Rib segmentation method, device, computer equipment and storage medium

Abstract

The present application provides a rib segmentation method, device, computer equipment and storage medium, which relate to the field of image processing technology. The method comprises: obtaining a medical image sequence to be processed, wherein the medical image sequence comprises multiple layers of two-dimensional scanned images, performing bone tissue segmentation on the multiple layers of two-dimensional scanned images to obtain ribs and spine regions, extracting the spine centerline from the multiple layers of two-dimensional scanned images to obtain the spine centerline and spine width, determining and removing the spine region in the rib and spine region based on the spine centerline and spine width to obtain a three-dimensional rib region, and generating a three-dimensional rib image based on the three-dimensional rib region. The present application can accurately segment the ribs in the medical image and improve the accuracy of rib segmentation.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a rib segmentation method, device, computer equipment and storage medium. Background Art

[0002] Rib fracture is a common chest trauma disease. In clinical practice, rib images are generally obtained through computed tomography (CT) technology. Doctors diagnose orthopedic trauma based on the rib images. Therefore, clear, complete and high-quality rib images are very important for doctors to accurately diagnose orthopedic trauma.

[0003] Existing methods generally use deep learning neural networks to perform rib segmentation on CT images. This rib segmentation method learns the characteristics of the ribs from the CT images to directly segment the rib area from the CT images. However, this segmentation method does not take into account the adhesion between the ribs and other bone tissues, resulting in inaccurate segmentation results. Summary of the invention

[0004] The purpose of the present invention is to provide a rib segmentation method, apparatus, computer equipment and storage medium to address the deficiencies in the above-mentioned prior art, so as to accurately segment the ribs in medical images and improve the accuracy of rib segmentation.

[0005] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0006] In a first aspect, an embodiment of the present application provides a rib segmentation method, the method comprising:

[0007] Acquire a medical image sequence to be processed, wherein the medical image sequence includes multiple layers of two-dimensional scanned images;

[0008] Performing bone tissue segmentation on the multi-layer two-dimensional scanned image to obtain rib and spine regions;

[0009] Extracting the spine centerline from the multi-layer two-dimensional scanning images to obtain the spine centerline and spine width;

[0010] According to the spine centerline and the spine width, determining and removing the spine region in the rib and spine region to obtain a three-dimensional rib region;

[0011] A three-dimensional rib image is generated according to the three-dimensional rib region.

[0012] Optionally, performing bone tissue segmentation on the multi-layer two-dimensional scanned image to obtain rib and spine regions includes:

[0013] Using a large law threshold segmentation method to segment each layer of the two-dimensional scanned image to obtain the lung parenchyma area in each layer of the two-dimensional scanned image;

[0014] According to the lung parenchyma area and a preset first threshold, segmenting the bone tissue of the multi-layer two-dimensional scanned image to obtain a three-dimensional clavicle area;

[0015] According to the lung parenchyma area and a preset second threshold, segmenting the bone tissue of the multi-layer two-dimensional scanned image to obtain a three-dimensional scapula area;

[0016] According to a preset third threshold, segmenting the bone tissue of the multi-layer two-dimensional scanned image to obtain a three-dimensional bone tissue region;

[0017] The rib and spine regions are determined from the three-dimensional bone tissue region based on the three-dimensional clavicle region and the three-dimensional scapula region.

[0018] Optionally, the method of adopting a large law threshold segmentation method to segment each layer of the two-dimensional scanned image to obtain the lung parenchyma area in each layer of the two-dimensional scanned image includes:

[0019] Using a large-law threshold segmentation method to perform binarization segmentation on each layer of the two-dimensional scanned image to obtain a first binarized image of each layer of the two-dimensional scanned image;

[0020] Determine the largest connected area in the first binary image as a skin contour area;

[0021] After the skin contour area is filled, it is subtracted from the first binarized image to obtain the lung parenchyma area.

[0022] Optionally, segmenting the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset first threshold to obtain a three-dimensional clavicle area includes:

[0023] According to the first threshold, binarization segmentation is performed on each layer of the two-dimensional scanned image to obtain a second binarized image;

[0024] After dilating the lung parenchyma region, subtracting the second binarized image from the second binarized image to obtain a first image corresponding to each layer of the two-dimensional scanned image;

[0025] Performing a first three-dimensional connected domain analysis on a first image corresponding to the multi-layer two-dimensional scanned image;

[0026] The three-dimensional clavicle region is segmented from the first three-dimensional connected domain according to the result of the analysis of the first three-dimensional connected domain and the preset clavicle features.

[0027] Optionally, segmenting the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset second threshold to obtain a three-dimensional scapula area includes:

[0028] According to the second threshold, binarization segmentation is performed on each layer of the two-dimensional scanned image to obtain a third binarized image;

[0029] After dilating the lung parenchyma region, subtracting the region from the third binary image to obtain a second image corresponding to each layer of the two-dimensional scanned image;

[0030] Performing a second three-dimensional connected domain analysis on a second image corresponding to the multi-layer two-dimensional scanned image;

[0031] The three-dimensional scapula region is segmented from the second three-dimensional connected domain according to the result of the analysis of the second three-dimensional connected domain and the preset scapula features.

[0032] Optionally, segmenting the bone tissue of the multi-layer two-dimensional scanned image according to a preset third threshold to obtain a three-dimensional bone tissue region includes:

[0033] According to the third threshold, binarization segmentation is performed on each layer of the two-dimensional scanned image to obtain a fourth binarized image;

[0034] Performing connected domain analysis on the fourth binarized image;

[0035] According to the result of the connected domain analysis, the sternum region is removed from the fourth binary image to obtain the bone segmentation result of each layer of the two-dimensional scanned image;

[0036] The three-dimensional bone tissue region includes: the bone segmentation results of the multi-layer two-dimensional scanning image.

[0037] Optionally, determining the rib and spine region from the three-dimensional bone tissue region according to the three-dimensional clavicle region and the three-dimensional scapula region includes:

[0038] Subtracting the three-dimensional clavicle region and the three-dimensional scapula region from the three-dimensional bone tissue region to obtain a partial three-dimensional region including ribs and spine;

[0039] Performing an expansion operation on the partial three-dimensional area in the left-right direction of the human body and in the extension direction of the spine;

[0040] The largest three-dimensional connected region is determined to be the rib and spine region from the three-dimensional region of the expansion operation.

[0041] Optionally, generating a three-dimensional rib image according to the three-dimensional rib region includes:

[0042] traversing the three-dimensional rib region from the left region and the right region of the head respectively;

[0043] The first pixel point whose pixel value is a preset pixel value found from the left area of ​​the head is used as the left seed point;

[0044] The first pixel point whose pixel value is the preset pixel value found from the right side area of ​​the head is used as the right seed point;

[0045] Using the left seed point to grow multiple first ribs on the left side in the three-dimensional region;

[0046] Using the right seed point to grow multiple second ribs on the left side in the three-dimensional region;

[0047] The three-dimensional rib image is generated according to the plurality of first ribs and the plurality of second ribs.

[0048] Optionally, the extracting of the spine centerline from the multi-layer two-dimensional scanned images to obtain the spine centerline and the spine width includes:

[0049] According to a preset fourth threshold, the multi-layer two-dimensional scanned image is binarized and segmented to obtain a fifth binarized image;

[0050] Determine a multi-layer spine binarization image from the fifth binarization image;

[0051] Determine the spinal mass points in the last layer of the spinal binary images in the multi-layer spinal binary images according to the preset spinal features, wherein the last layer of the spinal binary images is the image closest to the chest in the multi-layer spinal binary images;

[0052] Determine the spine mass points in other layers of spine binary images according to the spine mass points in the last layer of spine binary image;

[0053] Extracting a spinal sagittal image from the multi-layer spinal binary image according to the X-axis coordinates of the spinal particles in the multi-layer spinal binary image, wherein the width direction of each layer of the spinal binary image is the X-axis direction, the height direction of each layer of the spinal binary image is the Y-axis direction, and the spinal direction is the Z-axis direction of the multi-layer spinal binary image;

[0054] Performing an expansion operation on the spinal sagittal image to determine a three-dimensional connected area of ​​the spine;

[0055] Using the grayscale centroid method, the Y-axis coordinates of the spine particles in the multi-layer spine binary image are updated from the three-dimensional spine connected area;

[0056] Determine the spine centerline according to the X-axis coordinates and Y-axis coordinates of the spine particles in the multi-layer spine binary image;

[0057] The spine width is obtained according to the average spine width of the multi-layer spine binary image.

[0058] Optionally, before performing bone tissue segmentation on the multi-layer two-dimensional scanned images to obtain rib and spine regions, the method further includes:

[0059] According to a preset fifth threshold, the multi-layer two-dimensional scanned image is binarized and segmented to obtain a sixth binarized image;

[0060] Determine the connected area between the bed board and the human body from the sixth binarized image;

[0061] Determine the inner and outer contour lines of the connecting area between the bed board and the human body, and remove edge points that do not conform to the characteristics of the bed board from the inner and outer contour lines according to the distance between the upper and lower edges of the bed board;

[0062] Determine a seed point between the upper and lower edges of the bed board, and fill in the seed point to determine the bed board area;

[0063] The bed board area is segmented from the multi-layer two-dimensional scanning images.

[0064] In a second aspect, an embodiment of the present application further provides a rib segmentation device, the device comprising:

[0065] An image sequence acquisition module, used to acquire a medical image sequence to be processed, wherein the medical image sequence includes multiple layers of two-dimensional scanned images;

[0066] A bone tissue segmentation module, used to perform bone tissue segmentation on the multi-layer two-dimensional scanning image to obtain rib and spine regions;

[0067] A spine centerline extraction module, used to extract the spine centerline from the multi-layer two-dimensional scanning image to obtain the spine centerline and spine width;

[0068] A spine region removal module, used for determining and removing the spine region in the rib and spine region according to the spine centerline and the spine width, to obtain a three-dimensional rib region;

[0069] The three-dimensional rib image generation module is used to generate a three-dimensional rib image according to the three-dimensional rib area.

[0070] Optionally, the bone tissue segmentation module includes:

[0071] A lung parenchyma segmentation unit, used to segment each layer of the two-dimensional scanned image by using a large law threshold segmentation method to obtain a lung parenchyma region in each layer of the two-dimensional scanned image;

[0072] A clavicle segmentation unit, configured to segment the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset first threshold value to obtain a three-dimensional clavicle area;

[0073] A scapula segmentation unit, configured to segment the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset second threshold value to obtain a three-dimensional scapula area;

[0074] Another bone tissue segmentation unit is used to segment the bone tissue of the multi-layer two-dimensional scanned image according to a preset third threshold value to obtain a three-dimensional bone tissue area;

[0075] The rib and spine region determining unit is used to determine the rib and spine region from the three-dimensional bone tissue region according to the three-dimensional clavicle region and the three-dimensional scapula region.

[0076] Optionally, the lung parenchyma segmentation unit includes:

[0077] A first binarization segmentation subunit is used to perform binarization segmentation on each layer of the two-dimensional scanned image by adopting a large-law threshold segmentation method to obtain a first binarized image of each layer of the two-dimensional scanned image;

[0078] a skin contour region determining subunit, configured to determine the largest connected region in the first binarized image as the skin contour region;

[0079] The lung parenchyma segmentation subunit is used to fill the skin contour area and then subtract it from the first binary image to obtain the lung parenchyma area.

[0080] Optionally, the clavicle segmentation unit comprises:

[0081] A second binarization segmentation subunit is used to perform binarization segmentation on each layer of the two-dimensional scanned image according to the first threshold value to obtain a second binarized image;

[0082] A first image determination subunit is used for performing a dilation operation on the lung parenchyma region and then subtracting the second binarized image from the second binarized image to obtain a first image corresponding to each layer of the two-dimensional scanned image;

[0083] A first three-dimensional connected domain analysis subunit, configured to perform a first three-dimensional connected domain analysis on a first image corresponding to the multi-layer two-dimensional scanned image;

[0084] The clavicle segmentation subunit is used to segment the three-dimensional clavicle region from the first three-dimensional connected domain according to the result of the analysis of the first three-dimensional connected domain and the preset clavicle features.

[0085] Optionally, the scapula segmentation unit comprises:

[0086] A third binarization segmentation subunit is used to perform binarization segmentation on each layer of the two-dimensional scanned image according to the second threshold value to obtain a third binarization image;

[0087] A second image determination subunit is used to perform a dilation operation on the lung parenchyma region and then subtract the dilation operation from the third binarized image to obtain a second image corresponding to each layer of the two-dimensional scanned image;

[0088] A second three-dimensional connected domain analysis subunit, configured to perform a second three-dimensional connected domain analysis on a second image corresponding to the multi-layer two-dimensional scanned image;

[0089] The scapula segmentation subunit is used to segment the three-dimensional scapula region from the second three-dimensional connected domain according to the result of the analysis of the second three-dimensional connected domain and the preset scapula features.

[0090] Optionally, the other bone tissue segmentation unit includes:

[0091] a fourth binarization segmentation subunit, configured to perform binarization segmentation on each layer of the two-dimensional scanned image according to the third threshold value to obtain a fourth binarization image;

[0092] A connected domain segmentation subunit, used for performing connected domain analysis on the fourth binary image;

[0093] A sternum segmentation subunit, used for removing the sternum region from the fourth binary image according to the result of the connected domain analysis, to obtain a bone segmentation result of each layer of the two-dimensional scanned image;

[0094] The three-dimensional bone tissue region includes: the bone segmentation results of the multi-layer two-dimensional scanning image.

[0095] Optionally, the rib and spine region determination unit includes:

[0096] A bone tissue removal subunit, configured to subtract the three-dimensional clavicle region and the three-dimensional scapula region from the three-dimensional bone tissue region to obtain a partial three-dimensional region including ribs and spine;

[0097] An expansion subunit, used for expanding the partial three-dimensional area in the left-right direction of the human body and the extension direction of the spine;

[0098] The rib and spine region determination subunit is used to determine the largest three-dimensional connected region from the three-dimensional region of the expansion operation as the rib and spine region.

[0099] Optionally, the three-dimensional rib image generation module includes:

[0100] A traversal unit, used for traversing the three-dimensional rib region from the left region and the right region of the head respectively;

[0101] A left seed point determination unit, configured to take a pixel point whose first pixel value is a preset pixel value and is traversed from the left area of ​​the head as a left seed point;

[0102] A right seed point determination unit, configured to take a pixel point whose first pixel value traversed from the right area of ​​the head and whose pixel value is the preset pixel value as a right seed point;

[0103] A left rib growth unit, used to grow a plurality of first ribs on the left side in a three-dimensional area using the left seed point;

[0104] A right rib growth unit, used for growing a plurality of second ribs on the left side in a three-dimensional region using the right seed point;

[0105] The three-dimensional rib image generating unit is used to generate the three-dimensional rib image according to the plurality of first ribs and the plurality of second ribs.

[0106] Optionally, the spine centerline extraction module includes:

[0107] a fifth binarization segmentation unit, configured to perform binarization segmentation on the multi-layer two-dimensional scanned image according to a preset fourth threshold value to obtain a fifth binarized image;

[0108] A spine binary image determining unit, used for determining a multi-layer spine binary image from the fifth binary image;

[0109] A spine mass point determination unit, used to determine the spine mass points in the multi-layer spine binary image according to preset spine features;

[0110] A spinal sagittal image extraction unit, used for extracting spinal sagittal images from the multi-layer spinal binary images according to the X-axis coordinates of the spinal particles in the multi-layer spinal binary images, wherein the width direction of each layer of the spinal binary images is the X-axis direction, the height direction of each layer of the spinal binary images is the Y-axis direction, and the spinal direction is the Z-axis direction of the multi-layer spinal binary images;

[0111] A spine three-dimensional connected region determining unit, used for performing an expansion operation on the spine sagittal plane image to determine the spine three-dimensional connected region;

[0112] A spine mass point coordinate updating unit, used to update the Y-axis coordinates of the spine mass points in the multi-layer spine binary image from the spine three-dimensional connected area by using a grayscale centroid method;

[0113] A spine centerline determination unit, used for determining the spine centerline according to the X-axis coordinates and the Y-axis coordinates of the spine particles in the multi-layer spine binary image;

[0114] The spine width determination unit is used to obtain the spine width according to the average spine width of the multi-layer spine binary image.

[0115] Optionally, the device further comprises:

[0116] a sixth binarization segmentation unit, configured to perform binarization segmentation on the multi-layer two-dimensional scanned image according to a preset fifth threshold value to obtain a sixth binarized image;

[0117] A bed board and human body connected area determining unit, used for determining the connected area between the bed board and the human body from the sixth binarized image;

[0118] An edge point screening unit, used to determine the inner and outer contours of the connection area between the bed board and the human body, and remove edge points that do not conform to the bed board characteristics from the inner and outer contours according to the distance between the upper and lower edges of the bed board;

[0119] A bed board area determination unit, used to determine a seed point between the upper and lower edges of the bed board, and fill in the seed point to determine the bed board area;

[0120] The bed board area segmentation unit is used to segment the bed board area from the multi-layer two-dimensional scanning image.

[0121] In a third aspect, an embodiment of the present application further provides a computer device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the rib segmentation method as described in any of the above embodiments.

[0122] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the rib segmentation method as described in any of the above embodiments are executed.

[0123] The beneficial effects of this application are:

[0124] The present application provides a rib segmentation method, device, computer equipment and storage medium, which obtain a medical image sequence to be processed, wherein the medical image sequence includes multiple layers of two-dimensional scanned images, performs bone tissue segmentation on the multiple layers of two-dimensional scanned images to obtain ribs and spine regions, extracts the spine centerline from the multiple layers of two-dimensional scanned images to obtain the spine centerline and spine width, determines and removes the spine region in the rib and spine region based on the spine centerline and spine width to obtain a three-dimensional rib region, and generates a three-dimensional rib image based on the three-dimensional rib region. The present application performs bone tissue segmentation on multiple layers of two-dimensional scanned images and removes the spine region to obtain a three-dimensional rib region and generate a three-dimensional rib image, thereby avoiding the problem of inaccurate rib segmentation due to adhesion between bone tissues, achieving accurate rib segmentation from medical images, and improving the accuracy of rib segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0125] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0126] Figure 1 A schematic diagram of the process of the first rib segmentation method provided in an embodiment of the present application;

[0127] Figure 2 A schematic diagram of a flow chart of a second rib segmentation method provided in an embodiment of the present application;

[0128] Figure 3 A schematic diagram of a flow chart of a third rib segmentation method provided in an embodiment of the present application;

[0129] Figure 4 A schematic diagram of a flow chart of a fourth rib segmentation method provided in an embodiment of the present application;

[0130] Figure 5 A schematic diagram of a fifth rib segmentation method provided in an embodiment of the present application;

[0131] Figure 6 A schematic diagram of a sixth rib segmentation method provided in an embodiment of the present application;

[0132] Figure 7 A schematic flow chart of a seventh rib segmentation method provided in an embodiment of the present application;

[0133] Figure 8 A schematic flow chart of an eighth rib segmentation method provided in an embodiment of the present application;

[0134] Fig. 9 A schematic diagram of a three-dimensional rib image provided in an embodiment of the present application;

[0135] Fig.10 A schematic flow chart of a ninth rib segmentation method provided in an embodiment of the present application;

[0136] FIG11( a) is a schematic diagram of extracting a sagittal image of the spine provided in an embodiment of the present application;

[0137] FIG11( b ) is a sagittal image of the spine provided in an embodiment of the present application;

[0138] Fig.12 A schematic diagram of a flow chart of a tenth rib segmentation method provided in an embodiment of the present application;

[0139] Fig.13 A schematic diagram of the structure of a rib segmentation device provided in an embodiment of the present application;

[0140] Fig.14 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0141] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0142] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0143] In the description of the present invention, it should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0144] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0145] Please refer to Figure 1 , is a flow chart of the first rib segmentation method provided in the embodiment of the present application, such as Figure 1 As shown, the method includes:

[0146] S10: Acquire a medical image sequence to be processed, wherein the medical image sequence includes multiple layers of two-dimensional scanned images.

[0147] In this embodiment, a computed tomography scanner is used to scan the patient from the head to obtain a medical image sequence, which includes multi-layer two-dimensional scan images. "Layer" refers to the ability of the data acquisition system (DAS) in the CT scanner to synchronously obtain images, that is, the number of DAS channels for synchronously acquiring images or the number of layers when the rack rotates, which is used to reflect the scanning capability of the CT scanner. The number of layers represents the number of two-dimensional scan images that can be synchronously obtained by the CT scanner in one circle. For example, a 16-layer two-dimensional scan image means that 16 layers of images can be obtained by scanning one circle, and a 64-layer two-dimensional scan image means that 64 layers of images can be obtained by scanning one circle.

[0148] S20: Perform bone tissue segmentation on the multi-layer two-dimensional scanned image to obtain rib and spine regions.

[0149] In this embodiment, in the multi-layer two-dimensional scanning image, the distance between the ribs and other bone tissue areas of the human body, such as the scapula and clavicle, is very close. In order to avoid adhering other bone tissue areas to the ribs during rib segmentation, it is necessary to first segment the other bone tissue areas from the multi-layer two-dimensional scanning image to obtain the ribs and spine areas.

[0150] S30: Extracting the spine centerline from the multi-layer two-dimensional scanning images to obtain the spine centerline and spine width.

[0151] In this embodiment, since the ribs are connected to the spine and distributed on both sides of the spine, the center line of the spine is determined from the multi-layer two-dimensional scanned images according to the position of the spine, and the multi-layer two-dimensional scanned images are subjected to connected domain analysis, and the spine width is calculated based on the regional connectivity characteristics of the spine.

[0152] S40: According to the spine centerline and the spine width, determine and remove the spine region in the rib and spine region to obtain a three-dimensional rib region.

[0153] In this embodiment, each layer of the two-dimensional scanned image is traversed, and according to the x-axis coordinate xCoord of the spine centerline determined in S30 and the spine width w, the pixel values ​​in the interval greater than xCoord-w and less than xCoord+w are assigned a value of 0, so that the spinal region can be removed from the rib and spine region, and the multi-layer two-dimensional scanned images without the spine region are three-dimensionally connected to obtain a three-dimensional rib region.

[0154] In an optional implementation, the symmetry and volume of the ribs may be used to remove connected regions that do not meet the characteristics from the three-dimensional rib region and determine the number of connected regions. If the number of connected regions exceeds 24 or is less than 20, the rib segmentation is determined to be abnormal.

[0155] S50: Generate a three-dimensional rib image according to the three-dimensional rib region.

[0156] In this embodiment, a three-dimensional rib image can be generated by performing three-dimensional reconstruction on the three-dimensional rib region.

[0157] The rib segmentation method provided in the embodiment of the present application obtains a medical image sequence to be processed, wherein the medical image sequence includes multiple layers of two-dimensional scanned images, performs bone tissue segmentation on the multiple layers of two-dimensional scanned images to obtain ribs and spine regions, extracts the spine centerline from the multiple layers of two-dimensional scanned images to obtain the spine centerline and spine width, determines and removes the spine region in the rib and spine region based on the spine centerline and spine width to obtain a three-dimensional rib region, and generates a three-dimensional rib image based on the three-dimensional rib region. The embodiment of the present application performs bone tissue segmentation on multiple layers of two-dimensional scanned images and removes the spine region to obtain a three-dimensional rib region and generates a three-dimensional rib image, thereby avoiding the problem of inaccurate rib segmentation due to adhesion between bone tissues, achieving accurate rib segmentation from medical images, and improving the accuracy of rib segmentation.

[0158] Based on the above embodiments, the present application further provides a rib segmentation method. Figure 2 , is a flow chart of a second rib segmentation method provided in an embodiment of the present application, such as Figure 2 As shown, the above S20 includes:

[0159] S21: Using the large law threshold segmentation method, segment each layer of the two-dimensional scanned image to obtain the lung parenchyma area in each layer of the two-dimensional scanned image.

[0160] In this embodiment, each layer of the two-dimensional scanned image is binarized and segmented. Binarization segmentation is to convert the grayscale image into a binary image, set the grayscale maximum value of the pixel that is greater than the preset segmentation threshold, and set the grayscale minimum value of the pixel that is less than the preset segmentation threshold, so as to achieve binarization. According to the selection of the segmentation threshold, the binarization algorithm is divided into a fixed threshold and an adaptive threshold. The embodiment of the present application adopts an adaptive threshold, and the specific method is the OTSU threshold segmentation.

[0161] According to the grayscale characteristics of the two-dimensional scanned image, the threshold segmentation of the Dalu method divides each layer of the two-dimensional scanned image into two parts: background and target. Let t be the segmentation threshold of the background and target. The number of target pixels accounts for w0 of the image, and the average grayscale is u0; the number of background pixels accounts for w1 of the image, and the average grayscale is u1. The total average grayscale of the two-dimensional scanned image is: u = w0*u0+w1*u1. From the minimum grayscale value to the maximum grayscale value, t is traversed. When t makes the value g = w0*(u0-u) 2 +w1*(u1-u) 2 When t is the maximum, it is the optimal segmentation threshold.

[0162] The large-law threshold segmentation method is used to determine the optimal segmentation threshold for each layer of the two-dimensional scanned image, and each layer of the two-dimensional scanned image is binarized and segmented using the optimal segmentation threshold. Since the lung parenchyma area is a black area in the image after binary segmentation, it is necessary to invert the image after binary segmentation and convert the black area into a white area. According to the position of the lung parenchyma area, the lung parenchyma area is determined from the white area.

[0163] In an optional implementation, a closing operation is performed on the inverted binary image to fill the cavities in the lung parenchyma region.

[0164] Specifically, since there may be some cavities in the lung parenchyma area, the cavities need to be filled. A preset structural element can be used to dilate the inverted binary image, and then perform corrosion processing to fill the cavities in the lung parenchyma area.

[0165] S22: According to the lung parenchyma area and a preset first threshold, the bone tissue of the multi-layer two-dimensional scanned image is segmented to obtain a three-dimensional clavicle area.

[0166] In this embodiment, based on the characteristics of the clavicle, a first threshold for binarization segmentation of the multi-layer two-dimensional scanned image is determined, and the multi-layer two-dimensional scanned image is binarized using the first threshold. Based on the position information of the lung parenchyma area and the characteristics of the clavicle, the clavicle region is determined from the multi-layer binary segmented image to obtain a three-dimensional clavicle region.

[0167] S23: According to the lung parenchyma area and a preset second threshold, the bone tissue of the multi-layer two-dimensional scanned image is segmented to obtain a three-dimensional scapula area.

[0168] In this embodiment, a second threshold for binarization segmentation of the multi-layer two-dimensional scanned image is determined based on the characteristics of the scapula. The multi-layer two-dimensional scanned image is binarized using the second threshold. Based on the position information of the lung parenchyma area and the characteristics of the scapula, the scapula region is determined from the multi-layer binary segmented image to obtain a three-dimensional scapula region.

[0169] S24: Segment the bone tissue of the multi-layer two-dimensional scanned image according to a preset third threshold value to obtain a three-dimensional bone tissue region.

[0170] In this embodiment, the human body bone tissue region includes other bone tissue regions in addition to the scapula and clavicle. According to the characteristics of the other bone tissues, a third threshold for binarization segmentation of the multi-layer two-dimensional scanned image is determined. The multi-layer two-dimensional scanned image is binarized using the third threshold. According to the characteristics of the other bone tissue regions, the other bone tissue regions are segmented from the multi-layer binary segmented images to obtain a three-dimensional bone tissue region that no longer contains other bone tissue regions.

[0171] S25: According to the three-dimensional clavicle region and the three-dimensional scapula region, the rib and spine regions are determined from the three-dimensional bone tissue region.

[0172] In this embodiment, according to the three-dimensional clavicle region and the three-dimensional scapula region, the three-dimensional clavicle region and the three-dimensional scapula region are subtracted from the three-dimensional bone tissue region to obtain the rib and spine region.

[0173] The rib segmentation method provided in the embodiment of the present application adopts the large law threshold segmentation method to segment each layer of the two-dimensional scanned image to obtain the lung parenchyma area in each layer of the two-dimensional scanned image, segment the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and the preset first threshold to obtain the three-dimensional clavicle area, segment the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and the preset second threshold to obtain the three-dimensional scapula area, segment the bone tissue of the multi-layer two-dimensional scanned image according to the preset third threshold to obtain the three-dimensional bone tissue area, and determine the rib and spine area from the three-dimensional bone tissue area according to the three-dimensional clavicle area and the three-dimensional scapula area. The embodiment of the present application adopts multiple thresholds to segment different bone tissue areas, avoids the adhesion of ribs with other bone tissue areas caused by segmentation using a single threshold, and improves the accuracy of rib segmentation.

[0174] Based on the above embodiments, the present application further provides a rib segmentation method. Figure 3 , is a flow chart of a third rib segmentation method provided in an embodiment of the present application, such as Figure 3As shown, the above S21 includes:

[0175] S211: adopting the large law threshold segmentation method to perform binarization segmentation on each layer of the two-dimensional scanned image to obtain a first binarized image of each layer of the two-dimensional scanned image.

[0176] In this embodiment, the large law threshold segmentation method is used to determine the adaptive segmentation threshold of each layer of the two-dimensional scanned image, and the corresponding adaptive threshold is used to perform binarization segmentation on each layer of the two-dimensional scanned image to obtain the first binarized image of each layer of the two-dimensional scanned image. The process of calculating the segmentation threshold using the large law threshold segmentation method is referred to the above S21, which will not be described in detail here.

[0177] S212: Determine the largest connected area in the first binary image as the skin contour area.

[0178] In this embodiment, the skin contour region has the largest connected region in the first binary image, so the first binary image can be subjected to a connected region analysis, and the largest connected region can be determined as the skin contour region according to the areas of the connected regions.

[0179] In an optional implementation, the first binary image may be inverted and then closed to remove cavities in the lung parenchyma area, and then the image without the cavities may be inverted again to determine that the largest connected area is the skin contour area.

[0180] S213: After the skin contour area is filled, it is subtracted from the first binary image to obtain the lung parenchyma area.

[0181] In this embodiment, the skin contour area includes bone tissue areas such as ribs, clavicles, scapulae and vertebrae, and also includes lung parenchyma areas, wherein the bone tissue areas are white pixels and the lung parenchyma areas are black pixels. By pixel filling of the skin contour area, the skin contour area is filled with white pixels to obtain the entire skin area. The filled skin area image is subtracted from the first binary image to subtract all white pixels from the skin area image to obtain the lung parenchyma area with only black pixels left.

[0182] The rib segmentation method provided in the embodiment of the present application adopts the large law threshold segmentation method to perform binarization segmentation on each layer of the two-dimensional scanned image to obtain the first binarized image of each layer of the two-dimensional scanned image, and the largest connected area in the first binarized image is determined as the skin contour area. After the skin contour area is filled, it is subtracted from the first binarized image to obtain the lung parenchyma area. The embodiment of the present application determines the lung parenchyma area by subtracting the skin contour area from the first binarized image, so as to segment the clavicle and scapula according to the lung parenchyma area, thereby improving the accuracy of rib segmentation.

[0183] Based on the above embodiments, the present application further provides a rib segmentation method. Figure 4 , is a flow chart of a fourth rib segmentation method provided in an embodiment of the present application, such as Figure 4 As shown, the above S22 includes:

[0184] S221: performing binary segmentation on each layer of the two-dimensional scanned image according to the first threshold value to obtain a second binary image.

[0185] In this embodiment, each layer of the two-dimensional scanned image is binarized and segmented according to a fixed first threshold to obtain a second binary image. The first threshold can be determined according to the pixel characteristics of the clavicle region. In this embodiment, the first threshold is 400HU.

[0186] In an optional implementation, before performing binarization segmentation on each layer of two-dimensional scanned images, Gaussian filtering is performed on each layer of two-dimensional scanned images to remove impurity points or noise points in each layer of two-dimensional scanned images.

[0187] S222: After dilating the lung parenchyma area, subtract the second binarized image from the second binarized image to obtain a first image corresponding to each layer of the two-dimensional scanned image.

[0188] In this embodiment, a connected domain analysis is performed on the second binary image to remove connected domains that do not meet the characteristics. Since the lung parenchyma area in the human body is wrapped in the ribs, the lung parenchyma area is expanded according to a preset expansion range to wrap the ribs in the area, and the expanded lung parenchyma area is subtracted from the second binary image from which the connected domains that do not meet the characteristics are removed, so as to subtract the rib area from the second binary image to obtain a first image corresponding to each layer of the two-dimensional scanned image, wherein the rib area is not included in the first image.

[0189] S223: Perform a first three-dimensional connected domain analysis on the first image corresponding to the multi-layer two-dimensional scanned images.

[0190] In this embodiment, a first three-dimensional connected domain analysis is performed on the first images corresponding to the multiple layers of two-dimensional scanned images, so as to connect the connected regions of the multiple first images in the three-dimensional space.

[0191] S224: Segment a three-dimensional clavicle region from the first three-dimensional connected domain according to the result of the first three-dimensional connected domain analysis and the preset clavicle features.

[0192] In this embodiment, the result of the first three-dimensional connected domain analysis includes multiple three-dimensional connected domains, and the three-dimensional clavicle region is determined from the multiple three-dimensional connected domains according to preset clavicle features. For example, the preset clavicle features may include: the position, shape, symmetry and volume of the clavicle.

[0193] The rib segmentation method provided in the embodiment of the present application performs binary segmentation on each layer of the two-dimensional scanned image according to a first threshold value to obtain a second binary image, performs an expansion operation on the lung parenchyma region, and then subtracts the second binary image from the second binary image to obtain a first image corresponding to each layer of the two-dimensional scanned image, performs a first three-dimensional connected domain analysis on the first image corresponding to the multi-layer two-dimensional scanned image, and segments a three-dimensional clavicle region from the first three-dimensional connected domain according to the result of the first three-dimensional connected domain analysis and the preset clavicle feature. The embodiment of the present application determines the clavicle region by expanding the lung parenchyma region, which can avoid the adhesion of the ribs and the clavicle and improve the accuracy of rib segmentation.

[0194] Based on the above embodiments, the present application further provides a rib segmentation method. Figure 5 , is a flow chart of a fifth rib segmentation method provided in an embodiment of the present application, such as Figure 5 As shown, the above S23 includes:

[0195] S231: performing binary segmentation on each layer of the two-dimensional scanned image according to the second threshold value to obtain a third binary image.

[0196] In this embodiment, each layer of the two-dimensional scanned image is binarized and segmented according to a fixed second threshold to obtain a third binarized image. The second threshold can be determined according to the pixel characteristics of the scapula region. In this embodiment, the second threshold is 200HU.

[0197] S232: After dilating the lung parenchyma region, subtract the region from the third binarized image to obtain a second image corresponding to each layer of the two-dimensional scanned image.

[0198] In this embodiment, a connected domain analysis is performed on the third binary image to remove connected domains that do not meet the characteristics, and an expansion operation is performed on the lung parenchyma area to wrap the ribs in the area. The expanded lung parenchyma area is subtracted from the third binary image from which the connected domains that do not meet the characteristics are removed, and the rib area is subtracted from the third binary image to obtain a second image corresponding to each layer of the two-dimensional scanned image, and the second image does not include the rib area.

[0199] S233: Perform a second three-dimensional connected domain analysis on the second image corresponding to the multi-layer two-dimensional scanned image.

[0200] In this embodiment, a second three-dimensional connected domain analysis is performed on the second images corresponding to the multiple layers of two-dimensional scanned images, so as to connect the connected regions of the multiple second images in the three-dimensional space.

[0201] S234: Segment a three-dimensional scapula region from the second three-dimensional connected domain according to the result of the second three-dimensional connected domain analysis and the preset scapula features.

[0202] In this embodiment, the result of the second three-dimensional connected domain analysis includes multiple three-dimensional connected domains, and the three-dimensional scapula region is determined from the multiple three-dimensional connected domains according to preset scapula features. For example, the preset scapula features may include: the position, shape, symmetry and volume of the scapula.

[0203] The rib segmentation method provided in the embodiment of the present application performs binary segmentation on each layer of the two-dimensional scanned image according to the second threshold value to obtain a third binary image, performs an expansion operation on the lung parenchyma area, and then subtracts the third binary image from the third binary image to obtain a second image corresponding to each layer of the two-dimensional scanned image, performs a second three-dimensional connected domain analysis on the second image corresponding to the multiple layers of two-dimensional scanned images, and segments a three-dimensional scapula area from the second three-dimensional connected domain according to the result of the second three-dimensional connected domain analysis and the preset scapula features. The embodiment of the present application determines the scapula area by expanding the lung parenchyma area, which can avoid the adhesion of the ribs and the scapula and improve the accuracy of rib segmentation.

[0204] Based on the above embodiments, the present application further provides a rib segmentation method. Figure 6 , is a flow chart of a sixth rib segmentation method provided in an embodiment of the present application, such as Figure 6 As shown, the above S24 includes:

[0205] S241: performing binary segmentation on each layer of the two-dimensional scanned image according to the third threshold value to obtain a fourth binary image.

[0206] In this embodiment, each layer of the two-dimensional scanned image is binarized and segmented according to a fixed third threshold to obtain a fourth binarized image. The third threshold can be determined according to the pixel characteristics of the clavicle area. In this embodiment, the third threshold is 140HU.

[0207] S242: Perform connected domain analysis on the fourth binarized image.

[0208] In this embodiment, the fourth binary image is subjected to a connected domain analysis, and connected domains that do not meet the characteristics are removed according to the characteristics of each connected domain. The characteristics of the connected domain may be: the area of ​​the connected domain, the aspect ratio of the connected domain, etc., which is not limited in this application.

[0209] S243: According to the result of the connected domain analysis, the sternum region is removed from the fourth binary image to obtain the bone segmentation result of each layer of the two-dimensional scanning image; the three-dimensional bone tissue region includes: the bone segmentation results of multiple layers of two-dimensional scanning images.

[0210] In this embodiment, the sternum region is located between the rib regions and above the spinal region. Based on the position of the sternum region relative to the spinal region and the characteristics of the sternum region, the sternum region is removed from the fourth binary image to obtain the bone segmentation results of each layer of the two-dimensional scanning image, and the bone segmentation results of multiple two-dimensional scanning images are connected in three-dimensional space into a three-dimensional bone tissue region.

[0211] The rib segmentation method provided in the embodiment of the present application performs binary segmentation on each layer of the two-dimensional scanned image according to the third threshold value to obtain a fourth binary image, performs connected domain analysis on the fourth binary image, and removes the sternum region from the fourth binary image according to the result of the connected domain analysis to obtain the bone segmentation result of each layer of the two-dimensional scanned image; the three-dimensional bone tissue region includes: the bone segmentation result of multiple layers of two-dimensional scanned images. The embodiment of the present application can remove the sternum region, avoid the adhesion of the ribs and the sternum, and improve the accuracy of rib segmentation.

[0212] Based on the above embodiments, the present application further provides a rib segmentation method. Figure 7 , is a flow chart of the seventh rib segmentation method provided in the embodiment of the present application, such as Figure 7 As shown, the above S25 includes:

[0213] S251: Subtract the three-dimensional clavicle region and the three-dimensional scapula region from the three-dimensional bone tissue region to obtain a partial three-dimensional region including the ribs and spine.

[0214] In this embodiment, the three-dimensional bone tissue region is the three-dimensional region of other bone tissues after removing the sternum region. The three-dimensional clavicle region and the three-dimensional scapula region are removed from the three-dimensional bone tissue region to obtain a partial three-dimensional region including ribs and spine.

[0215] S252: performing an expansion operation on a portion of the three-dimensional region in the left-right direction of the human body and in the extension direction of the spine.

[0216] In this embodiment, since part of the three-dimensional area includes not only the rib area and the spine area, but also the impurity area, the rib area and the spine area are connected by expanding the part of the three-dimensional area in the left and right direction of the human body, and the spine area is connected by expanding the part of the three-dimensional area in the extension direction of the spine.

[0217] S253: Determine the largest three-dimensional connected region from the three-dimensional region of the expansion operation as the rib and spine region.

[0218] In this embodiment, after the expansion operation is performed on part of the three-dimensional area, the rib area and the spine area are completely connected, that is, the rib area and the spine area are adhered into a whole, and the largest three-dimensional connected area in the three-dimensional area is taken as the rib and spine area.

[0219] The rib segmentation method provided in the embodiment of the present application subtracts the 3D clavicle region and the 3D scapula region from the 3D bone tissue region to obtain a partial 3D region including the ribs and spine, performs an expansion operation on the partial 3D region in the left and right directions of the human body and the extension direction of the spine, and determines the maximum 3D connected region from the expanded 3D region as the rib and spine region. The embodiment of the present application can completely segment the clavicle region and the scapula region, avoid the adhesion of the clavicle region and the scapula region to the ribs, and improve the accuracy of rib segmentation.

[0220] Based on the above embodiments, the present application further provides a rib segmentation method. Figure 8 , is a flow chart of an eighth rib segmentation method provided in an embodiment of the present application, such as Figure 8 As shown, the above S50 includes:

[0221] S51: traverse the three-dimensional rib region from the left side region and the right side region of the head respectively.

[0222] In this embodiment, due to the symmetry of the ribs, the ribs are divided into a left area and a right area with the head as the middle boundary, and the left area and the right area of ​​the head are traversed respectively to identify the left ribs and the right ribs respectively.

[0223] S52: The first pixel point whose pixel value is a preset pixel value found from the left side area of ​​the head is taken as the left seed point.

[0224] In this embodiment, starting from the left side of the head, the three-dimensional rib region is pixel traversed until the first point with a pixel value of 255 is traversed and this point is used as the left seed point.

[0225] S53: The first pixel point whose pixel value is the preset pixel value found from the right side area of ​​the head is taken as the right seed point.

[0226] In this embodiment, starting from the right side of the head, the three-dimensional rib region is pixel traversed until the first point with a pixel value of 255 is traversed and this point is used as the right seed point.

[0227] S54: growing multiple first ribs on the left side in the three-dimensional region using the left seed point.

[0228] In this embodiment, the three-dimensional region growing is performed with the seed point on the left side to segment the first rib on the left side, and the pixel value of the first rib region is reassigned. Then the next point with a pixel value of 255 is traversed as the seed point to generate the second rib, until multiple first ribs on the left side are obtained, and the pixel values ​​of the multiple first ribs are different.

[0229] S55: multiple second ribs on the left side are grown in the three-dimensional region using the seed points on the right side.

[0230] In this embodiment, the method of generating multiple second ribs according to the seed points on the right side is the same as that on the left side, and will not be described in detail here.

[0231] S56: Generate a three-dimensional rib image according to the plurality of first ribs and the plurality of second ribs.

[0232] In this embodiment, a three-dimensional rib image is obtained based on the pixel values ​​of the first ribs and the second ribs after reassignment. Fig. 9 A schematic diagram of a three-dimensional rib image provided in an embodiment of the present application, such as Fig. 9 As shown, the pixel values ​​of multiple ribs are different.

[0233] The rib segmentation method provided in the embodiment of the present application traverses the three-dimensional rib area from the left area of ​​the head and the right area of ​​the head respectively, takes the pixel point whose first pixel value traversed from the left area of ​​the head is a preset pixel value as the left seed point, takes the pixel point whose first pixel value traversed from the right area of ​​the head is a preset pixel value as the right seed point, grows multiple first ribs on the left side in the three-dimensional area with the left seed point, grows multiple second ribs on the left side in the three-dimensional area with the right seed point, and generates a three-dimensional rib image based on the multiple first ribs and the multiple second ribs. The embodiment of the present application obtains a three-dimensional rib image by traversing the three-dimensional rib area, and there is no adhesion between the multiple rib images, so the state of each rib can be clearly understood from the three-dimensional rib image.

[0234] Based on the above embodiments, the present application further provides a rib segmentation method. Fig.10 , is a flow chart of a ninth rib segmentation method provided in an embodiment of the present application, such as Fig.10 As shown, the above S30 includes:

[0235] S31: performing binarization segmentation on the multi-layer two-dimensional scanned image according to a preset fourth threshold value to obtain a fifth binarized image.

[0236] In this embodiment, each layer of the two-dimensional scanned image is binarized and segmented according to a fixed fourth threshold to obtain a fifth binarized image. The fourth threshold can be determined according to the pixel characteristics of the spinal region. In this embodiment, the fourth threshold is 128HU.

[0237] S32: Determine a multi-layer spine binarization image from the fifth binarization image.

[0238] In this embodiment, the spine region is located at a specific position in the human body, and multiple layers of spine binary images corresponding to the spine region can be determined from a plurality of fifth binary images.

[0239] S33: Determine the spinal mass points in the last layer of the spinal binary image in the multi-layer spinal binary image according to the preset spinal features, wherein the last layer of the spinal binary image is the image closest to the chest in the multi-layer spinal binary image.

[0240] In this embodiment, based on the connected area characteristics of the spine, the spine area is determined from multiple layers of spine binary images, and the spine particles are determined from the spine area of ​​the last layer of spine binary images. In this embodiment, the last layer of spine binary images is defined as the image closest to the chest among the multiple layers of spine binary images, and of course it can also be the image farthest from the chest among the multiple layers of spine binary images.

[0241] S34: Determine the spine mass points in other layers of spine binary images according to the spine mass points in the last layer of spine binary images.

[0242] In this embodiment, since the spinal region may be adhered to the rib region during the connected domain analysis, or due to spinal curvature or spinal separation, the spinal point positions when determining each layer of spinal binary images from each layer of spinal binary images may not be accurate enough. Therefore, the spinal points in the last layer of spinal binary images and the deviations between the spinal points in different layers of spinal binary images are used to determine the spinal points in the previous layer of spinal binary images in turn to obtain the spinal points in multiple layers of spinal binary images.

[0243] S35: Extracting spinal sagittal images from multi-layer spinal binarization images according to the X-axis coordinates of spinal particles in the multi-layer spinal binarization images, wherein the width direction of each layer of spinal binarization images is the X-axis direction, the height direction of each layer of spinal binarization images is the Y-axis direction, and the spinal direction is the Z-axis direction of the multi-layer spinal binarization images.

[0244] For example, please refer to Figure 11(a), which is a schematic diagram of extracting a spinal sagittal image provided in an embodiment of the present application. As shown in Figure 11(a), the point x=w in each layer of the spine binary image is used as the sagittal extraction line, and the spinal sagittal image is extracted from each layer of the spine binary image to obtain a spinal sagittal image. For example, please refer to Figure 11(b), which is a spinal sagittal image provided in an embodiment of the present application.

[0245] In this embodiment, the width direction of each layer of spine binary image is taken as the X-axis direction, and the height direction of each layer of spine binary image is taken as the Y-axis direction. The coordinates of the spinal particles in each layer of spine binary image are determined, and according to the middle value of the X-axis coordinates of multiple spinal particles, the multi-layer spine binary images are segmented along the spine center line in three-dimensional space to extract the spinal sagittal plane image.

[0246] S36: Performing an expansion operation on the sagittal plane image of the spine to determine a three-dimensional connected area of ​​the spine.

[0247] In this embodiment, an expansion operation is performed on the sagittal plane image of the spine so that multiple vertebrae are connected on the sagittal plane to obtain a three-dimensional connected region of the spine.

[0248] S37: Using the grayscale centroid method, the Y-axis coordinates of the spine particles in the multi-layer spine binary image are updated from the three-dimensional connected area of ​​the spine.

[0249] In this embodiment, since the spine in the human body is in the form of sections, the three-dimensional connected area of ​​the spine is refined and re-divided into multiple layers of the spine. The grayscale centroid method is used to extract the center of the multiple layers of the spine to update the position of the spinal mass point in the Y-axis direction, thereby updating the Y-axis coordinate of the spinal mass point.

[0250] S38: Determine the spine centerline according to the X-axis coordinates and Y-axis coordinates of the spine particles in the multi-layer spine binary image.

[0251] In this embodiment, multiple spinal points are connected in three-dimensional space according to the X-axis coordinates and Y-axis coordinates of the spinal points in the multi-layer spinal binary images to form a spinal centerline.

[0252] S39: Obtain the spine width according to the average spine width of the multi-layer spine binarization image.

[0253] In this embodiment, the spine width of each layer of the spine binary image is calculated according to the connected area of ​​the spine, and the spine widths of the multiple layers of the spine binary images are averaged to obtain the spine width.

[0254] The rib segmentation method provided in this embodiment performs binarization segmentation on a multi-layer two-dimensional scanned image according to a preset fourth threshold value to obtain a fifth binarized image; determines a multi-layer spine binarized image from the fifth binarized image; determines the spine points in the last layer of the spine binarized image in the multi-layer spine binarized image according to preset spine features, wherein the last layer of the spine binarized image is the image closest to the chest among the multi-layer spine binarized images; determines the spine points in other multi-layer spine binarized images according to the spine points in the last layer of the spine binarized image; and determines the spine points in the multi-layer spine binarized images according to the X-axis coordinates of the spine points in the multi-layer spine binarized image. Extract spinal sagittal images from multi-layer spinal binary images, wherein the width direction of each layer of spinal binary images is the X-axis direction, the height direction of each layer of spinal binary images is the Y-axis direction, and the spinal direction is the Z-axis direction of the multi-layer spinal binary images; perform an expansion operation on the spinal sagittal images to determine the three-dimensional connected area of ​​the spine; use the grayscale centroid method to update the Y-axis coordinates of the spinal particles in the multi-layer spinal binary images from the three-dimensional connected area of ​​the spine; determine the spinal centerline based on the X-axis coordinates and Y-axis coordinates of the spinal particles in the multi-layer spinal binary images; obtain the spinal width based on the average spinal width of the multi-layer spinal binary images. The embodiment of the present application determines the spinal particles of the previous layer of spinal binary images in sequence based on the spinal particles of the last layer of spinal binary images, thereby avoiding the problem of inaccurate spinal particles determined due to adhesion of the spine and ribs, so as to improve the accuracy of rib segmentation.

[0255] Based on the above embodiments, the present application further provides a rib segmentation method. Fig.12 , is a flow chart of the tenth rib segmentation method provided in the embodiment of the present application, such as Fig.12 As shown, the method also includes:

[0256] S61: performing binarization segmentation on the multi-layer two-dimensional scanned image according to a preset fifth threshold value to obtain a sixth binarized image.

[0257] In this embodiment, each layer of the two-dimensional scanned image is binarized and segmented according to a fixed fifth threshold to obtain a sixth binarized image. The fifth threshold can be determined according to the pixel characteristics of the bed board area. In this embodiment, the fifth threshold is -200HU.

[0258] S62: Determine the connected area between the bed board and the human body from the sixth binarized image.

[0259] In this embodiment, a connected area analysis is performed on the sixth binary image, connected areas that do not meet the characteristics are removed, and the remaining connected areas are judged. If the number of connected areas is 1, it is determined that the corresponding connected area is the bed board area. If the number of connected areas is 0, it is determined that the corresponding connected area is the situation where the bed board is connected to the human body.

[0260] S63: Determine inner and outer contour lines of the connection area between the bed board and the human body, and remove edge points that do not conform to the characteristics of the bed board from the inner and outer contour lines according to the distance between the upper and lower edges of the bed board.

[0261] In this embodiment, for the connected area where the bed board and the human body are connected, the inner and outer contours of the connected area are obtained, and the inner and outer contours include the contours of the human body and the contours of the bed board. According to the double edge characteristics of the bed board, edge points that do not conform to the characteristics of the bed board are removed from the inner and outer contours. For example, the distance between the upper and lower edges is no more than 80 pixels, and the edge points that do not conform to the characteristics of the bed board are removed from the inner and outer contours.

[0262] Afterwards, a preset structure element is used to perform an opening operation on each sixth binary image to remove isolated edge points in each sixth binary image, and the sixth binary image is traversed from top to bottom again. According to the double-edge characteristics of the bed board, the distance between the upper and lower edges of the bed board is set to 40 pixels to determine the edge points belonging to the bed board.

[0263] S64: Determine a seed point between the upper and lower edges of the bed board, and fill in the seed point to determine the bed board area.

[0264] In this embodiment, the upper and lower edges of the bed board in the sixth binary image are determined based on the edge points of the bed board, a seed point is arbitrarily determined between the upper and lower edges of the bed board, a coordinate system is established in the sixth binary image, and the coordinates of the seed point and the edge point are determined. Based on the seed point, the flood filling method is used to fill in the bed board area from the sixth binary image, so that the entire bed board area is segmented independently.

[0265] In the seed filling method, the region boundary is defined by the color value of the pixel. Specifically, all pixels on the region boundary have a specific color value, all pixels inside the region do not take this specific color, and pixels outside the region boundary can have the same color value as the boundary. The steps of the flood filling method are: mark the seed (x, y), detect the color of the pixel point, if it is different from the boundary color and the filling color, fill the point with the filling color, otherwise do not fill, detect the color of the adjacent position of the seed point, fill the point, until all pixels within the region boundary are detected.

[0266] S65: Segmenting the bed board area from the multi-layer two-dimensional scanning images.

[0267] In this embodiment, the bed board area is segmented from the multi-layer two-dimensional scanning image according to the bed board area obtained by filling, so that the bed board area will not affect the segmentation result when bone tissue segmentation is performed later.

[0268] The rib segmentation method provided in the embodiment of the present application performs binarization segmentation on the multi-layer two-dimensional scanned image according to the preset fifth threshold value to obtain a sixth binarization image; determines the connected area between the bed board and the human body from the sixth binarization image; determines the inner and outer contour lines of the connected area between the bed board and the human body, and removes edge points that do not conform to the characteristics of the bed board from the inner and outer contour lines according to the distance between the upper and lower edges of the bed board; determines the seed point between the upper and lower edges of the bed board, and fills according to the seed point to determine the bed board area; and segments the bed board area from the multi-layer two-dimensional scanned image. Before performing the segmentation of the lung parenchyma, ribs, clavicle, and scapula, the embodiment of the present application completely removes the bed board area to improve the accuracy of bone tissue segmentation.

[0269] Based on the above embodiment, the present application embodiment also provides a virtual device applied to the above rib segmentation method, please refer to Fig.13 , is a schematic diagram of the structure of a rib segmentation device provided in an embodiment of the present application, such as Fig.13 As shown, the device comprises:

[0270] An image sequence acquisition module 10, used to acquire a medical image sequence to be processed, wherein the medical image sequence includes multi-layer two-dimensional scanned images;

[0271] The bone tissue segmentation module 20 is used to perform bone tissue segmentation on the multi-layer two-dimensional scanning image to obtain the rib and spine regions;

[0272] The spine centerline extraction module 30 is used to extract the spine centerline from the multi-layer two-dimensional scanning image to obtain the spine centerline and the spine width;

[0273] The spine region removal module 40 is used to determine and remove the spine region in the rib and spine region according to the spine centerline and the spine width to obtain a three-dimensional rib region;

[0274] The three-dimensional rib image generating module 50 is used to generate a three-dimensional rib image according to the three-dimensional rib region.

[0275] Optionally, the bone tissue segmentation module 20 includes:

[0276] The lung parenchyma segmentation unit is used to segment each layer of the two-dimensional scanned image by adopting a large law threshold segmentation method to obtain the lung parenchyma area in each layer of the two-dimensional scanned image;

[0277] A clavicle segmentation unit, used for segmenting the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset first threshold value to obtain a three-dimensional clavicle area;

[0278] A scapula segmentation unit, used for segmenting the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset second threshold value to obtain a three-dimensional scapula area;

[0279] Another bone tissue segmentation unit is used to segment the bone tissue of the multi-layer two-dimensional scanned image according to a preset third threshold value to obtain a three-dimensional bone tissue area;

[0280] The rib and spine region determination unit is used to determine the rib and spine region from the three-dimensional bone tissue region based on the three-dimensional clavicle region and the three-dimensional scapula region.

[0281] Optionally, the lung parenchyma segmentation unit includes:

[0282] The first binarization segmentation subunit is used to perform binarization segmentation on each layer of the two-dimensional scanned image by adopting a large-law threshold segmentation method to obtain a first binarized image of each layer of the two-dimensional scanned image;

[0283] A skin contour region determination subunit, used for determining the largest connected region in the first binary image as the skin contour region;

[0284] The lung parenchyma segmentation subunit is used to fill the skin contour area and then subtract it from the first binary image to obtain the lung parenchyma area.

[0285] Optionally, the clavicle segmentation unit comprises:

[0286] A second binarization segmentation subunit is used to perform binarization segmentation on each layer of the two-dimensional scanned image according to the first threshold value to obtain a second binarized image;

[0287] A first image determination subunit is used to perform an expansion operation on the lung parenchyma area and then subtract the second binary image from the second image to obtain a first image corresponding to each layer of the two-dimensional scanned image;

[0288] A first three-dimensional connected domain analysis subunit, used for performing a first three-dimensional connected domain analysis on a first image corresponding to the multi-layer two-dimensional scanned image;

[0289] The clavicle segmentation subunit is used to segment a three-dimensional clavicle region from the first three-dimensional connected domain according to the result of the first three-dimensional connected domain analysis and the preset clavicle features.

[0290] Optionally, the scapula segmentation unit includes:

[0291] A third binarization segmentation subunit is used to perform binarization segmentation on each layer of the two-dimensional scanned image according to the second threshold value to obtain a third binarization image;

[0292] A second image determination subunit is used to perform an expansion operation on the lung parenchyma area and then subtract the third binary image from the area to obtain a second image corresponding to each layer of the two-dimensional scanned image;

[0293] A second three-dimensional connected domain analysis subunit, used for performing a second three-dimensional connected domain analysis on a second image corresponding to the multi-layer two-dimensional scanned image;

[0294] The scapula segmentation subunit is used to segment a three-dimensional scapula region from the second three-dimensional connected domain according to the result of the second three-dimensional connected domain analysis and preset scapula features.

[0295] Optionally, other bone tissue segmentation units include:

[0296] A fourth binarization segmentation subunit is used to perform binarization segmentation on each layer of the two-dimensional scanned image according to the third threshold value to obtain a fourth binarized image;

[0297] A connected domain segmentation subunit, used for performing connected domain analysis on the fourth binary image;

[0298] A sternum segmentation subunit, used for removing the sternum region from the fourth binary image according to the result of the connected domain analysis, and obtaining the bone segmentation result of each layer of the two-dimensional scanned image;

[0299] The three-dimensional bone tissue area includes: bone segmentation results of multiple layers of two-dimensional scanning images.

[0300] Optionally, the rib and spine region determination unit includes:

[0301] The bone tissue removal subunit is used to subtract the three-dimensional clavicle region and the three-dimensional scapula region from the three-dimensional bone tissue region to obtain a partial three-dimensional region including ribs and spine;

[0302] An expansion subunit, used to expand a portion of a three-dimensional region in the left-right direction of the human body and in the extension direction of the spine;

[0303] The rib and spine region determination subunit is used to determine the maximum three-dimensional connected region as the rib and spine region from the three-dimensional region of the expansion operation.

[0304] Optionally, the three-dimensional rib image generation module 50 includes:

[0305] A traversal unit, used for traversing the three-dimensional rib region from the left region of the head and the right region of the head respectively;

[0306] A left seed point determination unit, configured to take the first pixel point whose pixel value is a preset pixel value traversed from the left area of ​​the head as the left seed point;

[0307] A right seed point determination unit, used for taking the first pixel point whose pixel value is a preset pixel value traversed from the right area of ​​the head as the right seed point;

[0308] A left rib growth unit, used to grow multiple first ribs on the left side in a three-dimensional area using a left seed point;

[0309] A right rib growth unit, used to grow multiple second ribs on the left side in a three-dimensional area using right seed points;

[0310] The three-dimensional rib image generating unit is used to generate a three-dimensional rib image according to a plurality of first ribs and a plurality of second ribs.

[0311] Optionally, the spine centerline extraction module 30 includes:

[0312] A fifth binarization segmentation unit, used for performing binarization segmentation on the multi-layer two-dimensional scanned image according to a preset fourth threshold value to obtain a fifth binarized image;

[0313] A spine binary image determining unit, used for determining a multi-layer spine binary image from the fifth binary image;

[0314] A spine mass point determination unit, used to determine spine mass points in a multi-layer spine binary image according to preset spine features;

[0315] A spinal sagittal image extraction unit is used to extract a spinal sagittal image from a multi-layer spinal binary image according to the X-axis coordinates of the spinal particles in the multi-layer spinal binary image, wherein the width direction of each layer of the spinal binary image is the X-axis direction, the height direction of each layer of the spinal binary image is the Y-axis direction, and the spinal direction is the Z-axis direction of the multi-layer spinal binary image;

[0316] A spine three-dimensional connected region determining unit, used for performing an expansion operation on the spine sagittal plane image to determine the spine three-dimensional connected region;

[0317] A spine mass point coordinate updating unit, used to update the Y-axis coordinates of the spine mass points in the multi-layer spine binary image from the spine three-dimensional connected area by using the grayscale centroid method;

[0318] A spine centerline determination unit, used to determine the spine centerline according to the X-axis coordinates and Y-axis coordinates of the spine mass points in the multi-layer spine binary image;

[0319] The spine width determination unit is used to obtain the spine width according to the average spine width of the multi-layer spine binary image.

[0320] Optionally, the device further comprises:

[0321] a sixth binarization segmentation unit, configured to perform binarization segmentation on the multi-layer two-dimensional scanned image according to a preset fifth threshold value to obtain a sixth binarized image;

[0322] A bed board and human body connected region determining unit, used for determining a connected region between the bed board and the human body from the sixth binarized image;

[0323] The edge point screening unit is used to determine the inner and outer contours of the connecting area between the bed board and the human body, and remove edge points that do not conform to the characteristics of the bed board from the inner and outer contours according to the distance between the upper and lower edges of the bed board;

[0324] A bed board area determination unit, used to determine seed points between the upper and lower edges of the bed board, and fill in the seed points to determine the bed board area;

[0325] The bed board area segmentation unit is used to segment the bed board area from the multi-layer two-dimensional scanning image.

[0326] The above-mentioned device is used to execute the method provided by the aforementioned embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0327] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital singnal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0328] Please refer to Fig.14 , is a schematic diagram of a computer device provided in an embodiment of the present application, the computer device 100 includes: a processor 101, a storage medium 102 and a bus, the storage medium 102 stores program instructions executable by the processor 101, when the computer device 100 is running, the processor 101 and the storage medium 102 communicate through the bus, and the processor 101 executes the program instructions to execute the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0329] Optionally, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor at runtime, it is used to execute the above method embodiment.

[0330] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0331] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0332] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0333] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

[0334] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A rib segmentation method, characterized in that: The method comprises: Acquire a medical image sequence to be processed, wherein the medical image sequence includes multiple layers of two-dimensional scanned images; Performing bone tissue segmentation on the multi-layer two-dimensional scanned image to obtain rib and spine regions; Extracting the spine centerline from the multi-layer two-dimensional scanning images to obtain the spine centerline; According to a preset fourth threshold, the multi-layer two-dimensional scanned image is binarized and segmented to obtain a fifth binarized image; Determine a multi-layer spine binarization image from the fifth binarization image; Obtaining the spine width according to the average spine width of the multi-layer spine binary image; According to the spine centerline and the spine width, determining and removing the spine region in the rib and spine region to obtain a three-dimensional rib region; A three-dimensional rib image is generated according to the three-dimensional rib region.

2. The method according to claim 1, characterized in that The step of performing bone tissue segmentation on the multi-layer two-dimensional scanned image to obtain rib and spine regions includes: Using a large law threshold segmentation method to segment each layer of the two-dimensional scanned image to obtain the lung parenchyma area in each layer of the two-dimensional scanned image; According to the lung parenchyma area and a preset first threshold, segmenting the bone tissue of the multi-layer two-dimensional scanned image to obtain a three-dimensional clavicle area; According to the lung parenchyma area and a preset second threshold, segmenting the bone tissue of the multi-layer two-dimensional scanned image to obtain a three-dimensional scapula area; According to a preset third threshold, segmenting the bone tissue of the multi-layer two-dimensional scanned image to obtain a three-dimensional bone tissue region; The rib and spine regions are determined from the three-dimensional bone tissue region based on the three-dimensional clavicle region and the three-dimensional scapula region.

3. The method according to claim 2, characterized in that The method of using the large law threshold segmentation method to segment each layer of the two-dimensional scanned image to obtain the lung parenchyma area in each layer of the two-dimensional scanned image includes: Using a large-law threshold segmentation method to perform binarization segmentation on each layer of the two-dimensional scanned image to obtain a first binarized image of each layer of the two-dimensional scanned image; Determine the largest connected area in the first binary image as a skin contour area; After the skin contour area is filled, it is subtracted from the first binarized image to obtain the lung parenchyma area.

4. The method according to claim 2, characterized in that: The step of segmenting the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset first threshold value to obtain a three-dimensional clavicle area includes: According to the first threshold, binarization segmentation is performed on each layer of the two-dimensional scanned image to obtain a second binarized image; After dilating the lung parenchyma region, subtracting the second binarized image from the second binarized image to obtain a first image corresponding to each layer of the two-dimensional scanned image; Performing a first three-dimensional connected domain analysis on a first image corresponding to the multi-layer two-dimensional scanned image; The three-dimensional clavicle region is segmented from the first three-dimensional connected domain according to the result of the analysis of the first three-dimensional connected domain and the preset clavicle features.

5. The method according to claim 2, characterized in that: The step of segmenting the bone tissue of the multi-layer two-dimensional scanned image according to the lung parenchyma area and a preset second threshold value to obtain a three-dimensional scapula area includes: According to the second threshold, binarization segmentation is performed on each layer of the two-dimensional scanned image to obtain a third binarized image; After dilating the lung parenchyma region, subtracting the region from the third binary image to obtain a second image corresponding to each layer of the two-dimensional scanned image; Performing a second three-dimensional connected domain analysis on a second image corresponding to the multi-layer two-dimensional scanned image; The three-dimensional scapula region is segmented from the second three-dimensional connected domain according to the result of the analysis of the second three-dimensional connected domain and the preset scapula features.

6. The method according to claim 2, characterized in that The step of segmenting the bone tissue of the multi-layer two-dimensional scanned image according to the preset third threshold value to obtain a three-dimensional bone tissue region includes: According to the third threshold, binarization segmentation is performed on each layer of the two-dimensional scanned image to obtain a fourth binarized image; Performing connected domain analysis on the fourth binarized image; According to the result of the connected domain analysis, the sternum region is removed from the fourth binary image to obtain the bone segmentation result of each layer of the two-dimensional scanned image; The three-dimensional bone tissue region includes: the bone segmentation results of the multi-layer two-dimensional scanning image.

7. The method according to claim 2, characterized in that The determining of the rib and spine region from the three-dimensional bone tissue region according to the three-dimensional clavicle region and the three-dimensional scapula region comprises: Subtracting the three-dimensional clavicle region and the three-dimensional scapula region from the three-dimensional bone tissue region to obtain a partial three-dimensional region including ribs and spine; Performing an expansion operation on the partial three-dimensional area in the left-right direction of the human body and in the extension direction of the spine; The largest three-dimensional connected region is determined to be the rib and spine region from the three-dimensional region of the expansion operation.

8. The method according to claim 1, characterized in that Generating a three-dimensional rib image according to the three-dimensional rib region includes: traversing the three-dimensional rib region from the left region and the right region of the head respectively; The first pixel point whose pixel value is a preset pixel value found from the left area of ​​the head is used as the left seed point; The first pixel point whose pixel value is the preset pixel value found from the right side area of ​​the head is used as the right seed point; Using the left seed point to grow multiple first ribs on the left side in the three-dimensional region; Using the right seed point to grow multiple second ribs on the left side in the three-dimensional region; The three-dimensional rib image is generated according to the plurality of first ribs and the plurality of second ribs.

9. The method according to claim 1, characterized in that: The step of extracting the spine centerline from the multi-layer two-dimensional scanned images to obtain the spine centerline includes: Determine the spinal mass points in the last layer of the spinal binary images in the multi-layer spinal binary images according to the preset spinal features, wherein the last layer of the spinal binary images is the image closest to the chest in the multi-layer spinal binary images; Determine the spine mass points in other layers of spine binary images according to the spine mass points in the last layer of spine binary image; Extracting a spinal sagittal image from the multi-layer spinal binary image according to the X-axis coordinates of the spinal particles in the multi-layer spinal binary image, wherein the width direction of each layer of the spinal binary image is the X-axis direction, the height direction of each layer of the spinal binary image is the Y-axis direction, and the spinal direction is the Z-axis direction of the multi-layer spinal binary image; Performing an expansion operation on the spinal sagittal image to determine a three-dimensional connected area of ​​the spine; Using the grayscale centroid method, the Y-axis coordinates of the spine particles in the multi-layer spine binary image are updated from the three-dimensional spine connected area; The spine centerline is determined according to the X-axis coordinates and the Y-axis coordinates of the spine particles in the multi-layer spine binary image.

10. The method according to claim 1, characterized in that Before performing bone tissue segmentation on the multi-layer two-dimensional scanned image to obtain rib and spine regions, the method further includes: According to a preset fifth threshold, the multi-layer two-dimensional scanned image is binarized and segmented to obtain a sixth binarized image; Determine the connected area between the bed board and the human body from the sixth binarized image; Determine the inner and outer contour lines of the connecting area between the bed board and the human body, and remove edge points that do not conform to the characteristics of the bed board from the inner and outer contour lines according to the distance between the upper and lower edges of the bed board; Determine a seed point between the upper and lower edges of the bed board, and fill in the seed point to determine the bed board area; The bed board area is segmented from the multi-layer two-dimensional scanning images.

11. A rib segmentation device, characterized in that: The device comprises: An image sequence acquisition module, used to acquire a medical image sequence to be processed, wherein the medical image sequence includes multiple layers of two-dimensional scanned images; A bone tissue segmentation module, used to perform bone tissue segmentation on the multi-layer two-dimensional scanning image to obtain rib and spine regions; A spine centerline extraction module is used to extract the spine centerline from the multi-layer two-dimensional scanned image to obtain the spine centerline, and to perform binarization segmentation on the multi-layer two-dimensional scanned image according to a preset fourth threshold value to obtain a fifth binarized image; to determine a multi-layer spine binarized image from the fifth binarized image; and to obtain the spine width according to an average spine width of the multi-layer spine binarized image; A spine region removal module, used for determining and removing the spine region in the rib and spine region according to the spine centerline and the spine width, to obtain a three-dimensional rib region; The three-dimensional rib image generation module is used to generate a three-dimensional rib image according to the three-dimensional rib area.

12. A computer device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor and the storage medium communicate through the bus, and the processor executes the program instructions to perform the steps of the rib segmentation method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the rib segmentation method according to any one of claims 1 to 10 are executed.

Images