Image segmentation method, device, computer equipment and readable storage medium

Abstract

The present application relates to an image segmentation method, device, computer equipment and readable storage medium, which obtains projection data of a scanned object; determines the initial region of the imaging region of the target object according to the projection data and the initial segmentation method; and segments the initial region according to the re-segmentation method to determine the imaging region of the target object. The image segmentation method provided by the present application can determine a more accurate imaging region of the target object, thereby being able to accurately segment the imaging region of the target object.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to an image segmentation method, apparatus, computer device and readable storage medium. Background Art

[0002] Digital Breast Tomosynthesis (DBT) is a tomographic synthesis technology that can overcome the problem of traditional two-dimensional breast mammography that affects lesion observation due to tissue overlap. When using DBT equipment to take breast tomographic images, a certain angle of time scanning is performed to obtain a set of projection data at different angles. The projection data is reconstructed through the filtered back-projection algorithm to obtain a tomographic image, which is used for medical diagnosis and treatment. During the actual examination and shooting process, there are usually other high-attenuation objects such as metals appearing in the scanning area. After the projection data of these objects are reconstructed through the filtered back-projection algorithm, they will form artifacts of varying degrees in the tomographic image, affecting the diagnosis of medical staff.

[0003] In traditional technology, threshold segmentation is usually used on projection images or reconstructed tomographic images to segment out high-attenuation objects such as metal in tomographic images, and then the artifacts are removed based on the artifact correction algorithm. However, due to the complexity of the human body, different regions may have relative morphology and density changes, and it is impossible to accurately segment out high-attenuation objects such as metal based only on the threshold. Summary of the invention

[0004] Based on this, it is necessary to provide an image segmentation method, apparatus, computer device and readable storage medium to address the above technical problems.

[0005] On the one hand, an embodiment of the present application provides an image segmentation method, including:

[0006] Acquire projection data of the scanned object, the projection data including an imaging area of ​​the target object, the target object being an object whose attenuation degree of the scanning ray is greater than or equal to a preset threshold;

[0007] Determine the initial region of the imaging region of the target object according to the projection data and the initial segmentation method;

[0008] The initial area is segmented according to the re-segmentation method to obtain the imaging area of ​​the target object.

[0009] In one embodiment, segmenting the initial area according to the re-segmentation method to obtain the imaging area of ​​the target object includes:

[0010] Determine an initial edge of the initial area using an edge detection algorithm according to the initial area and a first preset threshold;

[0011] Screening and connecting the initial edges to obtain the closed edges of the imaging area of ​​the target object;

[0012] The imaging area of ​​the target object is determined based on the initial edge and the closed edge.

[0013] In one embodiment, screening and connecting the initial edges to obtain closed edges of the imaging area of ​​the target object includes:

[0014] The initial edges are screened according to the preset edge length to obtain the target edge;

[0015] Connect the target edges to obtain closed edges.

[0016] In one embodiment, segmenting the initial area according to the re-segmentation method to obtain the imaging area of ​​the target object includes:

[0017] The initial region is input into the region determination model to obtain the imaging region of the target object; the region determination model is obtained by training the neural network model according to the initial region samples.

[0018] In one embodiment, determining an initial region of an imaging region of a target object according to projection data and an initial segmentation method includes:

[0019] Based on the gradient calculation method, determine the gradient image corresponding to the projection data;

[0020] An initial region of an imaging region of the target object is determined according to the second preset threshold and a gradient image corresponding to the projection data.

[0021] In one embodiment, determining an initial region of an imaging region of a target object according to projection data and an initial segmentation method includes:

[0022] Reconstructing the projection data to obtain a tomographic image;

[0023] Determine an initial region of an imaging region of a target object in a tomographic image according to an initial segmentation method;

[0024] The initial region of the imaging region of the target object in the projection data is determined according to the geometric relationship between the tomographic image and the projection data, and the initial region of the imaging region of the target object in the tomographic image.

[0025] In one embodiment, determining an initial region of an imaging region of a target object in a tomographic image according to a preliminary segmentation method includes:

[0026] Determine the maximum density projection of the tomographic image to obtain a maximum density projection image;

[0027] An initial region of an imaging region of the target object in the tomographic image is determined by using a gradient calculation method according to the maximum density projection image and a third preset threshold.

[0028] In one embodiment, determining an initial region of an imaging region of a target object in a tomographic image according to a preliminary segmentation method includes:

[0029] Based on the gradient calculation method, determining the gradient image corresponding to the tomographic image;

[0030] An initial region of an imaging region of a target object in the tomographic image is determined according to a gradient image corresponding to the tomographic image.

[0031] In one embodiment, determining an initial region of an imaging region of a target object according to projection data and an initial segmentation method includes:

[0032] Reconstructing the projection data to obtain a reconstructed volume;

[0033] Based on the region growing method, an initial region of the imaging region of the target object in the reconstructed volume is determined;

[0034] The initial region of the imaging region of the target object in the projection data is determined according to the geometric relationship between the reconstructed volume and the projection data, and the initial region of the imaging region of the target object in the reconstructed volume.

[0035] An embodiment of the present application provides an image segmentation device, including:

[0036] An acquisition module, used to acquire projection data of a scanned object, the projection data including an imaging area of ​​a target object, the target object being an object whose attenuation degree of the scanning ray is greater than or equal to a preset threshold;

[0037] A first determination module, used to determine an initial region of an imaging region of a target object according to projection data and an initial segmentation method;

[0038] The second determination module is used to segment the initial area according to a re-segmentation method to obtain an imaging area of ​​the target object.

[0039] An embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the above embodiment are implemented.

[0040] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method provided in the above embodiment are implemented.

[0041] The embodiment of the present application provides an image segmentation method, device, computer equipment and readable storage medium. The method obtains the projection data of the scanned object; determines the initial area of ​​the imaging area of ​​the target object according to the projection data and the initial segmentation method; and segments the initial area according to the re-segmentation method to obtain the imaging area of ​​the target object. The image segmentation method provided in the embodiment of the present application first uses the initial segmentation method to determine the initial area of ​​segmentation, and then uses the re-segmentation method to segment the initial area to determine the imaging area of ​​the target object. After two segmentation processes, a more accurate imaging area of ​​the target object can be determined, so that the imaging area of ​​the target object can be accurately segmented. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For different technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 A schematic diagram of the steps of an image segmentation method provided in one embodiment of the present application;

[0044] Figure 2 A schematic flow chart of the steps of an image segmentation method provided in another embodiment of the present application;

[0045] Figure 3 A schematic diagram of the structure of an initial edge provided by an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the structure of a closed edge provided by an embodiment of the present application;

[0047] Figure 5 A schematic structural diagram of the edge of an imaging area of ​​a target object provided by one embodiment of the present application;

[0048] Figure 6 A schematic flow chart of the steps of an image segmentation method provided in another embodiment of the present application;

[0049] Figure 7 A schematic flow chart of the steps of an image segmentation method provided in another embodiment of the present application;

[0050] Figure 8 A schematic diagram of the structure of a gradient image provided by an embodiment of the present application;

[0051] Fig. 9 A schematic flow chart of the steps of an image segmentation method provided in another embodiment of the present application;

[0052] Fig.10 A schematic flow chart of the steps of an image segmentation method provided in another embodiment of the present application;

[0053] Fig.11 A schematic flow chart of the steps of an image segmentation method provided in another embodiment of the present application;

[0054] Fig.12 A schematic flow chart of the steps of an image segmentation method provided in another embodiment of the present application;

[0055] Fig.13 A schematic diagram of the structure of an image segmentation device provided in one embodiment of the present application;

[0056] Fig.14 A schematic diagram of the structure of a computer device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0058] The serial numbers assigned to the components in this article, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0059] Digital Breast Tomosynthesis (DBT) is a tomography technology that can overcome the problem of traditional two-dimensional breast molybdenum targets affecting lesion observation due to tissue overlap. In the process of using DBT equipment to take breast tomographic images, a certain angle of time-series scanning is performed to obtain a set of projection data at different angles. The projection data is reconstructed through the filtered back-projection algorithm to obtain a tomographic image, which is used for medical diagnosis and treatment. In the actual examination and shooting process, there are usually various calcifications, or other high-attenuation objects such as metal implants and puncture needles appearing in the scanning area. After the projection data of these objects are reconstructed through the filtered back-projection algorithm, they will form artifacts of varying degrees in the tomographic image, affecting the diagnosis of medical staff. Therefore, it is necessary to remove the artifacts in the tomographic image.

[0060] In order to remove artifacts in tomographic images, it is necessary to segment high-attenuation objects such as metals, and then remove the artifacts according to the artifact correction algorithm. In traditional technology, the threshold segmentation method is usually used on the projection image or the reconstructed tomographic image to segment out the metal in the tomographic image. The method for determining the threshold can be determined through practical experience, or it can be calculated through a certain indicator. Although the threshold segmentation method is simple and clear, the accuracy of the segmentation is affected by the threshold. Due to the complexity of the human body, different regions may have relative morphology and density changes. It is impossible to accurately segment high-attenuation objects such as metals only by threshold segmentation. In this regard, the present application proposes an image segmentation method.

[0061] The image segmentation method provided in the present application can be implemented by a computer device. The computer device includes but is not limited to a personal computer, a laptop computer, a smart phone, a tablet computer, and a portable wearable device. The method provided in the present application can be implemented by JAVA software, and can also be applied to other software.

[0062] The technical solution of the present application and how the technical solution of the present application solves the technical problem are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0063] See also Figure 1 An embodiment of the present application provides an image segmentation method. This embodiment uses a computer device as the execution subject to illustrate the image segmentation method, and the specific steps include:

[0064] Step 100: Acquire projection data of a scanned object, where the projection data includes an imaging region of a target object, and the target object is an object whose attenuation degree of scanning rays is greater than or equal to a preset threshold.

[0065] Projection data refers to data at different angles obtained by using a DBT device to perform a time-series scan of a scanned object at a certain angle. The imaging area of ​​the target object refers to the imaging area of ​​a high-attenuation target object such as metal. A high-attenuation target object is an object whose attenuation level is greater than or equal to a preset threshold after the scanning ray reaches the scanned object during scanning. The preset threshold can be set by the user based on experience. The computer device obtains the projection data of the scanned object. This embodiment does not limit the specific method for the computer device to obtain the projection data of the scanned object, as long as its function can be achieved.

[0066] In an optional embodiment, the projection data may be stored in a memory of a computer device, and when image segmentation is required, the computer device may directly obtain the projection data from the memory.

[0067] Step 110: Determine the initial region of the imaging region of the target object according to the projection data and the initial segmentation method.

[0068] After obtaining the projection data, the computer device uses the initial segmentation method to process the projection data to determine the initial area of ​​the imaging area of ​​the target object in the projection data. This embodiment does not limit the specific initial segmentation method and the process of processing the projection data using the initial segmentation method, as long as its function can be achieved.

[0069] In an optional embodiment, the initial segmentation method may be a region-based segmentation method, a threshold-based segmentation method, a wavelet transform-based segmentation method, or a neural network-based segmentation method.

[0070] Step 120: Segment the initial area according to a re-segmentation method to obtain an imaging area of ​​the target object.

[0071] After determining the initial region of the imaging region of the target object, the computer device uses a re-segmentation method to re-segment the initial region, and can determine the accurate imaging region of the target object in the projection data. This embodiment does not limit the specific re-segmentation method, and the process of segmenting the initial region using the re-segmentation method, as long as its function can be achieved. The re-segmentation method can be the same as or different from the initial segmentation method. The description of the re-segmentation method can refer to the specific description of the initial segmentation method above, and will not be repeated here.

[0072] The image segmentation method provided in the embodiment of the present application obtains the projection data of the scanned object; determines the initial area of ​​the imaging area of ​​the target object according to the projection data and the initial segmentation method; and segments the initial area according to the re-segmentation method to obtain the imaging area of ​​the target object. The image segmentation method provided in the embodiment of the present application first uses the initial segmentation method to determine the initial area for segmentation, and then uses the re-segmentation method to segment the initial area to determine the imaging area of ​​the target object. After two segmentation processes, a more accurate imaging area of ​​the target object can be determined, so that the imaging area of ​​the target object can be accurately segmented.

[0073] See also Figure 2 In one embodiment, a possible implementation method of segmenting an initial area according to a re-segmentation method to obtain an imaging area of ​​a target object includes the following steps:

[0074] Step 200: Determine the initial edge of the initial area using an edge detection algorithm according to the initial area and a first preset threshold.

[0075] In this embodiment, the re-segmentation method used is an edge-based segmentation method, that is, an edge detection algorithm. After obtaining the initial area of ​​the imaging area of ​​the target object, the computer device segments the imaging area of ​​the target object in the projection data. The edge detection operator of the edge detection algorithm is used to convolve the segmented imaging area of ​​the target object, and then the initial edge of the imaging area of ​​the target object is extracted according to the first preset threshold. This embodiment does not limit the specific edge detection operator used. The first preset threshold can be a grayscale threshold preset by the user.

[0076] Step 210: Screen and connect the initial edges to obtain closed edges of the imaging area of ​​the target object.

[0077] After obtaining the initial edges, the computer device screens the edges in the initial edges, removes the edges that do not meet the preset conditions, and then connects the screened edges to obtain the closed edges of the imaging area of ​​the target object. This embodiment does not limit the preset conditions when screening the edges in the initial edges, and the user can set them according to the actual application. In addition, this embodiment does not limit the method of connecting the screened edges, as long as it can achieve its function.

[0078] Step 220: Determine the imaging area of ​​the target object according to the initial edge and the closed edge.

[0079] After obtaining the initial edge and the closed edge, the computer device determines the precise edge of the imaging area of ​​the target object according to the initial edge and the closed edge, and finally determines the imaging area of ​​the target object.

[0080] In an optional embodiment, the computer device performs edge tracking through the intersection of the initial edge and the closed edge to determine the precise edge of the imaging area of ​​the target object.

[0081] In this embodiment, the edge determined by the intersection of the initial edge and the closed edge is more accurate, so that the imaging area of ​​the target object finally obtained is more accurate, and further the imaging area segmentation of the target object in the projection data can be more accurate.

[0082] In an optional embodiment, the edge detection operator may include a Sobel operator, a Prewitt operator, a Roberts operator, a Gaussian Laplace (LOG) operator, and a Canny operator. The initial edges extracted using different edge detection operators and the first preset threshold value, and the edges after the initial edges are screened are as follows: Figure 3 As shown, Figure 3 The white irregular area in the figure corresponding to the initial area is the initial area. Figure 3It can be seen that the combination of LOG and Canny operators can determine the initial edge more accurately. Figure 4 As shown, the edge corresponding to the intersection of the closed edge and the initial edge, that is, the edge of the imaging area of ​​the target object is as shown in Figure 5 shown.

[0083] See also Figure 6 In one example, a possible implementation method of screening and connecting initial edges to obtain closed edges of an imaging area of ​​a target object includes the following steps:

[0084] Step 600: Screen the initial edges according to the preset edge length to obtain the target edge.

[0085] The preset edge length may be a preset condition set by the user based on actual experience. The computer device performs screening based on the preset edge length and the initial edge. That is, the computer device removes the edges in the initial edge that are smaller than the preset edge length, and the screened target edge can be obtained.

[0086] Step 610: Connect the target edges to obtain closed edges.

[0087] After obtaining the filtered target edge, the computer device may traverse and connect all edges in the target edge. Specifically, all edges in the target edge may be connected in pairs, or adjacent edges in all edges in the target edge may be connected, and finally a closed edge may be obtained.

[0088] In this embodiment, by screening the initial edges, the interference edges existing in the initial edges can be removed, so that a more accurate closed edge can be obtained.

[0089] In one embodiment, a possible implementation method of segmenting the initial area according to the re-segmentation method to obtain the imaging area of ​​the target object includes:

[0090] The initial region is input into the region determination model to obtain the imaging region of the target object; the region determination model is obtained by training the neural network model according to the initial region samples.

[0091] In this embodiment, the re-segmentation method adopted is a segmentation method based on a neural network. A pre-trained region determination model is stored in the computer device. After the initial region is obtained, it is input into the region determination module to obtain the accurate imaging region of the target object. The region determination model is obtained by the computer device training the neural network model in advance according to the collected initial region samples. The initial region sample is of the same type as the initial region of the imaging region of the target object. The description of the initial region sample can refer to the specific description of the initial region above, which will not be repeated here.

[0092] In this embodiment, the imaging region of the target object is determined by using a pre-trained region determination model, which can improve the efficiency of determining the imaging region of the target object, thereby improving the efficiency of segmenting the imaging region of the target object.

[0093] See also Figure 7 In one embodiment, a possible implementation method for determining an initial region of an imaging region of a target object according to projection data and an initial segmentation method includes the following steps:

[0094] Step 700: Determine a gradient image corresponding to the projection data based on a gradient calculation method.

[0095] In this embodiment, the initial segmentation method used is a gradient calculation method. After obtaining the projection data, the computer device performs gradient calculation processing on the projection data to obtain a gradient image corresponding to the projection data. In other words, the computer device converts the projection data into a gradient image according to the gradient calculation method. This embodiment does not limit the specific process of obtaining the gradient image corresponding to the projection data.

[0096] In an optional embodiment, the projection data is a grayscale value, and after the projection data is converted into a gradient image, the pixel value in the gradient image is a gradient value of the grayscale value.

[0097] Step 710: Determine an initial region of an imaging region of the target object according to a second preset threshold and a gradient image corresponding to the projection data.

[0098] The second preset threshold value may be pre-set by the user based on actual experience and stored in the memory of the computer device, and the second preset threshold value is a gradient threshold value. After obtaining the gradient image corresponding to the projection data, the computer device screens the gradient image corresponding to the projection data according to the second preset threshold value, and the initial area of ​​the imaging area of ​​the target object can be obtained. In other words, the computer device determines the initial area of ​​the imaging area of ​​the target object based on the pixel points whose gradient values ​​in the gradient image corresponding to the projection data are greater than the second preset threshold value.

[0099] The method for determining the initial region provided in this embodiment is simple, easy to understand and implement. In addition, the embodiment of the present application adopts a gradient calculation method during the initial segmentation, that is, the gradient value of the projection data is used to determine the initial region, which can improve the accuracy of determining the imaging region of the target object.

[0100] The gradient image corresponding to the projection data is as follows Figure 8 As shown, Figure 8 The black dots in are the pixels whose values ​​are greater than the second preset threshold value, and the computer device can determine the initial area of ​​the imaging area of ​​the target object based on these pixels.

[0101] See also Fig. 9 In one embodiment, a possible implementation method for determining an initial region of an imaging region of a target object according to projection data and an initial segmentation method includes the following steps:

[0102] Step 900: reconstruct the projection data to obtain a tomographic image;

[0103] After acquiring the projection data of the scanned object, the computer device reconstructs the projection data to obtain a tomographic image. The projection data includes the imaging area of ​​the target object. After the projection data is reconstructed, the obtained tomographic image also includes the imaging area of ​​the target object. This embodiment does not limit the reconstruction method as long as its function can be achieved.

[0104] In an optional embodiment, the computer device reconstructs the projection data using a filtered back projection algorithm (FBP).

[0105] Step 910: Determine the initial region of the imaging region of the target object in the tomographic image according to the initial segmentation method.

[0106] After obtaining the tomographic image, the computer device uses the initial segmentation method to segment the tomographic image and determine the initial region of the imaging region of the target object in the tomographic image. The description of the initial segmentation method can refer to the specific description in the above embodiment, which will not be repeated here.

[0107] Step 920: Determine the initial region of the imaging region of the target object in the projection data according to the geometric relationship between the tomographic image and the projection data, and the initial region of the imaging region of the target object in the tomographic image.

[0108] Since the tomographic image is obtained after reconstructing the projection data, after determining the imaging area of ​​the target object in the tomographic image, the computer device can correspond the imaging area of ​​the target object in the tomographic image to the projection data according to the reconstruction relationship (geometric relationship) between the projection data and the tomographic image, thereby obtaining the initial area of ​​the imaging area of ​​the target object in the projection data. The geometric relationship between the tomographic image and the projection data is related to the reconstruction method, and this embodiment does not limit this, as long as its function can be achieved.

[0109] See also Fig.10 In one embodiment, a possible implementation method for determining an initial region of an imaging region of a target object in a tomographic image according to an initial segmentation method comprises the following steps:

[0110] Step 101: determine the maximum density projection of the tomographic image to obtain a maximum density projection image.

[0111] The maximum density projection is a two-dimensional image obtained by the perspective method, that is, it is generated by calculating the maximum density pixel encountered along each ray of the scanned object. After obtaining the tomographic image, the computer equipment uses the perspective method to obtain a two-dimensional image of the tomographic image, that is, the maximum density projection image.

[0112] In an optional embodiment, the computer device can determine the maximum density projection of the tomographic image in a preset direction, and the preset direction can be set by the user according to actual application. The maximum density projection image obtained in this way can make the final initial area more accurate.

[0113] Step 102: Determine an initial region of an imaging region of the target object in the tomographic image by using a gradient calculation method according to the maximum density projection image and a third preset threshold.

[0114] The third preset threshold can be set by the user based on actual experience. After obtaining the maximum density projection image, the computer device processes the maximum density projection image using a gradient calculation method, that is, converts the maximum density projection image into a gradient image. Then, based on the third preset threshold and the gradient image, the initial area of ​​the imaging area of ​​the target object in the tomographic image is determined. The specific process of determining the initial area can refer to the description of the process of determining the initial area based on the second preset threshold and the gradient image corresponding to the projection data, which will not be repeated here.

[0115] In an optional embodiment, when the computer device performs gradient processing on the maximum intensity projection image, it may perform gradient processing in the FBP filtering direction, so that the determined initial area is more accurate.

[0116] See also Fig.11 In one embodiment, a possible implementation method for determining an initial region of a target object in a tomographic image according to an initial segmentation method includes the following steps:

[0117] Step 201: Determine a gradient image corresponding to a tomographic image based on a gradient calculation method.

[0118] In this embodiment, the initial segmentation method used is a gradient calculation method. After obtaining the tomographic image, the computer device performs gradient calculation processing on the tomographic image to obtain a gradient image corresponding to the tomographic image. In other words, the computer device converts the tomographic image into a gradient image according to the gradient calculation method. This embodiment does not limit the process of obtaining the gradient image corresponding to the tomographic image.

[0119] Step 202: Determine an initial region of an imaging region of a target object in the tomographic image according to a gradient image corresponding to the tomographic image.

[0120] After obtaining the gradient image, the computer device screens the gradient image according to a preset gradient threshold value, and can obtain the initial region of the imaging region of the target object in the tomographic image. In other words, the computer device determines the initial region of the imaging region of the target object according to the pixel points whose gradient values ​​in the gradient image corresponding to the projection data are greater than the preset gradient threshold value.

[0121] See also Fig.12 In one embodiment, the method involves determining an initial region of an imaging region of a target object based on projection data and an initial segmentation method, including:

[0122] Step 301: reconstruct the projection data to obtain a reconstructed volume;

[0123] After acquiring the projection data of the scanned object, the computer device reconstructs the projection data to obtain a reconstructed volume. The reconstructed volume is a complete three-dimensional image corresponding to the scanned object, and multiple tomographic images can form a reconstructed volume. The projection data includes the imaging area of ​​the target object. After the projection data is reconstructed, the obtained reconstructed volume also includes the imaging area of ​​the target object. This embodiment does not limit the reconstruction method as long as it can achieve its function.

[0124] Step 302: Determine an initial region of the imaging region of the target object in the reconstructed volume based on a region growing method.

[0125] The computer device determines the initial region of the imaging region of the target object in the reconstructed volume according to the region growing method. The specific process is: first select a seed region (usually a pixel or some pixel points) in the reconstructed volume, and consider this seed region to be within the initial region of the imaging region of the target object. The neighborhood pixels of the selected seed region will be calculated to determine whether the neighborhood pixel is included in the seed region. If it is determined that the neighborhood pixel is included in the seed region, then the next pixel point is judged, and eventually the seed region will become larger and larger. When all the pixel points in the reconstructed volume are judged, the initial region of the imaging region of the target object in the reconstructed volume can be obtained.

[0126] Step 303: Determine the initial region of the imaging region of the target object in the projection data according to the geometric relationship between the reconstructed volume and the projection data, and the initial region of the imaging region of the target object in the reconstructed volume.

[0127] Since the reconstructed volume is obtained after reconstructing the projection data, after determining the imaging area of ​​the target object in the tomographic image, the computer device can correspond the imaging area of ​​the target object in the reconstructed volume to the projection data according to the reconstruction relationship (geometric relationship) between the projection data and the tomographic image, thereby obtaining the initial area of ​​the imaging area of ​​the target object in the projection data. The geometric relationship between the reconstructed volume and the projection data is related to the reconstruction method, and this embodiment does not limit this, as long as its function can be achieved.

[0128] In an optional embodiment, after determining the imaging area of ​​the target object, the process of correcting the artifacts of the imaging of the target object is as follows: segmenting the imaging area of ​​the target object in the projection data, and backfilling the projection data of the surrounding area to obtain the projection data of the imaging area without the target object and the projection data of the imaging area including only the target object; reconstructing the projection data of the imaging area without the target object and the projection data of the imaging area including only the target object respectively to obtain a reconstruction of the imaging area without the target object and without artifacts, referred to as a first reconstruction, and a reconstruction of the imaging area including only the target object and with artifacts, referred to as a second reconstruction; determining the position information of the imaging area of ​​the target object in the second reconstruction according to the geometric relationship between the imaging area of ​​the target object and the second reconstruction, and segmenting the imaging area of ​​the target object from the second reconstruction; fusing the imaging area of ​​the target object segmented according to the determined position information into the first reconstruction to obtain a reconstruction including the target object and without artifacts. In this way, it can be ensured that there are no artifacts in the reconstruction obtained by the medical staff in the end, which will not affect the diagnosis of the medical staff.

[0129] In another embodiment, in order to accurately and clearly determine the position information of the target object in the second reconstructed body, after determining the imaging area of ​​the target object, the imaging area of ​​the target object in the projection data is marked as 1, and the remaining areas are marked as 0, so as to generate a 0-1 template. By reconstructing the 0-1 template, the position information of the imaging area of ​​the target object in the corresponding second reconstructed body can be obtained.

[0130] It should be understood that, although the various steps in the flowchart in the figure are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0131] See also Fig.13 An embodiment of the present application provides an image segmentation device 10, which includes an acquisition module 11, a first determination module 12 and a second determination module 13.

[0132] The acquisition module 11 is used to acquire projection data of the scanned object, where the projection data includes an imaging area of ​​the target object, and the target object is an object whose attenuation degree of the scanning ray is greater than or equal to a preset threshold;

[0133] The first determination module 12 is used to determine the initial area of ​​the imaging area of ​​the target object according to the projection data and the initial segmentation method;

[0134] The second determining module 13 is used to segment the initial area according to a re-segmentation method to obtain an imaging area of ​​the target object.

[0135] In one embodiment, the second determination module 13 includes a first determination unit, a second determination unit and a third determination unit. The first determination unit is used to determine the initial edge of the initial area by using an edge detection algorithm according to the initial area and the first preset threshold; the second determination unit is used to screen and connect the initial edge to obtain the closed edge of the imaging area of ​​the target object; the third determination unit is used to determine the imaging area of ​​the target object according to the initial edge and the closed edge.

[0136] In one embodiment, the second determining unit is specifically configured to screen the initial edges according to a preset edge length to obtain target edges; and connect the target edges to obtain closed edges.

[0137] In one embodiment, the second determination module 13 is specifically used to input the initial region into the region determination model to obtain the imaging region of the target object; the region determination model is obtained by training the neural network model according to the initial region samples.

[0138] In one embodiment, the first determination module 12 includes a first gradient image determination unit and an initial region determination unit. The first gradient image determination unit is used to determine the gradient image corresponding to the projection data based on a gradient calculation method; the initial region determination unit is used to determine the initial region of the imaging region of the target object according to the second preset threshold and the gradient image corresponding to the projection data.

[0139] In one embodiment, the first determination module 12 includes a first reconstruction unit, a fourth determination unit, and a fifth determination unit. The first reconstruction unit is used to reconstruct the projection data to obtain a tomographic image; the fourth determination unit is used to determine the initial area of ​​the imaging area of ​​the target object in the tomographic image according to the initial segmentation method; the fifth determination unit is used to determine the initial area of ​​the imaging area of ​​the target object in the projection data according to the geometric relationship between the tomographic image and the projection data, and the initial area of ​​the imaging area of ​​the target object in the tomographic image.

[0140] In one embodiment, the fourth determination unit is specifically used to determine the maximum density projection of the tomographic image to obtain the maximum density projection image; based on the maximum density projection image and the third preset threshold, the initial area of ​​the imaging area of ​​the target object in the tomographic image is determined using a gradient calculation method.

[0141] In one embodiment, the fourth determination unit is further configured to determine a gradient image corresponding to the tomographic image based on a gradient calculation method; and determine an initial region of an imaging region of the target object in the tomographic image according to the gradient image corresponding to the tomographic image.

[0142] In one embodiment, the second determination module 12 further includes a second reconstruction unit, a sixth determination unit, and a seventh determination unit. The second reconstruction unit is used to reconstruct the projection data to obtain a reconstructed volume; the sixth determination unit is used to determine the initial region of the imaging region of the target object in the reconstructed volume based on the region growing method; the seventh determination unit is used to determine the initial region of the imaging region of the target object in the projection data according to the geometric relationship between the reconstructed volume and the projection data, and the initial region of the imaging region of the target object in the reconstructed volume.

[0143] For the specific definition of the above-mentioned image segmentation device 10, please refer to the definition of the image segmentation method above, which will not be repeated here. Each module in the image segmentation device 10 can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned devices, modules or units can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned devices or modules.

[0144] See also Fig.14 In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.14As shown. The computer device includes a processor, a memory, a network interface and a database 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store projection data, a first preset threshold value and a second preset threshold value, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer device is executed by the processor, an image segmentation method is implemented.

[0145] Those skilled in the art will understand that Fig.14 The structure shown in the figure is only a block diagram of a part of the structure 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 arrangement of components.

[0146] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0147] Acquire projection data of the scanned object, the projection data including an imaging area of ​​the target object, the target object being an object whose attenuation degree of the scanning ray is greater than or equal to a preset threshold;

[0148] Determine the initial region of the imaging region of the target object according to the projection data and the initial segmentation method;

[0149] The initial area is segmented according to the re-segmentation method to obtain the imaging area of ​​the target object.

[0150] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the initial area and the first preset threshold, an initial edge of the initial area is determined using an edge detection algorithm; the initial edge is screened and connected to obtain a closed edge of the imaging area of ​​the target object; and based on the initial edge and the closed edge, the imaging area of ​​the target object is determined.

[0151] In one embodiment, when the processor executes the computer program, the following steps are further implemented: screening the initial edges according to a preset edge length to obtain target edges; and connecting the target edges to obtain closed edges.

[0152] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the initial area is input into the area determination model to obtain the imaging area of ​​the target object; the area determination model is obtained by training the neural network model based on the initial area samples.

[0153] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the gradient calculation method, a gradient image corresponding to the projection data is determined; according to the second preset threshold and the gradient image corresponding to the projection data, an initial area of ​​the imaging area of ​​the target object is determined.

[0154] In one embodiment, the processor further implements the following steps when executing the computer program: reconstructing the projection data to obtain a tomographic image; determining the initial area of ​​the imaging area of ​​the target object in the tomographic image according to the initial segmentation method; determining the initial area of ​​the imaging area of ​​the target object in the projection data according to the geometric relationship between the tomographic image and the projection data, and the initial area of ​​the imaging area of ​​the target object in the tomographic image.

[0155] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the maximum density projection of the tomographic image to obtain a maximum density projection image; and determining the initial area of ​​the imaging area of ​​the target object in the tomographic image using a gradient calculation method based on the maximum density projection image and a third preset threshold.

[0156] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the gradient calculation method, a gradient image corresponding to the tomographic image is determined; and according to the gradient image corresponding to the tomographic image, an initial area of ​​the imaging area of ​​the target object in the tomographic image is determined.

[0157] In one embodiment, when the processor executes the computer program, the following steps are also implemented: reconstructing the projection data to obtain a reconstructed volume; determining the initial area of ​​the imaging area of ​​the target object in the reconstructed volume based on the region growing method; and determining the initial area of ​​the imaging area of ​​the target object in the projection data based on the geometric relationship between the reconstructed volume and the projection data, and the initial area of ​​the imaging area of ​​the target object in the reconstructed volume.

[0158] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0159] Acquire projection data of the scanned object, the projection data including an imaging area of ​​the target object, the target object being an object whose attenuation degree of the scanning ray is greater than or equal to a preset threshold;

[0160] Determine the initial region of the imaging region of the target object according to the projection data and the initial segmentation method;

[0161] The initial area is segmented according to the re-segmentation method to obtain the imaging area of ​​the target object.

[0162] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the initial area and the first preset threshold, an initial edge of the initial area is determined using an edge detection algorithm; the initial edge is screened and connected to obtain a closed edge of the imaging area of ​​the target object; and based on the initial edge and the closed edge, the imaging area of ​​the target object is determined.

[0163] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: screening the initial edges according to a preset edge length to obtain target edges; and connecting the target edges to obtain closed edges.

[0164] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the initial area is input into the area determination model to obtain the imaging area of ​​the target object; the area determination model is obtained by training the neural network model based on the initial area samples.

[0165] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the gradient calculation method, a gradient image corresponding to the projection data is determined; based on the second preset threshold and the gradient image corresponding to the projection data, an initial area of ​​the imaging area of ​​the target object is determined.

[0166] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: reconstructing the projection data to obtain a tomographic image; determining the initial area of ​​the imaging area of ​​the target object in the tomographic image based on the initial segmentation method; determining the initial area of ​​the imaging area of ​​the target object in the projection data based on the geometric relationship between the tomographic image and the projection data, and the initial area of ​​the imaging area of ​​the target object in the tomographic image.

[0167] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the maximum density projection of the tomographic image to obtain a maximum density projection image; and determining the initial area of ​​the imaging area of ​​the target object in the tomographic image using a gradient calculation method based on the maximum density projection image and a third preset threshold.

[0168] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the gradient calculation method, a gradient image corresponding to the tomographic image is determined; according to the gradient image corresponding to the tomographic image, an initial area of ​​the imaging area of ​​the target object in the tomographic image is determined.

[0169] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: reconstructing the projection data to obtain a reconstructed volume; determining the initial region of the imaging region of the target object in the reconstructed volume based on the region growing method; determining the initial region of the imaging region of the target object in the projection data based on the geometric relationship between the reconstructed volume and the projection data, and the initial region of the imaging region of the target object in the reconstructed volume.

[0170] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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 embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0171] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0172] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image segmentation method, characterized in that: include: Acquiring projection data of a scanned object, wherein the projection data includes an imaging area of ​​a target object, wherein the target object is an object whose attenuation degree of the scanning ray is greater than or equal to a preset threshold; Determining an initial region of an imaging region of the target object according to the projection data and the initial segmentation method; Segmenting the initial area according to a re-segmentation method to obtain an imaging area of ​​the target object; Wherein, segmenting the initial area according to the re-segmentation method to obtain the imaging area of ​​the target object includes: Determining an initial edge of the initial area using an edge detection algorithm according to the initial area and a first preset threshold; Screening and connecting the initial edges to obtain closed edges of the imaging area of ​​the target object; An imaging area of ​​the target object is determined according to the initial edge and the closed edge.

2. The image segmentation method according to claim 1, characterized in that: The screening and connecting processing of the initial edges to obtain the closed edges of the imaging area of ​​the target object includes: Screening the initial edge according to a preset edge length to obtain a target edge; The target edges are connected to obtain the closed edges.

3. The image segmentation method according to claim 1, characterized in that: The step of segmenting the initial area according to the re-segmentation method to obtain the imaging area of ​​the target object includes: The initial region is input into a region determination model to obtain an imaging region of the target object; the region determination model is obtained by training a network model based on the initial region samples.

4. The image segmentation method according to claim 1, characterized in that: Determining the initial region of the imaging region of the target object according to the projection data and the initial segmentation method includes: Determining a gradient image corresponding to the projection data based on a gradient calculation method; An initial area of ​​the imaging area of ​​the target object is determined according to a second preset threshold and a gradient image corresponding to the projection data.

5. The image segmentation method according to claim 1, characterized in that: Determining the initial region of the imaging region of the target object according to the projection data and the initial segmentation method includes: Reconstructing the projection data to obtain a tomographic image; Determining an initial region of an imaging region of the target object in the tomographic image according to the initial segmentation method; The initial region of the imaging region of the target object in the projection data is determined according to a geometric relationship between the tomographic image and the projection data, and an initial region of the imaging region of the target object in the tomographic image.

6. The image segmentation method according to claim 5, characterized in that: Determining the initial region of the imaging region of the target object in the tomographic image according to the initial segmentation method includes: Determine the maximum density projection of the tomographic image to obtain a maximum density projection image; An initial region of an imaging region of the target object in the tomographic image is determined by using a gradient calculation method according to the maximum density projection image and a third preset threshold.

7. The image segmentation method according to claim 5, characterized in that: Determining the initial region of the imaging region of the target object in the tomographic image according to the initial segmentation method includes: Determining a gradient image corresponding to the tomographic image based on a gradient calculation method; An initial region of an imaging region of the target object in the tomographic image is determined according to a gradient image corresponding to the tomographic image.

8. The image segmentation method according to claim 1, characterized in that: The step of determining an initial region of an imaging region of a target object according to the projection data and the initial segmentation method comprises: Reconstructing the projection data to obtain a reconstructed volume; Determining an initial region of an imaging region of the target object in the reconstructed volume based on a region growing method; The initial region of the imaging region of the target object in the projection data is determined according to a geometric relationship between the reconstructed volume and the projection data, and an initial region of the imaging region of the target object in the reconstructed volume.

9. An image segmentation device, characterized in that: include: An acquisition module, used to acquire projection data of a scanned object, wherein the projection data includes an imaging area of ​​a target object, and the target object is an object whose attenuation degree of the scanning ray is greater than or equal to a preset threshold; A first determination module, used to determine an initial area of ​​the imaging area of ​​the target object according to the projection data and the initial segmentation method; A second determination module is used to segment the initial area according to a re-segmentation method to obtain an imaging area of ​​the target object; The second determining module includes a first determining unit, a second determining unit and a third determining unit; The first determining unit is used to determine the initial edge of the initial area by using an edge detection algorithm according to the initial area and a first preset threshold; The second determining unit is used to screen and connect the initial edges to obtain closed edges of the imaging area of ​​the target object; The third determining unit is used to determine the imaging area of ​​the target object according to the initial edge and the closed edge.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images