Image sketching method based on deformation registration, image sketching device and storage medium

Abstract

The invention relates to an image sketching method and device based on deformation registration, computer equipment and a storage medium. The method comprises the steps of obtaining a first image and a second image of an object, determining constraint information for constraining a deformation field based on floating sketching information in the first image and the deformation field of the first image, and determining target sketching information in the second image based on the floating sketching information, the constraint information and the deformation field. According to the method, the deformation field of the first image is constrained through the floating sketching information of the first image, so that the deformation field is more accurate, an irregular deformation field is avoided, and sketching accuracy can be improved by sketching the second image based on the deformation field.

Description

Technical Field

[0001] The present application relates to the field of image processing technologies, and particularly to an image delineation method, an image delineation apparatus, and a storage medium based on deformation registration. Background Art

[0002] Radiation or radioactive delivery (e.g., radiotherapy, radiation flaw detection, radiation processing, radiation testing, etc.) can be based on image guidance technology to achieve more accurate delivery.

[0003] For example, adaptive radiation technology uses image guidance technology to judge various changes of an object, such as changes in the size, shape, and position of the radiation object, etc. By analyzing the differences between each treatment fraction image and the initial plan image, it guides the re-design of the plan. In the process of plan design, obtaining the delineation of the radiation object and the protected object is a key step. Through the deformation registration technology, a new image of a certain fraction can be registered with the initial plan image, and then the delineation on the new image can be obtained.

[0004] In the related art, since using image gray information for image registration cannot guarantee the registration effect, the accuracy of delineating a new image is relatively low. Summary of the Invention

[0005] Based on this, it is necessary to provide an image delineation method, an image delineation apparatus, and a storage medium based on deformation registration that can improve the delineation accuracy for the above technical problems.

[0006] In a first aspect, the present application provides an image delineation method based on deformation registration. The method includes:

[0007] Obtain a first image and a second image of an object; wherein, the first image includes floating delineation information;

[0008] Determine constraint information for constraining the deformation field based on the floating delineation information and the deformation field of the first image; and

[0009] Determine target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field.

[0010] In one embodiment, the determining constraint information for constraining the deformation field based on the floating delineation information and the deformation field of the first image includes:

[0011] Obtain an image region corresponding to the floating delineation information in the first image;

[0012] Determine deformation information of the image region based on the deformation field; and

[0013] Determine the constraint information based on the deformation information of the image region.

[0014] In one embodiment, the determining the constraint information based on the deformation information of the image region includes:

[0015] Based on the deformation information of each pair of pixels among multiple pixels in the image region, determine the distance between each pair of pixels to obtain a distance set; and

[0016] Based on the distance set, obtain the constraint information.

[0017] In one embodiment, the determining the target contour information in the second image based on the floating contour information, the constraint information, and the deformation field includes:

[0018] Constrain the deformation field based on the constraint information to obtain a target deformation field;

[0019] Based on the target deformation field, obtain registration information representing the correspondence of pixel points between the second image and the first image; and

[0020] Based on the registration information and the floating contour information, determine the target contour information in the second image.

[0021] In one embodiment, the constraining the deformation field based on the constraint information to obtain a target deformation field includes:

[0022] Perform regularization processing on the deformation field to obtain the regularization information of the deformation field;

[0023] Use a first preset adjustment amount to perform weighted adjustment on the constraint information to obtain target constraint information;

[0024] Use a second preset adjustment amount to perform weighted adjustment on the regularization information to obtain target regularization information; and

[0025] Based on the target constraint information and the target regularization information, determine the target deformation field.

[0026] In one embodiment, the method further includes:

[0027] Based on the coordinate system of the second image, convert the coordinate system of the first image to obtain a converted first image; and

[0028] The obtaining the registration information representing the correspondence of pixel points between the second image and the first image based on the target deformation field includes:

[0029] Based on the target deformation field, perform image registration on the second image and the transformed first image to obtain the registration information.

[0030] In one embodiment, the performing image registration on the second image and the transformed first image based on the target deformation field to obtain the registration information includes:

[0031] Determine the similarity between the second image and the transformed first image; and

[0032] Based on the similarity and the target deformation field, perform image registration on the second image and the transformed first image to obtain the registration information.

[0033] In one embodiment, the determining the target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field includes:

[0034] Construct a registration objective function that is associated with the constraint information and the deformation field;

[0035] Based on the registration objective function, determine the target deformation field; and

[0036] Based on the target deformation field and the floating delineation information, determine the target delineation information.

[0037] In a second aspect, the present application further provides an image delineation device. The device includes:

[0038] A first acquisition module, configured to acquire a first image and a second image of an object; wherein, the first image includes floating delineation information;

[0039] A first determination module, configured to determine constraint information for constraining the deformation field based on the floating delineation information and the deformation field of the first image;

[0040] A second determination module, configured to determine the target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field.

[0041] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect above is implemented.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect above is implemented.

[0043] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program which, when executed by a processor, implements the method described in the first aspect above.

[0044] The above-described method, apparatus, computer device, and storage medium for image delineation based on deformation registration obtain a first image and a second image of an object, determine constraint information for constraining a deformation field based on floating delineation information in the first image and the deformation field of the first image, and then determine target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field. This method constrains the deformation field of the first image through the floating delineation information of the first image, enabling the deformation field to be more accurate and avoiding the occurrence of irregular deformation fields. Based on this, delineating the second image can improve the accuracy of delineation.

[0045] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented in accordance with the content of the description. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically illustrates the embodiments of the present application. Description of the Drawings

[0046] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. Moreover, in all the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0047] Figure 1 It is a schematic diagram of registered images in an embodiment;

[0048] Figure 2 It is a schematic diagram of the structure of a computer device in an embodiment;

[0049] Figure 3 It is a schematic flowchart of an image delineation method in an embodiment;

[0050] Figure 4 It is a schematic flowchart of an image delineation method in another embodiment;

[0051] Figure 5 It is a schematic diagram of a mesh processing image in an embodiment;

[0052] Figure 6 It is a schematic flowchart of an image delineation method in another embodiment;

[0053] Figure 7 It is a schematic flowchart of an image delineation method in another embodiment;

[0054] Figure 8 It is a schematic flowchart of an image delineation method in another embodiment;

[0055] Figure 9 It is a schematic flowchart of an image delineation method in another embodiment;

[0056] Figure 10 It is a schematic flowchart of an image delineation method in another embodiment;

[0057] Figure 11 It is a schematic flowchart of an image delineation method in another embodiment;

[0058] Figure 12 It is a structural block diagram of an image delineation device in one embodiment. Detailed implementation manners

[0059] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above drawings are intended to cover non-exclusive inclusion.

[0061] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present application, "a plurality of" means more than two unless otherwise specifically defined.

[0062] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0063] In the current medical field, radiotherapy is one of the important methods for tumor treatment. With the continuous progress and maturity of radiotherapy technology, radiotherapy has become more precise. By achieving better dose conformity in the target area, a higher dose can be delivered to the tumor while ensuring a low dose to normal tissues. However, during the radiotherapy process, phenomena such as tumor volume changes and patient weight changes may occur. These changes are likely to cause the tumor to move out of the high-dose area and important organs to enter the high-dose area, resulting in under-dosing of the target area and over-dosing of critical organs, ultimately leading to a decrease in the local control rate of the tumor and an increase in the incidence of complications. The currently proposed adaptive radiotherapy can avoid the occurrence of the above problems. Adaptive radiotherapy uses image-guided technology to judge the anatomical and physiological changes of the patient, such as changes in the size, shape, and position of the tumor. By analyzing the differences between each treatment fraction and the initial plan, it guides the re-design of the plan. During the plan design process, obtaining the delineation of the target area and critical organs is a key step. Being able to obtain the delineation quickly and accurately is a prerequisite for ensuring the smooth progress of adaptive radiotherapy. Through the deformation registration technique, the new image of a certain fraction can be registered with the initial plan image, and then the delineation on the initial plan image can be copied to the new image to obtain the delineation on the new image.

[0064] Currently, there are mainly two types of deformation registration methods. One is the registration method based on image gray values, and the other is the registration method based on geometric shapes. For the registration method based on image gray values, the registration effect is easily affected by the image gray values. For example, in low-contrast regions, different deformations can give the same similarity value, making it difficult to determine the deformation field well and possibly obtaining an irregular deformation field; it is sensitive to regions with sudden gray value changes and may obtain abnormal deformations, such as air in the intestine. For the registration method based on geometric shapes, the geometric shapes on both images need to be extracted simultaneously, such as points, lines, and planes. Once the geometric shapes are obtained, the deformation field near the geometric shapes can be obtained, and image information can be avoided. This method can avoid the influence of image noise and modalities. However, this method cannot obtain the deformation field in areas far from the geometric shapes. In adaptive radiotherapy, it is necessary to perform deformation registration on the initial plan image and the image of a certain fraction, and then copy the delineation on the initial plan image to the fraction image. Since there is no pre-existing delineation on the fraction image, the current method can only use image gray information for registration. Due to the problems of image gray registration mentioned above, the applicability of this registration method is not good for certain situations. If the deformation field is used to copy the delineation again, the obtained delineation is likely to be discontinuous or non-smooth, resulting in an increase in the time for subsequent delineation modification and affecting the efficiency and treatment effect of adaptive radiotherapy (for example, see Figure 1The images shown, where a is the reference image of the initial plan, b is the floating image of the fractionated plan, and c is the image obtained by performing deformation registration and copying using image grayscale). To address the above problems, the embodiments of the present application provide an image delineation method that can constrain the deformation field, thereby avoiding the occurrence of an irregular deformation field and improving the effect of delineation by copying using the deformation field. The following embodiments will specifically illustrate this method.

[0065] The image delineation method provided by the embodiments of the present application can be applied to, for example, Figure 2 the computer device shown. Among them, the computer device can be a terminal, and its internal structure diagram can be as shown in Figure 2 The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes an image delineation method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0066] Those skilled in the art can understand that Figure 2 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different component layout.

[0067] In one embodiment, as shown in Figure 3 a method for image delineation based on deformation registration is provided. Taking the application of this method to the computer device in Figure 1 as an example, it includes the following steps:

[0068] S201, obtain a first image and a second image of an object; where the first image includes floating delineation information.

[0069] Optionally, the first image may be an initially planned image, and correspondingly, the second image may be a fractionated planned image. Optionally, the first image may also be a "floating image", such as an image of an object obtained before radiation delivery; correspondingly, the second image may be a "reference image", such as an image of the object obtained during radiation delivery. The object may include all or part of a person, an animal, or an object. For example, the object may be or include a target area (e.g., the area that should be irradiated) or a region of interest. The floating contour information refers to the contour information obtained by contouring the target area or region of interest in the first image. The floating contour information may include contours and / or information related to the contours. Optionally, the floating contour information may include one or more of the size, boundary information, pixel values of each pixel point in the target area or region of interest outlined in the first image, etc.

[0070] In the embodiments of the present application, the computer device may scan the object in fractions by connecting to a scanning device to obtain the initial image of the initially planned image and the initial image of the fractionated planned image of the same object; optionally, the computer device may also directly download from a medical database the initial image of the initially planned image and the initial image of the fractionated planned image of the same object. When the initial image of the initially planned image and the initial image of the fractionated planned image are obtained, the computer device may use the initial image of the initially planned image as the first image and perform contouring processing on the target area or region of interest in the first image. Specifically, it may be manual contouring by a person or automatic contouring by the device. The method of contouring processing is not limited in this article. Thus, the floating contour information can be obtained. It should be noted that the types of the first image and the second image may be any one of Computed Tomography (CT) images, magnetic resonance images, ultrasound images, etc.

[0071] S202, determine the constraint information for constraining the deformation field based on the floating contour information and the deformation field of the first image; and determine the target contour information in the second image based on the floating contour information, the constraint information, and the deformation field.

[0072] In an embodiment of the present application, the computer device may first determine (for example, calculate or read from a storage device) the deformation field of the first image. The deformation field of the first image may include displacement information of at least some pixel points in the first image during registration. As an example, the deformation field of the first image may include the deformation values of each point in the target area or the region of interest in the first image during registration. As another example, the deformation field of the first image may include the deformation values of all points in the first image during registration. The deformation field can be used to register the first image and the second image with each other. The computer device may correct, constrain, etc. the deformation field of the first image according to the floating contour information to obtain constraint information. Optionally, the computer device may also correct, constrain, etc. the abnormal deformation values in the deformation field of the first image according to the floating contour information to obtain constraint information. Optionally, the computer device may obtain constraint information according to the constraint relationship between the floating contour information and the deformation field (for example, the deformation values corresponding to each point in the floating contour area are less than a specific value, so that the total value obtained by summing the differences between the deformation values corresponding to any two points in the floating contour area is minimized, etc.). As an example, afterwards, the computer device may correct, constrain, etc. the deformation field of the first image according to the floating contour information and the constraint information to obtain a new deformation field; or, the computer device may re-register the first image and the second image according to the floating contour information and the constraint information to obtain a new deformation field. Finally, based on the new deformation field and in combination with the coordinates of the pixel points corresponding to the floating contour information in the first image, the position, shape, etc. information of the contour area in the second image can be determined, and based on the position, shape, etc. information of the contour area, the target contour information in the second image can be obtained. As another example, after determining the constraint information, a registration objective function may be constructed according to the floating contour information, the constraint information, and the deformation field, and the target deformation field may be determined by finding the extreme value of this registration objective function. Finally, the target contour information in the second image can be obtained by applying the target deformation field to the floating contour information or the first image including the floating contour information. The above specific implementation manners are only non-limiting examples, and in this document, the specific implementation manner of step S202 is not limited.

[0073] The image contouring method described in the embodiment of the present application obtains the first image and the second image of an object, determines constraint information for constraining the deformation field based on the floating contour information in the first image and the deformation field of the first image, and then determines the target contour information in the second image based on the floating contour information, the constraint information, and the deformation field. This method constrains the deformation field of the first image through the floating contour information of the first image, can make the deformation field more accurate, avoid the occurrence of irregular deformation fields, and based on this, contour the second image, which can improve the accuracy of contouring.

[0074] In one embodiment, an implementation manner for determining constraint information is provided, such asFigure 4 As shown, the feature in the above S202, “determining constraint information for constraining the deformation field based on the floating delineation information and the deformation field of the first image”, includes:

[0075] S301, obtaining an image area corresponding to floating outline information in a first image.

[0076] In an embodiment of the present application, a computer device may identify or segment a target area or a region of interest in the first image based on the floating outline information in the first image, and obtain an image area corresponding to the floating outline information in the first image. As an example, the image area may include only the target area or the region of interest, or may include the target area or the region of interest and the area around it (e.g., a endangered area). Optionally, the computer device may also grid the target area or the region of interest in the first image, and identify or segment the target area or the region of interest in the first image based on the floating outline information and the gridded image, and obtain an image area corresponding to the floating outline information in the first image. For example, see Figure 5 The images shown, wherein Figure a is the first image, and Figure b is the image after gridding the target area or the region of interest in the first image.

[0077] S302: Determine deformation information of the image region based on the deformation field.

[0078] The deformation information of the image area may be the deformation information of multiple points in the image area, and the multiple points may be a part or all of the pixel points in the image, or may be points with specific positions (e.g., feature points, edge points, etc.); optionally, the deformation information of the image area may also be the deformation information of some points in the image area. Optionally, the deformation information of the image area may also be the deformation information of the edge features of the image area or the deformation information of the shape features of the image area.

[0079] In an embodiment of the present application, after the computer device determines the image area, it can further determine the deformation value of the corresponding pixel point in the deformation field of the first image according to the coordinates of each pixel point in the image area, and obtain the deformation information of the image area. Optionally, the computer device may first locate the deformation field area corresponding to the image area in the deformation field of the first image, and then determine the deformation value of each pixel point in the deformation field area to obtain the deformation information of the image area. Optionally, the computer device may first locate the deformation field area corresponding to the image area in the deformation field of the first image, and then determine the shape features or edge features of the deformation field area, and then use the deformation values ​​of the pixel points corresponding to the shape features or edge features as the deformation information of the image area.

[0080] S303: Determine constraint information based on deformation information of the image region.

[0081] In the embodiments of the present application, when the deformation information of the image region is the deformation information of the edge feature or the deformation information of the shape feature, the deformation condition of the image region can be determined by analyzing the deformation information of the edge feature or the deformation information of the shape feature, and then the constraint information can be obtained based on the deformation condition. Optionally, when the deformation information of the image region is the deformation information of multiple pixel points in the image region, the computer device can screen out some pixel points from the multiple pixel points, and then determine the constraint information based on the deformation information of the partial pixel points; optionally, the computer device can also screen out the pixel points belonging to the grid vertices from the multiple pixel points, and then determine the constraint information based on the deformation information of the pixel points of the grid vertices. Optionally, the computer device can determine the constraint information based on the pixel value of the pixel point and the deformation information of the pixel point, or the computer device can determine the constraint information based on the pixel value of the pixel point belonging to the grid vertex and the corresponding deformation information of the pixel point.

[0082] In one embodiment, another implementation manner for determining the constraint information is provided, as Figure 6 shown, that is, the above S303 "determine the constraint information based on the deformation information of the image region" includes:

[0083] S401, based on the deformation information of each pair of pixel points among multiple pixel points in the image region, determine the distance between each pair of pixel points to obtain a distance set.

[0084] In the embodiments of the present application, when the computer device obtains multiple pixel points in the image region, it can first determine the deformation value of each pixel point according to the coordinates of each pixel point in combination with the deformation field of the first image, then determine the distance difference between the deformation values of each pair of pixel points, and determine the distance between each pair of pixel points according to the distance difference between the deformation values of each pair of pixel points, so as to construct a distance set; optionally, the computer device can perform grid division on the target area or the region of interest outlined in the first image to obtain the deformation value of each grid vertex, then calculate the deformation difference between the deformation values of each pair of grid vertices, and construct a distance set according to the deformation difference between each pair of grid vertices.

[0085] S402, based on the distance set, obtain the constraint information.

[0086] In the embodiments of the present application, the computer device may add all items in the distance set to obtain the constraint information; optionally, the computer device may also add all items in the distance set, and after obtaining the sum item, use a preset correction coefficient to correct the sum item to obtain the constraint information; optionally, the computer device may also perform weighted accumulation on all items in the distance set, that is, different weights are assigned to different pixel points for calculation to obtain the constraint information; optionally, the computer device may also fuse all items in the distance set to obtain the constraint information.

[0087] Optionally, the computer device may obtain the constraint information based on the following relational expression (1):

[0088] (1);

[0089] Wherein, represents the th grid vertex in the th region of interest. The in the summation defines the edge of the grid. represents the pixel value of the th grid vertex in the first image. represents the pixel value of the th grid vertex in the first image. represents the deformation value of the th pixel point. represents the deformation value of the th pixel point.

[0090] In one embodiment, an implementation manner for determining the target delineation information is provided. As Figure 7 shown, that is, the feature in S202 above "determine the target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field" includes:

[0091] S501, constrain the deformation field based on the constraint information to obtain the target deformation field, and based on the target deformation field, obtain the registration information representing the correspondence between the pixel points in the second image and the first image.

[0092] In an embodiment of the present application, when the computer device obtains the constraint information based on the aforementioned steps, it can correct the deformation field of the first image according to the constraint information to constrain the deformation field, or use the constraint information as a correction item to correct the deformation field of the first image to obtain a constrained deformation field, that is, a target deformation field, which represents the correspondence between each pixel point between the second image and the first image, that is, the registration information. The method described in the embodiment of the present application is essentially to register the second image and the first image according to the target deformation field to obtain the registration information representing the correspondence between the pixel points of the second image and the first image. Optionally, the computer device can also directly calculate the registration information representing the correspondence between the pixel points of the second image and the first image.

[0093] S502: Determine target delineation information in the second image based on the registration information and the floating delineation information.

[0094] The target delineation information refers to the delineation information obtained after delineating the target area or the region of interest in the second image. Optionally, the target delineation information may include the size, boundary information, pixel value of each pixel in the target area or the region of interest delineated in the second image, etc.

[0095] In an embodiment of the present application, when the computer device determines the registration information including the correspondence between each pixel point between the second image and the first image, the coordinates of each pixel point in the target area or region of interest corresponding to the floating outlining information can be further transformed according to the registration information, and then outlining is performed in the second image according to the coordinates of each pixel point after the conversion to obtain the target outlining information; optionally, the computer device can also copy the target area or region of interest outlined in the first image to the second image according to the registration information, and then determine the target outlining information in the second image.

[0096] Optionally, when a computer device determines the correspondence between each pixel point between the second image and the first image, the following method can be used to determine it: first, the similarity between the second image and the first image is determined based on the floating outline information, and then based on the similarity and the target deformation field, the second image and the first image are registered to obtain registration information.

[0097] In the embodiment of the present application, the computer device can calculate the similarity between each pixel in the second image and the corresponding pixel in the first image, and construct a similarity set based on the similarity of each pixel, and then filter out the maximum similarity from the similarity, and determine it as the similarity between the second image and the first image. Optionally, the similarity that meets the registration requirements can also be filtered out, for example, a similarity greater than a preset threshold is determined as the similarity between the second image and the first image.

[0098] Optionally, the computer device may use the following relational expressions (2) and (3) to determine the correspondence between the second image and the first image, that is, the registration information:

[0099] (2);

[0100] (3);

[0101] Wherein, represents the second image, represents the first image, represents the deformation field of the first image, represents the similarity degree (which can also be called the similarity measure) for measuring the similarity between the second image and the first image, represents the regularization term of the deformation field of the first image, represents the weight factor, represents the weight factor.

[0102] In one embodiment, an implementation manner for determining the target deformation field is provided. As Figure 8 shown, that is, the above S501 "constrain the deformation field based on the constraint information to obtain the target deformation field" includes:

[0103] S601, perform regularization processing on the deformation field to obtain the regularization information of the deformation field.

[0104] In the embodiments of the present application, the computer device may use a preset regularization processing algorithm to perform regularization processing on the deformation field of the first image; optionally, the computer device may also use the following relational expression (4) to perform regularization processing on the deformation field of the first image to obtain the regularization information of the deformation field.

[0105] S602, use the first preset adjustment amount to perform weighted adjustment on the constraint information to obtain the target constraint information.

[0106] Wherein, the first preset adjustment amount is used to correct the constraint information, and it can be determined in advance by the computer device.

[0107] In the embodiments of the present application, the computer device may perform a weighted product operation on the first preset adjustment amount and the constraint information, and determine the operation result as the target constraint information; optionally, the computer device may first determine whether to perform weighted adjustment on the constraint information according to the value of the constraint information. If it is determined to perform weighted adjustment on the constraint information, the first preset adjustment amount may be directly used to perform weighted adjustment on the constraint information, and the adjusted constraint information may be determined as the target constraint information; if it is determined not to perform weighted adjustment on the constraint information, the constraint information may be directly determined as the target constraint information.

[0108] S603. Use the second preset adjustment amount to perform weighted adjustment on the regularization information of the deformation field to obtain the target regularization information.

[0109] Among them, the second preset adjustment amount is used to correct the regularization information of the deformation field, and it can be determined by the computer device in advance.

[0110] In the embodiment of the present application, the computer device can perform a weighted product operation on the second preset adjustment amount and the regularization information of the deformation field, and determine the operation result as the target regularization information; optionally, the computer device can also first determine whether to perform weighted adjustment on the regularization information according to the value of the regularization information. If it is determined to perform weighted adjustment on the regularization information, the second preset adjustment amount can be directly used to perform weighted adjustment on the regularization information, and the adjusted regularization information is determined as the target regularization information; if it is determined not to perform weighted adjustment on the regularization information, the regularization information is directly determined as the target regularization information.

[0111] S604. Based on the target constraint information and the target regularization information, determine the target deformation field.

[0112] In the embodiment of the present application, the computer device can determine the sum of the target constraint information and the target regularization information as the target deformation field; optionally, the computer device can also perform a weighted accumulation sum on the target constraint information and the target regularization information, and determine the accumulation sum as the target deformation field.

[0113] Optionally, the above target deformation field can be determined according to the following relational formula (4):

[0114] (4);

[0115] Among them, represents the constraint information, represents the first preset adjustment amount, represents the target constraint information, represents the regularization information of the deformation field of the first image, represents the second preset adjustment amount, represents the target regularization information, represents the target deformation field.

[0116] In one embodiment, before registering the second image and the first image, or determining the registration information according to the second image and the first image, since the coordinate systems of the second image and the first image are not unified, the computer device also needs to convert the coordinate system of the first image. Specifically, the computer executes the steps: based on the coordinate system of the second image, convert the coordinate system of the first image to obtain the converted first image, and when the computer device specifically executes the above steps of S501, it specifically executes the steps: based on the target deformation field, perform image registration on the second image and the converted first image to obtain the registration information.

[0117] In an embodiment of the present application, the second image and the transformed first image are registered according to the target deformation field to obtain registration information characterizing the corresponding relationship between the pixel points of the second image and the transformed first image. Optionally, the computer device can also directly calculate the registration information characterizing the corresponding relationship between the pixel points of the second image and the transformed first image.

[0118] In one embodiment, a specific registration method is provided, as Figure 9 shown, the method includes:

[0119] S701, determine the similarity between the second image and the transformed first image.

[0120] In an embodiment of the present application, the computer device can calculate the similarity between each pixel point in the second image and the corresponding pixel point in the transformed first image, construct a similarity set according to the similarity of each pixel point, and then screen out the maximum similarity from it and determine it as the similarity between the second image and the transformed first image. Optionally, the similarity that meets the registration requirements can also be screened out from it. For example, the similarity greater than the preset threshold is determined as the similarity between the second image and the transformed first image.

[0121] S702, perform image registration on the second image and the transformed first image based on the similarity and the target deformation field to obtain registration information.

[0122] In an embodiment of the present application, when the computer device obtains the similarity between the second image and the transformed first image, it can perform registration on the second image and the transformed first image according to the similarity and the deformation value of each pixel point in the target deformation field to obtain the corresponding relationship between the second image and the transformed first image, that is, registration information; optionally, the computer device can also determine the target registration amount according to the similarity and the deformation value of the corresponding pixel point in the target deformation field, and then determine the corresponding relationship between the second image and the transformed first image according to the target registration amount, that is, registration information. Optionally, the computer device can determine the corresponding relationship between the second image and the transformed first image, that is, registration information, based on the foregoing relational expressions (2) and (3), and represents the transformed first image, represents the deformation field of the transformed first image, represents the measurement of the similarity between the second image and the transformed first image, represents the regularization term of the deformation field of the transformed first image.

[0123] In one embodiment, an implementation manner for determining the target delineation information is provided, as Figure 10As shown, that is, the feature in S202 above, "determine the target delineation information in the second image based on the floating delineation information, constraint information, and deformation field", includes:

[0124] S801, construct a registration objective function, which is associated with the constraint information and the deformation field.

[0125] Among them, the registration objective function is used for image registration. Image registration can be regarded as an optimization problem. Specifically, by transforming the coordinate system of the first image (floating image), a new image is obtained, and then the similarity with the second image (reference image) is measured. When the similarity between the first image and the second image is the highest, the registration position is obtained. The registration objective function can be an objective function for determining the registration deformation field, specifically, it can be an extreme value function. For example, when the registration objective function takes an extreme value (e.g., minimum or maximum), the corresponding deformation field is the registration deformation field that best meets the registration requirements. As an example, the relational expression (2) can be used as the registration objective function. However, the form of the registration objective function is not limited to this. For example, some parameters can also be added, subtracted, or replaced with respect to the relational expression (2) to obtain other forms of the registration objective function.

[0126] In the embodiments of the present application, the computer device can pre-construct the terms of the constraint information, the terms of the deformation field, and the similarity measurement term (which can also be called the similarity measure term), and then construct the registration objective function based on these three terms of the constraint information, the terms of the deformation field, and the similarity measurement term.

[0127] S802, determine the target deformation field based on the registration objective function.

[0128] In the embodiments of the present application, the registration objective function includes variables to be solved (e.g., the deformation amounts of each point, which correspond to the deformation field). When the computer device constructs the registration objective function based on the foregoing steps, it can target a specific value (maximum or minimum) to solve this registration objective function, and solve to obtain the target deformation field. For example, make the registration objective function take a specific value to obtain the desired target deformation field. As an example, make the relational expression (2) take the minimum value, and determine the corresponding deformation field when the relational expression (2) takes the minimum value (e.g., at this time the registration is the most accurate), and use this deformation field as the target deformation field.

[0129] S803, determine the target delineation information based on the target deformation field and the floating delineation information.

[0130] In the embodiments of the present application, as an example, the target deformation field can be applied to the floating contour information, so as to obtain the target contour information corresponding to the floating contour information on the second image after registration. As another example, the target deformation field can be applied to the entire first image to obtain the deformation values of each pixel point on the first image during registration, and then combined with the floating contour information on the first image to determine the target contour information.

[0131] Combining all the above embodiments, a method for image contouring based on deformation registration is further provided. As Figure 11 shown, the method includes:

[0132] S901, obtaining a first image and a second image of an object; wherein the first image includes floating contour information.

[0133] S902, obtaining the image region corresponding to the floating contour information in the first image.

[0134] S903, determining the deformation information of the image region based on the deformation field.

[0135] S904, determining the distance between every two pixel points among multiple pixel points in the image region based on the deformation information of every two pixel points among the multiple pixel points in the image region, to obtain a distance set.

[0136] S905, obtaining constraint information based on the distance set.

[0137] S906, constraining the deformation field based on the constraint information to obtain a target deformation field, and based on the target deformation field, obtaining registration information representing the corresponding relationship between the pixel points of the second image and the first image.

[0138] S907, determining the target contour information in the second image based on the registration information and the floating contour information.

[0139] In the embodiments of the present application, the above steps have been described above. For detailed descriptions, please refer to the foregoing content and will not be elaborated here. The image contouring method described in the embodiments of the present application increases the use of existing contours to constrain the deformation field, which can improve the accuracy of determining the deformation field, and further improve the accuracy of registering different images; in addition, during the registration process, only one image needs to have a contour, and it is not necessary to have contours on both images simultaneously for registration, which improves the registration efficiency. Moreover, using this image contouring method to register two images makes the boundary of the contoured region after registration smoother and more continuous.

[0140] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0141] Based on the same inventive concept, an embodiment of the present application further provides an image outlining device for implementing the above-mentioned image outlining method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following image outlining devices can refer to the limitations on the image outlining method in the above text, and will not be repeated here.

[0142] In one embodiment, as Figure 12 shown, an image outlining device is provided, including:

[0143] A first acquisition module 10, configured to acquire a first image and a second image of an object; wherein, the first image includes floating outlining information;

[0144] A first determination module 11, configured to determine constraint information for constraining the deformation field based on the floating outlining information and the deformation field of the first image;

[0145] A second determination module 12, configured to determine target outlining information in the second image based on the floating outlining information, the constraint information, and the deformation field.

[0146] In one embodiment, the above-mentioned first determination module 11 includes:

[0147] A first acquisition unit, configured to acquire an image region corresponding to the floating outlining information in the first image;

[0148] A first determination unit, configured to determine deformation information of the image region based on the deformation field;

[0149] A second determination unit, configured to determine the constraint information based on the deformation information of the image region.

[0150] In one embodiment, the second determination unit is specifically configured to determine the distance between each two pixel points based on the deformation information of each two pixel points among multiple pixel points in the image region, obtain a distance set, and obtain the constraint information based on the distance set.

[0151] In one embodiment, the above-mentioned second determination module 12 includes:

[0152] A constraint unit, configured to constrain the deformation field based on the constraint information to obtain a target deformation field;

[0153] A third determination unit, configured to obtain registration information characterizing the correspondence of pixel points between the second image and the first image based on the target deformation field;

[0154] A fourth determination unit, configured to determine target delineation information in the second image based on the registration information and the floating delineation information.

[0155] In one embodiment, the above-mentioned constraint unit is specifically configured to perform regularization processing on the deformation field to obtain regularization information of the deformation field; perform weighted adjustment on the constraint information by using a first preset adjustment amount to obtain target constraint information; perform weighted adjustment on the regularization information by using a second preset adjustment amount to obtain target regularization information; determine the target deformation field based on the target constraint information and the target regularization information.

[0156] In one embodiment, the above-mentioned second determination module 12 further includes:

[0157] A conversion unit, configured to convert the coordinate system of the first image based on the coordinate system of the second image to obtain a converted first image;

[0158] Correspondingly, the above-mentioned constraint unit is specifically configured to perform image registration on the second image and the converted first image based on the target deformation field to obtain the registration information.

[0159] In one embodiment, the above-mentioned constraint unit is specifically configured to determine the similarity between the second image and the converted first image; perform image registration on the second image and the converted first image based on the similarity and the target deformation field to obtain the registration information.

[0160] Each module in the above image delineation device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0161] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0162] Obtain a first image and a second image of an object; wherein, the first image includes floating contour information;

[0163] Based on the floating contour information and the deformation field of the first image, determine constraint information for constraining the deformation field, where the deformation field is used to register the second image with the first image; and

[0164] Based on the floating contour information, the constraint information, and the deformation field, determine target contour information in the second image.

[0165] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0166] Obtain an image region corresponding to the floating contour information in the first image;

[0167] Based on the deformation field, determine deformation information of the image region;

[0168] Based on the deformation information of the image region, determine the constraint information.

[0169] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0170] Based on the deformation information between every two pixel points among multiple pixel points in the image region, determine the distance between every two pixel points, obtaining a distance set;

[0171] Based on the distance set, obtain the constraint information.

[0172] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0173] Based on the constraint information, constrain the deformation field to obtain a target deformation field;

[0174] Based on the target deformation field, obtain registration information representing the correspondence relationship of pixel points between the second image and the first image;

[0175] Based on the registration information and the floating contour information, determine target contour information in the second image.

[0176] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0177] Perform regularization processing on the deformation field to obtain regularization information of the deformation field;

[0178] The constraint information is weighted and adjusted by a first preset adjustment amount to obtain target constraint information;

[0179] The regularization information is weighted and adjusted by a second preset adjustment amount to obtain target regularization information;

[0180] Based on the target constraint information and the target regularization information, the target deformation field is determined.

[0181] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0182] Based on the coordinate system of the second image, the coordinate system of the first image is converted to obtain a converted first image; and,

[0183] The obtaining the registration information representing the correspondence relationship of pixel points between the second image and the first image based on the target deformation field includes:

[0184] Based on the target deformation field, image registration is performed on the second image and the converted first image to obtain the registration information.

[0185] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0186] Determine the similarity between the second image and the converted first image;

[0187] Based on the similarity and the target deformation field, image registration is performed on the second image and the converted first image to obtain the registration information.

[0188] For the computer device provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0190] Obtain a first image and a second image of an object; wherein, the first image includes floating contour information;

[0191] Based on the floating contour information and the deformation field of the first image, determine constraint information for constraining the deformation field, where the deformation field is used to register the second image with the first image; and

[0192] Based on the floating contour information, the constraint information and the deformation field, determine the target contour information in the second image.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0194] Obtain the image region corresponding to the floating contour information in the first image;

[0195] Based on the deformation field, determine the deformation information of the image region;

[0196] Based on the deformation information of the image region, determine the constraint information.

[0197] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0198] Based on the deformation information between every two pixel points among multiple pixel points in the image region, determine the distance between every two pixel points to obtain a distance set;

[0199] Based on the distance set, obtain the constraint information.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0201] Based on the constraint information, constrain the deformation field to obtain a target deformation field;

[0202] Based on the target deformation field, obtain registration information characterizing the correspondence of pixel points between the second image and the first image;

[0203] Based on the registration information and the floating contour information, determine the target contour information in the second image.

[0204] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0205] Perform regularization processing on the deformation field to obtain regularization information of the deformation field;

[0206] Use a first preset adjustment amount to perform weighted adjustment on the constraint information to obtain target constraint information;

[0207] Use a second preset adjustment amount to perform weighted adjustment on the regularization information to obtain target regularization information;

[0208] Based on the target constraint information and the target regularization information, determine the target deformation field.

[0209] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0210] Based on the coordinate system of the second image, convert the coordinate system of the first image to obtain a converted first image; and,

[0211] Obtaining registration information characterizing the correspondence of pixel points between the second image and the first image based on the target deformation field includes:

[0212] Performing image registration on the second image and the transformed first image based on the target deformation field to obtain the registration information.

[0213] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0214] Determining the similarity between the second image and the transformed first image;

[0215] Performing image registration on the second image and the transformed first image based on the similarity and the target deformation field to obtain the registration information.

[0216] For the computer-readable storage medium provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0217] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the following steps:

[0218] Obtaining a first image and a second image of an object; wherein, the first image includes floating contour information;

[0219] Determining constraint information for constraining the deformation field based on the floating contour information and the deformation field of the first image, the deformation field being used to register the second image with the first image; and

[0220] Determining target contour information in the second image based on the floating contour information, the constraint information, and the deformation field.

[0221] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0222] Obtaining an image region corresponding to the floating contour information in the first image;

[0223] Determining deformation information of the image region based on the deformation field;

[0224] Determining the constraint information based on the deformation information of the image region.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0226] Based on the deformation information of every two pixel points among multiple pixel points within the image region, determine the distance between every two pixel points to obtain a distance set;

[0227] Based on the distance set, obtain the constraint information.

[0228] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0229] Based on the constraint information, constrain the deformation field to obtain a target deformation field;

[0230] Based on the target deformation field, obtain registration information characterizing the corresponding relationship of pixel points between the second image and the first image;

[0231] Based on the registration information and the floating contour information, determine the target contour information in the second image.

[0232] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0233] Perform regularization processing on the deformation field to obtain regularization information of the deformation field;

[0234] Use a first preset adjustment amount to perform weighted adjustment on the constraint information to obtain target constraint information;

[0235] Use a second preset adjustment amount to perform weighted adjustment on the regularization information to obtain target regularization information;

[0236] Based on the target constraint information and the target regularization information, determine the target deformation field.

[0237] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0238] Based on the coordinate system of the second image, convert the coordinate system of the first image to obtain a converted first image; and,

[0239] The obtaining the registration information characterizing the corresponding relationship of pixel points between the second image and the first image based on the target deformation field includes:

[0240] Based on the target deformation field, perform image registration on the second image and the converted first image to obtain the registration information.

[0241] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0242] Determine the similarity between the second image and the converted first image;

[0243] Based on the similarity and the target deformation field, perform image registration on the second image and the transformed first image to obtain the registration information.

[0244] For a computer program product provided by the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0245] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random-access memories (ReRAMs), magnetoresistive random-access memories (MRAMs), ferroelectric random-access memories (FRAMs), phase change memories (PCMs), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0246] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0247] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An image delineation method based on deformation registration, characterized in that, it includes: Obtaining a first image and a second image of an object; wherein, the first image includes floating delineation information; Determining constraint information for constraining the deformation field based on the floating delineation information and the deformation field of the first image; and Determining target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field.

2. The image delineation method according to claim 1, characterized in that, The determining constraint information for constraining the deformation field based on the floating delineation information and the deformation field of the first image includes: Obtaining an image region corresponding to the floating delineation information in the first image; Determining deformation information of the image region based on the deformation field; and Determining the constraint information based on the deformation information of the image region.

3. The image delineation method according to claim 2, characterized in that, The determining the constraint information based on the deformation information of the image region includes: Determining the distance between each two of multiple pixel points in the image region based on the deformation information between each two of the multiple pixel points in the image region, obtaining a distance set; and Obtaining the constraint information based on the distance set.

4. The image delineation method according to claim 1, characterized in that, The determining target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field includes: Constraining the deformation field based on the constraint information to obtain a target deformation field; Obtaining registration information characterizing the correspondence of pixel points between the second image and the first image based on the target deformation field; and Determining target delineation information in the second image based on the registration information and the floating delineation information.

5. The image delineation method according to claim 4, characterized in that, The constraining the deformation field based on the constraint information to obtain a target deformation field includes: Performing regularization processing on the deformation field to obtain regularization information of the deformation field; Performing weighted adjustment on the constraint information using a first preset adjustment amount to obtain target constraint information; Performing weighted adjustment on the regularization information using a second preset adjustment amount to obtain target regularization information; and Determining the target deformation field based on the target constraint information and the target regularization information.

6. The image delineation method according to claim 4, characterized in that, The method further includes: Converting the coordinate system of the first image based on the coordinate system of the second image to obtain a converted first image; and The obtaining registration information characterizing the correspondence of pixel points between the second image and the first image based on the target deformation field includes: Performing image registration on the second image and the converted first image based on the target deformation field to obtain the registration information.

7. The image delineation method according to claim 6, characterized in that, Performing image registration on the second image and the transformed first image based on the target deformation field to obtain the registration information includes: Determining the similarity between the second image and the transformed first image; and Performing image registration on the second image and the transformed first image based on the similarity and the target deformation field to obtain the registration information.

8. The image delineation method according to claim 1, wherein determining the target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field includes: Constructing a registration objective function that is associated with the constraint information and the deformation field; Determining a target deformation field based on the registration objective function; and Determining the target delineation information based on the target deformation field and the floating delineation information.

9. An image delineation apparatus, wherein it includes: A first acquisition module for acquiring a first image and a second image of an object; wherein, the first image includes floating delineation information; A first determination module for determining constraint information for constraining the deformation field based on the floating delineation information and the deformation field of the first image; and A second determination module for determining the target delineation information in the second image based on the floating delineation information, the constraint information, and the deformation field.

10. A computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the image delineation method according to any one of claims 1 to 8 are implemented.

Images