Method, apparatus, and computer readable storage medium for generating a rib image

Abstract

The application relates to the technical field of medical imaging, and discloses a method for generating a rib image. After an original scanning image is acquired, the center line of each rib sub-region is extracted, the center line is divided into a plurality of center line segments, and a rib image is generated based on the center line segments. In the embodiment of the application, in each rib sub-region, the center line is further divided into center line segments. Since the center line segments with large differences in position correspond to ribs with bending, each center line segment after division can represent the actual morphology of the ribs. The rib image generated based on the plane where the center line segment is located restores the actual spatial morphology of the ribs, reduces the deformation in the image, and improves the image generation quality. The application also discloses a device for generating a rib image and a computer readable storage medium.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and for example to a method, apparatus and computer-readable storage medium for generating rib images. Background Technology

[0002] In medical imaging, the ribs have a complex structure and a large number of ribs, making rib image interpretation a time-consuming task for radiology. To allow doctors to see the shape of each rib clearly and intuitively, a high degree of image clarity is required.

[0003] In related technologies, deformation occurs during rib imaging, meaning that the generated rib image cannot fully reflect the actual shape of the rib. This can lead to problems such as the inability to identify minor fractures, thus causing some difficulties in clinical diagnosis.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0006] This application provides a method, apparatus, and computer-readable storage medium for generating rib images to reduce rib image deformation and improve imaging quality.

[0007] In some embodiments, the method includes: acquiring an original scan image containing rib regions; wherein the original scan image includes multiple rib sub-regions, each rib sub-region corresponding to one rib; extracting a centerline containing multiple centerline segments from each rib sub-region in the original scan image; wherein the positional difference between pixels within the centerline segment is less than the positional difference between pixels between the centerline segments; and generating a rib image based on the plane containing each centerline segment.

[0008] Optionally, acquiring the original scan image containing the rib region includes: acquiring original image data; performing tissue segmentation on the original image data; and determining the region formed by the pixels belonging to the rib region in the original image data as the original scan image.

[0009] Optionally, the original image data is segmented into an organization, including: inputting the original image data into a pre-trained neural network model to obtain the category identifier of each pixel output by the neural network model; and identifying regions composed of pixels with the same category identifier as the same organization.

[0010] Optionally, each rib sub-region in the original scanned image is determined by the following method: dividing the original scanned image into multiple initial sub-regions; calculating the distance between each point in each initial sub-region and the nearest point outside the initial sub-region; and performing clustering based on the distances to obtain the rib sub-region corresponding to each initial sub-region.

[0011] Optionally, extracting a centerline containing multiple centerline segments from each rib sub-region from the original scanned image includes: extracting the centerline of each rib sub-region; connecting adjacent center points on the centerline; and dividing the centerline into multiple centerline segments according to the slope of the connecting lines.

[0012] Optionally, extracting a centerline containing multiple centerline segments from each rib sub-region from the original scanned image includes: extracting the centerline of each rib sub-region; connecting adjacent center points on the centerline; and dividing the centerline into multiple centerline segments based on the slope of the connecting lines and the thickness of the three-dimensional region formed by the connecting lines.

[0013] Optionally, based on the slope of the connecting line and the thickness of the three-dimensional region formed by the connecting line, the center line is divided into multiple center line segments, including: after connecting the Nth center point with the (N+1)th center point, a cube is formed based on the thickness of the (N+1)th center point and the connecting line; wherein N is an integer greater than 1, and the first N center points constitute the current center line segment; if the cube contains the 1st to Nth center points, the Nth center point is determined to belong to the current center line segment; if the cube does not completely contain the 1st to Nth center points, the Nth center point is determined not to belong to the current center line segment, and the current center line segment is determined.

[0014] In some embodiments, the apparatus includes: an acquisition module configured to acquire an original scan image containing rib regions; wherein the original scan image includes multiple rib sub-regions, each rib sub-region corresponding to one rib; an extraction module configured to extract a centerline containing multiple centerline segments from each rib sub-region; wherein the positional difference between pixels within the centerline segment is less than the positional difference between pixels between the centerline segments; and an image generation module configured to generate a rib image based on the plane containing each centerline segment.

[0015] The method, apparatus, and computer-readable storage medium for generating rib images provided in this application can achieve the following technical effects:

[0016] After acquiring the original scanned image, the centerline of each rib sub-region is extracted and divided into multiple centerline segments. A rib image is then generated based on these centerline segments. In this embodiment, within each rib sub-region, the centerline is further divided into centerline segments. Since centerline segments with significant positional differences correspond to ribs with bends, each divided centerline segment can characterize the actual shape of the rib. The rib image generated based on the plane containing the centerline segment restores the actual spatial shape of the rib, reduces image distortion, and improves image generation quality.

[0017] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0018] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0019] Figure 1 A rib image generated using CPR technology;

[0020] Figure 2 A flowchart of a method for generating rib images provided in an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the center line segment of a rib sub-region generated according to the method for generating rib images provided in the embodiments of this application;

[0022] Figure 4 A flowchart illustrating another method for generating rib images provided in this application embodiment;

[0023] Figure 5 A schematic diagram illustrating the slope of the centerline provided in an embodiment of this application;

[0024] Figure 6 A flowchart illustrating a method for generating a centerline segment provided in this application embodiment;

[0025] Figure 7 A rib image generated according to the method provided in the embodiments of this application;

[0026] Figure 8 This refers to the entire image of the rib region generated according to the method provided in the embodiments of this application;

[0027] Figure 9 A schematic diagram of an apparatus for generating rib images provided in an embodiment of this application;

[0028] Figure 10 This is a schematic diagram of an apparatus for generating rib images, provided as an embodiment of this application. Detailed Implementation

[0029] To provide a more detailed understanding of the features and technical content of the embodiments of this application, the implementation of the embodiments of this application will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this application. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0030] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0031] Unless otherwise stated, the term "multiple" means two or more.

[0032] In this embodiment, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0033] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0034] Rib image interpretation is a time-consuming task in radiology. The ribs encompass a wide area and have a three-dimensional semi-enclosed structure, making it difficult for conventional imaging techniques to fully display all details, easily leading to the omission of subtle lesions. There are many methods for rendering medical images, including MPR (Multiplanar Reconstruction) and CPR (Curved Planar Reformation) based on the original scan image. CPR, or Curved Planar Reformation, is a method of displaying images based on a defined curved path. This technique allows the entire tubular structure to be displayed in a single image, with the region of interest projected onto the image. The orientation can then be changed, i.e., the image can be rotated, allowing users to observe and diagnose abnormalities such as vascular stenosis and calcification. The direction vector and the center line define a drawing line; all pixels touched by this line are calculated to form the CPR image.

[0035] This technology allows the entire length of a tubular structure to be displayed in a single image. Doctors can then observe vascular abnormalities (i.e., stenosis, occlusion, aneurysms, and calcification of the vessel wall). Traditional methods for generating MPR images using MPR (Multi-Planar Reconstruction) technology produce MPR images in parallel, perpendicular, or other orientations. Multi-planar reconstruction creates new images calculated from volumetric CT scans along arbitrary directions. MPR images can originate from straight or curved surfaces and contain density information from the corresponding CT slices, including average density, maximum density, and minimum density. MPR images are typically used to display anatomy and lesions from various angles in non-original scan orientations, allowing lesions to be displayed logically on a non-transverse image. Medical processing software allows for arbitrary rotation of the image angle to obtain MPR images from different perspectives.

[0036] However, CPR straightens the ribs, revealing some deformation. Through... Figure 1 As can be seen, CPR inherently involves deformation. For subtle fractures, assuming the fracture location is precisely within the deformation zone, the deformation can prevent the fracture from being detected. Furthermore, MPR cannot display the full extent of the fracture.

[0037] Based on this, the embodiments of this application divide the rib region into sub-regions according to each rib, and further divide each sub-region into multiple center line segments according to the rib bending direction. Based on the center line segments, a two-dimensional image is generated, which can effectively avoid the problem of rib region deformation and make the rib image have higher clinical value.

[0038] Combination Figure 2 As shown, this application provides a method for generating rib images, such as... Figure 2 As shown, the method specifically includes the following steps:

[0039] S201: Obtain the raw scan image containing the rib region.

[0040] The original scan image includes multiple rib sub-regions, each corresponding to one rib.

[0041] First, image information and image data are loaded. Specifically, the scanned DICOM image is loaded into the system, and data areas, orientations, and pixel intervals are read. The positional intervals between layers are calculated to form a three-dimensional data field, i.e., the original scanned image. It can be understood that the original scanned image includes the rib region, and based on relevant image segmentation methods, the rib region is further divided into multiple rib sub-regions, each corresponding to one rib.

[0042] S202: Extract the center line containing multiple center line segments from each rib sub-region of the original scan image.

[0043] The positional difference between pixels within the center line segment is smaller than the positional difference between pixels between the center line segments.

[0044] Specifically, after dividing the rib sub-regions, the centerline of each rib sub-region can be extracted first, and then the centerline can be divided into multiple centerline segments. The positional differences between pixels within each centerline segment should be small; for example, the slope or direction vector difference of the line connecting adjacent pixels should be less than a preset threshold, so that the lines connecting all pixels within the centerline segment approximate a straight line. In other examples, the positional differences between pixels within a centerline segment can be set to be less than the positional differences between pixels between centerline segments. For example, if the slope or direction vector of the line connecting two adjacent pixels is greater than a threshold, it indicates that a rib bend has occurred at that point, and the edge pixel between the two pixels is then separated from the current centerline segment. In other examples, to improve the efficiency of centerline segmentation, a centerline segmentation model can be pre-trained. In practical applications, the pixel information of the rib sub-regions is directly input into the centerline segmentation model to obtain the segmented centerline segments. Figure 3 The diagram shown is a schematic diagram of the center line segment of a rib sub-region generated according to the method for generating rib images provided in the embodiments of this application.

[0045] S203: Generate a rib image based on the plane containing each of the central line segments.

[0046] Specifically, the plane containing the center line segment can be generated as follows:

[0047] The FOV (Field of View) is calculated based on the vector and center point, and the width and height (WH) of the displayed surface are recorded. Sampling is performed along the width W direction H times, and for each point, a value is obtained using a specific interpolation method, forming a sampling plane for a center line segment. This process is iterated to obtain sampling planes for all center line segments. The image is then unfolded along the direction of the sampling planes to generate the rib image.

[0048] The method provided in this application, after acquiring the original scanned image, extracts the centerline of each rib sub-region and divides the centerline into multiple centerline segments, generating a rib image based on these centerline segments. In this application embodiment, within each rib sub-region, the centerline is further divided into centerline segments. Since centerline segments with significant positional differences correspond to ribs with bends, each divided centerline segment can characterize the actual shape of the rib. The rib image generated based on the plane containing the centerline segment restores the actual spatial shape of the rib, reduces deformation in the image, and improves the image generation quality.

[0049] Optionally, obtaining the original scan image containing the rib region in the above embodiments includes: obtaining original image data; performing tissue segmentation on the original image data; and determining the region formed by the pixels belonging to the rib region in the original image data as the original scan image.

[0050] Optionally, the organization segmentation of the original image data in the above embodiments includes: inputting the original image data into a pre-trained neural network model to obtain the category identifier of each pixel output by the neural network model; and determining the regions formed by pixels with the same category identifier as the same organization.

[0051] As an example, deep learning networks can be used to identify different tissues in raw image data. Alternatively, full-pixel semantic segmentation can be used, assigning a category ID to each pixel in the image based on its associated object of interest, performing tissue identification and segmentation, and obtaining the identifier of the target tissue. It is understood that other image segmentation methods can also be used for segmenting raw image data, and this application does not limit these methods.

[0052] Combination Figure 4 As shown, another method for generating rib images is provided in this application embodiment. This embodiment focuses on describing how to divide multiple rib sub-regions from an original scan image. The method includes the following steps:

[0053] S401: Acquire the raw scan image containing the rib region.

[0054] S402: Divide the original scanned image into multiple initial sub-regions.

[0055] S403: Calculate the distance between each point in each initial sub-region and the nearest point outside the initial sub-region.

[0056] S404: Perform clustering based on the distance to obtain the rib sub-region corresponding to each initial sub-region.

[0057] S405: Extract the center line containing multiple center line segments from each rib sub-region of the original scan image.

[0058] Wherein, the positional difference between pixels within the center line segment is smaller than the positional difference between pixels between the center line segments;

[0059] S406: Generate a rib image based on the plane containing each of the central line segments.

[0060] Specifically, in the original scanned image, the original scanned image is first divided into multiple initial sub-regions according to the image segmentation method. Each initial sub-region contains a rib. There are multiple ways to divide the initial sub-regions. Any image segmentation method can be used for division. This application embodiment does not limit this.

[0061] In each initial sub-region, the distance between each pixel and its nearest pixel outside the initial sub-region is calculated; this is known as calculating the distance field. Pixels within the initial sub-region can be called target points. The closer a target point is to the boundary of the initial sub-region, the smaller its distance value; conversely, the farther a target point is from the boundary, the larger its distance value. Based on the distance field, rib sub-regions can be accurately delineated from the initial sub-regions.

[0062] Furthermore, for each rib sub-region, the center point of the rib sub-region is extracted, and the center point is connected to obtain the center line of the rib sub-region.

[0063] Optionally, after extracting the centerline of each rib sub-region, the centerline needs to be segmented. Therefore, in the above embodiment, extracting the centerline containing multiple centerline segments from the original scanned image includes: extracting the centerline of each rib sub-region; connecting adjacent center points on the centerline; and dividing the centerline into multiple centerline segments according to the slope of the connecting lines.

[0064] Because ribs are curved, the image is further divided into multiple segments based on the slope of the bend, starting from the center line. The slopes of the lines connecting pixels within each segment remain relatively similar, aiming to make the connecting lines as close to straight as possible, thus creating an image without distortion. Dividing the center line into segments based on its slope allows for quick and efficient acquisition of these segments, improving the efficiency of rib image generation. Figure 5 The diagram shown is a schematic representation of the slope of the centerline provided in an embodiment of this application.

[0065] Optionally, since the rib region is not planar but exists in three dimensions, the method of only considering the slope of the centerline does not take into account the differences in the z-square of the rib outside the xy plane. In order to further improve the segmentation accuracy of the rib region, in the above embodiment, the centerline containing multiple centerline segments in each rib sub-region is extracted from the original scan image, including: extracting the centerline of each rib sub-region; connecting adjacent center points on the centerline; and dividing the centerline into multiple centerline segments according to the slope of the connecting lines and the thickness of the three-dimensional region formed after the connecting lines.

[0066] Optionally, in the above embodiments, dividing the center line into multiple center line segments based on the slope of the connecting line and the thickness of the three-dimensional region formed by the connecting line includes: after connecting the Nth center point with the (N+1)th center point, forming a cube based on the thickness of the (N+1)th center point and the connecting line; wherein N is an integer greater than 1, and the first N center points constitute the current center line segment; if the cube contains the 1st to Nth center points, determining that the Nth center point belongs to the current center line segment; if the cube does not completely contain the 1st to Nth center points, determining that the Nth center point does not belong to the current center line segment, and the current center line segment is determined.

[0067] Starting from the first seed point in the center point set, lines are drawn to cover the second seed point, forming an MPR cross-section. Thickness is considered from the cross-section; if the thickness does not exceed the tissue list, the process continues, adding more seed points. This loop continues until the last center point, forming all the MPR processing results. The seed point is the center point on the center line, and the selection method can be set according to the actual center line length. For example, a seed point can be selected every X number of pixels.

[0068] Specifically, a vector is created based on the first seed point of the current centerline, following the direction of its adjacent seed points, and the input seed points are placed in a queue. During the iteration process, it is determined whether the currently generated vector surface can include all corresponding organizations, i.e., adjacent seed points form a vector surface. If the vector surface can include all seed points before the current adjacent seed point, it means that the directional difference between the current vector surface and the previous seed points is small, and the current seed point and all previous seed points can be assigned to the region corresponding to the centerline segment. Conversely, if it cannot include all previous seed points, it means that the direction of the current vector surface differs significantly from the direction of the previous seed points, and therefore it cannot be assigned to the region corresponding to the centerline segment.

[0069] If the current vector plane can contain all previous seed points, the iteration continues, acquiring points of interest within the adjacent region of the next new seed point. Points are marked as fixed-structure points based on their thickness range. The process continues to grow, acquiring center points within the range. The distance and direction between the updated center points and the initial seed point are calculated and updated. If the range formed by the newly added center point and the initial seed point cannot completely encompass all previous ranges, the growth iteration stops, and all seed points in the current queue are saved as the segmented region result for this iteration. In other words, if the current vector plane cannot contain all previous seed points, the current vector plane is discarded, and all previous seed points are divided into a central line segment.

[0070] Since the bending of ribs is reflected not only in the plane but also in the thickness, meaning the area formed by ribs is a three-dimensional region, in order to further reflect the details of the ribs, the slope and thickness of the line connecting the center points are considered, so that the division of the center line segment is in three-dimensional space, thereby improving the imaging effect of the rib area and reducing deformation.

[0071] For ease of understanding, combined with Figure 6 As shown, this application provides a method for segmenting a center line segment, the method comprising:

[0072] S601: Obtain the Nth seed point and the (N+1)th seed point.

[0073] S602: Connect the Nth seed point and the (N+1)th seed point to form a direction vector.

[0074] S603: Combine the thickness and direction vector of the current seed point to form a cube.

[0075] S604: Determine whether the current cube contains 1 to N+1 seed points.

[0076] S605: If yes, then continue to obtain the N+2th seed point and execute step S601.

[0077] S606: If not included, the current center line segment division ends, and the line connecting the 1st to Nth seed points is determined as the current center line segment.

[0078] Figure 7 A rib image generated according to the method provided in the embodiments of this application. Figure 8 This is an overall image of the rib region generated according to the method provided in the embodiments of this application. Using the method described above in the embodiments of this application, an MPR image covering the entire rib can be obtained, allowing doctors to perform diagnostic operations on the entire rib cross-section based on the MPR.

[0079] For a given original scan sequence covering a 35 cm area with a 1 mm slice interval, 350 images are required. Calculating based on ribs (12 pairs, 24 ribs), and assuming each rib is represented by two images, this method yields approximately 50 images. Therefore, it can fully visualize rib details while reducing the diagnostic workload for doctors.

[0080] Combination Figure 9 As shown, an apparatus 900 for generating rib images, provided in an embodiment of this application, includes:

[0081] The acquisition module 901 is configured to acquire an original scan image containing a rib region; wherein the original scan image includes multiple rib sub-regions, each rib sub-region corresponding to one rib;

[0082] Extraction module 902 is configured to extract the center line containing multiple center line segments in each rib sub-region; wherein the positional difference between pixels within the center line segment is smaller than the positional difference between pixels between the center line segments.

[0083] The image generation module 903 is configured to generate rib images based on the plane in which each of the central line segments is located.

[0084] The apparatus provided in this application, after acquiring the original scanned image, extracts the centerline of each rib sub-region and divides the centerline into multiple centerline segments, generating a rib image based on the centerline segments. In this application embodiment, in each rib sub-region, the centerline is further divided into centerline segments. Since centerline segments with significant positional differences correspond to ribs with bends, each divided centerline segment can characterize the actual shape of the rib. The rib image generated based on the plane where the centerline segment is located restores the actual spatial shape of the rib, reduces deformation in the image, and improves the image generation quality.

[0085] Optionally, the acquisition module 901 is further configured to acquire raw image data; perform tissue segmentation on the raw image data; and determine the region formed by pixels belonging to the rib region in the raw image data as the raw scan image.

[0086] Optionally, the original image data is segmented into an organization, including: inputting the original image data into a pre-trained neural network model to obtain the category identifier of each pixel output by the neural network model; and identifying regions composed of pixels with the same category identifier as the same organization.

[0087] Optionally, each rib sub-region in the original scanned image is determined by the following method: dividing the original scanned image into multiple initial sub-regions; calculating the distance between each point in each initial sub-region and the nearest point outside the initial sub-region; and performing clustering based on the distances to obtain the rib sub-region corresponding to each initial sub-region.

[0088] Optionally, the extraction module 902 is further configured to extract the centerline of each rib sub-region;

[0089] Connect adjacent center points on the center line; divide the center line into multiple center line segments according to the slope of the connecting lines.

[0090] Optionally, the extraction module 902 is further configured to extract the centerline of each rib sub-region; connect adjacent center points on the centerline; and divide the centerline into multiple centerline segments according to the slope of the connecting lines and the thickness of the three-dimensional region formed by the connecting lines.

[0091] Optionally, based on the slope of the connecting line and the thickness of the three-dimensional region formed by the connecting line, the center line is divided into multiple center line segments, including: after connecting the Nth center point with the (N+1)th center point, a cube is formed based on the thickness of the (N+1)th center point and the connecting line; wherein N is an integer greater than 1, and the first N center points constitute the current center line segment; if the cube contains the 1st to Nth center points, the Nth center point is determined to belong to the current center line segment; if the cube does not completely contain the 1st to Nth center points, the Nth center point is determined not to belong to the current center line segment, and the current center line segment is determined.

[0092] Combination Figure 10As shown, this application provides an apparatus 1000 for generating rib images, including a processor 100 and a memory 101. Optionally, the apparatus may further include a communication interface 102 and a bus 103. The processor 100, communication interface 102, and memory 101 can communicate with each other via the bus 103. The communication interface 102 can be used for information transmission. The processor 100 can call logical instructions in the memory 101 to execute the method for generating rib images described in the above embodiment.

[0093] Furthermore, the logic instructions in the aforementioned memory 101 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0094] The memory 101, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 100 executes functional applications and data processing by running the program instructions / modules stored in the memory 101, that is, it implements the method for generating rib images described in the above embodiments.

[0095] The memory 101 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 101 may include high-speed random access memory and may also include non-volatile memory.

[0096] This application provides a computer-readable storage medium storing computer-executable instructions configured to perform the method for generating rib images described in the above embodiments.

[0097] This application provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions that, when executed by a computer, cause the computer to perform the method for generating rib images described in the above embodiments.

[0098] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0099] The technical solutions of this application embodiment can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this application embodiment. The aforementioned storage medium can be a non-transitory storage medium, including: USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0100] The foregoing description and accompanying drawings fully illustrate embodiments of this application to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or,” as used herein, means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0101] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0102] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of this application 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.

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for generating a rib image, characterized by, include: Obtain a raw scan image containing the rib region; wherein the raw scan image includes multiple rib sub-regions, each rib sub-region corresponding to one rib; Extract the centerline of each rib subregion; Connect adjacent center points on the center line; Based on the slope of the connecting line, the center line is divided into multiple center line segments; wherein the positional difference between pixels within a center line segment is smaller than the positional difference between pixels between center line segments. A rib image is generated based on the plane containing each of the central line segments.

2. The method of claim 1, wherein, Obtain raw scan images containing the rib region, including: Obtain the raw image data; The original image data is then organized and segmented; The region formed by the pixels belonging to the rib area in the original image data is determined as the original scanned image.

3. The method of claim 2, wherein, Organizing and segmenting the original image data includes: The original image data is input into a pre-trained neural network model to obtain the category label of each pixel output by the neural network model; Regions consisting of pixels with the same category identifier are identified as belonging to the same organization.

4. The method of claim 1, wherein, Each rib sub-region in the original scan image was determined by the following method: The original scanned image is divided into multiple initial sub-regions; Calculate the distance between each point in each initial sub-region and the nearest point outside the initial sub-region; Clustering is performed based on the distance to obtain the rib sub-region corresponding to each initial sub-region.

5. The method of claim 1, wherein, Based on the slope of the connecting line, the centerline is divided into multiple centerline segments, including: Based on the slope of the connecting line and the thickness of the three-dimensional region formed by the connecting line, the center line is divided into multiple center line segments.

6. The method of claim 5, wherein, Based on the slope of the connecting line and the thickness of the three-dimensional region formed by the connecting line, the center line is divided into multiple center line segments, including: After connecting the Nth center point with the (N+1)th center point, a cube is formed based on the thickness of the (N+1)th center point and the connecting line; where N is an integer greater than 1, and the first N center points constitute the current center line segment; If the cube contains the first to the Nth center points, then the Nth center point is determined to belong to the current center line segment; If the cube does not completely contain the 1st to Nth center points, it is determined that the Nth center point does not belong to the current center line segment, and the current center line segment is determined.

7. An apparatus for generating a rib image, characterized by include: The acquisition module is configured to acquire a raw scan image containing a rib region; wherein the raw scan image includes multiple rib sub-regions, each rib sub-region corresponding to one rib; The extraction module is configured to extract the center line of each rib sub-region; connect adjacent center points on the center line; divide the center line into multiple center line segments according to the slope of the connecting lines; wherein the positional difference between pixels within the center line segment is smaller than the positional difference between pixels between the center line segments. The image generation module is configured to generate rib images based on the plane in which each of the central line segments lies.

8. An apparatus for generating a rib image, comprising a processor and a memory having stored program instructions, characterized in that, The processor is configured to execute, when executing the program instructions, the method for generating a rib image according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions configured to execute the method for generating a rib image according to any one of claims 1 to 6.

Images