A three-dimensional object segmentation system and method in three-dimensional volume data

Abstract

The application relates to a three-dimensional object segmentation system and method in three-dimensional body data, and belongs to the technical field of CT detection, which solves the problem of how to quickly and accurately segment all objects in three-dimensional body data in the prior art. The system comprises a two-dimensional tomography acquisition unit, a two-dimensional object segmentation unit and a connectivity judgment unit, wherein the connectivity judgment unit comprises a preliminary judgment unit, a connected region determination unit, a return control unit and a repetition control unit. The three-dimensional object in the three-dimensional body data is quickly and accurately segmented.

Description

Technical Field

[0001] This invention relates to the field of CT detection technology, and in particular to a three-dimensional object segmentation system and method in three-dimensional volume data. Background Technology

[0002] CT (Computed Tomography) inspection is a technique that uses X-rays to inspect materials, workpieces, and equipment without damaging the object being inspected. It plays a crucial role in industries such as aerospace, metallurgy, power, petrochemicals, shipbuilding, spaceflight, railways, and automobiles. Accurate segmentation of 3D objects is a key prerequisite for object identification and location. Image segmentation is currently divided into two main categories: one is based on artificial intelligence technology, which, through training, directly segments one or more 3D objects from a training set. This method generally relies on training samples and is heavily dependent on the shape and texture of objects in the training samples, and cannot segment all 3D objects. The other is traditional segmentation methods, commonly including thresholding, 3D region growing, boundary methods, and artificial intelligence. Thresholding is the most common and simplest segmentation method. Its principle is to draw a grayscale histogram of the image and select a threshold from the histogram to classify the image and obtain the segmentation result. Thresholding requires that the grayscale values ​​of the image be uniformly distributed, and that peaks and valleys be clearly observed in the histogram; otherwise, it cannot accurately segment the specified region, and its limitations are significant. Three-dimensional region growing, typically a region growing method, uses a seed point to merge adjacent pixels or regions with similar properties into a new growth point, repeating this process until no further growth is possible. Boundary methods, on the other hand, identify dissimilar pixels to form boundaries, thus separating different regions. Boundary methods are edge-detection-based segmentation algorithms that utilize the differences in features between regions in an image, employing gradient concepts to detect edges and segment the boundaries of different regions. The accuracy of the three-dimensional boundary segmentation results is crucial.

[0003] With advancements in hardware and the emergence of diverse algorithms, the demands on 3D object segmentation time are increasing. Therefore, how to quickly and accurately segment all objects in 3D volumetric data has become a pressing technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] Based on the above analysis, the embodiments of the present invention aim to provide a three-dimensional object segmentation system and method in three-dimensional volume data, so as to solve the existing problem of how to quickly and accurately segment all objects in three-dimensional volume data.

[0005] On one hand, the present invention provides a three-dimensional object segmentation system in three-dimensional volume data, the system comprising:

[0006] The two-dimensional tomographic acquisition unit is used to reconstruct the projection data of the scanned part at different angles obtained by dual-energy CT scanning, obtain multiple two-dimensional tomes, and number the two-dimensional tomes in sequence.

[0007] Two-dimensional object segmentation unit is used to segment two-dimensional objects in each two-dimensional section, obtain the features of each two-dimensional object in each two-dimensional section, and number the two-dimensional objects in each two-dimensional section in sequence.

[0008] The connectivity determination unit is used to perform connectivity analysis based on the parameter differences between the basic two-dimensional objects in the basic two-dimensional fault and the two-dimensional objects in the two-dimensional faults above the basic two-dimensional fault, to determine the connected regions and complete the three-dimensional volume connectivity analysis; the parameters include center position, area, average density and average atomic number;

[0009] Preferably, the connectivity determination unit includes a preliminary determination unit, a connected region determination unit, a return control unit, and a repeat control unit;

[0010] The preliminary judgment unit is used to determine the k-th two-dimensional object M of the i-th two-dimensional fault. ik Based on this, traverse each two-dimensional object in the (i-1)th two-dimensional fault, and determine whether each two-dimensional object in the (i-1)th two-dimensional fault is related to two-dimensional object M. ik The unit determines whether the differences in the center position, area, average density, and average atomic number meet the threshold requirements. When the preliminary judgment unit determines that there is a two-dimensional object meeting the threshold requirements in the (i-1)th two-dimensional fault, the unit comprehensively scores the two-dimensional object meeting the threshold requirements based on the differences in center position, area, average density, and average atomic number. The smaller the difference, the higher the score. The two-dimensional object with the highest comprehensive score is determined as the one in the (i-1)th two-dimensional fault that is most similar to two-dimensional object M. ik A connected region with connectivity; the return control unit is used to return the program to the preliminary judgment unit when the preliminary judgment unit determines that there is no two-dimensional object that meets the threshold requirement in the (i-1)th two-dimensional fault, so that the preliminary judgment unit traverses each two-dimensional object in the ij-th two-dimensional fault and repeats the preliminary judgment; where i≥2, k≥1, i≥j≥2; j takes values ​​from small to large, and only when there is no two-dimensional object that meets the threshold requirement in the two-dimensional fault with the current value, j takes a value that is 1 greater than the current value; the repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to repeat until the connectivity analysis of each two-dimensional object in each two-dimensional fault is completed.

[0011] Preferably, the system further includes an image preprocessing unit for preprocessing the two-dimensional tomographic image obtained by the two-dimensional tomographic acquisition unit to improve the signal-to-noise ratio of the image.

[0012] Preferably, the image preprocessing includes image smoothing, image enhancement, image region segmentation, and dilation erosion.

[0013] Preferably, in the two-dimensional object segmentation unit, the features of the two-dimensional object include mean density, root mean square deviation of density, mean atomic number, root mean square deviation of atomic number, object area, object perimeter, abscissa of region centroid, ordinate of region centroid, and minimum bounding rectangle.

[0014] Preferably, the connected region determination unit is provided with a comprehensive scoring module, which calculates the comprehensive score according to formula (I):

[0015]

[0016] Where s0 is a two-dimensional object M ik The area of ​​the two-dimensional object M, ρ0. ik The average density, Z0 is the density of the two-dimensional object M. ik The average atomic number, x0 and y0 are the two-dimensional object M ik The x and y coordinates of the center position of the two-dimensional object are: s1, ρ1, Z1, x1, and y1. s1 is the area of ​​the two-dimensional object that meets the threshold requirement; ρ1 is the average density of the two-dimensional object that meets the threshold requirement; Z1 is the average atomic number of the two-dimensional object that meets the threshold requirement; x1 and y1 are the x and y coordinates of the center position of the two-dimensional object that meets the threshold requirement, respectively; and a, b, c, and d are parameters greater than 0.

[0017] Preferably, a two-dimensional tomography that does not contain a two-dimensional object that meets the threshold requirement is defined as an error tomography. The return control unit is equipped with an error tomography restriction module, which is set to allow the number of error tomography layers A to be traversed. When j equals A, if there is still no two-dimensional object that meets the threshold requirement in the iA-th two-dimensional tomography, the error tomography restriction module restricts the return control unit from returning the program to the preliminary judgment unit. Wherein, A≥1.

[0018] Preferably, the connectivity determination unit further includes a number modification unit, which is used to modify the number of the two-dimensional object M. ik The numbering of the object is modified to be the same as the number of the two-dimensional object with the highest comprehensive score determined in the connected region determination unit; or, if the preliminary judgment unit fails to find a two-dimensional object that meets the threshold requirement, the numbering modification unit will modify the numbering of the two-dimensional object M. ik The numbering is changed to be one more than the maximum number of the connectivity region that has already completed connectivity analysis.

[0019] Preferably, the repeat control unit includes a two-dimensional object repeat control unit and a two-dimensional fault repeat control unit. The two-dimensional object repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in the i-th two-dimensional fault. The two-dimensional fault repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in the two-dimensional fault.

[0020] Preferably, the system further includes a three-dimensional object feature acquisition unit, used to combine two-dimensional objects with connectivity to form a three-dimensional object and acquire the features of each three-dimensional object.

[0021] On the other hand, the present invention also provides a method for segmenting three-dimensional objects in three-dimensional volume data, using the above-mentioned system, the method comprising:

[0022] The two-dimensional tomographic acquisition unit reconstructs the projection data of the scanned part at different angles obtained by dual-energy CT scanning to obtain multiple two-dimensional tomographic layers, and numbers the two-dimensional tomographic layers in sequence.

[0023] The image preprocessing unit performs image smoothing, image enhancement, image region segmentation, and dilatation erosion processing on the two-dimensional tomographic image obtained by the two-dimensional tomographic acquisition unit.

[0024] The two-dimensional object segmentation unit segments the two-dimensional objects in each two-dimensional section, obtains the features of each two-dimensional object in each two-dimensional section, and numbers the two-dimensional objects in each two-dimensional section in sequence.

[0025] The connectivity determination unit performs connectivity analysis based on the parameter differences between the basic two-dimensional objects in the basic two-dimensional fault and the two-dimensional objects in the two-dimensional faults above the basic two-dimensional fault, determines the connected regions, and completes the three-dimensional volume connectivity analysis; the parameters include center position, area, average density, and average atomic number;

[0026] The 3D object feature acquisition unit combines connected 2D objects to form a 3D object and acquires the features of each 3D object.

[0027] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0028] 1. The system of this invention uses each two-dimensional object in a two-dimensional tomographic section as the connectivity assessment object for connectivity determination; that is, this invention is a two-dimensional region growing method. Compared with the existing three-dimensional region growing method, this invention reduces the range of regions that need to be grown from 26 pixels in three dimensions to 8 pixels in two dimensions. Therefore, the three-dimensional object segmentation system and method of this invention are faster.

[0029] 2. Compared with the threshold method in the prior art, which cannot accurately segment all objects due to artifacts in CT images, the present invention uses two-dimensional region growing, which can accommodate differences and reduce the impact of artifacts. Therefore, the present invention has higher accuracy in segmenting three-dimensional objects.

[0030] 3. Compared with the boundary method of the prior art, which requires first or second-order differential calculation and iterative operation, the system of the present invention can segment three-dimensional objects without any iteration. Therefore, the three-dimensional object segmentation system and method of the present invention are faster.

[0031] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0032] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0033] Figure 1 This is a flowchart illustrating the principle of the three-dimensional object segmentation system in the three-dimensional volume data of the present invention.

[0034] Figure 2 This is a schematic diagram showing the changes in the numbering of each two-dimensional object before and after connectivity analysis using the three-dimensional object segmentation system in the three-dimensional volume data of this invention. Detailed Implementation

[0035] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0036] On the one hand, this invention provides a three-dimensional object segmentation system in three-dimensional volume data, the system principle of which is as follows: Figure 1 As shown, the system includes:

[0037] M1: Two-dimensional tomographic acquisition unit, used to reconstruct and invert the projection data of the scanned specimen at different angles (e.g., 0 to 360 degrees, with an angle set at 1 degree interval) obtained by dual-energy CT scanning to obtain high-energy, low-energy, density and atomic number data images, thereby obtaining multiple two-dimensional tomographic images, and numbering the two-dimensional tomographic images sequentially.

[0038] M2: Image preprocessing unit, used to preprocess the two-dimensional tomographic image obtained by the two-dimensional tomographic acquisition unit to improve the signal-to-noise ratio of the image and make the segmentation result more accurate.

[0039] Specifically, the image preprocessing includes image smoothing, image enhancement, image region segmentation, and dilation erosion.

[0040] M3: Two-dimensional object segmentation unit, used to segment two-dimensional objects in each two-dimensional section, obtain the features of each two-dimensional object in each two-dimensional section, and number the two-dimensional objects in each two-dimensional section in sequence.

[0041] Specifically, the two-dimensional object segmentation unit is a region growing segmentation unit or a boundary segmentation unit.

[0042] For example, the region growing segmentation unit is used to traverse each two-dimensional fault and select a seed point in each two-dimensional fault, and then traverse the neighborhood of the seed point in the two-dimensional fault. In the neighborhood, the points whose difference from the seed point is less than a threshold are used as growth points for neighborhood growth, thereby completing the segmentation of the two-dimensional object in each two-dimensional fault.

[0043] For example, the difference threshold for seed points in density image segmentation is 0.1.

[0044] The features of the two-dimensional object include mean density, root mean square deviation of density, mean atomic number, root mean square deviation of atomic number, object area, object perimeter, horizontal coordinate of the centroid of the region, vertical coordinate of the centroid of the region, and minimum bounding rectangle.

[0045] M4: Connectivity determination unit, used to perform connectivity analysis based on the parameter differences between the basic two-dimensional object in the basic two-dimensional fault and the two-dimensional object in the two-dimensional fault above the basic two-dimensional fault, to determine the connected regions, and to complete the three-dimensional volume connectivity analysis; the parameters include center position, area, average density, and average atomic number.

[0046] The connectivity determination unit includes a preliminary determination unit, a connected region determination unit, a return control unit, a number modification unit, and a repeat control unit.

[0047] M4.1: Preliminary Judgment Unit

[0048] The preliminary judgment unit is used to determine the k-th two-dimensional object M of the i-th two-dimensional fault. ik Based on this, traverse each two-dimensional object in the (i-1)th two-dimensional fault, and determine whether each two-dimensional object in the (i-1)th two-dimensional fault is related to two-dimensional object M. ik Do the differences in the center position, area, average density, and average atomic number meet the threshold requirements?

[0049] M4.2: Connectivity Component Determination Unit

[0050] The connected region determination unit is used to comprehensively score the two-dimensional objects that meet the threshold requirements in the (i-1)th two-dimensional fault when the preliminary judgment unit determines that there are two-dimensional objects that meet the threshold requirements based on differences in center position, area, average density, and average atomic number. The smaller the difference, the higher the score. The two-dimensional object with the highest comprehensive score is determined as the one in the (i-1)th two-dimensional fault that is connected to two-dimensional object M. ik Connected regions that are connected.

[0051] For example, the difference thresholds for the center position, area, average density, and average atomic number are 14, 50, 0.1, and 1, respectively.

[0052] Furthermore, the connected region determination unit is equipped with a comprehensive scoring module, which calculates the comprehensive score according to formula (I):

[0053]

[0054] Where s0 is a two-dimensional object M ik The area of ​​the two-dimensional object M, ρ0. ik The average density, Z0 is the density of the two-dimensional object M. ik The average atomic number, x0 and y0 are the two-dimensional object M ik The x and y coordinates of the center position of the two-dimensional object are: s1, ρ1, Z1, x1, and y1. s1 is the area of ​​the two-dimensional object that meets the threshold requirement; ρ1 is the average density of the two-dimensional object that meets the threshold requirement; Z1 is the average atomic number of the two-dimensional object that meets the threshold requirement; x1 and y1 are the x and y coordinates of the center position of the two-dimensional object that meets the threshold requirement, respectively; and a, b, c, and d are parameters greater than 0.

[0055] The values ​​of a, b, c, and d are weighted proportions, determined according to the difference thresholds of the corresponding features. For example, a is 14 / 4, b is 50 / 4, c is 0.1 / 4, and d is 1 / 4, indicating that the four have the same weight under the above difference thresholds.

[0056] M4.3: Return to Control Unit

[0057] The return control unit is used to return the program to the preliminary judgment unit when the preliminary judgment unit determines that there is no two-dimensional object in the (i-1)th two-dimensional fracture that meets the threshold requirement. This allows the preliminary judgment unit to traverse each two-dimensional object in the ij-th two-dimensional fracture and repeat the preliminary judgment. Here, i≥2, k≥1, i≥j≥2; j takes values ​​from small to large. Only when there is no two-dimensional object in the two-dimensional fracture that meets the threshold requirement in the current value will j take a value that is 1 greater than the current value.

[0058] It should be noted that i≥2 means that the preliminary judgment unit does not need to analyze the connectivity of the first two-dimensional fault, but directly takes it as the existing connected region, and directly starts to analyze connectivity based on the two-dimensional objects in the second two-dimensional fault.

[0059] In this invention, a two-dimensional tomography that does not contain a two-dimensional object that meets the threshold requirement is defined as an error tomography. The return control unit is equipped with an error tomography restriction module, which sets the number of error tomography layers A that can be traversed. When j equals A, if there is still no two-dimensional object that meets the threshold requirement in the iA-th two-dimensional tomography, the error tomography restriction module restricts the return control unit from returning the program to the preliminary judgment unit. Wherein, A≥1 (e.g., A=1, 2 or 3).

[0060] In other words, when the preliminary judgment unit determines that there is no two-dimensional object that meets the threshold requirement in the (i-1)th two-dimensional fault, the return control unit returns the program to the preliminary judgment unit, causing the preliminary judgment unit to traverse each two-dimensional object in the ij-th two-dimensional fault, i≥j≥2, with j taking values ​​from small to large, and repeating the preliminary judgment. Only when there is no two-dimensional object that meets the threshold requirement in the two-dimensional fault with the current value will j take a value 1 greater than the current value, until a two-dimensional object (connected region) that meets the threshold requirement is found or j=A is found. If there is a two-dimensional object that meets the threshold requirement in the two-dimensional fault with the current value of j, the current traversal ends. If no two-dimensional object that meets the threshold requirement is found, the current traversal ends.

[0061] M4.4: Numbering Modification Unit

[0062] The number modification unit is used to modify the two-dimensional object M ik The numbering of the object is modified to be the same as the number of the two-dimensional object with the highest comprehensive score determined in the connected region determination unit; or, if the preliminary judgment unit fails to find a two-dimensional object that meets the threshold requirement, the numbering modification unit will modify the numbering of the two-dimensional object M. ik The numbering is changed to be one more than the maximum number of the connectivity region that has already completed connectivity analysis.

[0063] It should be noted that each two-dimensional object in the first fault can be regarded as a connected region that has already undergone connectivity analysis.

[0064] M4.5: Repeat Control Unit

[0065] The repeat control unit is used to control the initial judgment unit, the connected region determination unit, and the return control unit to repeat until the connectivity analysis of each two-dimensional object in each two-dimensional fault is completed. The repeat control unit includes a two-dimensional object repeat control unit and a two-dimensional fault repeat control unit.

[0066] The two-dimensional object repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in the i-th two-dimensional fault.

[0067] The two-dimensional fault repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis of two-dimensional objects in each two-dimensional fault.

[0068] M5: 3D object feature acquisition unit, used to combine connected 2D objects to form a 3D object and acquire the features of each 3D object.

[0069] The features of the three-dimensional object include spatial location, volume, average density, average atomic number, root mean square deviation of density, and root mean square deviation of atomic number. The corresponding features of the three-dimensional object are as follows:

[0070]

[0071]

[0072]

[0073]

[0074]

[0075] Among them, S i ρ represents the area corresponding to the i-th pixel of a 3D object, Voxel represents the pixel size, and ρ represents the area corresponding to the pixel. i and Z i V and ρ represent the density value and atomic number value corresponding to the pixel, respectively. mean Z mean σ ρ σ Z These represent the volume, average density, average atomic number, root mean square deviation of density, and root mean square deviation of atomic number of a three-dimensional object, respectively.

[0076] To quickly obtain the root mean square error characteristics, the root mean square error of density and the root mean square error of atomic number can be simplified as σ. ρsimple and σ Zsimple :

[0077]

[0078]

[0079] Among them, S k,i ρ k,i Z k,iThese represent the area, density, and atomic number of the i-th pixel in the k-th (k = 1-K) layer slice, respectively.

[0080] On the other hand, the present invention also provides a method for segmenting three-dimensional objects in three-dimensional volume data, using the above-mentioned system, the method comprising:

[0081] The two-dimensional tomographic acquisition unit reconstructs the projection data of the scanned object at different angles obtained by dual-energy CT scanning to obtain multiple two-dimensional tomographic layers, and numbers the two-dimensional tomographic layers in sequence.

[0082] The image preprocessing unit performs image smoothing, image enhancement, image region segmentation, and dilatation erosion processing on the two-dimensional tomographic image obtained by the two-dimensional tomographic acquisition unit.

[0083] The two-dimensional object segmentation unit segments the two-dimensional objects in each two-dimensional section, obtains the features of each two-dimensional object in each two-dimensional section, and numbers the two-dimensional objects in each two-dimensional section in sequence.

[0084] The connectivity determination unit performs connectivity analysis based on the parameter differences between the basic two-dimensional objects in the basic two-dimensional fault and the two-dimensional objects in the two-dimensional faults above the basic two-dimensional fault, determines the connected regions, and completes the three-dimensional volume connectivity analysis; the parameters include center position, area, average density, and average atomic number.

[0085] Specifically, taking the k-th two-dimensional object M of the i-th two-dimensional fault as an example. ik Based on this, the initial judgment unit traverses each two-dimensional object in the (i-1)th two-dimensional fault, and determines whether each two-dimensional object in the (i-1)th two-dimensional fault is related to two-dimensional object M. ik The unit determines whether the differences in the center position, area, average density, and average atomic number meet the threshold requirements. If the preliminary judgment unit determines that there is a two-dimensional object that meets the threshold requirements in the (i-1)th two-dimensional fracture, the connected region determination unit performs a comprehensive score on the two-dimensional object that meets the threshold requirements based on the differences in center position, area, average density, and average atomic number. The smaller the difference, the higher the score. The two-dimensional object with the highest comprehensive score is determined as the one in the (i-1)th two-dimensional fracture that is related to two-dimensional object M. ikA connected region with connectivity; if the preliminary judgment unit determines that there is no two-dimensional object meeting the threshold requirement in the (i-1)th two-dimensional fault, the return control unit returns the program to the preliminary judgment unit, so that the preliminary judgment unit traverses each two-dimensional object in the ij-th two-dimensional fault and repeats the preliminary judgment; where i≥2, k≥1, i≥j≥2; j takes values ​​from small to large, and only when there is no two-dimensional object meeting the threshold requirement in the two-dimensional fault with the current value, j takes a value 1 greater than the current value; when j equals A, if there is still no two-dimensional object meeting the threshold requirement in the iA-th two-dimensional fault, the error fault limiting module restricts the return control unit from returning the program to the preliminary judgment unit; the two-dimensional object repeat control unit controls the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in the i-th two-dimensional fault; the two-dimensional fault repeat control unit controls the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in each two-dimensional fault.

[0086] The number modification unit will modify the two-dimensional object M ik The numbering of the object is modified to be the same as the number of the two-dimensional object with the highest comprehensive score determined in the connected region determination unit; or, if the preliminary judgment unit fails to find a two-dimensional object that meets the threshold requirement, the numbering modification unit will modify the numbering of the two-dimensional object M. ik The numbering is changed to be one more than the maximum number of the connectivity region that has already completed connectivity analysis.

[0087] The 3D object feature acquisition unit combines connected 2D objects to form a 3D object and acquires the features of each 3D object.

[0088] To further clarify the connectivity analysis process of the two-dimensional tomography acquisition unit, image preprocessing unit, two-dimensional object segmentation unit, and connectivity determination unit, Figure 2 Let's take an example to illustrate.

[0089] S1: The two-dimensional tomographic acquisition unit reconstructs the projection data of the scanned specimen at different angles obtained through dual-energy CT scanning, resulting in four two-dimensional tomographic images. Figure 2 (Only 4 two-dimensional fractures are shown for ease of explanation). The image preprocessing unit performs image smoothing, image enhancement, image region segmentation and dilation erosion processing on the two-dimensional fracture image obtained by the two-dimensional fracture acquisition unit, and numbers the 4 two-dimensional fractures sequentially from top to bottom as 1, 2, 3 and 4.

[0090] S2: The two-dimensional object segmentation unit segments the two-dimensional objects in each two-dimensional section and obtains the features of each two-dimensional object in each two-dimensional section. The two-dimensional objects in each two-dimensional section are numbered sequentially. The two-dimensional objects in the first two-dimensional section are numbered as 1, 2, 3, 4; the two-dimensional objects in the second two-dimensional section are numbered as 1, 2, 3; the two-dimensional objects in the third two-dimensional section are numbered as 1, 2; and the two-dimensional objects in the fourth two-dimensional section are numbered as 1, 2, 3.

[0091] S3: Connectivity determination unit analysis to determine the connectivity of a 3D volume:

[0092] S3.1: First analyze the connectivity of the second two-dimensional fault, taking the first two-dimensional object M of the second two-dimensional fault as an example. 21 Based on this, the initial judgment unit traverses each two-dimensional object in the first two-dimensional fault. The first and second two-dimensional objects in the first two-dimensional fault meet the threshold requirements, and the connectivity judgment unit determines that the first two-dimensional object has the highest comprehensive score. Therefore, the first two-dimensional object in the first two-dimensional fault is two-dimensional object M. 21 The connected regions, the numbering modification unit will change the two-dimensional object M 21 The numbering is changed to be the same as the number of the first two-dimensional object in the first two-dimensional fault (their numbers are both 1, so no change is needed here); the two-dimensional object repeat control unit controls the preliminary judgment unit to use the second two-dimensional object M in the second two-dimensional fault. 22 Based on this, we iterate through each two-dimensional object in the first two-dimensional fault. The second and third two-dimensional objects in the first two-dimensional fault meet the threshold requirements, and the connectivity judgment unit determines that the third two-dimensional object has the highest comprehensive score. Therefore, the third two-dimensional object in the first two-dimensional fault is two-dimensional object M. 22 The connected regions, the numbering modification unit will change the two-dimensional object M 22 The numbering was changed to be the same as the numbering of the third two-dimensional object in the first two-dimensional fault, that is, two-dimensional object M 22 The number is changed to 3; the two-dimensional object repeat control unit controls the preliminary judgment unit with the third two-dimensional object M of the second two-dimensional fault. 23 Based on this, iterate through each two-dimensional object in the first two-dimensional fault. Since there are no two-dimensional objects in the first two-dimensional fault that meet the threshold requirement, and the maximum number of two-dimensional objects in the first two-dimensional fault is 4, the numbering modification unit will modify the two-dimensional object M. 23 The number was changed to 5; the connectivity analysis of the second two-dimensional fault was completed.

[0093] The two-dimensional fault repeat control unit controls the preliminary judgment unit, the connected region determination unit, and the return control unit to analyze the connectivity of the third two-dimensional fault, using the first two-dimensional object M of the third two-dimensional fault as an example. 31Based on this, the preliminary judgment unit traverses each two-dimensional object in the second two-dimensional fracture. If no two-dimensional object in the second two-dimensional fracture meets the threshold requirement, the control unit returns to the preliminary judgment unit. The preliminary judgment unit then traverses each two-dimensional object in the first two-dimensional fracture. The second and third two-dimensional objects in the first two-dimensional fracture meet the threshold requirement, and the connectivity judgment unit determines that the second two-dimensional object has the highest overall score, meaning that the second two-dimensional object in the first two-dimensional fracture is two-dimensional object M. 31 The connected regions, the numbering modification unit will change the two-dimensional object M 31 The numbering of object M is changed to be the same as that of the second two-dimensional object in the first two-dimensional fault, that is, two-dimensional object M 31 The number is changed to 2; the two-dimensional object repeat control unit controls the preliminary judgment unit with the second two-dimensional object M of the third two-dimensional fault. 32 Based on this, each two-dimensional object in the second two-dimensional fault is traversed. Two-dimensional objects numbered 1 and 5 in the second two-dimensional fault meet the threshold requirements. The connectivity judgment unit determines that two-dimensional object numbered 5 has the highest comprehensive score, that is, two-dimensional object numbered 5 in the second two-dimensional fault is two-dimensional object M. 32 The connected regions, the numbering modification unit will change the two-dimensional object M 32 The number was changed to 5; the connectivity analysis of the third two-dimensional fault was completed.

[0094] The two-dimensional fault repeat control unit controls the preliminary judgment unit, the connected region determination unit, and the return control unit to analyze the connectivity of the fourth two-dimensional fault, using the first two-dimensional object M of the fourth two-dimensional fault as an example. 41 Based on this, the preliminary judgment unit traverses each two-dimensional object in the third two-dimensional fault. If no two-dimensional object meets the threshold requirement in the third two-dimensional fault, the control program returns to the preliminary judgment unit. The preliminary judgment unit then traverses each two-dimensional object in the second two-dimensional fault. If no two-dimensional object meets the threshold requirement in the second two-dimensional fault, the control program returns to the preliminary judgment unit. The preliminary judgment unit then traverses each two-dimensional object in the first two-dimensional fault. If no two-dimensional object meets the threshold requirement in the first two-dimensional fault, it is determined that no two-dimensional object meeting the threshold requirement has been found. The numbering modification unit, based on the maximum number of the previously found connected region being 5, then modifies the two-dimensional object M. 41 The number was changed to 6; the two-dimensional object repeat control unit controlled the preliminary judgment unit with the second two-dimensional object M of the fourth two-dimensional fault. 42Based on this, the system iterates through each two-dimensional object in the third two-dimensional fault. If no two-dimensional object meets the threshold requirement in the third two-dimensional fault, the system returns to the control unit and then to the preliminary judgment unit. The preliminary judgment unit iterates through each two-dimensional object in the second two-dimensional fault. If no two-dimensional object meets the threshold requirement in the second two-dimensional fault, the system returns to the control unit and then to the preliminary judgment unit. The preliminary judgment unit iterates through each two-dimensional object in the first two-dimensional fault. If no two-dimensional object meets the threshold requirement in the first two-dimensional fault, and it is determined that no two-dimensional object meeting the threshold requirement has been found, the numbering modification unit, based on the maximum number of the previously found connected region being 6, then modifies the two-dimensional object M. 42 The number was changed to 7; the two-dimensional object repeat control unit controlled the preliminary judgment unit with the third two-dimensional object M of the fourth two-dimensional fault. 43 Based on this, each two-dimensional object in the third two-dimensional fault is traversed. Two-dimensional objects numbered 5 and 3 in the third two-dimensional fault meet the threshold requirements. The connectivity judgment unit determines that two-dimensional object numbered 5 has the highest comprehensive score. The numbering modification unit then modifies the two-dimensional object M. 43 The number is changed to 5. That is, the connectivity analysis of all two-dimensional objects in all two-dimensional faults is completed.

[0095] The following specific embodiments further illustrate the three-dimensional object segmentation system and method in three-dimensional volume data of the present invention.

[0096] Example 1

[0097] A three-dimensional object segmentation system for three-dimensional volume data includes a two-dimensional tomography acquisition unit, an image preprocessing unit, a two-dimensional object segmentation unit, a connectivity judgment unit, and a three-dimensional object feature acquisition unit. The connectivity judgment unit includes a preliminary judgment unit, a connected region determination unit, a return control unit, a number modification unit, and a repetition control unit. The connected region determination unit is equipped with a comprehensive scoring module as shown in the above formula (I), where a is 14 / 4, b is 50 / 4, c is 0.1 / 4, and d is 1 / 4. The return control unit is equipped with an error tomography limitation module, which sets the number of error tomography layers A allowed to be traversed, where A = 3. The repetition control unit includes a two-dimensional object repetition control unit and a two-dimensional tomography repetition control unit.

[0098] Example 2

[0099] The system of Example 1 is used to segment three-dimensional objects in three-dimensional volume data, including:

[0100] The two-dimensional tomographic acquisition unit reconstructs the projection data of the scanned part at different angles obtained by dual-energy CT scanning to obtain multiple two-dimensional tomographic layers, and numbers the two-dimensional tomographic layers in sequence.

[0101] The image preprocessing unit performs image smoothing, image enhancement, image region segmentation, and dilatation erosion processing on the two-dimensional tomographic image obtained by the two-dimensional tomographic acquisition unit.

[0102] The two-dimensional object segmentation unit segments the two-dimensional objects in each two-dimensional section, obtains the features of each two-dimensional object in each two-dimensional section, and numbers the two-dimensional objects in each two-dimensional section in sequence.

[0103] Take the k-th two-dimensional object M of the i-th two-dimensional fault as an example. ik Based on this, the initial judgment unit traverses each two-dimensional object in the (i-1)th two-dimensional fault, and determines whether each two-dimensional object in the (i-1)th two-dimensional fault is related to two-dimensional object M. ik The unit determines whether the differences in the center position, area, average density, and average atomic number meet the threshold requirements. If the preliminary judgment unit determines that there is a two-dimensional object that meets the threshold requirements in the (i-1)th two-dimensional fracture, the connected region determination unit performs a comprehensive score on the two-dimensional object that meets the threshold requirements based on the differences in center position, area, average density, and average atomic number. The smaller the difference, the higher the score. The two-dimensional object with the highest comprehensive score is determined as the one in the (i-1)th two-dimensional fracture that is related to two-dimensional object M. ik A connected region with connectivity; if the preliminary judgment unit determines that there is no two-dimensional object meeting the threshold requirement in the (i-1)th two-dimensional fault, the return control unit returns the program to the preliminary judgment unit, so that the preliminary judgment unit traverses each two-dimensional object in the ij-th two-dimensional fault and repeats the preliminary judgment; where i≥2, k≥1, i≥j≥2; j takes values ​​from small to large, and only when there is no two-dimensional object meeting the threshold requirement in the two-dimensional fault with the current value, j takes a value 1 greater than the current value; when j equals A, if there is still no two-dimensional object meeting the threshold requirement in the iA-th two-dimensional fault, the error fault limiting module restricts the return control unit from returning the program to the preliminary judgment unit; the two-dimensional object repeat control unit controls the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in the i-th two-dimensional fault; the two-dimensional fault repeat control unit controls the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in each two-dimensional fault;

[0104] The number modification unit will modify the two-dimensional object M ik The numbering of the object is modified to be the same as the number of the two-dimensional object with the highest comprehensive score determined in the connected region determination unit; or, if the preliminary judgment unit fails to find a two-dimensional object that meets the threshold requirement, the numbering modification unit will modify the numbering of the two-dimensional object M. ik The numbering is modified to be one greater than the maximum number of the connectivity region that has already undergone connectivity analysis;

[0105] The 3D object feature acquisition unit combines connected 2D objects to form a 3D object and acquires the features of each 3D object.

[0106] In Example 2, on a 2.4GHz computer, a 512*512*343 three-dimensional volume data was segmented into three-dimensional objects. The three-dimensional object segmentation was completed in 5 seconds, and 11 types of three-dimensional objects were segmented.

[0107] Comparative Example 1

[0108] The same scanned document as in Example 2 was scanned, and the three-dimensional objects in the three-dimensional volume data of the scanned document were segmented using the existing three-dimensional region growing method. On a 2.4GHz computer, the region growing process takes about 50 seconds to complete for a 512*512*343 volume data.

[0109] Comparative Example 2

[0110] The same scanned document as in Example 2 was scanned, and the three-dimensional objects in the three-dimensional volume data of the scanned document were segmented using the threshold method in the prior art. On a 2.4GHz computer, for a three-dimensional volume data of 512*512*343, the threshold method can only segment out 6 kinds of three-dimensional objects.

[0111] Comparative Example 3

[0112] The same scanned document as in Example 2 was scanned, and the three-dimensional objects in the three-dimensional volume data of the scanned document were segmented using the boundary method in the prior art. On a 2.4GHz computer, the boundary method took 45 seconds for a 512*512*343 three-dimensional volume data.

[0113] A comparison of the results of Example 2 with those of Comparative Examples 1 and 3 shows that, compared with existing 3D region growing methods and boundary methods, the system of the present invention can complete the 3D object segmentation in 3D volume data more quickly. A comparison of the results of Example 2 with those of Comparative Example 2 shows that, compared with existing threshold methods, the present invention has higher accuracy in segmenting 3D objects.

[0114] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0115] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A three-dimensional object segmentation system in three-dimensional volume data, characterized in that, The system includes: The two-dimensional tomographic acquisition unit is used to reconstruct the projection data of the scanned part at different angles obtained by dual-energy CT scanning, obtain multiple two-dimensional tomes, and number the two-dimensional tomes in sequence. Two-dimensional object segmentation unit is used to segment two-dimensional objects in each two-dimensional section, obtain the features of each two-dimensional object in each two-dimensional section, and number the two-dimensional objects in each two-dimensional section in sequence. The connectivity determination unit is used to perform connectivity analysis based on the parameter differences between the basic two-dimensional objects in the basic two-dimensional fault and the two-dimensional objects in the two-dimensional faults above the basic two-dimensional fault, to determine the connected regions and complete the three-dimensional volume connectivity analysis; the parameters include center position, area, average density and average atomic number; The connectivity determination unit includes a preliminary determination unit, a connected region determination unit, a return control unit, and a repeat control unit. The preliminary judgment unit is used to determine the k-th two-dimensional object M of the i-th two-dimensional fault. ik Based on this, traverse each two-dimensional object in the (i-1)th two-dimensional fault, and determine whether each two-dimensional object in the (i-1)th two-dimensional fault is related to two-dimensional object M. ik Whether the differences in the center position, area, average density, and average atomic number meet the threshold requirements; The connected region determination unit is used to comprehensively score the two-dimensional objects that meet the threshold requirements in the (i-1)th two-dimensional fault when the preliminary judgment unit determines that there are two-dimensional objects that meet the threshold requirements based on differences in center position, area, average density, and average atomic number. The smaller the difference, the higher the score. The two-dimensional object with the highest comprehensive score is determined as the one in the (i-1)th two-dimensional fault that is connected to two-dimensional object M. ik Connected regions that are connected; The return control unit is used to return the program to the preliminary judgment unit when the preliminary judgment unit determines that there is no two-dimensional object in the (i-1)th two-dimensional fracture that meets the threshold requirement. This allows the preliminary judgment unit to traverse each two-dimensional object in the ij-th two-dimensional fracture and repeat the preliminary judgment. Here, i≥2, k≥1, i≥j≥2; j takes values ​​from small to large. Only when there is no two-dimensional object in the two-dimensional fracture that meets the threshold requirement in the currently selected value will j take a value that is 1 greater than the current value. The repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to repeat until the connectivity analysis of each two-dimensional object in each two-dimensional fault is completed.

2. The system according to claim 1, characterized in that, The system also includes an image preprocessing unit for preprocessing the two-dimensional tomographic image obtained by the two-dimensional tomographic acquisition unit to improve the signal-to-noise ratio of the image.

3. The system according to claim 1, characterized in that, In the two-dimensional object segmentation unit, the features of the two-dimensional object include mean density, root mean square deviation of density, mean atomic number, root mean square deviation of atomic number, object area, object perimeter, abscissa of region centroid, ordinate of region centroid, and minimum bounding rectangle.

4. The system according to claim 1, characterized in that, The connected region determination unit is equipped with a comprehensive scoring module, which calculates the comprehensive score according to formula (I): Formula (I); Where s0 is a two-dimensional object M ik The area of ​​the two-dimensional object M, ρ0. ik The average density, Z0 is the density of the two-dimensional object M. ik The average atomic number, x0 and y0 are the two-dimensional object M ik The x and y coordinates of the center position of the two-dimensional object are given; s1 is the area of ​​the two-dimensional object that meets the threshold requirement; ρ1 is the average density of the two-dimensional object that meets the threshold requirement; Z1 is the average atomic number of the two-dimensional object that meets the threshold requirement; x1 and y1 are the x and y coordinates of the center position of the two-dimensional object that meets the threshold requirement, respectively; a, b, c, and d are weight parameters greater than 0, and their specific values ​​are: d = center position difference threshold / 4, a = area difference threshold / 4, b = average density difference threshold / 4, c = average atomic number difference threshold / 4, used to balance the influence of the differences of each parameter on connectivity judgment.

5. The system according to claim 1, characterized in that, Two-dimensional faults of two-dimensional objects that do not meet the threshold requirements are defined as error faults. The return control unit is equipped with an error fault limitation module, and the error fault limitation module is set to allow the number of error faults A to be traversed. When j equals A, if there is no two-dimensional object that meets the threshold requirement in the iA-th two-dimensional tomography, the error tomography limitation module restricts the return control unit from returning the program to the preliminary judgment unit; where A≥1.

6. The system according to claim 5, characterized in that, The connectivity determination unit further includes a number modification unit, which is used to modify the two-dimensional object M. ik The numbering of the object is modified to be the same as the number of the two-dimensional object with the highest comprehensive score determined in the connected region determination unit; or, if the preliminary judgment unit fails to find a two-dimensional object that meets the threshold requirement, the numbering modification unit will modify the numbering of the two-dimensional object M. ik The numbering is changed to be one more than the maximum number of the connectivity region that has already completed connectivity analysis.

7. The system according to claim 1, characterized in that, The repeat control unit includes a two-dimensional object repeat control unit and a two-dimensional fault repeat control unit. The two-dimensional object repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in the i-th two-dimensional fault. The two-dimensional fault repeat control unit is used to control the preliminary judgment unit, the connected region determination unit, and the return control unit to perform connectivity analysis on each two-dimensional object in the two-dimensional fault.

8. The system according to claim 1, characterized in that, The system also includes a three-dimensional object feature acquisition unit, which is used to combine two-dimensional objects with connectivity to form a three-dimensional object and acquire the features of each three-dimensional object.

9. A method for segmenting three-dimensional objects from three-dimensional volume data, characterized in that, The method using the system according to any one of claims 1-8 comprises: The two-dimensional tomographic acquisition unit reconstructs the projection data of the scanned part at different angles obtained by dual-energy CT scanning to obtain multiple two-dimensional tomographic layers, and numbers the two-dimensional tomographic layers in sequence. The image preprocessing unit performs image smoothing, image enhancement, image region segmentation, and dilatation erosion processing on the two-dimensional tomographic image obtained by the two-dimensional tomographic acquisition unit. The two-dimensional object segmentation unit segments the two-dimensional objects in each two-dimensional section, obtains the features of each two-dimensional object in each two-dimensional section, and numbers the two-dimensional objects in each two-dimensional section in sequence. The connectivity determination unit performs connectivity analysis based on the parameter differences between the basic two-dimensional objects in the basic two-dimensional fault and the two-dimensional objects in the two-dimensional faults above the basic two-dimensional fault, determines the connected regions, and completes the three-dimensional volume connectivity analysis; the parameters include center position, area, average density, and average atomic number; The 3D object feature acquisition unit combines connected 2D objects to form a 3D object and acquires the features of each 3D object.

Images