A method and system for identifying parathyroid lesions in ultrasound images

Abstract

The present application provides a method and system for identifying parathyroid lesions in ultrasonic images, belonging to the technical field of image processing. Among them, a method for identifying parathyroid lesions in ultrasonic images includes obtaining the current ultrasonic image of a patient and the historical ultrasonic images in a database; determining the feature region in the current ultrasonic image according to the current ultrasonic image and the sample ultrasonic image; obtaining the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; calculating the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculating the trend influence data according to the historical ultrasonic images and the growth distance data; analyzing the comprehensive attention degree data of the feature region according to the basic attention degree data and the trend influence data; adopting this solution can mark the feature region and help doctors observe the ultrasonic images of patients more intuitively.

Description

Technical Field

[0001] This application relates to the technical field of image processing, and in particular, to a method and system for identifying parathyroid lesions in ultrasonic images. Background Art

[0002] When scanning a patient's parathyroid gland, generally, an ultrasonic probe device is used to scan the position of the patient's parathyroid gland, so as to obtain parathyroid ultrasonic images at different angles, and these images are stored in a database. These images all carry time stamps indicating the examination time of the patient; in this way, for patients undergoing regular examinations, the periodic parathyroid ultrasonic images of the patient can be retrieved from the database to analyze the changes in the patient's parathyroid gland. It can be understood that when comparing and analyzing all the parathyroid ultrasonic images of the patient, since the scanned parathyroid ultrasonic images represent the parathyroid glands of the patient at different angles, when comparing and analyzing any two parathyroid ultrasonic images at different times, it is to compare and analyze any two parathyroid ultrasonic images representing the same angle; and in order to help doctors more intuitively observe the changes in the patient's parathyroid gland, it is very necessary to specially mark some areas in the parathyroid ultrasonic images. Summary of the Invention

[0003] This application provides a method and system for identifying parathyroid lesions in ultrasonic images, which can help doctors quickly and intuitively observe the ultrasonic images of patients.

[0004] In a first aspect, this application provides a method for identifying parathyroid lesions in ultrasonic images. The method includes:

[0005] Obtain the current ultrasonic image of the patient and the historical ultrasonic image in the database; the historical ultrasonic image carries a time stamp indicating that the patient has undergone parathyroid scanning; and determine a sample ultrasonic image based on the historical ultrasonic image and the time stamp carried by the historical ultrasonic image; the sample ultrasonic image is the historical ultrasonic image closest to the current moment;

[0006] Determine the feature region in the current ultrasonic image according to the current ultrasonic image and the sample ultrasonic image; the feature region is the non-intersecting region in the current ultrasonic image and the sample ultrasonic image;

[0007] Obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculate trend influence data according to the historical ultrasonic image and the growth distance data;

[0008] Analyze the comprehensive attention data of the feature region based on the described basic attention data and the trend influence data, and determine the annotation presentation method of the current ultrasonic image corresponding to the feature region based on the comprehensive attention data.

[0009] Furthermore, obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate the basic attention data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculating the trend influence data according to the historical ultrasonic image and the growth distance data includes:

[0010] Determine the shape influence data according to the shape data and the preset shape influence comparison table;

[0011] Determine the clarity influence data according to the boundary clarity data and the preset clarity influence comparison table;

[0012] Calculate the basic attention data according to the region perimeter data, region area data, shape influence data, clarity influence data, and the echo characteristic quantity data.

[0013] Furthermore, the calculation method of the basic attention data includes:

[0014] ;

[0015] In the formula, is the basic attention data, is the region perimeter data, is the region area data, is the shape influence data, is the clarity influence data, is the echo characteristic quantity data; are the preset first weight, preset second weight, preset third weight, and preset fourth weight respectively; and, ; The basic attention data is associated with the value of the region perimeter data, the value of the region area data, the value of the shape data, and the boundary clarity data.

[0016] Further, obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculating trend influence data according to the historical ultrasound image and the growth distance data includes:

[0017] Analyze the historical difference region between any two adjacent historical ultrasound images according to the timestamps carried by the historical ultrasound images; based on the timestamps, determine that among any two adjacent historical ultrasound images, the historical ultrasound image closer to the current moment is the latter historical ultrasound image, and the historical ultrasound image farther from the current moment is the former historical ultrasound image; the historical difference region is the non-intersection region in the latter historical ultrasound image and the former historical ultrasound image;

[0018] Calculate the historical growth data of each historical difference region; the historical growth data is the length data of the longest parallel line in the historical difference region;

[0019] Calculate trend influence data based on the historical growth data and the growth distance data.

[0020] Further, the calculation method of the trend influence data includes:

[0021] Let the total number of the historical growth data plus the growth distance data be n, where the growth distance data is the nth growth data, and the historical growth data farthest from the current moment is the 1st growth data; then the ith growth data is ;

[0022] Calculate n - 1 growth difference data based on n growth data ; where, ;

[0023] Judge whether the signs of all growth difference data are all greater than 0 or all not greater than 0;

[0024] If so, the calculation method of the trend influence data is ;

[0025] If not, the calculation method of the trend influence data is ; where, is the number of growth difference data greater than 0, is the number of growth difference data not greater than 0.

[0026] In a second aspect, the present application provides an identification system for parathyroid lesions in ultrasound images, the system includes:

[0027] An acquisition module, configured to acquire the current ultrasound image of a patient and the historical ultrasound images in a database; the historical ultrasound images carry time stamps indicating the time when the patient undergoes parathyroid scanning; and determine a sample ultrasound image based on the historical ultrasound images and the time stamps carried by the historical ultrasound images; the sample ultrasound image is the historical ultrasound image closest to the current moment;

[0028] A determination module, configured to determine a feature region in the current ultrasound image according to the current ultrasound image and the sample ultrasound image; the feature region is the non-intersection region in the current ultrasound image and the sample ultrasound image;

[0029] A calculation module, configured to obtain size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate basic attention data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculate trend influence data according to the historical ultrasound image and the growth distance data;

[0030] An analysis module, configured to analyze comprehensive attention data of the feature region according to the basic attention data and the trend influence data, and determine the annotation presentation mode of the current ultrasound image corresponding to the feature region based on the comprehensive attention data.

[0031] Further, the calculation module is further configured to obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate basic attention data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculating trend influence data according to the historical ultrasound image and the growth distance data includes:

[0032] Determine shape influence data according to the shape data and a preset shape influence comparison table;

[0033] Determine clarity influence data according to the boundary clarity data and a preset clarity influence comparison table;

[0034] Calculate basic attention data according to the region perimeter data, region area data, shape influence data, clarity influence data, and the echo characteristic quantity data.

[0035] Further, the calculation module is further configured to, the calculation method of the basic attention data includes:

[0036] ;

[0037] wherein, is the basic attention data, is the perimeter data of the region, is the area data of the region, is the shape influence data, is the clarity influence data, is the echo characteristic quantity data; are the preset first weight, the preset second weight, the preset third weight and the preset fourth weight respectively; and, ; The basic attention data is associated with the value of the perimeter data of the region, the value of the area data of the region, the value of the shape data and the boundary clarity data.

[0038] Further, the calculation module is further configured to obtain the size data, shape data, boundary clarity data and echo characteristic quantity data of the feature region; the size data includes the perimeter data of the region, the area data of the region and the growth distance data; and calculate the basic attention data according to the perimeter data of the region, the area data of the region, the shape data, the boundary clarity data and the echo characteristic quantity data; calculating the trend influence data according to the historical ultrasonic image and the growth distance data includes:

[0039] Analyze the historical difference region of any two adjacent historical ultrasonic images according to the time stamps carried by the historical ultrasonic images; based on the time stamps, determine that among any two adjacent historical ultrasonic images, the historical ultrasonic image closer to the current moment is the latter historical ultrasonic image, and the historical ultrasonic image farther from the current moment is the former historical ultrasonic image; the historical difference region is the non-intersection region in the latter historical ultrasonic image and the former historical ultrasonic image;

[0040] Calculate the historical growth data of each historical difference region; the historical growth data is the length data of the longest parallel line in the historical difference region;

[0041] Calculate the trend influence data based on the historical growth data and the growth distance data.

[0042] Further, the calculation module is further configured to, the calculation method of the trend influence data includes:

[0043] Suppose the total number of the historical growth data plus the growth distance data is n, where the growth distance data is the nth growth data, and the historical growth data farthest from the current moment is the 1st growth data; then the ith growth data is ;

[0044] Calculate n - 1 growth difference data based on n growth data ; wherein, ;

[0045] Determine whether the signs of all the growth difference data are all greater than 0 or all not greater than 0;

[0046] If so, the calculation method of the trend influence data is, ;

[0047] If not, the calculation method of the trend influence data is, ; wherein, is the number of growth difference data greater than 0, is the number of growth difference data not greater than 0.

[0048] It should be understood that the content described in the invention content part is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Combined with the drawings and referring to the following detailed description, the above and other features, advantages and aspects of the embodiments of the present application will become more obvious. In the drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0050] Figure 1 shows a flowchart of a method for identifying parathyroid lesions in an ultrasound image according to an embodiment of the present application;

[0051] Figure 2 shows a block diagram of a system for identifying parathyroid lesions in an ultrasound image according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0053] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the front and rear associated objects.

[0054] The present application provides a method and system for identifying parathyroid lesions in ultrasonic images, which can quickly label the characteristic regions in the ultrasonic images of patients and help doctors observe the ultrasonic images of patients more intuitively.

[0055] In a first aspect, the present application provides a method for identifying parathyroid lesions in ultrasonic images. Refer to Figure 1 , the specific steps included in the method are as follows.

[0056] Step S110: Obtain the current ultrasonic image of the patient and the historical ultrasonic images in the database; the historical ultrasonic images carry time stamps indicating the time when the patient undergoes parathyroid scanning; and determine the sample ultrasonic image based on the historical ultrasonic images and the time stamps carried by the historical ultrasonic images; the sample ultrasonic image is the historical ultrasonic image closest to the current moment.

[0057] It can be understood that generally, when obtaining the ultrasonic image of a patient, it is first necessary to collect and preprocess the image data, and the preprocessing steps include standardization, denoising, enhancement, etc.; then extract the features of the image, and then an appropriate model can be selected and corresponding training can be carried out.

[0058] It can be understood that in the embodiments of the present application, the obtained current ultrasonic image corresponds to the historical ultrasonic image, and the current ultrasonic image includes all angles of the historical ultrasonic image, that is, all angles of the ultrasonic images obtained when the patient undergoes parathyroid ultrasonic scanning are the same, so the historical ultrasonic images corresponding to all angles of the current ultrasonic image can be found in the database; here, any current ultrasonic image is taken as an example for the analysis and calculation of the comprehensive attention degree, and when analyzing and comparing the current ultrasonic image, multiple historical ultrasonic images with the same angle are also selected from the database for analysis and comparison.

[0059] Step S120: Determine the characteristic region in the current ultrasonic image according to the current ultrasonic image and the sample ultrasonic image; the characteristic region is the non-intersection region in the current ultrasonic image and the sample ultrasonic image.

[0060] It can be understood that the feature region here can be understood as the extra partial region in the current ultrasound image compared with the sample ultrasound image; that is, the current ultrasound image contains the sample ultrasound image and the extra partial region, and this extra partial region is the feature region, which represents the change region of the parathyroid gland during this patient examination compared with the previous patient examination. It can be understood that the feature region here refers to the ultrasonic imaging features in the ultrasound image; generally speaking, the three diseases included in the parathyroid gland, parathyroid hyperplasia, parathyroid adenoma, and parathyroid carcinoma, show different features in ultrasonic imaging; for example, parathyroid hyperplasia usually shows multiple parathyroid glands uniformly enlarged, with uniform echo and clear boundary; parathyroid adenoma is mostly single, round or oval, with uniform or non-uniform echo, clear boundary, and sometimes a capsule can be seen; the ultrasonic imaging features of parathyroid carcinoma are more complex, usually showing irregular shape, non-uniform echo, unclear boundary, and may be accompanied by calcification or infiltration of surrounding tissues.

[0061] Step S130: Obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculate the trend influence data according to the historical ultrasound image and the growth distance data.

[0062] In the embodiment of the present application, calculating the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data specifically includes determining the shape influence data according to the shape data and the preset shape influence comparison table; determining the clarity influence data according to the boundary clarity data and the preset clarity influence comparison table; calculating the basic attention degree data according to the region perimeter data, region area data, shape influence data, clarity influence data, and the echo characteristic quantity data.

[0063] It can be understood that in the embodiment of the present application, the preset shape influence comparison table for the feature region includes two cases of regular shape and irregular shape, and the shape influence data corresponding to the two cases are both fixed parameters; among them, the fixed parameter of the irregular shape is not less than that of the regular shape; the boundary clarity data here also includes two cases of clear and fuzzy, and the boundary clarity data here is determined based on the boundary comparison between the current ultrasound image and the sample ultrasound image. If the boundary clarity of the current ultrasound image is higher than that of the sample ultrasound image, it is clear; otherwise, it is fuzzy; similarly, the clarity influence data corresponding to the two cases here are both fixed parameters, among which the fixed parameter of the fuzzy is not less than that of the clear.

[0064] Specifically, in the embodiments of the present application, the calculation method for the shape influence data is as follows: Shape descriptors can be used to characterize the shape of the feature region, such as circularity, eccentricity, etc. Taking circularity as an example, ; The obtained circularity value is compared with a preset circularity threshold. If the circularity value is not less than the preset circularity threshold, it indicates that the shape of the feature region is a regular shape; otherwise, it is an irregular shape. The above-mentioned preset shape influence comparison table includes multiple shape descriptors and corresponding comparison thresholds. After determining whether the shape of the feature region is regular, the shape influence data can be determined based on the preset fixed parameters corresponding to regular or irregular shapes.

[0065] The calculation method for the clarity influence data is as follows: Specifically, the boundary clarity of the feature region can be measured by calculating the gradient variance of the feature region boundary. The gradient calculation is performed on the boundary pixels of the feature region, such as using the Sobel operator, to obtain the gradient magnitude image, and then the variance of the gradient magnitude image is calculated, and this variance value is used as the boundary clarity data. After calculating the boundary clarity data, the boundary clarity data of the calculated actual image is compared with the boundary clarity of the preset sample ultrasound image. If the boundary clarity data of the calculated actual image is not less than the boundary clarity of the preset sample ultrasound image, it indicates that the boundary of the feature region is clear; otherwise, it indicates that the boundary of the feature region is blurred. After determining whether the boundary of the feature region is clear, the clarity influence data can be determined based on the preset fixed parameters corresponding to clear or blurred boundaries.

[0066] It should be noted that for the echo characteristics, the number thereof may be 0 or 1 or not less than 1. When the number of echo characteristics is 0, it will not affect the basic attention data. Therefore, in this solution, it is defaulted that the minimum number of echo characteristics is 1. If the number of echo characteristics is 1, it will have a greater impact. If the number of echo characteristics exceeds 1, the fluctuation of the impact generated will instead decrease.

[0067] Calculating the trend influence data according to the historical ultrasound image and the growth distance data specifically includes analyzing the historical difference region between any two adjacent historical ultrasound images according to the time stamps carried by the historical ultrasound images; determining, based on the time stamps, that among any two adjacent historical ultrasound images, the historical ultrasound image closer to the current moment is the latter historical ultrasound image, and the historical ultrasound image farther from the current moment is the former historical ultrasound image; the historical difference region is the non-intersection region of the latter historical ultrasound image and the former historical ultrasound image; calculating the historical growth data of each historical difference region; the historical growth data is the length data of the longest parallel line within the historical difference region; calculating the trend influence data based on the historical growth data and the growth distance data.

[0068] Among them, the calculation methods of the basic attention degree data include:

[0069] ;

[0070] In the formula, is the basic attention degree data, is the regional perimeter data, is the regional area data, is the shape influence data, is the clarity influence data, is the echo characteristic quantity data; are the preset first weight, the preset second weight, the preset third weight and the preset fourth weight respectively; and, ; The basic attention degree data is associated with the numerical value of the regional perimeter data, the numerical value of the regional area data, the numerical value of the shape data and the boundary clarity data.

[0071] It can be understood that in this solution, the calculation of the basic attention degree data involves five influencing factors: regional perimeter data, regional area data, shape influence data, clarity influence data and echo characteristic quantity data; and in the specific calculation process, for the four data of regional perimeter data, regional area data, shape influence data and clarity influence data, only their specific numerical values are used for calculation, and the mathematical units corresponding to the perimeter and area are not involved; while the shape influence data and clarity influence data mentioned above participate in the calculation in the form of preset fixed parameters, and only their specific numerical values are used for calculation during the calculation; specifically, the perimeter and area reflect the changes of the characteristic region, which can be understood as the degree of deviation from the standard values of the perimeter and area. The greater the deviation, the higher the degree of attention required for the thyroid; and the forms corresponding to the shape and clarity are only the four forms of whether the shape is regular or not and whether the boundary is clear or not. Similarly, irregular shape and blurred boundary are manifestations of an abnormal state, and the thyroid in an abnormal state requires a higher degree of attention.

[0072] Among them, the calculation methods of the trend influence data include:

[0073] Let the total number of the historical growth data plus the growth distance data be n, where the growth distance data is the nth growth data, and the historical growth data farthest from the current moment is the 1st growth data; then the ith growth data is ;

[0074] Calculate n - 1 growth difference data based on n growth data ; Among them, ;

[0075] Judge whether the signs of all the growth difference data are all greater than 0 or all not greater than 0;

[0076] If so, the calculation method of the trend impact data is ;

[0077] If not, the calculation method of the trend impact data is ; where is the number of growth difference data greater than 0, is the number of growth difference data not greater than 0.

[0078] It should be noted that in the embodiments of the present application, calculations are performed using the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; in addition to this part of the data, data characteristics such as size data, morphological data, echo characteristic data, whether the boundary of the mass is clear, blood supply conditions, whether there is calcification, and whether it invades surrounding tissues can also be used for data statistics and data analysis.

[0079] Step S140: Analyze the comprehensive attention data of the feature region based on the basic attention data and the trend impact data, and determine the annotation presentation method of the current ultrasonic image corresponding to the feature region based on the comprehensive attention data.

[0080] In the embodiments of the present application, the calculation method of the comprehensive attention data is: comprehensive attention data = basic attention data * trend impact data; after determining the comprehensive attention data of the current ultrasonic image, it is determined whether the current ultrasonic image is specially marked and displayed based on a preset attention threshold; if the comprehensive attention data of the current ultrasonic image is not less than the preset attention threshold, the feature region of the current ultrasonic image is specially marked, and the historical ultrasonic image closest to the current moment at the same angle as the current ultrasonic image is synchronously displayed to reflect the change of the patient's parathyroid gland at this angle, so as to provide a more intuitive ultrasonic image display for the doctor.

[0081] Generally speaking, the diseases of the parathyroid gland mainly include three types: parathyroid hyperplasia, parathyroid carcinoma, and parathyroid adenoma; after specially marking the feature region of the ultrasonic image, it can help the doctor better identify that the ultrasonic image of the current patient more conforms to one of the above three diseases.

[0082] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0083] In a second aspect, the present application provides a recognition system for parathyroid lesions based on ultrasonic images. As Figure 2 shown, the system includes an acquisition module 210 configured to acquire the current ultrasonic image of a patient and the historical ultrasonic images in a database; the historical ultrasonic images carry time stamps indicating the time when the patient underwent parathyroid scanning; and determine a sample ultrasonic image based on the historical ultrasonic images and the time stamps carried by the historical ultrasonic images; the sample ultrasonic image is the historical ultrasonic image closest to the current moment; a determination module 220 configured to determine a feature region in the current ultrasonic image according to the current ultrasonic image and the sample ultrasonic image; the feature region is the non-intersecting region in the current ultrasonic image and the sample ultrasonic image; a calculation module 230 configured to obtain size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate basic attention data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculate trend influence data according to the historical ultrasonic images and the growth distance data; an analysis module 240 configured to analyze comprehensive attention data of the feature region according to the basic attention data and the trend influence data, and determine a marking presentation mode of the current ultrasonic image corresponding to the feature region based on the comprehensive attention data.

[0084] Further, the calculation module 230 is further configured to obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate basic attention data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; calculating trend influence data according to the historical ultrasonic images and the growth distance data includes:

[0085] Determine shape influence data according to the shape data and a preset shape influence comparison table;

[0086] Determine clarity influence data according to the boundary clarity data and a preset clarity influence comparison table;

[0087] Calculate basic attention data according to the region perimeter data, region area data, shape influence data, clarity influence data, and the echo characteristic quantity data.

[0088] Further, the calculation module 230 is further configured to, the calculation method of the basic attention data includes:

[0089] ;

[0090] In the formula, is the basic attention data, is the perimeter data of the region, is the area data of the region, is the shape influence data, is the clarity influence data, is the echo characteristic quantity data; are the preset first weight, preset second weight, preset third weight and preset fourth weight respectively; and, ; The basic attention data is associated with the value of the perimeter data of the region, the value of the area data of the region, the value of the shape data, and the boundary clarity data.

[0091] Further, the calculation module 230 is further configured to obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes perimeter data, area data, and growth distance data of the region; and calculate the basic attention data according to the perimeter data, area data, shape data, boundary clarity data, and echo characteristic quantity data of the region; calculating the trend influence data according to the historical ultrasonic image and the growth distance data includes:

[0092] Analyze the historical difference region of any two adjacent historical ultrasonic images according to the time stamps carried by the historical ultrasonic images; determine that among any two adjacent historical ultrasonic images based on the time stamps, the historical ultrasonic image closer to the current moment is the latter historical ultrasonic image, and the historical ultrasonic image farther from the current moment is the former historical ultrasonic image; the historical difference region is the non-intersection region of the latter historical ultrasonic image and the former historical ultrasonic image;

[0093] Calculate the historical growth data of each historical difference region; the historical growth data is the length data of the largest parallel line in the historical difference region;

[0094] Calculate the trend influence data based on the historical growth data and the growth distance data.

[0095] Further, the calculation module 230 is further configured to, the calculation method of the trend influence data includes:

[0096] Let the total number of the historical growth data plus the growth distance data be n, where the growth distance data is the nth growth data, and the historical growth data farthest from the current moment is the 1st growth data; then the ith growth data is ;

[0097] Calculating n - 1 growth difference data based on n growth data ; wherein, ;

[0098] Judging whether the signs of all the growth difference data are all greater than 0 or all not greater than 0;

[0099] If so, the calculation method of the trend influence data is ;

[0100] If not, the calculation method of the trend influence data is ; wherein, is the number of growth difference data greater than 0, is the number of growth difference data not greater than 0.

[0101] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the described device can refer to the corresponding process in the foregoing method embodiment, which will not be elaborated herein.

[0102] The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the present application.

Claims

1. A method for identifying parathyroid lesions in ultrasonic images, characterized in that, Including: Obtain the current ultrasound image of the patient and the historical ultrasound images in the database; the historical ultrasound images carry timestamps indicating the time when the patient underwent parathyroid scanning; and determine a sample ultrasound image based on the historical ultrasound images and the timestamps carried by the historical ultrasound images; the sample ultrasound image is the historical ultrasound image closest to the current moment; Determine the feature region in the current ultrasound image according to the current ultrasound image and the sample ultrasound image; the feature region is the non-intersecting region in the current ultrasound image with the sample ultrasound image; Obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; Calculate the trend influence data according to the historical ultrasound image and the growth distance data; Analyze the comprehensive attention degree data of the feature region according to the basic attention degree data and the trend influence data, and determine the annotation presentation method of the current ultrasound image corresponding to the feature region based on the comprehensive attention degree data; The obtaining the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculating the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; Calculating the trend influence data according to the historical ultrasound image and the growth distance data includes: Analyze the historical difference regions of any two adjacent historical ultrasound images according to the timestamps carried by the historical ultrasound images; based on the timestamps, determine that among any two adjacent historical ultrasound images, the historical ultrasound image closer to the current moment is the latter historical ultrasound image, and the historical ultrasound image farther from the current moment is the former historical ultrasound image; the historical difference region is the non-intersecting region in the latter historical ultrasound image with the former historical ultrasound image; Calculate the historical growth data of each historical difference region; the historical growth data is the length data of the largest parallel line in the historical difference region; Calculate the trend influence data based on the historical growth data and the growth distance data; The calculation method of the trend influence data includes: Let the total number of the historical growth data plus the growth distance data be n, where the growth distance data is the nth growth data, and the historical growth data farthest from the current moment is the 1st growth data; then the ith growth data is ; Calculating n - 1 growth difference data based on n growth data , …, ; among them, , …, ; Judge whether the signs of all growth difference data are all greater than 0 or all not greater than 0; If so, the calculation method of the trend influence data is ; Otherwise, the calculation method of the trend influence data is as follows: where T is the trend influence data, is the number of growth difference data greater than 0, is the number of growth difference data not greater than 0.

2. The method according to claim 1, wherein The obtaining the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculating the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; Calculating the trend influence data according to the historical ultrasound image and the growth distance data includes: Determine shape influence data according to the shape data and a preset shape influence comparison table; Determine clarity influence data according to the boundary clarity data and a preset clarity influence comparison table; Calculate basic attention data according to the regional perimeter data, regional area data, shape influence data, clarity influence data, and the echo characteristic quantity data.

3. The method according to claim 2, wherein The calculation method of the basic attention data includes: ； Wherein, is the basic attention data, is the regional perimeter data, is the regional area data, is the shape influence data, is the clarity influence data, is the echo characteristic quantity data; , , , are the preset first weight, preset second weight, preset third weight and preset fourth weight respectively; and, 1; the basic attention data is associated with the value of the regional perimeter data, the value of the regional area data, the value of the shape data and the value of the boundary clarity data, and e is the natural constant.

4. An identification system for parathyroid lesions in ultrasound images, characterized in that, Including: An acquisition module (210) for acquiring the current ultrasound image of the patient and the historical ultrasound images in the database; the historical ultrasound images carry time stamps indicating that the patient has undergone parathyroid scans; and determine a sample ultrasound image based on the historical ultrasound images and the time stamps carried by the historical ultrasound images; the sample ultrasound image is the historical ultrasound image closest to the current moment; A determination module (220) for determining a feature region in the current ultrasound image according to the current ultrasound image and the sample ultrasound image; the feature region is the non-intersecting region in the current ultrasound image and the sample ultrasound image; A calculation module (230) for acquiring the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes regional perimeter data, regional area data, and growth distance data; and calculate basic attention data according to the regional perimeter data, regional area data, shape data, boundary clarity data, and echo characteristic quantity data; Calculate trend influence data according to the historical ultrasound images and the growth distance data; An analysis module (240) for analyzing the comprehensive attention data of the feature region according to the basic attention data and the trend influence data, and determining the annotation presentation method of the current ultrasound image corresponding to the feature region based on the comprehensive attention data; The calculation module (230) is further configured to acquire the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes regional perimeter data, regional area data, and growth distance data; and calculate basic attention data according to the regional perimeter data, regional area data, shape data, boundary clarity data, and echo characteristic quantity data; Calculating trend influence data according to the historical ultrasound images and the growth distance data includes: Analyze the historical difference regions of any two adjacent historical ultrasound images according to the time stamps carried by the historical ultrasound images; based on the time stamps, determine that among any two adjacent historical ultrasound images, the historical ultrasound image closer to the current moment is the latter historical ultrasound image, and the historical ultrasound image farther from the current moment is the former historical ultrasound image; the historical difference region is the non-intersecting region in the latter historical ultrasound image and the former historical ultrasound image; Calculate the historical growth data of each historical difference region; the historical growth data is the length data of the longest parallel line in the historical difference region; Calculate trend influence data based on the historical growth data and the growth distance data; The calculation module (230) is further configured such that the calculation method of the trend influence data includes: Let the total number of the historical growth data plus the growth distance data be n, where the growth distance data is the nth growth data, and the historical growth data farthest from the current moment is the 1st growth data; then the ith growth data is ; Calculating n - 1 growth difference data based on n growth data , …, ; among which, , …, ; Determining whether the signs of all the growth difference data are all greater than 0 or all not greater than 0; If so, the calculation method of the trend influence data is ; If not, the calculation method of the trend influence data is as follows: where T is the trend influence data, is the number of growth difference data greater than 0, is the number of growth difference data not greater than 0.

5. The system according to claim 4, wherein The calculation module (230) is further configured to obtain the size data, shape data, boundary clarity data, and echo characteristic quantity data of the feature region; the size data includes region perimeter data, region area data, and growth distance data; and calculate the basic attention degree data according to the region perimeter data, region area data, shape data, boundary clarity data, and echo characteristic quantity data; Calculating the trend influence data according to the historical ultrasound image and the growth distance data includes: Determining the shape influence data according to the shape data and a preset shape influence comparison table; Determining the clarity influence data according to the boundary clarity data and a preset clarity influence comparison table; Calculating the basic attention degree data according to the region perimeter data, region area data, shape influence data, clarity influence data, and the echo characteristic quantity data.

6. The system according to claim 5, characterized in that, The calculation module (230) is further configured such that the calculation method of the basic attention degree data includes: ； In the formula, is the basic attention data, is the regional perimeter data, is the regional area data, is the shape influence data, is the clarity influence data, is the echo characteristic quantity data; , , , are the preset first weight, the preset second weight, the preset third weight and the preset fourth weight respectively; and, = 1; The basic attention data is associated with the value of the regional perimeter data, the value of the regional area data, the value of the shape data and the value of the boundary clarity data, and e is the natural constant.

Images