Pulmonary airway nodule identification method, device, equipment and computer-readable storage medium

Abstract

The present application discloses a method, apparatus, device, and computer-readable storage medium for identifying pulmonary airway nodules. The method comprises: acquiring a pulmonary airway medical image and extracting a pulmonary airway contour image from the pulmonary airway medical image; determining a target variation of a target field corresponding to the pulmonary airway contour image based on coordinates corresponding to pixel points in the pulmonary airway contour image, wherein the target field is a direction field or a gradient field; comparing the target variation with a preset first variation threshold to obtain a comparison result, and identifying pulmonary airway nodules in the pulmonary airway contour image based on the comparison result. By determining the target variation of the target field corresponding to the pulmonary airway contour image and utilizing the target variation of the target field on the airway contour surface, the location of protrusions on the pulmonary airway in the medical image is determined, thereby identifying the location of small nodules and improving the accuracy of early pulmonary airway nodule recognition.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, apparatus, device and computer-readable storage medium for identifying pulmonary airway nodules. Background Art

[0002] The pulmonary airways are important organs that control breathing. Due to environmental influences, nodules may form on the walls of the pulmonary airways. These nodules grow rapidly, and when they reach a certain size, they can affect breathing and even be fatal. Currently, during pulmonary airway examinations, doctors typically analyze medical images of the pulmonary airways to determine if there are pulmonary airway nodules. However, due to the small size of the nodules in their early stages, they are difficult to detect with the naked eye. This can lead to early pulmonary airway nodules being easily overlooked, leading to missed diagnoses.

[0003] Therefore, how to improve the accuracy of early identification of pulmonary airway nodules is an urgent problem that needs to be solved. Summary of the Invention

[0004] The embodiments of the present application provide a method, apparatus, device, and computer-readable storage medium for identifying pulmonary airway nodules, which can improve the accuracy of early pulmonary airway nodule identification.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying pulmonary airway nodules, the method comprising:

[0006] Acquire a lung airway medical image, and extract a lung airway contour image from the lung airway medical image;

[0007] determining a target change amount of a target field corresponding to the lung airway contour image based on coordinates corresponding to pixel points in the lung airway contour image, wherein the target field is a direction field or a gradient field;

[0008] The target variation is compared with a preset first variation threshold to obtain a comparison result, and the pulmonary airway nodules in the pulmonary airway contour image are identified based on the comparison result.

[0009] In a second aspect, the present invention provides a device for identifying pulmonary airway nodules.

[0010] an acquisition unit, configured to acquire a lung airway medical image and extract a lung airway contour image from the lung airway medical image;

[0011] a determining unit, configured to determine a target variation of a target field corresponding to the lung airway contour image based on coordinates corresponding to pixel points in the lung airway contour image, wherein the target field is a direction field or a gradient field;

[0012] The identification unit is used to compare the target change amount with a preset first change amount threshold to obtain a comparison result, and identify the pulmonary airway nodules in the pulmonary airway contour image based on the comparison result.

[0013] In a third aspect, an embodiment of the present application also provides a pulmonary airway nodule identification device, comprising a memory storing a computer program; a processor loading the computer program from the memory to execute the steps of any pulmonary airway nodule identification method provided in the embodiment of the present application.

[0014] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the computer program is suitable for loading by a processor to execute the steps of any one of the pulmonary airway nodule identification methods provided in the embodiments of the present application.

[0015] In a fifth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the pulmonary airway nodule identification methods provided in the embodiments of the present application.

[0016] Using the solution of the embodiment of the application, a lung airway medical image is acquired, and a lung airway contour image in the lung airway medical image is extracted; based on the coordinates corresponding to the pixel points in the lung airway contour image, a target variation of a target field corresponding to the lung airway contour image is determined, where the target field is a direction field or a gradient field; the target variation is compared with a preset first variation threshold to obtain a comparison result, and lung airway nodules in the lung airway contour image are identified based on the comparison result. By determining the target variation of the target field corresponding to the lung airway contour image, lung airway nodules in the lung airway contour image are identified. Since the target variation of the target field on the airway contour surface is used to determine the location of the protrusion on the lung airway in the medical image, the location of the small nodule is identified, thereby improving the accuracy of early lung airway nodule identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a flow chart of a first embodiment of the method for identifying pulmonary airway nodules provided in the embodiments of the present application;

[0019] Figure 2 2 is a flow chart of a second embodiment of the method for identifying pulmonary airway nodules provided in the embodiments of the present application;

[0020] Figure 3 1 is a flow chart of a third embodiment of the method for identifying pulmonary airway nodules provided in the embodiments of the present application;

[0021] Figure 4 1 is a flow chart of a fourth embodiment of the method for identifying pulmonary airway nodules provided in the embodiments of the present application;

[0022] Figure 5 Schematic diagram of the structure of the pulmonary airway nodule identification device provided in the embodiment of the present application;

[0023] Figure 6 It is a structural diagram of the pulmonary airway nodule identification device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application. At the same time, in the description of the embodiments of the present application, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0025] Embodiments of the present application provide a method, apparatus, device, and computer-readable storage medium for identifying pulmonary airway nodules.

[0026] Specifically, this embodiment will be described from the perspective of a pulmonary airway nodule identification device, which can be specifically integrated into a pulmonary airway nodule identification apparatus, that is, the pulmonary airway nodule identification method of the embodiment of the present application can be executed by the pulmonary airway nodule identification device.

[0027] The pulmonary airway nodule identification method provided in the embodiment of the present application can be applied to a pulmonary airway nodule identification device, which can be a smart terminal, a PC terminal, a mobile terminal, or other device.

[0028] The following detailed description is provided in conjunction with the accompanying drawings. This embodiment uses a pulmonary airway nodule identification device as an example. It should be noted that the order in which the following embodiments are described does not limit the preferred order of the embodiments. Although the flowcharts illustrate a logical order, in some cases, the steps shown or described may be performed in a different order than that shown in the accompanying drawings.

[0029] Please refer to Figure 1, a first embodiment of the pulmonary airway nodule identification method is proposed, and the first embodiment includes the following steps:

[0030] Step 101: Acquire a lung airway medical image, and extract a lung airway contour image from the lung airway medical image;

[0031] Step 102, determining a target change amount of a target field corresponding to the lung airway contour image based on coordinates corresponding to pixel points in the lung airway contour image, wherein the target field is a direction field or a gradient field;

[0032] Step 103 : Compare the target variation with a preset first variation threshold to obtain a comparison result, and identify pulmonary airway nodules in the pulmonary airway contour image based on the comparison result.

[0033] In this embodiment, when it is necessary to identify pulmonary airway nodules, the relevant user inputs the pulmonary airway medical image into the pulmonary airway nodule recognition device; after the pulmonary airway nodule recognition device obtains the pulmonary airway medical image, it extracts the pulmonary airway contour image in the pulmonary airway medical image, and creates a coordinate system based on the pulmonary airway contour image, and determines the coordinates of each pixel point on the pulmonary airway contour image based on the coordinate system; the pulmonary airway nodule recognition device determines the target field corresponding to each pixel point in the pulmonary airway contour image based on the coordinates corresponding to each pixel point, and then determines the target change amount of the target field corresponding to the pulmonary airway contour image based on the target fields corresponding to all the pixels, and the target field is a direction field or a gradient field; the pulmonary airway nodule recognition device compares the target change amount with a preset first change amount threshold to obtain a comparison result, and identifies the pulmonary airway nodules in the pulmonary airway contour image based on the comparison result.

[0034] It should be noted that both the lung airway medical image and the lung airway contour image are three-dimensional medical images, and the coordinate system created based on the lung airway contour image is a three-dimensional coordinate system.

[0035] The pulmonary airway nodule identification device of this embodiment obtains a pulmonary airway medical image and extracts a pulmonary airway contour image from the pulmonary airway medical image; based on the coordinates corresponding to the pixel points in the pulmonary airway contour image, determines the target variation of the target field corresponding to the pulmonary airway contour image, where the target field is a direction field or a gradient field; compares the target variation with a preset first variation threshold to obtain a comparison result, and identifies the pulmonary airway nodules in the pulmonary airway contour image based on the comparison result. By determining the target variation of the target field corresponding to the pulmonary airway contour image and utilizing the target variation of the target field on the airway contour surface, the location of the protrusion on the pulmonary airway in the medical image is determined, thereby identifying the location of small nodules and improving the accuracy of early pulmonary airway nodule identification.

[0036] Specifically, each step is described in detail below:

[0037] Step 101: Acquire a lung airway medical image, and extract a lung airway contour image from the lung airway medical image;

[0038] In this step, the pulmonary airway nodule recognition device includes an interactive module for interacting with the user. Based on the interactive module, the user can input a pulmonary airway medical image for pulmonary airway nodule recognition into the pulmonary airway nodule recognition device. The pulmonary airway nodule recognition device then acquires the pulmonary airway medical image and extracts a pulmonary airway contour image from the pulmonary airway medical image. It is understood that the pulmonary airway contour image only includes the pulmonary airway contours in the pulmonary airway medical image.

[0039] Exemplarily, the pulmonary airway nodule identification device uses CT, MR, 4D ultrasound and other scanning methods to scan the human body to obtain pulmonary airway medical images, and then uses a pre-selected segmentation model to segment the physiological tissue in the pulmonary airway medical image to obtain a segmented image of the physiological tissue in the pulmonary airway. The medical image of the pulmonary airway edge contour is then extracted from the segmented image of the physiological tissue in the pulmonary airway to obtain a pulmonary airway contour image, which serves as the image basis for subsequent pulmonary airway nodule identification.

[0040] Step 102, determining a target change amount of a target field corresponding to the lung airway contour image based on coordinates corresponding to pixel points in the lung airway contour image, wherein the target field is a direction field or a gradient field;

[0041] In this step, after the pulmonary airway nodule recognition device obtains the pulmonary airway contour image, it creates a coordinate system based on the pulmonary airway contour image, and determines the coordinates of each pixel point on the pulmonary airway contour image based on the coordinate system; the pulmonary airway nodule recognition device determines the target vector corresponding to each pixel point based on the coordinates corresponding to each pixel point in the pulmonary airway contour image, and then determines the target change of the target field corresponding to the pulmonary airway contour image based on the target vectors corresponding to all the pixel points, where the target field is a direction field or a gradient field.

[0042] Optionally, the pulmonary airway nodule recognition device includes a calculation model for calculating the target change amount of the target field. After the pulmonary airway nodule recognition device obtains the pulmonary airway contour image, the pulmonary airway contour image is input into the calculation model. The calculation model creates a coordinate system based on the pulmonary airway contour image, and determines the coordinates of each pixel point on the pulmonary airway contour image based on the coordinate system. The calculation model determines the target vector corresponding to each pixel point based on the coordinates corresponding to each pixel point in the pulmonary airway contour image, and then determines the target change amount of the target field corresponding to the pulmonary airway contour image based on the target vectors corresponding to all the pixel points.

[0043] It should be noted that the direction field describes the direction of the vector at each point, but not necessarily the magnitude of the vector. In a direction field, the lengths of the vectors can be different, but at any given point, all vectors point in the same direction. The gradient field is a special type of vector field in which the magnitude and direction of the vector are determined by the gradient of a scalar function. In other words, the gradient field describes the rate of change and direction of a scalar field at each point.

[0044] Step 103 : Compare the target variation with a preset first variation threshold to obtain a comparison result, and identify pulmonary airway nodules in the pulmonary airway contour image based on the comparison result.

[0045] In this step, the pulmonary airway nodule identification compares the target field target variation corresponding to the pulmonary airway contour image with a preset first variation threshold to obtain a comparison result, and identifies the pulmonary airway nodules in the pulmonary airway contour image based on the comparison result. It can be understood that when the target field target variation corresponding to the pulmonary airway contour image is greater than the preset first variation threshold, it indicates that there is a sudden change in the target field of the pulmonary airway contour in the pulmonary airway contour image, and this sudden change is usually caused by the presence of bulges in the pulmonary airway contour, and these bulges are usually pulmonary airway nodules; when the target field target variation corresponding to the pulmonary airway contour image is not greater than the preset first variation threshold, it indicates that there is no sudden change in the target field of the pulmonary airway contour in the pulmonary airway contour image, that is, there are no pulmonary airway nodules in the pulmonary airway contour.

[0046] The pulmonary airway nodule identification device of this embodiment obtains a pulmonary airway medical image and extracts a pulmonary airway contour image from the pulmonary airway medical image; based on the coordinates corresponding to the pixel points in the pulmonary airway contour image, determines the target variation of the target field corresponding to the pulmonary airway contour image, where the target field is a direction field or a gradient field; compares the target variation with a preset first variation threshold to obtain a comparison result, and identifies the pulmonary airway nodules in the pulmonary airway contour image based on the comparison result. By determining the target variation of the target field corresponding to the pulmonary airway contour image and utilizing the target variation of the target field on the airway contour surface, the location of the protrusion on the pulmonary airway in the medical image is determined, thereby identifying the location of small nodules and improving the accuracy of early pulmonary airway nodule identification.

[0047] Further, refer to Figure 2 A second embodiment of the pulmonary airway nodule identification method is proposed. The difference between the second embodiment and the first embodiment is that the target field is a direction field. The method of determining the target change of the target field corresponding to the pulmonary airway contour image based on the coordinates corresponding to the pixel points in the pulmonary airway contour image includes:

[0048] Step 1021, obtaining a lung airway centerline in the lung airway contour image, and dividing the lung airway contour into a plurality of circles with each centerline point on the lung airway centerline as a circle center;

[0049] In this step, the lung airway nodule recognition device obtains the lung airway centerline in the lung airway contour image, and divides the lung airway contour into multiple circles with each centerline point on the lung airway centerline as the center of the circle; it can be understood that the lung airway contour can be regarded as a cylindrical structure, and the centerline of the cylindrical structure is composed of multiple centerline point sets. With each centerline point as the center of the circle, multiple circles can be drawn on the lung airway contour, and the multiple circles stacked together form the cylindrical structure of the lung airway.

[0050] Optionally, the lung airway nodule identification device includes a computational model for calculating the target change amount of the direction field, and the computational model includes a segmentation model. The segmentation model obtains the lung airway centerline in the lung airway contour image, and divides the lung airway contour into multiple circles with each centerline point on the lung airway centerline as the center of the circle.

[0051] It is understandable that the pulmonary airways usually have branches. Dividing the pulmonary airway contour into multiple circles with each centerline point on the pulmonary airway centerline as the center of the circle is equivalent to removing the branches of the pulmonary airways and treating the pulmonary airways as a cylindrical structure. Ignoring the cylindrical structure of the pulmonary airways can avoid misjudging the target change of the target field at the pulmonary airway branches as the target change of the target field caused by the pulmonary airway nodules during subsequent processing, which can help improve the accuracy of pulmonary airway nodule identification.

[0052] Furthermore, the pulmonary airway nodule identification device numbers the pixels on the pulmonary airway corresponding to the circumference according to the order of the centerline points. For example, the pixels on the pulmonary airway corresponding to centerline point 1 are numbered 11, 12, 13, etc. The pixels on the pulmonary airway corresponding to centerline point 2 are numbered 21, 22, 23, etc. This ordering and numbering is completed in this way.

[0053] Step 1022, calculating the direction vector of each pixel point on the lung airway contour based on the coordinates corresponding to the two adjacent pixel points closest to each other on each two adjacent circles;

[0054] In this step, the pulmonary airway nodule recognition device calculates the direction vector of each pixel point on the pulmonary airway contour based on the coordinates corresponding to the two adjacent pixels closest to each other on each two adjacent circles;

[0055] Optionally, the calculation model for calculating the target change amount of the direction field in the pulmonary airway nodule recognition device includes a vector calculation model. The pulmonary airway nodule recognition device obtains the coordinates corresponding to the two adjacent pixel points closest to each other on each two adjacent circles, and inputs the coordinates corresponding to the two adjacent pixel points into the vector calculation model to calculate the direction vector of each pixel point on the pulmonary airway contour.

[0056] Optionally, in the above steps, the pulmonary airway nodule identification device sorted and numbered all the pixel points on the pulmonary airway contour. At this time, the pulmonary airway nodule identification device can determine that the two adjacent pixel points closest to each other on each two adjacent circles can be, for example: two pixel points numbered 11 and 21, two pixel points numbered 12 and 22, two pixel points numbered 21 and 31, etc. Based on the coordinates numbered 11 and 21, the direction vector of the pixel point numbered 11 is calculated; based on the coordinates numbered 12 and 22, the direction vector of the pixel point numbered 12 is calculated; based on the coordinates numbered 21 and 31, the direction vector of the pixel point numbered 21 is calculated; and so on to determine the direction vector of each pixel point on the pulmonary airway contour.

[0057] Optionally, in the above steps, the pulmonary airway nodule identification device sorts and numbers all the pixel points on the pulmonary airway contour, and the pulmonary airway nodule identification device calculates the distance between each pixel point and each pixel point on the adjacent circle, and then determines the two adjacent pixel points with the closest distance on each two adjacent circles, and then calculates the direction vector of the corresponding pixel point based on the two adjacent pixel points with the closest distance on each two adjacent circles, until the direction vector of each pixel point on the pulmonary airway contour is determined.

[0058] Step 1023 : Determine a target change amount of the direction field corresponding to the lung airway contour image based on the direction vector of each pixel point and a preset direction vector.

[0059] In this step, the pulmonary airway nodule identification device determines the target change in the direction field corresponding to the pulmonary airway contour image based on the direction vector of each pixel and the preset direction vector. It should be noted that the preset direction vector is the direction vector of the pixel when the pulmonary airway contour does not contain pulmonary airway nodules.

[0060] Optionally, the direction vector of each pixel point of the pulmonary airway nodule recognition device and the preset direction vector are input into a calculation model for calculating the target change amount of the direction field to obtain the target change amount of the direction field corresponding to the pulmonary airway contour image.

[0061] Specifically, step 1023 includes:

[0062] Step 10231, calculating a reference change in the direction vector of each pixel based on the direction vector of each pixel and a preset direction vector;

[0063] Step 10232: Accumulate the reference variation of the direction vector of each pixel point to determine the target variation of the direction field corresponding to the lung airway contour image.

[0064] In steps 10231 to 10232, for each pixel point on the lung airway contour, the lung airway nodule recognition device calculates the reference change of the direction vector of each pixel point based on the direction vector of each pixel point and the preset direction vector, and then accumulates the reference change of the direction vector of each pixel point to determine the target change of the direction field corresponding to the lung airway contour image.

[0065] Optionally, the pulmonary airway nodule identification device inputs the direction vector of each pixel point and the preset direction vector into a calculation model for calculating the target change of the direction field. The calculation model calculates the reference change of the direction vector of each pixel point based on the direction vector of each pixel point and the preset direction vector, and then accumulates the reference change of the direction vector of each pixel point to determine the target change of the direction field corresponding to the pulmonary airway contour image.

[0066] The pulmonary airway nodule identification device of this embodiment divides the pulmonary airway contour into multiple circles, using each centerline point on the pulmonary airway centerline as the center of the circle. Based on the coordinates corresponding to the two closest adjacent pixels on each of the two adjacent circles, the device calculates the direction vector of each pixel on the pulmonary airway contour. Based on the direction vector of each pixel and a preset direction vector, the device determines the target change in the direction field corresponding to the pulmonary airway contour image. This prevents the target change in the target field at a pulmonary airway branch from being misidentified as the target change in the target field caused by a pulmonary airway nodule during subsequent processing, thereby improving the accuracy of pulmonary airway nodule identification.

[0067] Further, refer to Figure 3 A third embodiment of the pulmonary airway nodule identification method is proposed. The third embodiment differs from the first and second embodiments in that the target field is a gradient field. Determining the target variation of the target field corresponding to the pulmonary airway contour image based on the coordinates corresponding to the pixel points in the pulmonary airway contour image includes:

[0068] Step 1024, performing region division on the lung airway contour image to obtain lung airway contour sub-images;

[0069] In this step, the lung airway nodule recognition device divides the lung airway contour image into regions based on the minimum nodule diameter to obtain lung airway contour sub-images; it can be understood that the lung airway contour can be regarded as a cylindrical structure, and the cylindrical structure can be divided into multiple cylindrical sub-structures with a height equal to the minimum nodule diameter, and each cylindrical sub-structure corresponds to a lung airway contour sub-image.

[0070] Optionally, the lung airway nodule identification device includes a calculation model for calculating the target change amount of the gradient field, and the calculation model includes a partitioning model. The partitioning model obtains the lung airway contour image, divides the lung airway contour image into regions according to the minimum nodule diameter, and obtains lung airway contour sub-images.

[0071] Step 1025: for each of the lung airway contour sub-images, determine a gradient field reference variation corresponding to the lung airway contour sub-image based on the coordinates corresponding to each pixel point in the lung airway contour sub-image;

[0072] In this step, for each lung airway contour sub-image, the lung airway nodule recognition device calculates the gradient vector corresponding to each pixel point based on the coordinates corresponding to each pixel point in the lung airway contour sub-image, determines the gradient vector reference change corresponding to each pixel point based on the gradient vector corresponding to each pixel point, and determines the gradient field reference change corresponding to the lung airway contour sub-image based on the gradient vector reference change corresponding to each pixel point.

[0073] Optionally, for each lung airway contour sub-image, the lung airway nodule recognition device inputs the lung airway contour sub-image into a calculation model for calculating the target change of the gradient field. The calculation model calculates the gradient vector corresponding to each pixel based on the coordinates corresponding to each pixel in the lung airway contour sub-image, determines the gradient vector reference change corresponding to each pixel based on the gradient vector corresponding to each pixel, and determines the gradient field reference change corresponding to the lung airway contour sub-image based on the gradient vector reference change corresponding to each pixel.

[0074] Specifically, step 1025 includes:

[0075] Step 10251: for each pixel in the lung airway contour sub-image, calculate a normal vector corresponding to the pixel based on the coordinates corresponding to the pixel;

[0076] In this step, the pulmonary airway nodule recognition device calculates the normal vector corresponding to each pixel point in the pulmonary airway contour sub-image based on the coordinates corresponding to the pixel point; it can be understood that the coordinates of each pixel point are three-dimensional coordinates. For the three-dimensional coordinates of each pixel point, the normal vector of the pixel point can be estimated according to the coordinates of adjacent pixels by methods including least squares fitting, average normal vector calculation based on neighborhood points, etc.

[0077] Optionally, for each lung airway contour sub-image, the lung airway nodule recognition device inputs the lung airway contour sub-image into a calculation model for calculating the target change amount of the gradient field. The calculation model calculates the normal vector corresponding to each pixel point in the lung airway contour sub-image based on the coordinates corresponding to the pixel point.

[0078] Step 10252: Calculate the gradient vector corresponding to the pixel point based on the normal vector and coordinates corresponding to the pixel point;

[0079] In this step, for each pixel point, the pulmonary airway nodule recognition device calculates the gradient vector corresponding to the pixel point based on the normal vector and coordinates corresponding to the pixel point. Specifically, in, is the partial derivative operator, and x, y, and z are the horizontal, vertical, and vertical coordinates of the pixel point, respectively.

[0080] Optionally, after the computational model determines the normal vector of each pixel in the lung airway contour sub-image, the gradient vector corresponding to each pixel in the lung airway contour sub-image is calculated based on the normal vector and coordinates corresponding to the pixel.

[0081] Step 10253: determining a reference change amount of the gradient vector corresponding to the pixel point based on the gradient vector corresponding to the pixel point and the gradient vector corresponding to each pixel point in the adjacent lung airway contour sub-image;

[0082] In this step, for each pixel point, the pulmonary airway nodule recognition device selects the pulmonary airway contour sub-image that is closest to and adjacent to the pixel point, and obtains the gradient vectors of multiple pixel points in the pulmonary airway contour sub-image that are closest to and adjacent to the pixel point. Based on the gradient vector of the pixel point and the gradient vectors of the multiple obtained pixel points, the gradient vector reference change of the pixel point is calculated.

[0083] Optionally, after the computational model determines the gradient vector of each pixel point in the lung airway contour sub-image, it selects the lung airway contour sub-image that is closest to and adjacent to the pixel point, and obtains the gradient vectors of multiple pixel points in the lung airway contour sub-image that are closest to and adjacent to the pixel point. Based on the gradient vector of the pixel point and the gradient vectors of the multiple obtained pixel points, the gradient vector reference change of the pixel point is calculated.

[0084] It should be noted that, based on the gradient vector of the pixel point and the acquired gradient vectors of multiple pixel points, a differential method, such as partial derivative or directional derivative, is used to approximately calculate the reference change of the gradient vector of the pixel point.

[0085] Step 10254: Accumulate the gradient vector reference variation corresponding to each pixel point in the lung airway contour sub-image to determine the gradient field reference variation corresponding to the lung airway contour sub-image.

[0086] In this step, after determining the gradient vector reference change corresponding to each pixel point in the lung airway contour sub-image, the lung airway nodule recognition device accumulates the gradient vector reference change corresponding to each pixel point in the lung airway contour sub-image to determine the gradient field reference change corresponding to the lung airway contour sub-image.

[0087] Optionally, after the computational model determines the gradient vector reference change of each pixel point in the lung airway contour sub-image, the gradient vector reference change corresponding to each pixel point in the lung airway contour sub-image is accumulated to determine the gradient field reference change corresponding to the lung airway contour sub-image.

[0088] Step 1026 : Determine a target gradient field variation corresponding to the lung airway contour image based on the number of the lung airway contour sub-images and each gradient field reference variation.

[0089] In this step, after determining the gradient field reference change amount corresponding to each lung airway contour sub-image, the lung airway nodule recognition device accumulates the gradient field reference change amount corresponding to each lung airway contour sub-image and divides it by the number of lung airway contour sub-images to determine the gradient field target change amount corresponding to the lung airway contour image.

[0090] Optionally, after the computational model determines the gradient vector reference change of each pixel point in the lung airway contour sub-image, the gradient field reference change corresponding to each lung airway contour sub-image is accumulated and divided by the number of lung airway contour sub-images to determine the gradient field target change corresponding to the lung airway contour image.

[0091] The pulmonary airway nodule recognition device of this embodiment calculates the gradient field target change amount corresponding to the pulmonary airway contour image, so that the pulmonary airway nodules in the pulmonary airway contour image can be subsequently judged and identified based on the gradient field target change amount. Since the pulmonary airway can be regarded as a cylindrical structure, for a simple cylindrical structure surface, the calculation of the gradient field is relatively direct and may have a higher accuracy in detecting protrusions. Therefore, calculating the gradient field target change amount corresponding to the pulmonary airway contour image can help improve the accuracy of pulmonary airway nodule recognition.

[0092] Further, refer to Figure 4 A fourth embodiment of the pulmonary airway nodule identification method is proposed. The difference between the third embodiment and the first to third embodiments is that the target change amount is compared with a preset first change amount threshold to obtain a comparison result, and the pulmonary airway nodule is identified in the pulmonary airway contour image based on the comparison result, including:

[0093] Step 1031, comparing the target variation with a preset first variation threshold to obtain a comparison result, wherein the preset first variation threshold is a target field variation corresponding to a lung airway contour image without lung airway nodules;

[0094] In this step, the pulmonary airway nodule identification device compares the target change amount of the target field of the pulmonary airway contour image with a preset first change amount threshold to obtain a comparison result, wherein the preset first change amount threshold is the target field change amount corresponding to the pulmonary airway contour image without pulmonary airway nodules. When the target field is a direction field, the preset first change amount threshold is the direction field change amount corresponding to the pulmonary airway contour image without pulmonary airway nodules. When the target field is a gradient field, the preset first change amount threshold is the gradient field change amount corresponding to the pulmonary airway contour image without pulmonary airway nodules.

[0095] Step 1032: If the comparison result shows that the target change is not greater than a preset first change threshold, it is determined that no pulmonary airway nodules exist in the pulmonary airway contour image;

[0096] In this step, if the comparison result obtained by the pulmonary airway nodule recognition device is that the target change amount is not greater than the preset first change amount threshold, it is determined that there is no pulmonary airway nodule in the pulmonary airway contour image.

[0097] Step 1033: If the comparison result shows that the target variation is greater than the preset first variation threshold, the pulmonary airway nodules in the pulmonary airway contour image are identified based on the preset second variation threshold and the target field reference variation corresponding to each pixel point.

[0098] In this step, if the comparison result obtained by the pulmonary airway nodule identification device is that the target change is greater than the preset first change threshold, it is determined that there are pulmonary airway nodules in the pulmonary airway contour image, and the pulmonary airway nodules in the pulmonary airway contour image are identified based on the preset second change threshold and the target field reference change corresponding to each pixel point.

[0099] Specifically, step 1033 includes:

[0100] Step 10331: Compare a preset second variation threshold with a target field reference variation corresponding to each pixel, wherein the preset second variation threshold is an average value of target field variations corresponding to all pixels in a pulmonary airway contour image without pulmonary airway nodules.

[0101] In this step, the pulmonary airway nodule identification device compares the preset second variation threshold with the target field reference variation corresponding to each pixel point, wherein the preset second variation threshold is the average value of the target field variation corresponding to all pixel points in the pulmonary airway contour image without pulmonary airway nodules. When the target field is a direction field, the preset second variation threshold is the average value of the direction field variation corresponding to the pulmonary airway contour image without pulmonary airway nodules. When the target field is a gradient field, the preset second variation threshold is the average value of the gradient field variation corresponding to the pulmonary airway contour image without pulmonary airway nodules.

[0102] Step 10332: Determine the contour region composed of pixel points whose target field reference variation is greater than a preset second variation threshold as the region of the pulmonary airway nodule in the pulmonary airway contour image.

[0103] In this step, the pulmonary airway nodule recognition device determines the contour area composed of pixel points whose target field reference variation is greater than a preset second variation threshold as the area of ​​the pulmonary airway nodule in the pulmonary airway contour image.

[0104] Furthermore, after determining the contour region composed of pixels whose target field reference variation is greater than a preset second variation threshold as the region of the pulmonary airway nodules in the pulmonary airway contour image, the method includes:

[0105] Step a, determining anatomical location information corresponding to the pulmonary airway nodule based on preset anatomical information, the area of ​​the pulmonary airway nodule, and the pulmonary airway contour image;

[0106] In this step, the pulmonary airway nodule identification device determines the anatomical position information corresponding to the pulmonary airway nodule based on the preset anatomical information, the area of ​​the pulmonary airway nodule and the pulmonary airway contour image; specifically, the preset anatomical information includes the position and name of each segment of the pulmonary airway, including: the main airway, also called the trachea, which is the starting part of the airway connecting the larynx and the bronchi, and the main airway includes the larynx, cervical trachea, and chest trachea; the bronchi, the main airway branches into two main bronchi, namely the left and right main bronchi, and the bronchi include the main bronchi, secondary bronchi, segmental bronchi, and subsegmental bronchi; the bronchioles, which are the most terminal branches of the bronchi, leading to the alveoli; the terminal bronchioles, which are the very end of the bronchioles, leading to the alveoli. The pulmonary airway nodule recognition device determines the anatomical location information corresponding to the pulmonary airway nodule based on the area of ​​the pulmonary airway nodule and the pulmonary airway contour image, combined with preset anatomical information, such as: the area of ​​the pulmonary airway nodule is located in the cervical trachea segment of the main airway; for example: the area of ​​the pulmonary airway nodule is located in the segmental bronchus segment of the bronchus.

[0107] Step b, calculating size information corresponding to the pulmonary airway nodule based on the coordinates of each pixel point in the region of the pulmonary airway nodule in the pulmonary airway contour image;

[0108] In this step, the pulmonary airway nodule recognition device calculates the size information corresponding to the pulmonary airway nodule based on the coordinates of each pixel point in the area of ​​the pulmonary airway nodule in the pulmonary airway contour image; further, the pulmonary airway nodule recognition device obtains the scale ratio of the pulmonary airway contour image, multiplies the size information of the pulmonary airway nodule calculated based on the coordinates of each pixel point by the scale ratio, and obtains the true size information of the pulmonary airway nodule.

[0109] Step c: marking the anatomical position information and the size information at a marked position corresponding to the region of the pulmonary airway nodule in the pulmonary airway contour image.

[0110] In this step, the pulmonary airway nodule recognition device marks the anatomical position information and size information at the marked position corresponding to the area of ​​the pulmonary airway nodule in the pulmonary airway contour image, so as to facilitate relevant users to determine the location of the pulmonary airway nodule.

[0111] The pulmonary airway nodule identification device of this embodiment compares the target variation with a preset first variation threshold to obtain a comparison result, where the preset first variation threshold is the target field variation corresponding to the pulmonary airway contour image in which no pulmonary airway nodules exist; if the comparison result is that the target variation is not greater than the preset first variation threshold, it is determined that no pulmonary airway nodules exist in the pulmonary airway contour image; if the comparison result is that the target variation is greater than the preset first variation threshold, the pulmonary airway nodules in the pulmonary airway contour image are identified based on the preset second variation threshold and the target field reference variation corresponding to each pixel point. By determining the target variation of the target field corresponding to the pulmonary airway contour image and utilizing the target variation of the target field on the airway contour surface, the location of the protrusion on the pulmonary airway in the medical image is determined, thereby identifying the location of small nodules and improving the accuracy of early pulmonary airway nodule identification.

[0112] This embodiment also provides a pulmonary airway nodule identification device, which can be integrated into pulmonary airway nodule identification devices such as smart terminals, PC terminals, and mobile terminals. Figure 5 As shown, the pulmonary airway nodule identification device may include:

[0113] An acquiring unit 1001 is configured to acquire a lung airway medical image and extract a lung airway contour image from the lung airway medical image;

[0114] A determining unit 1002 is configured to determine a target variation of a target field corresponding to the lung airway contour image based on coordinates corresponding to pixel points in the lung airway contour image, wherein the target field is a direction field or a gradient field;

[0115] The identification unit 1003 is configured to compare the target variation with a preset first variation threshold to obtain a comparison result, and identify pulmonary airway nodules in the pulmonary airway contour image based on the comparison result.

[0116] In an optional example, the determining unit is further configured to:

[0117] Acquire a pulmonary airway centerline in the pulmonary airway contour image, and divide the pulmonary airway contour into a plurality of circles with each centerline point on the pulmonary airway centerline as a circle center;

[0118] Calculating the direction vector of each pixel point on the lung airway contour based on the coordinates corresponding to the two adjacent pixel points closest to each other on each two adjacent circles;

[0119] Based on the direction vector of each pixel point and the preset direction vector, a target change amount of the direction field corresponding to the lung airway contour image is determined.

[0120] In an optional example, the determining unit is further configured to:

[0121] Calculating a reference change in the direction vector of each pixel based on the direction vector of each pixel and a preset direction vector;

[0122] The reference variation of the direction vector of each pixel point is accumulated to determine the target variation of the direction field corresponding to the lung airway contour image.

[0123] In an optional example, the determining unit is further configured to:

[0124] Performing regional division on the lung airway contour image to obtain lung airway contour sub-images;

[0125] For each of the lung airway contour sub-images, determining a reference change amount of the gradient field corresponding to the lung airway contour sub-image based on the coordinates corresponding to each pixel point in the lung airway contour sub-image;

[0126] Based on the number of the lung airway contour sub-images and each of the gradient field reference variations, a gradient field target variation corresponding to the lung airway contour image is determined.

[0127] In an optional example, the determining unit is further configured to:

[0128] For each pixel point in the lung airway contour sub-image, calculating a normal vector corresponding to the pixel point based on the coordinates corresponding to the pixel point;

[0129] Calculating a gradient vector corresponding to the pixel point based on the normal vector and coordinates corresponding to the pixel point;

[0130] Calculating a spatial length corresponding to the gradient vector, and determining a reference change amount of the gradient vector corresponding to the pixel point based on the spatial length and vector direction corresponding to the gradient vector;

[0131] The gradient vector reference variation corresponding to each pixel point in the lung airway contour sub-image is accumulated to determine the gradient field reference variation corresponding to the lung airway contour sub-image.

[0132] In an optional example, the identification unit is further configured to:

[0133] Comparing the target variation with a preset first variation threshold to obtain a comparison result, wherein the preset first variation threshold is a target field variation corresponding to a lung airway contour image without lung airway nodules;

[0134] If the comparison result shows that the target change amount is not greater than a preset first change amount threshold, it is determined that no pulmonary airway nodules exist in the pulmonary airway contour image;

[0135] If the comparison result is that the target change is greater than the preset first change threshold, the pulmonary airway nodules in the pulmonary airway contour image are identified based on the preset second change threshold and the target field reference change corresponding to each pixel point.

[0136] In an optional example, the identification unit is further configured to:

[0137] Comparing a preset second variation threshold with a target field reference variation corresponding to each pixel, wherein the preset second variation threshold is an average value of target field variations corresponding to all pixels in a pulmonary airway contour image without pulmonary airway nodules;

[0138] A contour region composed of pixel points whose target field reference variation is greater than a preset second variation threshold is determined as a region of pulmonary airway nodules in the pulmonary airway contour image.

[0139] In an optional example, the identification unit is further configured to:

[0140] Determining anatomical position information corresponding to the pulmonary airway nodule based on preset anatomical information, the area of ​​the pulmonary airway nodule, and the pulmonary airway contour image;

[0141] Calculating size information corresponding to the pulmonary airway nodule based on the coordinates of each pixel point in the region of the pulmonary airway nodule in the pulmonary airway contour image;

[0142] The anatomical position information and the size information are marked at a marked position corresponding to the region of the pulmonary airway nodule in the pulmonary airway contour image.

[0143] Using the solution of this embodiment, a lung airway medical image is acquired, and a lung airway contour image is extracted from the lung airway medical image; based on the coordinates corresponding to the pixel points in the lung airway contour image, a target variation of a target field corresponding to the lung airway contour image is determined, where the target field is a direction field or a gradient field; the target variation is compared with a preset first variation threshold to obtain a comparison result, and lung airway nodules in the lung airway contour image are identified based on the comparison result. By determining the target variation of the target field corresponding to the lung airway contour image and utilizing the target variation of the target field on the airway contour surface, the location of protrusions on the lung airway in the medical image is determined, thereby identifying the location of small nodules and improving the accuracy of early lung airway nodule identification.

[0144] Accordingly, the present application also provides a device for identifying pulmonary airway nodules, such as Figure 6 As shown, Figure 6 A schematic diagram of the structure of a pulmonary airway nodule identification device provided in an embodiment of the present application. The pulmonary airway nodule identification device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. Those skilled in the art will appreciate that the structure of the pulmonary airway nodule identification device shown in the figure does not constitute a limitation on the pulmonary airway nodule identification device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0145] Processor 1101 is the control center of pulmonary airway nodule identification device 1100. It connects the various components of pulmonary airway nodule identification device 1100 using various interfaces and lines. By running or loading software programs and / or units stored in memory 1102 and calling data stored in memory 1102, it executes various functions of pulmonary airway nodule identification device 1100 and processes data, thereby providing overall monitoring of pulmonary airway nodule identification device 1100. Processor 1101 can be a processor CPU, graphics processor GPU, network processor (NP), etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0146] In an embodiment of the present application, the processor 1101 in the pulmonary airway nodule identification device 1100 will load the instructions corresponding to the processes of one or more applications into the memory 1102 in accordance with the following steps, and the processor 1101 will run the applications stored in the memory 1102 to implement various functions. For specific implementation, please refer to the previous embodiments and will not be repeated here.

[0147] Optional, such as Figure 5 As shown, the pulmonary airway nodule identification device 1100 further includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107 respectively. Those skilled in the art will understand that Figure 6 The structure of the pulmonary airway nodule identification device shown in the figure does not constitute a limitation of the pulmonary airway nodule identification device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0148] The touch screen display 1103 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch screen display 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the pulmonary airway nodule identification device, and these graphical user interfaces can be composed of graphics, text, icons, videos and any combination thereof. Optionally, a liquid crystal display (LCD), an organic light emitting diode (OLED, Organic Light-Emitting Diode) and the like can be used to configure the display panel. The touch panel can be used to collect the user's touch operations on or near it (such as the user uses any suitable object or accessory such as a finger, stylus or the like on the touch panel or near the touch panel) and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 1101, and can receive the command sent by the processor 1101 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event. Then the processor 1101 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 1103 can also be used as part of the input unit 1106 to realize the input function.

[0149] The radio frequency circuit 1104 can be used to send and receive radio frequency signals to establish wireless communication with a network device or other pulmonary airway nodule identification device through wireless communication, and to send and receive signals between the network device or other pulmonary airway nodule identification device.

[0150] The audio circuit 1105 can be used to provide an audio interface between the user and the pulmonary airway nodule identification device through a speaker and a microphone. The audio circuit 1105 can convert the received audio data into an electrical signal and transmit it to the speaker, which converts it into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and converted into audio data. The audio data is then output to the processor 1101 for processing, and then sent to another pulmonary airway nodule identification device through the radio frequency circuit 1104, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earphone jack to provide communication between an external headset and the pulmonary airway nodule identification device.

[0151] The input unit 1106 may be configured to receive input digital, character information, or user feature information (such as fingerprint, iris, or facial information), and to generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control.

[0152] Power supply 1107 is used to power the various components of pulmonary airway nodule identification device 1100. Optionally, power supply 1107 can be logically connected to processor 1101 via a power management device, thereby enabling the power management device to manage charging, discharging, and power consumption. Power supply 1107 can also include one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0153] although Figure 6 Not shown in the figure, the pulmonary airway nodule identification device 1100 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be repeated here.

[0154] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0155] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0156] To this end, embodiments of the present application provide a computer-readable storage medium storing a plurality of computer programs capable of being loaded by a processor to execute any of the pulmonary airway nodule identification methods provided in embodiments of the present application. The computer program can execute the pulmonary airway nodule identification method. Specific implementations can be found in the previous embodiments and will not be further described here.

[0157] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0158] Since the computer program stored in the computer-readable storage medium can execute any of the pulmonary airway nodule identification methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the pulmonary airway nodule identification methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0159] According to one aspect of the present application, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a pulmonary airway nodule identification device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the pulmonary airway nodule identification device to perform the methods provided in various optional implementations of the aforementioned embodiments.

[0160] In the above-mentioned embodiments of the pulmonary airway nodule identification device, computer-readable storage medium, pulmonary airway nodule identification equipment, and computer program product, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes and beneficial effects of the above-described pulmonary airway nodule identification device, computer-readable storage medium, computer program product, pulmonary airway nodule identification equipment, and their corresponding units can be referred to the description of the pulmonary airway nodule identification method in the above embodiments, and will not be described in detail here.

[0161] The above is a detailed introduction to the pulmonary airway nodule identification method, device, equipment, computer-readable storage medium and computer program product provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for identifying pulmonary airway nodules, characterized in that: The pulmonary airway nodule identification method comprises: Acquire a lung airway medical image, and extract a lung airway contour image from the lung airway medical image; determining a target change amount of a target field corresponding to the lung airway contour image based on coordinates corresponding to pixel points in the lung airway contour image, wherein the target field is a direction field; Comparing the target change amount with a preset first change amount threshold to obtain a comparison result, and identifying pulmonary airway nodules in the pulmonary airway contour image based on the comparison result; Wherein, determining the target change amount of the target field corresponding to the lung airway contour image based on the coordinates corresponding to the pixel points in the lung airway contour image includes: The lung airway contour image is input into the computational model, and the computational model calculates the direction vector of each pixel point on the lung airway contour; Determining a target change amount of the direction field corresponding to the lung airway contour image based on the direction vector of each pixel point and a preset direction vector, wherein the preset direction vector is the direction vector of the pixel point when there is no lung airway nodule in the lung airway contour; The determining, based on the coordinates corresponding to the pixel points in the lung airway contour image, a target change amount of a target field corresponding to the lung airway contour image further includes: Acquire a pulmonary airway centerline in the pulmonary airway contour image, and divide the pulmonary airway contour into a plurality of circles with each centerline point on the pulmonary airway centerline as a circle center; Calculating the direction vector of each pixel point on the lung airway contour based on the coordinates corresponding to the two adjacent pixel points closest to each other on each two adjacent circles; Determining a target change amount of the direction field corresponding to the lung airway contour image based on the direction vector of each pixel point and a preset direction vector includes: Calculating a reference change in the direction vector of each pixel based on the direction vector of each pixel and a preset direction vector; Accumulating the reference change of the direction vector of each pixel point to determine the target change of the direction field corresponding to the lung airway contour image; The step of comparing the target variation with a preset first variation threshold to obtain a comparison result, and identifying pulmonary airway nodules in the pulmonary airway contour image based on the comparison result, includes: Comparing the target variation with a preset first variation threshold to obtain a comparison result, wherein the preset first variation threshold is a target field variation corresponding to a lung airway contour image without lung airway nodules; If the comparison result shows that the target change amount is not greater than a preset first change amount threshold, it is determined that no pulmonary airway nodules exist in the pulmonary airway contour image; If the comparison result shows that the target variation is greater than a preset first variation threshold, a preset second variation threshold is compared with a target field reference variation corresponding to each pixel point, where the preset second variation threshold is the average value of the target field variation corresponding to all pixels in the pulmonary airway contour image without pulmonary airway nodules; A contour region composed of pixel points whose target field reference variation is greater than a preset second variation threshold is determined as a region of pulmonary airway nodules in the pulmonary airway contour image.

2. The method for identifying pulmonary airway nodules according to claim 1, characterized in that: After determining the contour region composed of pixels whose target field reference variation is greater than a preset second variation threshold as the region of the pulmonary airway nodules in the pulmonary airway contour image, the method includes: Determining anatomical position information corresponding to the pulmonary airway nodule based on preset anatomical information, the area of ​​the pulmonary airway nodule, and the pulmonary airway contour image; Calculating size information corresponding to the pulmonary airway nodule based on the coordinates of each pixel point in the region of the pulmonary airway nodule in the pulmonary airway contour image; The anatomical position information and the size information are marked at a marked position corresponding to the region of the pulmonary airway nodule in the pulmonary airway contour image.

3. A device for identifying pulmonary airway nodules, characterized in that: The pulmonary airway nodule identification device comprises: an acquisition unit, configured to acquire a lung airway medical image and extract a lung airway contour image from the lung airway medical image; a determination unit, configured to determine a target variation of a target field corresponding to the lung airway contour image based on coordinates corresponding to pixels in the lung airway contour image, wherein the target field is a direction field, and further configured to input the lung airway contour image into a calculation model, wherein the calculation model calculates a direction vector for each pixel on the lung airway contour; and determine a target variation of the direction field corresponding to the lung airway contour image based on the direction vector of each pixel and a preset direction vector; an identification unit, configured to compare the target variation with a preset first variation threshold to obtain a comparison result, and identify pulmonary airway nodules in the pulmonary airway contour image based on the comparison result; Wherein, the determination unit is further used to obtain the lung airway centerline in the lung airway contour image, and divide the lung airway contour into multiple circles with each centerline point on the lung airway centerline as the center of the circle; based on the coordinates corresponding to the two adjacent pixel points closest to each other on each two adjacent circles, calculate the direction vector of each pixel point on the lung airway contour, and based on the direction vector of each pixel point and a preset direction vector, the preset direction vector is the direction vector of the pixel point when there is no lung airway nodule in the lung airway contour, calculate the direction vector reference change of each pixel point; accumulate the direction vector reference change of each pixel point to determine the target change of the direction field corresponding to the lung airway contour image; The identification unit is further used to compare the target change with a preset first change threshold to obtain a comparison result, wherein the preset first change threshold is the target field change corresponding to the lung airway contour image without lung airway nodules; if the comparison result is that the target change is not greater than the preset first change threshold, it is determined that there are no lung airway nodules in the lung airway contour image; if the comparison result is that the target change is greater than the preset first change threshold, the preset second change threshold and the target field reference change corresponding to each pixel point are compared, wherein the preset second change threshold is the average value of the target field change corresponding to all pixel points in the lung airway contour image without lung airway nodules; the contour area composed of pixel points whose target field reference change is greater than the preset second change threshold is determined as the area of ​​lung airway nodules in the lung airway contour image.

4. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program; the processor loads the computer program from the memory to execute the steps of the pulmonary airway nodule identification method according to any one of claims 1-2.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which is suitable for being loaded by a processor to execute the steps of the pulmonary airway nodule identification method according to any one of claims 1-2.

Images