase MRI image.

[0094] Similarly, the fourth abnormality feature of all pixel points in the pixel cluster in the arterial phase MRI image is obtained, and the mean value of the fourth abnormality feature of all pixel points in the pixel cluster in the arterial phase MRI image is taken as the fourth abnormality feature of the pixel cluster in the arterial phase MRI image as a whole.

[0095] Further, the fourth abnormality feature of the pixel cluster in the arterial phase MRI image is subtracted by the difference of the difference of the overall gray scale between the equilibrium phase MRI image and the delayed phase MRI image, as the fourth abnormality degree of the pixel cluster in the arterial phase MRI image, and the specific calculation formula is:

[0096] ;

[0097] In the formula, represents the fourth abnormality degree of the pixel cluster in the arterial phase MRI image; represents the fourth abnormality feature of the pixel cluster in the arterial phase MRI image as a whole; represents the difference of the overall gray scale between the equilibrium phase MRI image and the delayed phase MRI image.

[0098] ​​It should be noted that the first, second, third and fourth abnormality degrees of the pixel point cluster in the above arterial phase MRI image are for measuring the gray level change degree of the pixel points in the pixel point cluster; since the liver cancer tissue is more susceptible to the influence of the contrast agent than the normal tissue, the greater the gray level change degree of the pixel points in the pixel point cluster, the more abnormal the pixel point cluster. Since the liver cancer is mainly supplied by the hepatic artery, it will show early significant enhancement in the arterial phase, so the first, second and third abnormality degrees are obtained by comparing the differences in gray values between the arterial phase MRI image and other MRI images; and since the gray values of the pixel points gradually increase from the initial MRI image to the equilibrium phase MRI image, and gradually decrease from the equilibrium phase MRI image to the delayed phase MRI image, the fourth abnormality degree is obtained by comparing the differences in gray values between the equilibrium phase MRI image and the delayed phase MRI image.

[0099] It should be further noted that the greater the first, second, third and fourth abnormality degrees of the pixel point cluster in the arterial phase MRI image, the more likely the pixel point cluster in the arterial phase MRI image is a liver cancer region, so the first liver cancer factor of the pixel point cluster is obtained based on this; and since the liver cancer is mainly supplied by the hepatic artery, and the normal liver tissue is double-supplied by the portal vein and the hepatic artery, with a blood supply ratio of about 3:1, if the pixel point cluster is a liver cancer region, the difference between the pixel point cluster and its adjacent pixel point cluster in the first abnormality degree is much greater than the differences in the second, third and fourth abnormality degrees, so the second liver cancer factor of the pixel point cluster in the arterial phase MRI image can be obtained.

[0100] Specifically, for any pixel point cluster in the arterial phase MRI image, the absolute value of the product of the first, second and third abnormality degrees of the pixel point cluster is taken as the first liver cancer factor of the pixel point cluster in the arterial phase MRI image.

[0101] Further, for any pixel point cluster in the arterial phase MRI image, the pixel point clusters adjacent to the pixel point cluster in the arterial phase MRI image are taken as the neighborhood clusters of the pixel point cluster; the second liver cancer factor of the pixel point cluster in the arterial phase MRI image is obtained according to the differences between the neighborhood clusters of the pixel point cluster and the pixel point cluster in the first, second and third abnormality degrees, and the specific calculation formula is:

[0102] ;

[0103] In the formula, represents the second liver cancer factor of the pixel point cluster in the arterial phase MRI image; represents the number of neighborhood clusters of the pixel point cluster in the arterial phase MRI image. Indicates the difference between the neighborhood cluster of the pixel cluster and the pixel cluster in terms of the first abnormality degree; Indicates the difference between the neighborhood cluster of the pixel cluster and the pixel cluster in a second abnormality degree; Indicates the difference between the neighboring cluster of the pixel cluster and the pixel cluster in a third abnormality degree; Indicates the difference between the neighboring cluster of the pixel cluster and the pixel cluster in a fourth abnormality degree; Represents a linear normalization function, whose specific normalization range is all pixel clusters in the arterial phase MRI image .

[0104] It should be noted that and The larger the ratio, the greater the difference between the pixel cluster and its adjacent pixel clusters in the first abnormality level is than the difference in the second, third, and fourth abnormality levels, that is, the more the pixel cluster has the characteristics of the liver cancer area.

[0105] Thus, the first liver cancer factor and the second liver cancer factor of all pixel clusters in the arterial phase MRI image are obtained.

[0106] Step S004: Based on the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image, the possibility that the area corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer area is obtained, and whether the area corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer area is determined.

[0107] It should be noted that after obtaining the first liver cancer factor and the second liver cancer factor for each pixel cluster in the arterial phase MRI image through the above-mentioned step S003, the possibility that the area corresponding to each pixel cluster in the arterial phase MRI image is a liver cancer area can be quantified based on the first liver cancer factor and the second liver cancer factor for each pixel cluster in the arterial phase MRI image. Further, based on the possibility that the area corresponding to each pixel cluster in the arterial phase MRI image is a liver cancer area, whether the patient has liver cancer can be determined.

[0108] Specifically, for any pixel cluster in the arterial phase MRI image, the product of the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image is normalized, and the normalized result is used as the possibility that the area corresponding to the pixel cluster in the arterial phase MRI image is a liver cancer area; in this embodiment, the specific function for normalizing the product of the first liver cancer factor and the second liver cancer factor is: function.

[0109] Furthermore, a probability threshold is preset , The specific value of can be set according to the actual situation. This embodiment does not make a hard requirement. For example, for any pixel cluster in the arterial phase MRI image, if the probability that the area corresponding to the pixel cluster in the arterial phase MRI image is the liver cancer area is greater than or equal to , then the region corresponding to the pixel cluster in the arterial phase MRI image is the liver cancer region; if the possibility that the region corresponding to the pixel cluster in the arterial phase MRI image is the liver cancer region is less than , then the area corresponding to the pixel cluster in the arterial phase MRI image is not a liver cancer area.

[0110] This embodiment provides an auxiliary diagnosis system for primary liver cancer based on imaging data, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the auxiliary diagnosis method for primary liver cancer based on imaging data in steps S001 to S004 is implemented.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A primary liver cancer auxiliary diagnosis system based on imaging data, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, characterized in that, The computer program is executed by the processor to realize the steps of the auxiliary diagnosis method for primary liver cancer based on imaging data, and the method comprises the following steps: Obtain initial MRI images, arterial phase MRI images, portal vein phase MRI images, equilibrium phase MRI images and delayed phase MRI images, and obtain the human body region in each MRI image; According to the pixel points in the local range of each pixel point in the human body region, the blur degree of each pixel point in the human body region is obtained; according to the gray value and blur degree of adjacent pixel points in the human body region, the possibility that adjacent pixel points in the human body region are located in the same tissue region is obtained; according to the possibility that adjacent pixel points in the human body region are located in the same tissue region, the human body region is divided into a plurality of pixel point cluster classes; According to the pixel point cluster classes in different MRI images, the first abnormality degree, the second abnormality degree, the third abnormality degree and the fourth abnormality degree of the pixel point cluster class in the arterial phase MRI image are obtained; For the human body region in any MRI image, the average gray value of all pixel points in the human body region in the MRI image is taken as the overall gray value of the MRI image; For any pixel cluster in the arterial phase MRI image, pixel points, and the coordinates of all MRI images are compared with the The pixel point with the same pixel points as the first The corresponding pixel point of the pixel point; The pixel point corresponding to the pixel point in the initial MRI image is The difference in grayscale value of pixels is used as the The first abnormal feature of the pixel; Obtain the first abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image, and take the average value of the first abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image as the first abnormality feature of the pixel point cluster class in the arterial phase MRI image as a whole; Subtract the difference between the difference in overall gray value between the initial MRI image and the arterial phase MRI image from the first abnormality feature of the pixel point cluster class in the arterial phase MRI image as a whole, to obtain the first abnormality degree of the pixel point cluster class in the arterial phase MRI image; The said The pixel point corresponding to the pixel point in the portal venous phase MRI image is the same as the pixel point in the The difference in grayscale value of pixels is used as the The second abnormal feature of the pixel; Obtain the second abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image, and take the average value of the second abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image as the second abnormality feature of the pixel point cluster class in the arterial phase MRI image as a whole; Subtract the difference between the difference in overall gray value between the arterial phase MRI image and the portal vein phase MRI image from the second abnormality feature of the pixel point cluster class in the arterial phase MRI image as a whole, to obtain the second abnormality degree of the pixel point cluster class in the arterial phase MRI image; a difference in gray value between the first pixel point and a pixel point corresponding to the first pixel point in the equilibrium phase MRI image is taken as a third abnormal feature of the first pixel point. a difference in gray value between the first pixel point and a pixel point corresponding to the first pixel point in the equilibrium phase MRI image is taken as a third abnormal feature of the first pixel point. a difference in gray value between the first pixel point and a pixel point corresponding to the first pixel point in the equilibrium phase MRI image is taken as a third abnormal feature of the first pixel point. a difference in gray value between the first pixel point Obtain the third abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image, and take the average value of the third abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image as the third abnormality feature of the pixel point cluster class in the arterial phase MRI image as a whole; Subtract the difference between the difference in overall gray value between the arterial phase MRI image and the equilibrium phase MRI image from the third abnormality feature of the pixel point cluster class in the arterial phase MRI image as a whole, to obtain the third abnormality degree of the pixel point cluster class in the arterial phase MRI image; The said The pixel point in the equilibrium MRI image corresponds to the pixel point The difference in grayscale value between the corresponding pixel points in the delayed MRI image is used as the first pixel point. The fourth abnormal feature of the pixel; Obtain the fourth abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image, and take the average value of the fourth abnormality feature of all pixel points in the pixel point cluster class in the arterial phase MRI image as the fourth abnormality feature of the pixel point cluster class in the arterial phase MRI image as a whole; Subtracting the difference of the difference of the fourth abnormality feature of the pixel cluster in the arterial phase MRI image and the difference of the overall gray scale of the equilibrium phase MRI image and the delay phase MRI image as the fourth abnormality degree of the pixel cluster in the arterial phase MRI image; According to the first abnormality degree, the second abnormality degree, the third abnormality degree and the fourth abnormality degree of the pixel cluster in the arterial phase MRI image, the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image are obtained; For any pixel cluster in the arterial phase MRI image, the absolute value of the product of the first abnormality degree, the second abnormality degree and the third abnormality degree of the pixel cluster is taken as the first liver cancer factor of the pixel cluster in the arterial phase MRI image; For any pixel cluster in the arterial phase MRI image, the pixel cluster adjacent to the pixel cluster in the arterial phase MRI image is taken as the neighborhood cluster of the pixel cluster, and the second liver cancer factor of the pixel cluster in the arterial phase MRI image is obtained according to the difference between the neighborhood cluster and the pixel cluster in the first abnormality degree, the second abnormality degree and the third abnormality degree, and the specific calculation formula is: ； In the formula, represents a second liver cancer factor of the pixel cluster class in the arterial phase MRI image; represents a number of neighborhood cluster classes of the pixel cluster class in the arterial phase MRI image; represents a difference between the neighborhood cluster class and the pixel cluster class in the first abnormality degree; represents a difference between the neighborhood cluster class and the pixel cluster class in the second abnormality degree; represents a difference between the neighborhood cluster class and the pixel cluster class in the third abnormality degree; represents a difference between the neighborhood cluster class and the pixel cluster class in the fourth abnormality degree; represents a linear normalization function; According to the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image, the possibility that the corresponding region of the pixel cluster in the arterial phase MRI image is a liver cancer region is obtained, and whether the corresponding region of the pixel cluster in the arterial phase MRI image is a liver cancer region is determined.

2. The system for auxiliary diagnosis of primary liver cancer based on imaging data according to claim 1, wherein, The method for obtaining the blur degree of each pixel point in the human body region according to the pixel points in the local range of each pixel point in the human body region includes the following specific method: For any pixel point in any human body area, a pixel point in the human body area is constructed with the pixel point in the human body area as the center. The local window of the pixel point in the human body area is obtained by using a local window of the pixel point in the human body area; pixels, if the If the grayscale values ​​of the pixels in the eight neighborhoods of the pixel are smaller than the grayscale values ​​of the pixel, then the pixel Pixel points are recorded as maximum points; For the local window of the pixel point in the human body area maximum value points, connecting the maximum value point in the local window of the pixel point in the human body area with each other The maximum point is obtained The line segments of the maximum point will be located at the The pixel point on the line segment of the maximum point is taken as the The blur degree of the pixel point in the human body area is obtained according to the distance between all the maximum points in the local window of the pixel point in the human body area and the difference in grayscale between all the maximum points and their reference points. The specific calculation formula is: ； Where, Indicates the blur degree of the pixel point in the human body area; The number of maximum value points in the local window representing the pixel point in the human body area; The pixel point in the human body area is represented by the first pixel in the local window. The first and The distance between the maximum points; The pixel point in the human body area is represented by the first pixel in the local window. The number of control points for each maximum point; The pixel point in the human body area is represented by the first pixel in the local window. The gray value of the maximum value; The pixel point in the human body area is represented by the first pixel in the local window. The maximum value of Gray value of the control point; represents the absolute value function; represents the linear normalization function. 3.The system for auxiliary diagnosis of primary liver cancer based on imaging data according to claim 1, wherein, The method for obtaining the possibility that adjacent pixel points in the human body region are located in the same tissue region according to the gray scale value and the blur degree of the adjacent pixel points in the human body region includes the following specific method: For any two adjacent pixel points in any human body region, the similarity degree of the two adjacent pixel points in the human body region is obtained according to the gray scale value and the blur degree of the two adjacent pixel points in the human body region, and the specific calculation formula is: ； In the formula, represents the possibility that the two adjacent pixel points in the human body region are located in the same tissue region; represents the difference in blur degree of the two adjacent pixel points in the human body region; represents the difference in gray value of the two adjacent pixel points in the human body region; represents the mean value of the blur degree of the two adjacent pixel points in the human body region; represents the absolute value function; represents the exponential function with a natural constant as the base.

4. The system for auxiliary diagnosis of primary liver cancer based on imaging data according to claim 1, wherein, The method for obtaining the possibility that the corresponding region of the pixel cluster in the arterial phase MRI image is a liver cancer region according to the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image, and determining whether the corresponding region of the pixel cluster in the arterial phase MRI image is a liver cancer region, includes the following specific method: For any pixel cluster in the arterial phase MRI image, the product of the first liver cancer factor and the second liver cancer factor of the pixel cluster in the arterial phase MRI image is normalized, and the normalized result is taken as the possibility that the corresponding region of the pixel cluster in the arterial phase MRI image is a liver cancer region. A preset possibility threshold For any pixel point cluster in the arterial phase MRI image, if the possibility that the region corresponding to the pixel point cluster in the arterial phase MRI image is a liver cancer region is greater than or equal to the preset possibility threshold , the region corresponding to the pixel point cluster in the arterial phase MRI image is a liver cancer region.

Images