Methods, display methods, apparatuses, devices, and storage media for determining jaw features

Abstract

This application discloses a method, display method, apparatus, device, and storage medium for determining jawbone features. The method includes: obtaining a radicular bone scan image; segmenting the jawbone based on the radicular bone scan image to determine a segmented jawbone image; using a neural network, taking both the radicular bone scan image and the segmented jawbone image representing the same jawbone location as input, to determine a jawbone feature image and a cancellous bone feature image; comparing the jawbone feature image and the cancellous bone feature image, and determining a cortical bone feature image based on the differences; and determining and outputting cortical bone feature information based on the cortical bone feature image. The method provided in this application can improve the accuracy and efficiency of jawbone feature determination.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, display method, apparatus, device and storage medium for determining jawbone features. Background Technology

[0002] With societal development and rising demands for quality of life, oral hygiene and aesthetic oral health maintenance have gradually become key concerns. During related treatments, jawbone features serve as crucial intermediate data, revealing the user's current dental and jaw condition and assisting the operator in determining the treatment plan.

[0003] When determining jawbone features, it is necessary to determine the state information of the jawbone, cancellous bone, or cortical bone. Existing technologies include methods based on image grayscale information analysis and methods based on deep neural network analysis. The former relies on the operator's experience, has high requirements for scanned images, and is inefficient with poor segmentation results; the latter applies to the entire jawbone, making it difficult to determine the specific structural features of the jawbone. Summary of the Invention

[0004] One of the objectives of this application is to provide a method for determining jawbone features, in order to solve the technical problem of poor accuracy in jawbone structure segmentation and difficulty in segmenting the specific structure of the jawbone in the prior art.

[0005] One of the purposes of this application is to provide a display method.

[0006] One of the purposes of this application is to provide a jawbone structure segmentation device.

[0007] One of the purposes of this application is to provide an electronic device.

[0008] One of the purposes of this application is to provide a storage medium.

[0009] To achieve one of the objectives, one embodiment of this application provides a method for determining jawbone features, comprising: obtaining a radicular bone scan image; segmenting the jawbone based on the radicular bone scan image to determine a jawbone segmentation image; using a neural network, taking both the radicular bone scan image and the jawbone segmentation image representing the same jawbone location as input, to determine a jawbone feature image and a cancellous bone feature image; comparing the jawbone feature image and the cancellous bone feature image, and determining a cortical bone feature image based on the differences; and determining and outputting cortical bone feature information based on the cortical bone feature image.

[0010] Optionally, the cortical bone feature image can be determined by pixel-by-pixel subtraction between the jawbone feature image and the cancellous bone feature image.

[0011] Optionally, a neural network can be used to extract features from the root bone scan image by referring to the jawbone segmentation image, thereby determining the jawbone feature image and the cancellous bone feature image.

[0012] Optionally, it includes at least one of the following: obtaining an oral scan model, performing coordinate transformation on the cortical bone feature information to display the cortical bone feature information at the oral scan model; determining the cancellous bone feature information based on the cancellous bone feature image, obtaining an oral scan model, performing coordinate transformation on the cancellous bone feature information to display the cancellous bone feature information at the oral scan model; determining and outputting cortical bone size information based on the cortical bone feature image; determining and outputting bone density information based on the cancellous bone feature image; establishing a three-dimensional model of the jawbone based on several jawbone feature images corresponding to several jawbone positions; establishing a three-dimensional model of cancellous bone based on several cancellous bone feature images corresponding to several jawbone positions; and establishing a three-dimensional model of the cortical bone based on several cortical bone feature images corresponding to several jawbone positions.

[0013] Optionally, a root bone scan image and a jaw segmentation image representing the same jawbone location in a first direction are obtained, wherein the first direction is perpendicular to the display plane of the root bone scan image and the jaw segmentation image; based on the jaw segmentation image, the region representing the jawbone location in the root bone scan image is determined; and the root bone scan image is cropped.

[0014] Optionally, determine the region representing the jawbone area in the segmented jawbone image; crop the segmented jawbone image; and determine the region representing the jawbone area in the root bone scan image based on the region representing the jawbone area in the segmented jawbone image.

[0015] Optionally, the calcaneal scan images may include cone-beam computed tomography (CBCT) images.

[0016] Optionally, a neural network can be used to segment the maxilla and mandible based on the root bone scan image to determine the segmented image of the maxilla and the segmented image of the mandible.

[0017] To achieve one of the objectives, one embodiment of this application provides a display method comprising at least one of the following: presenting a jawbone feature image in a graphical user interface, wherein the jawbone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input, and the jawbone feature image is used to determine a cortical bone feature image based on its difference from a cancellous bone feature image; presenting a cancellous bone feature image in a graphical user interface, wherein the cancellous bone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input, and the cancellous bone feature image is used to determine a cortical bone feature image based on its difference from a jawbone feature image; and presenting a cortical bone feature image in a graphical user interface, wherein the cortical bone feature image is determined by comparing the differences between the jawbone feature image and the cancellous bone feature image, and the jawbone feature image and the cancellous bone feature image are determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input.

[0018] Optionally, at least one of the following may be included: the jawbone feature image, the cancellous bone feature image, and the cortical bone feature image are three-dimensional models; the jawbone feature image, the cancellous bone feature image, and the cortical bone feature image are two-dimensional images.

[0019] Optionally, it includes at least one of the following: presenting an oral scan model and a corresponding cortical bone feature image in a graphical user interface, the cortical bone feature image being used to characterize the cortical bone region; presenting an oral scan model and a corresponding cancellous bone feature image in a graphical user interface, the cancellous bone feature image being used to characterize the cancellous bone region; presenting an oral scan model and a corresponding jawbone feature image in a graphical user interface, the jawbone feature image being used to characterize the jawbone region.

[0020] Optionally, it includes at least one of the following: presenting a selection box surrounding the maxillary region in a graphical user interface; presenting a selection box surrounding the mandibular region in a graphical user interface; the selection box is a two-dimensional selection box or a three-dimensional selection box; the selection box is determined based on the region representing the jawbone region in the jawbone segmentation image, and the jawbone segmentation image is determined based on the jawbone segmentation of the root bone scan image using a neural network.

[0021] To achieve one of the objectives, one embodiment of this application provides an apparatus for determining jawbone features, comprising: a first module for obtaining a radicular bone scan image; a second module for segmenting the jawbone based on the radicular bone scan image to determine a segmented jawbone image; a third module for using a neural network, taking both the radicular bone scan image and the segmented jawbone image representing the same jawbone location as input, to determine a jawbone feature image and a cancellous bone feature image; a fourth module for comparing the jawbone feature image and the cancellous bone feature image, and determining a cortical bone feature image based on the differences; and a fifth module for determining and outputting cortical bone feature information based on the cortical bone feature image.

[0022] Optionally, the device is connected to a first device for implementing a cone-beam annular headgear to obtain radicular bone scan images, which are used to obtain jawbone feature images and / or cancellous bone feature images.

[0023] To achieve one of the objectives, one embodiment of this application provides an electronic device, including a processor, a memory, and a communication bus, wherein the processor and the memory communicate with each other through the communication bus; the memory is used to store application programs; and the processor is used to implement the steps of any method for determining jawbone features or any display method when executing the application programs stored in the memory.

[0024] To achieve this objective, one embodiment of this application provides a storage medium on which an application program is stored, which, when executed, implements the steps of any method for determining jawbone features, or the steps of any display method.

[0025] Compared with existing technologies, the method for determining jawbone features provided in this application uses a segmented jawbone image obtained by segmenting the radicular bone scan image and the radicular bone scan image itself as a dual-channel input to a neural network. This enhances the feature extraction capability of the neural network and achieves accurate determination of overall jawbone features and cancellous bone features. The method provided in this application also determines cortical bone features based on the differences between cancellous bone features and overall jawbone features. Compared with existing technologies, the accuracy of cortical bone feature extraction is higher, and the computation is more efficient. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of jawbone features in one embodiment of this application.

[0027] Figure 2 This is a schematic diagram of the structure of a device for determining jawbone features according to one embodiment of this application.

[0028] Figure 3 This is a schematic diagram of the structure of an electronic device according to one embodiment of this application.

[0029] Figure 4 This is a schematic diagram of the steps of a method for determining jawbone features according to one embodiment of this application.

[0030] Figure 5 This is a schematic diagram of a pedicle scan image and sequence according to one embodiment of this application.

[0031] Figure 6 This is a schematic diagram of an embodiment of the jawbone segmentation process in one aspect of this application.

[0032] Figure 7 This is a schematic diagram of another embodiment of the jawbone segmentation process in one embodiment of this application.

[0033] Figure 8 This is a schematic diagram of one embodiment of the neural network processing procedure in one of the embodiments of this application.

[0034] Figure 9 This is a schematic diagram of another embodiment of the neural network processing procedure in one embodiment of this application.

[0035] Figure 10 This is a schematic diagram of one embodiment of the comparison process in one implementation of this application.

[0036] Figure 11 This is a schematic diagram of another embodiment of the comparison process in one embodiment of this application.

[0037] Figure 12 This is a schematic diagram of the first embodiment of establishing a three-dimensional model in one of the embodiments of this application.

[0038] Figure 13 This is a schematic diagram of a second embodiment of establishing a three-dimensional model according to an embodiment of this application.

[0039] Figure 14 This is a schematic diagram of a third embodiment of establishing a three-dimensional model in one of the embodiments of this application.

[0040] Figure 15 This is a schematic diagram of the fourth embodiment of establishing a three-dimensional model in one embodiment of this application.

[0041] Figure 16 This is a schematic diagram of the cutting process in one embodiment of this application.

[0042] Figure 17 This is a schematic diagram of the cutting process in one embodiment of this application.

[0043] Figure 18 This is a schematic diagram showing the steps of a method in one embodiment of this application. Detailed Implementation

[0044] The present application will now be described in detail with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present application, and any structural, methodological, or functional modifications made by those skilled in the art based on these embodiments are included within the scope of protection of this application.

[0045] It should be noted that the term "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0046] The terms "first," "second," and "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. There is no necessary correlation between the terms "first," etc.; the inclusion of a feature related to "second" in one embodiment does not necessarily mean that the embodiment must include a feature related to "first."

[0047] The main idea of ​​this application is that, when identifying jawbone features, overall segmentation of the target image often leads to poor accuracy in distinguishing detailed features, resulting in jawbone features that do not reflect the actual situation of the subject and cannot be used to assist in medical work. Based on this, the method for determining jawbone features provided in this application first performs preliminary jawbone segmentation on the root bone scan image. The preliminary segmentation result and the root bone scan image itself are used as inputs to a neural network. Based on the distribution characteristics of the overall jawbone and cancellous bone, or the relationship between the two, a dual-channel approach is used to determine the overall jawbone features and cancellous bone features, which can greatly improve the accuracy of feature determination. This application also utilizes the difference between overall jawbone features and cancellous bone features to determine cortical bone features, making feature determination entirely based on the actual situation of the scanned subject, simplifying the processing steps, and balancing speed and accuracy.

[0048] Jawbone features refer to the characteristics corresponding to the structure of the jawbone, which can include overall jawbone features and local jawbone features. When the analysis object includes both the maxilla and mandible, jawbone features can also include features corresponding to the maxilla or features corresponding to the mandible, such as... Figure 1 As shown.

[0049] Classified by tooth position region, local jawbone features can include characteristics of the jawbone region corresponding to the anterior teeth and characteristics of the jawbone region corresponding to the posterior teeth. Classified by the physiological structure of the jawbone, local jawbone features can include characteristics of the cortical bone and the cancellous bone, such as... Figure 1 As shown.

[0050] Figure 1 It is a tomographic image corresponding to the transverse section of the jawbone. Figure 1 The colors shown are only for distinguishing different parts. The calcaneal scan image obtained by implementing this application can be a grayscale image or a color image as shown in the image. Figure 1 The color image shown.

[0051] Figure 1 The diagram shows the maxillary region J1 and the mandibular region J2. The maxillary region J1 includes the cortical bone CO1 and cancellous bone sp1 of the maxilla. The mandibular region J2 includes the cortical bone CO2 and cancellous bone sp2 of the mandible.

[0052] The cortical bone, located on the outer layer of the jawbone, provides protection and support; the cancellous bone, located on the inner layer of the jawbone, is typically spongy and responsible for hematopoiesis. The bone density of the cancellous bone is lower than that of the cortical bone.

[0053] During orthodontic treatment, external forces are applied to move the teeth, and these forces are transmitted to the jawbone. At this time, the cancellous bone is responsible for absorbing and dispersing the force and is highly active in bone remodeling, while the cortical bone provides support and protection. Based on this, the practitioner can adjust the treatment plan according to the different responses of the cancellous and cortical bone to the orthodontic process. For example, the practitioner can adjust the magnitude of the applied force to prevent damage to the cortical bone.

[0054] Jawbone features can be characterized by images. Images can be two-dimensional images or three-dimensional models. Two-dimensional images can be color renderings along various directions or masked images along various directions (specifically, binary images). Three-dimensional models can be stereoscopic models that can represent the distribution features of the jawbone.

[0055] Jawbone features can be characterized using data. This data can be dimensional information corresponding to different dimensions of the jawbone as a whole, positional information of different local parts of the jawbone, or information about the relationships between different parts of the jawbone.

[0056] One embodiment of this application provides a storage medium.

[0057] Storage media can be installed in a computer and store applications. Storage media can be any available medium that the computer can access data from, or it can be a storage device such as a server or data center that integrates one or more available media. Available media can be magnetic media such as floppy disks, hard disks, and magnetic tapes; optical media such as DVDs (Digital Video Discs); or semiconductor media such as SSDs (Solid State Disks).

[0058] In one embodiment, when the application is executed, it implements the steps of a method for determining jawbone features. In a specific embodiment, the method for determining jawbone features includes at least one of the following steps:

[0059] Obtain radicular bone scan images;

[0060] Based on the radicular bone scan image, the jawbone is segmented to determine the segmented jawbone image;

[0061] Using a neural network, the jawbone feature image and the cancellous bone feature image are determined by taking both the root bone scan image and the jawbone segmentation image representing the same jawbone location as input.

[0062] Compare jawbone feature images with cancellous bone feature images, and determine cortical bone feature images based on the differences;

[0063] Determine and output the bone cortex feature information based on the bone cortex feature image.

[0064] The stored content of the storage medium can also be configured based on the method for determining jawbone features provided below.

[0065] In one embodiment, when the application executes, it implements a display method. In a specific embodiment, the display method includes at least one of the following steps:

[0066] A jawbone feature image is presented in a graphical user interface. The jawbone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input. The jawbone feature image is used to determine a cortical bone feature image based on its difference from a cancellous bone feature image.

[0067] A cancellous bone feature image is presented in a graphical user interface. The cancellous bone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input. The cancellous bone feature image is used to determine a cortical bone feature image based on its difference from the jawbone feature image.

[0068] The graphical user interface presents a cortical bone feature image, which is determined by comparing the differences between a jawbone feature image and a cancellous bone feature image. The jawbone feature image and the cancellous bone feature image are determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input.

[0069] The stored content of the storage medium can also be configured based on the method for determining jawbone features in any of the technical solutions provided below.

[0070] like Figure 2 As shown, one embodiment of this application provides an apparatus 100 for determining jawbone features.

[0071] The device 100 for determining jawbone features includes at least one of the following components:

[0072] The first module 11 is used to obtain pedicle scan images;

[0073] The second module 12 is used to segment the jawbone based on the root bone scan image and determine the segmented jawbone image;

[0074] The third module 13 is used to determine the jawbone feature image and the cancellous bone feature image by using a neural network with both the root bone scan image and the jawbone segmentation image representing the same jawbone location as input.

[0075] Module 4, 14, is used to compare jawbone feature images and cancellous bone feature images, and determine cortical bone feature images based on the differences.

[0076] Module 5, 15, is used to determine and output cortical bone feature information based on the cortical bone feature image.

[0077] The first module 11 can obtain pedicle scan images acquired by external devices, or it can perform acquisition operations itself to obtain pedicle scan images.

[0078] In one embodiment, the device 100 for determining jawbone features may also be connected to the first device 200.

[0079] The first device 200 can be disposed outside the device 100 for determining jawbone features, serving as an external device to the device 100 for determining jawbone features. The first device 200 and the device 100 can also be integrated together.

[0080] The first device 200 is used to perform scanning to obtain radicular bone scanning information. The radicular bone scanning information can be the radicular bone scanning image or data related to the radicular bone scanning image. The first device 200 can scan the jawbone area or perform an oral cavity scan.

[0081] The first device 200 can be used to implement a cone-beam annular hood to obtain calcaneal scan images. The calcaneal scan images can be CBCT (cone beam computed tomography) images.

[0082] CBCT images are created by scanning a target volume area with cone-shaped X-rays, obtaining three-dimensional data through a single rotation. CBCT images can display the structure of teeth, bones, and soft tissues, with high pixel or grayscale values, making them suitable for imaging small anatomical areas. CBCT images offer advantages such as high accuracy, ease of assessment of tooth roots and bone, convenient location of impacted teeth, and convenient temporomandibular joint assessment.

[0083] CBCT images can include multiple two-dimensional images corresponding to multiple slices. Slices can correspond to the coronal plane (from anterior to posterior), sagittal plane (from left to right), or cross-section plane (from top to bottom).

[0084] Periatomy scan images can be used to obtain jawbone feature images. For example, one or more convolutional neural networks can be used to process periatomy scan images to extract jawbone features and obtain jawbone feature images.

[0085] Peripheral bone scan images can be used to obtain images of cancellous bone features. For example, one or more convolutional neural networks can be used to process peripheral bone scan images to extract cancellous bone features and obtain images of cancellous bone features.

[0086] Perialar bone scan images can also be used to obtain cortical bone feature images. For example, one or more convolutional neural networks can be used to process perialar bone scan images to obtain jawbone feature images and cancellous bone images, and then cortical bone feature images can be obtained based on both. Or, for example, one or more convolutional neural networks can be used to process perialar bone scan images to extract cortical bone features and obtain cortical bone feature images.

[0087] The apparatus 100 for determining jawbone features can also be configured based on the method for determining jawbone features in any of the technical solutions provided below. Specifically, depending on the relationship between the steps, related steps can be implemented in the same or different modules.

[0088] Electrical or communication connections can be established between the first module 11, the second module 12, the third module 13, the fourth module 14, and the fifth module 15 to enable data transmission.

[0089] One embodiment of this application may also provide a display device.

[0090] The display device includes at least one of the following:

[0091] The sixth module presents a jawbone feature image in a graphical user interface. The jawbone feature image is determined by a neural network based on two inputs: a root bone scan image representing the same jawbone location and a jawbone segmentation image. The jawbone feature image is used to determine a cortical bone feature image based on its difference from a cancellous bone feature image.

[0092] The seventh module presents a cancellous bone feature image in a graphical user interface. The cancellous bone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input. The cancellous bone feature image is used to determine a cortical bone feature image based on its difference from the jawbone feature image.

[0093] The eighth module presents a cortical bone feature image in a graphical user interface. The cortical bone feature image is determined by comparing the differences between a jawbone feature image and a cancellous bone feature image. The jawbone feature image and the cancellous bone feature image are determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input.

[0094] The display device can also be configured based on the display method of any of the technical solutions provided below. Specifically, depending on the relationship between the steps, related steps can be implemented in the same or different modules.

[0095] Electrical or communication connections can be established between the sixth, seventh, and eighth modules to enable data transmission.

[0096] The device, or its modules or units, may be implemented by a computer chip or physical entity, or by a product with corresponding functions. While the device is described in terms of multiple modules, in some embodiments, the functions of the modules may be implemented in one or more software or hardware components.

[0097] One embodiment of this application provides an electronic device 200, such as... Figure 3 As shown.

[0098] The electronic device 200 may be a computer, mobile phone, tablet computer, etc., and this application does not limit the specific type of the electronic device 200.

[0099] Electronic device 200 includes at least one processor 21, at least one memory 22 and communication bus 33.

[0100] At least one processor 21 and at least one memory 22 communicate with each other via a communication bus 23.

[0101] Memory 22 is used to store application programs.

[0102] In one embodiment, the processor 21 is configured to implement the steps of a method for determining jawbone features when executing an application stored in the memory 22.

[0103] In one specific embodiment, the method for determining jawbone features includes at least one of the following steps:

[0104] Obtain radicular bone scan images;

[0105] Based on the radicular bone scan image, the jawbone is segmented to determine the segmented jawbone image;

[0106] Using a neural network, the jawbone feature image and the cancellous bone feature image are determined by taking both the root bone scan image and the jawbone segmentation image representing the same jawbone location as input.

[0107] Compare jawbone feature images with cancellous bone feature images, and determine cortical bone feature images based on the differences;

[0108] Determine and output the bone cortex feature information based on the bone cortex feature image.

[0109] The steps for determining jawbone features can also be configured based on any of the technical solutions provided below.

[0110] In one embodiment, the processor 21 is configured to implement a display method when executing an application stored in the memory 22.

[0111] In one specific embodiment, the display method includes at least one of the following steps:

[0112] A jawbone feature image is presented in a graphical user interface. The jawbone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input. The jawbone feature image is used to determine a cortical bone feature image based on its difference from a cancellous bone feature image.

[0113] A cancellous bone feature image is presented in a graphical user interface. The cancellous bone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input. The cancellous bone feature image is used to determine a cortical bone feature image based on its difference from the jawbone feature image.

[0114] The graphical user interface presents a cortical bone feature image, which is determined by comparing the differences between a jawbone feature image and a cancellous bone feature image. The jawbone feature image and the cancellous bone feature image are determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input.

[0115] The steps of the display method can also be configured based on any of the technical solutions provided below.

[0116] In one embodiment, the communication bus 23 may include any number of buses and bridge circuits. In some embodiments, in addition to connecting the processor and memory, the communication bus may also be used to connect peripheral devices or other peripheral circuits.

[0117] In one embodiment, the electronic device 200 may include a user interface 24 and at least one network interface 25. The user interface 23 may include a display, keyboard, mouse, trackball, click wheel, buttons, a touchpad, or a touch screen, etc.

[0118] like Figure 4 As shown, one embodiment of this application provides a method for determining jawbone features.

[0119] The application corresponding to this method can be mounted in an electronic device, a device for determining jawbone features and / or a storage medium, or in the carrier of the display method provided below, or in a display device, to achieve the corresponding technical effect.

[0120] Methods for determining jawbone features may include at least one of the following steps.

[0121] Step S11: Obtain a radicular bone scan image.

[0122] A root bone scan image can be an image used to characterize bones and / or tooth roots, which can be obtained by scanning the subject.

[0123] Periatomy scans can be used to determine jawbone features. Periatomy scans can be images used to characterize the jawbone. Periatomy scans can also be used to determine tooth root features. Periatomy scans can also be images used to characterize tooth roots.

[0124] A calcaneal bone scan image can be a tomographic image. A tomographic image can be a two-dimensional image or a combination of two-dimensional images. Specifically, CT (Computed Tomography) technology can be used to scan the subject layer by layer using X-rays, obtaining multiple tomographic images corresponding to different locations. The tomographic sections can correspond to the coronal plane (from front to back), sagittal plane (from left to right), or cross-section plane (from top to bottom).

[0125] When the tomographic section is transverse, the calcaneal scan image can be obtained by scanning layer by layer along the vertical direction. In this case, the calcaneal scan image can be obtained as follows: Figure 5 As shown in (a), the tissue structure is illustrated at a cross-section in the vertical direction. In radicular bone scan images, the pixel or grayscale values ​​of hard tissues such as bones and teeth can be higher than those of soft tissues.

[0126] Root bone scan images can be in the form of a two-dimensional image sequence or a two-dimensional image set. The image sequence or image set can include multiple images, each corresponding to a tomographic image at a different location along the scanning direction, such as... Figure 5 As shown in (b). When further processing the calcaneal scan image, the processed image can correspond one-to-one with the original calcaneal scan image; the processed images can form another image sequence or image set, with the number of images before and after processing corresponding, and the positions of the tested object represented by the images before and after processing corresponding.

[0127] The radicular bone scan image can be a sequence of two-dimensional tomographic images of the jawbone region.

[0128] Periatomy images include cone-beam computed tomography (CBCT) images. Periatomy images can be composed of cone-beam computed tomography (CBCT) images. CBCT images are obtained through cone-beam X-ray scanning and are particularly suitable for examining hard tissue structures such as the jawbone and tooth roots. CBCT images provide three-dimensional image information of the jawbone structure of the subject being examined.

[0129] When the calcaneal scan image is a CBCT image, the method for determining jawbone features provided in this application can also overcome the complex situation of uneven gray-level distribution, artifacts and low signal-to-noise ratio in CBCT images, and improve the accuracy of jawbone feature determination.

[0130] The calcaneal scan image obtained in step S11 can be a normalized CBCT image.

[0131] Step S12: Based on the root bone scan image, perform jawbone segmentation to determine the jawbone segmentation image.

[0132] Jawbone segmentation can be performed by distinguishing the region representing the jawbone in a calcaneal scan image from regions representing other parts of the jawbone in the same image. This process can also be defined as identifying the jawbone region as the region of interest and segmenting that region within the calcaneal scan image.

[0133] Jaw segmentation can also be performed by separating the region representing the maxilla from the region representing the mandible in the radicular bone scan image.

[0134] Compared to segmenting specific tissue structures in the jawbone (e.g., cortical bone, cancellous bone, etc.), the regional segmentation or differentiation of the upper and lower jaws performed in step S12 can be understood as coarse segmentation.

[0135] The jaw segmentation image can include a mask image corresponding to the maxillary region and a mask image corresponding to the background. The mask image can be a binary image, where 1 represents the foreground and 0 represents the background.

[0136] The jaw segmentation image can include a mask image corresponding to the mandibular region and a mask image corresponding to the background.

[0137] The method for determining jawbone features provided in this application may include: jawbone segmentation using a neural network.

[0138] The input to this neural network can be a root bone scan image. The neural network can include three output channels: the first channel outputs a mask image corresponding to the maxilla, the second channel outputs a mask image corresponding to the mandible, and the third channel outputs a mask image corresponding to the background.

[0139] This neural network can include a fully convolutional deep neural network. The neural network is used to achieve global segmentation of pedicle scan images. For example, the neural network can be a UNet, Atten-UNet, UNet++, or similar architecture.

[0140] Jaw segmentation images can simultaneously include information for the corresponding maxillary region (lighter colored area) and information for the corresponding mandibular region (darker colored area), such as... Figure 6 As shown.

[0141] The calcaneal scan image can be a two-dimensional image. Based on this, each calcaneal scan image in the calcaneal scan image sequence can be segmented into the jawbone separately to obtain multiple two-dimensional jawbone segmentation images. These multiple jawbone segmentation images can then be combined in the same order as the calcaneal scan image sequence to obtain a jawbone segmentation image sequence that represents the three-dimensional jawbone segmentation result.

[0142] At this point, if a neural network is used for jawbone segmentation, the neural network can be a two-dimensional deep fully convolutional neural network.

[0143] The calcaneal scan image can be a three-dimensional image. Based on this, the jawbone can be segmented from the calcaneal scan image to obtain a three-dimensional segmented jawbone image.

[0144] At this point, if a neural network is used for jawbone segmentation, the neural network can be a three-dimensional deep fully convolutional neural network.

[0145] In one embodiment, the method for determining jawbone features provided in this application may include the steps of: using a neural network to segment the maxilla and mandible based on a root bone scan image, and determining a segmented image of the maxilla representing the maxilla and a segmented image of the mandible representing the mandible.

[0146] This step can be included in step S12; when implementing step S12, this step can be implemented in detail.

[0147] The determined segmented images of the maxilla and mandible can be obtained as follows: Figure 6 As shown, the maxillary and mandibular regions are presented in the same jawbone segmentation image.

[0148] The determined segmented images representing the maxilla and mandible can be presented as two separate segmented images. When the radicular bone scan image sequence contains multiple radicular bone scan images, segmenting the jawbone can yield a segmented image sequence for the corresponding maxilla and a segmented image sequence for the corresponding mandible, such as... Figure 7 As shown.

[0149] When calcaneal scan images are used to compose a calcaneal scan image sequence, and the calcaneal scan images are transverse tomographic images, multiple calcaneal scan images have a predetermined order in the scanning direction (e.g., the vertical direction). After jawbone segmentation of the calcaneal scan images (i.e., the calcaneal scan image sequence), the determined jawbone segmentation images correspond one-to-one with the calcaneal scan images in that scanning direction, and correspond to different jawbone positions with respect to that scanning direction. The number of images in the calcaneal scan image sequence is equal to the number of images in the jawbone segmentation images.

[0150] Step S13: Using a neural network, the root bone scan image and the jaw segmentation image representing the same jawbone location are used as inputs to determine the jawbone feature image and the cancellous bone feature image.

[0151] The segmented image of the jawbone is determined based on the radicular bone scan image. The segmented image of the jawbone corresponds to the radicular bone scan image; the segmented image of the jawbone and the radicular bone scan image are located in the same coordinate system.

[0152] The radicular bone scan image and the jawbone segmentation image represent the same jawbone location. This can be achieved by: the radicular bone scan image corresponding to the maxilla of the subject being tested, and the jawbone segmentation image corresponding to the maxilla being used together to determine the jawbone feature image and cancellous bone feature image of the corresponding maxilla; or, the radicular bone scan image and the jawbone segmentation image corresponding to the mandible being used together to determine the jawbone feature image and cancellous bone feature image of the corresponding mandible.

[0153] The root bone scan image and the jawbone segmentation image represent the same jawbone location. They can be: a root bone scan image corresponding to a first region of the jawbone of the subject, and a jawbone segmentation image corresponding to the same first region, which are used together to determine the jawbone feature image and cancellous bone feature image corresponding to the first region.

[0154] The radicular bone scan images constitute a radicular bone scan image sequence, and the jawbone segmentation images constitute a jawbone segmentation image sequence. The radicular bone scan image corresponding to the first position in the scanning direction in the radicular bone scan image sequence, and the jawbone segmentation image corresponding to the same first position in the jawbone segmentation image sequence, are used together to determine the jawbone feature image and cancellous bone feature image corresponding to the first position.

[0155] This neural network can be a fully convolutional deep neural network. Specifically, it can be a multi-label fully convolutional deep neural network, which can predict multiple labels simultaneously for each pixel or voxel using a fully convolutional network (FCN). Fully convolutional neural networks process inputs of arbitrary size within a certain range and output results with the same spatial resolution, facilitating further processing. Combined with its multi-label feature, it can predict the probabilities of different labels through multiple output channels or branches.

[0156] In this application, when the neural network is a fully convolutional deep neural network, the neural network can simultaneously output jawbone feature images and cancellous bone feature images through multiple output channels, and make the jawbone feature images and cancellous bone feature images have the same spatial structure.

[0157] This neural network can be trained using binary cross-entropy as a loss function.

[0158] The neural network can include two input channels. The first input channel is used to input either a radicular bone scan image or a processed radicular bone scan image; the second input channel is used to input either a segmented jawbone image or a processed segmented jawbone image.

[0159] The processed radicular bone scan image can be a cropped radicular bone scan image containing only the region of interest; similarly, the processed jawbone segmentation image can also be a cropped jawbone segmentation image containing only the region of interest. The region of interest in the radicular bone scan image and the jawbone segmentation image are consistent.

[0160] The jawbone segmentation image can be the image obtained by coarse segmentation of the corresponding root bone scan image.

[0161] Compared to the segmented image of the jawbone, step S13 distinguishes the features of the cancellous bone, which can be understood as fine segmentation.

[0162] Specifically, the radicular bone scan image (e.g., ...) input to the first input channel Figure 8 (Included in the radicular bone scan image sequence set11), which can be a normalized radicular bone scan image containing the corresponding local region of interest in the maxilla; the jawbone segmentation image input to the second input channel (e.g., Figure 8 (Included in the jawbone segmentation image sequence set21), which can be a normalized jawbone segmentation image containing a local region of interest corresponding to the maxilla. Alternatively, the root bone scan image input to the first input channel corresponds to the mandibular region (e.g., Figure 9 The radicular bone scan image is included in the radicular bone scan image sequence set12), and the jawbone segmentation image input to the second input channel corresponds to the mandibular region (e.g., Figure 9 The jawbone segmentation images are contained in the jawbone segmentation image sequence set22.

[0163] The neural network can include two output channels. The first output channel is used to output a jawbone feature image, and the second output channel is used to output a cancellous bone feature image.

[0164] Specifically, the jawbone feature image output by the first output channel can be a jawbone feature image corresponding to the maxilla and having a binary mask image format (e.g., Figure 8 (Included in the jawbone feature image sequence set31); the cancellous bone feature image output by the second output channel can be a cancellous bone feature image corresponding to the maxillary region and in the form of a binary masked image (e.g. Figure 8 (Included in the cancellous bone feature image sequence set41). Alternatively, the jawbone feature image output by the first output channel corresponds to the mandibular region (e.g., Figure 9The jawbone feature image is contained in the jawbone feature image sequence set32), and the cancellous bone feature image output by the second input channel corresponds to the mandibular region (e.g., Figure 9 The cancellous bone feature images are contained in the cancellous bone feature image sequence set42.

[0165] In the masked image, 1 represents the foreground and 0 represents the background.

[0166] The calcaneal scan images and jawbone segmentation images can be two-dimensional images. Based on this, each calcaneal scan image in the calcaneal scan image sequence set1, and its corresponding jawbone segmentation image in the jawbone segmentation image sequence set2, can be processed separately or sequentially using a neural network to obtain multiple two-dimensional jawbone feature images and corresponding cancellous bone feature images. Then, following the same order as the calcaneal scan image sequence and jawbone segmentation image sequence, the multiple jawbone feature images and cancellous bone feature images can be combined to obtain the jawbone feature image sequence set3, representing the results of three-dimensional feature extraction of the jawbone, and the cancellous bone feature image sequence set4, representing the results of three-dimensional feature extraction of the cancellous bone.

[0167] At this point, the neural network can be a two-dimensional deep fully convolutional neural network.

[0168] Both the radicular bone scan image and the jawbone segmentation image can be three-dimensional images. Based on this, a neural network can be used to process both to obtain a three-dimensional jawbone feature image and a corresponding cancellous bone feature image. Alternatively, the three-dimensional radicular bone scan image and the jawbone segmentation image can be divided into several overlapping or non-overlapping three-dimensional sub-regions. Each three-dimensional sub-region of the radicular bone scan image, along with its corresponding three-dimensional sub-region of the jawbone segmentation image, is input into a neural network for processing to obtain a three-dimensional sub-region of the jawbone feature image corresponding to that sub-region, and a corresponding three-dimensional sub-region of the cancellous bone feature image. Then, the three-dimensional sub-regions of the jawbone feature image are combined to obtain a jawbone feature image representing the result of three-dimensional feature extraction; similarly, the three-dimensional sub-regions of the cancellous bone feature image are combined to obtain a cancellous bone feature image representing the result of three-dimensional feature extraction.

[0169] At this point, the neural network can be a three-dimensional deep fully convolutional neural network.

[0170] Thus, by using a "coarse-to-fine" feature determination method, the accuracy of determining jawbone features and cancellous bone features can be significantly improved.

[0171] The differences between radicular bone scan images, jawbone segmentation images, and jawbone feature images:

[0172] A radicular bone scan image can be an image obtained by scanning the subject and containing the most complete hard and / or soft tissue features of the jawbone. The jawbone structural features are mixed with other features and require professional analysis or further processing to extract the specific features of the jawbone.

[0173] Jaw segmentation images can be "coarse segmentation" results obtained by directly processing root bone scan images based on global jaw segmentation. Jaw segmentation images at least distinguish the corresponding maxilla and mandible parts in the root bone scan images, indicating the distribution area and relationship of the maxilla and mandible. However, the specific structures in each group of jaws still need further analysis or processing.

[0174] Jawbone feature images can be the result of "fine segmentation" obtained after processing radicular bone scan images. The distribution area of ​​the jawbone region determined in the jawbone feature image is more accurate than that in the jawbone segmentation image, and the jawbone feature image includes the corresponding cancellous bone feature image.

[0175] In step S12, the jawbone is segmented. After separating the region corresponding to the maxilla and the region corresponding to the mandible in the root bone scan image, the steps of determining the structural features of the corresponding maxilla and mandible can be performed simultaneously or sequentially.

[0176] For example, in step S12: the segmented image of the maxilla and the segmented image of the mandible are obtained. If they are executed sequentially, then in step S13: using a neural network, with the root bone scan image and the segmented image of the mandible representing the same position of the maxilla as input, the corresponding maxillary feature image and cancellous bone feature image are determined; then, using the same or another neural network, with the root bone scan image and the segmented image of the mandible representing the same position of the mandible as input, the corresponding mandibular feature image and cancellous bone feature image are determined.

[0177] The neural network used to process images of the corresponding maxillary region and the neural network used to process images of the corresponding mandibular region can have the same configuration or different configurations. Based on the structural differences between the maxillary and mandibular regions, it is preferable to use two different neural networks and train them separately.

[0178] In one embodiment, the method for determining jawbone features provided in this application may include the steps of: using a neural network to extract features from a root bone scan image with reference to a segmented jawbone image, and determining a jawbone feature image and a cancellous bone feature image.

[0179] Considering that the location and distribution area of ​​the jawbone have been determined in the segmented image, using the segmented image as a reference for feature extraction can enhance the neural network's ability to extract features from the foreground region and improve the accuracy of the determined jawbone feature image and cancellous bone feature image.

[0180] Specifically, the method for determining jawbone features provided in this application enables a neural network to extract features from a root bone scan image using a segmented jawbone image as prior knowledge.

[0181] This step can be included in step S13; when implementing step S13, this step can be implemented in detail.

[0182] Step S14: Compare the jawbone feature image and the cancellous bone feature image, and determine the cortical bone feature image based on the differences.

[0183] The jawbone structure mainly consists of the cancellous bone and the cortical bone. When determining the characteristics of the cancellous bone and jawbone, the cortical bone characteristics can be determined based on the differences between the jawbone characteristics and the cancellous bone characteristics. Since the cortical bone is usually thin (especially the maxillary cortex), directly predicting the cortical bone results in class imbalance, leading to low segmentation accuracy. However, cortical bone characteristics determined by comparing differences have higher accuracy, and the determination process is computationally less and more efficient.

[0184] For the maxillary region, such as Figure 10 As shown, step S14 can be to compare the corresponding maxillary bone feature image fig31 with the corresponding maxillary cancellous bone feature image fig41, and determine the corresponding maxillary cortical bone feature image fig51 based on the differences.

[0185] The maxillary bone feature image fig31 can be included in the maxillary bone feature image sequence set31; the maxillary cancellous bone feature image fig41 can be included in the maxillary cancellous bone feature image sequence set41.

[0186] For the lower jaw area, such as Figure 11 As shown, step S14 can be to compare the jawbone feature image fig32 of the corresponding mandible with the cancellous bone feature image fig42 of the corresponding mandible, and determine the cortical bone feature image fig52 of the corresponding mandible based on the difference.

[0187] The corresponding mandibular bone feature image fig32 can be included in the corresponding mandibular bone feature image sequence set32; the corresponding mandibular bone cancellous feature image fig42 can be included in the corresponding mandibular bone cancellous feature image sequence set42.

[0188] The jawbone feature image sequence set3 contains multiple jawbone feature images fig3, and the cancellous bone feature image sequence set4 contains multiple cancellous bone feature images fig4. Jawbone feature images fig3 and cancellous bone feature images fig4 representing the same jawbone location are compared, and the corresponding cortical bone feature image fig5 is determined based on the differences.

[0189] In one embodiment, the method for determining jawbone features provided in this application may include the steps of: performing pixel-by-pixel subtraction between a jawbone feature image and a cancellous bone feature image to determine a cortical bone feature image.

[0190] This step can be included in step S14; when implementing step S14, this step can be implemented in detail.

[0191] The jawbone feature image and the cancellous bone feature image can be a masked image; the masked image can be a binary image or a grayscale image. Specifically, the jawbone feature image and the cancellous bone feature image can be a binary masked image, where the pixel value in the image is 0 or 255.

[0192] For each pixel position (x, y), the following operation can be performed:

[0193] fig5(x,y)=fig3(x,y)–fig4(x,y).

[0194] In this way, the cortical bone feature image can be determined based on the difference between the jawbone feature image and the cancellous bone feature image.

[0195] Step S15: Determine and output the bone cortex feature information based on the bone cortex feature image.

[0196] The method for determining jawbone features provided in this application can directly output the cortical bone feature image obtained in step S14 as the cortical bone feature information to present the cortical bone features; or it can output at least one of the cortical bone feature image, cancellous bone feature image and jawbone feature image.

[0197] The method for determining jawbone features provided in this application can determine the data information contained in a bone cortex feature image and output the data information as the bone cortex feature information. For example, at least one of the following can be determined from the bone cortex feature image: bone cortex size information (e.g., shape, thickness), resorption status, etc. Alternatively, bone cortex bone density information can be determined by combining the bone cortex feature image and the calcaneal scan image.

[0198] In one embodiment, the method for determining jawbone features provided in this application may include the steps of: determining and outputting cortical bone size information based on a cortical bone feature image.

[0199] This step can be included in step S15; when implementing step S15, this step can be implemented in detail.

[0200] The method for determining jawbone features provided in this application can also determine the data information contained in a cancellous bone feature image and output the data information. For example, at least one of the following cancellous bone features can be determined from the cancellous bone feature image: structural information (e.g., trabecular morphology, trabecular arrangement, trabecular spacing), thickness information, etc.

[0201] In one embodiment, the method for determining jawbone features provided in this application may include the steps of: determining and outputting bone density information based on a cancellous bone feature image and a root bone scan image.

[0202] This step can be included in step S15; when implementing step S15, this step can be implemented in detail.

[0203] When the cortical bone feature image obtained in step S14 is a two-dimensional image, the method for determining jawbone features provided in this application can establish a three-dimensional model containing cortical bone feature information based on a sequence of cortical bone feature images composed of multiple cortical bone feature images, and output this as cortical bone feature information.

[0204] In one embodiment, the method for determining jawbone features provided in this application may include the step of: establishing a three-dimensional model of the bone cortex based on several bone cortex feature images corresponding to several jawbone locations.

[0205] This step can be included in step S15; when implementing step S15, this step can be implemented in detail.

[0206] The bone cortical feature images used to build a three-dimensional model of the bone cortex can be all or part of a sequence of bone cortical feature images.

[0207] When the jawbone feature image is a two-dimensional image, the method for determining jawbone features provided in this application can establish and output a three-dimensional model 3d-3 containing jawbone features based on a jawbone feature image sequence set3 composed of multiple jawbone feature images.

[0208] like Figure 12 As shown, a 3D model (3d-31) of the corresponding maxillary jawbone features can be reconstructed from the corresponding maxillary jawbone feature image sequence (set31). Figure 13 As shown, a three-dimensional model 3d-32 of the corresponding mandibular bone features can be obtained by three-dimensional reconstruction based on the corresponding mandibular bone feature image sequence set32.

[0209] In one embodiment, the method for determining jawbone features provided in this application may include the steps of: establishing a three-dimensional model of the jawbone based on several jawbone feature images corresponding to several jawbone locations.

[0210] This step can be included in step S15; when implementing step S15, this step can be implemented in detail.

[0211] The jawbone feature images used to create a three-dimensional model of the jawbone can be all or part of a sequence of jawbone feature images.

[0212] When the cancellous bone feature image is a two-dimensional image, the method for determining jawbone features provided in this application can establish and output a three-dimensional model 3d-4 containing cancellous bone features based on a sequence of cancellous bone feature images set4 composed of multiple cancellous bone feature images.

[0213] like Figure 14 As shown, a 3D model (3d-41) of the cancellous bone features of the corresponding maxilla can be obtained by 3D reconstruction based on the image sequence set41 of the cancellous bone features of the corresponding maxilla. Figure 15 As shown, a three-dimensional model 3d-42 of the cancellous bone features of the corresponding mandible can be obtained by three-dimensional reconstruction based on the image sequence set42 of the cancellous bone features of the corresponding mandible.

[0214] In one embodiment, the method for determining jawbone features provided in this application may include the step of: establishing a three-dimensional model of cancellous bone based on several cancellous bone feature images corresponding to several jawbone locations.

[0215] This step can be included in step S15; when implementing step S15, this step can be implemented in detail.

[0216] The cancellous bone feature images used to build a three-dimensional model of cancellous bone can be all or part of a sequence of cancellous bone feature images.

[0217] At least one of the jawbone features, cortical bone features, and cancellous bone features can also be displayed on the oral scan model or other three-dimensional models to serve as a reminder and indication.

[0218] The method for determining jawbone features provided in this application can obtain an oral scan model and display the cortical bone feature information at the oral scan model.

[0219] An oral scan model can correspond to the same test subject as a calcaneal scan image; an oral scan model can correspond to the same test subject as cortical bone feature information.

[0220] In one embodiment, the method for determining jawbone features provided in this application may include the steps of:

[0221] Step P11: Obtain the oral scan model;

[0222] Step P12 involves performing coordinate transformation on the cortical bone feature information to display it on the oral scan model.

[0223] Step P12 can be included in step S15; when step S15 is implemented, step P12 can be specifically implemented. Step P11 can be implemented at any time before step P12.

[0224] In step P12, coordinate transformation can also be performed on the cortical bone feature image.

[0225] The coordinate transformation method may include at least one of the following steps: determining the calcaneal model based on the calcaneal scan image; registering the calcaneal model and the oral scan model to obtain coordinate transformation information; and performing coordinate transformation on the cortical bone feature information based on the coordinate transformation information to display the cortical bone feature information at the oral scan model.

[0226] In step P12, the cortical bone feature information can be combined with the intraoral scan model for display. Specifically, the cortical bone feature information can be combined and displayed according to the correspondence between the position of the crowns, gingiva, etc., in the intraoral scan model. In this way, the cortical bone feature information will be displayed within the area of ​​the intraoral scan model, providing a reference for comparison.

[0227] By implementing step P12, the areas of cortical bone features in the oral scan model can be highlighted, or information such as cortical bone size can be annotated in the oral scan model to provide guidance.

[0228] The method for determining jawbone features provided in this application can obtain an oral scan model and display the cancellous bone feature information at the oral scan model.

[0229] The characteristics of cancellous bone can be determined based on images of cancellous bone features.

[0230] An oral scan model can correspond to the same test subject as a calcaneal scan image; an oral scan model can correspond to the same test subject as cancellous bone feature information.

[0231] In one embodiment, the method for determining jawbone features provided in this application may include the steps of:

[0232] Step P21: Determine the characteristic information of cancellous bone based on the cancellous bone characteristic image;

[0233] Step P22, obtain the oral scan model;

[0234] Step P23: Perform coordinate transformation on the cancellous bone feature information to display the cancellous bone feature information at the oral scan model.

[0235] Step P21 can be included in step S14; when implementing step S14, step P21 can be specifically implemented.

[0236] Step P23 can be included in step S15; when step S15 is implemented, step P23 can be specifically implemented. Step P22 can be implemented at any time before step P23.

[0237] In step P23, coordinate transformation can also be performed on the cancellous bone feature image.

[0238] The coordinate transformation method may include at least one of the following steps: determining the calcaneal model based on the calcaneal scan image; registering the calcaneal model and the oral scan model to obtain coordinate transformation information; and performing coordinate transformation on the cancellous bone feature information based on the coordinate transformation information to display the cancellous bone feature information at the oral scan model.

[0239] In step P23, the cancellous bone feature information can be combined with the intraoral scan model for display. Specifically, the combination can be based on the correspondence between the cancellous bone feature information and the positions of the crowns, gingiva, etc., in the intraoral scan model. In this way, the cancellous bone feature information will be displayed within the area of ​​the intraoral scan model, providing a reference for comparison.

[0240] By implementing step P23, the areas of cancellous bone features in the oral scan model can be highlighted, or bone density information such as cancellous bone can be annotated in the oral scan model to provide indication.

[0241] In step S13 above, the corresponding radicular bone scan image and jawbone segmentation image can be images containing the jawbone region obtained through cropping. Step S13 may include a cropping step of the radicular bone scan image, or may include a cropping step of both the radicular bone scan image and the jawbone segmentation image.

[0242] The jawbone segmentation image obtained in step S12 can be used to determine the region where the jawbone is located. Since the jawbone segmentation image corresponds to the root bone scan image, the region where the jawbone is located can be determined in the root bone scan image and cropped accordingly.

[0243] In one embodiment, such as Figure 16 The method for determining jawbone features provided in this application may include the following steps:

[0244] Step M11: Obtain a root bone scan image and a segmented image of the jawbone at the same jawbone location in the first direction;

[0245] Step M12: Based on the segmented jawbone image, determine the region representing the jawbone area in the root bone scan image;

[0246] Step M13: Crop the radicular bone scan image.

[0247] Combination Figure 17In step M11, the first direction D1 is perpendicular to the display plane of the radicular bone scan image and the jawbone segmentation image. The radicular bone scan image is contained in the original radicular bone scan image sequence set01, and the jawbone segmentation image is contained in the original jawbone segmentation image sequence set02.

[0248] The radicular bone scan image and the segmented jawbone image can be two-dimensional images.

[0249] The display plane can be the distribution plane of the area shown in the root bone scan image and the jawbone segmentation image in the actual jawbone area.

[0250] The calcaneal scan image can specifically be a tomographic scan image. Based on this, the first direction D1 can be a direction perpendicular to the tomographic plane or the scanning direction of the tomographic scan. The display plane can be the tomographic plane of the tomographic scan image. The tomographic plane can be a transverse section, and the first direction D1 can be along the vertical direction.

[0251] The jawbone segmentation image is determined based on the root bone scan image. The first direction D1 is perpendicular to the plane where the root bone scan image is located, therefore the first direction D1 is perpendicular to the plane where the jawbone segmentation image is located.

[0252] The original calcaneal scan image sequence set01 includes several original calcaneal scan images. Different original calcaneal scan images correspond to different positions on the first direction D1, and also to different jawbone positions. Similarly, the original jawbone segmentation image sequence set02 contains different original jawbone segmentation images that correspond to different positions on the first direction D1.

[0253] Original root bone scan images and original jaw segmentation images corresponding to the same jawbone position and the same position on the first direction D1 exist in pairs. When executing step M11, multiple sets of original root bone scan images and original jaw segmentation images are confirmed.

[0254] After obtaining the original jawbone segmentation image based on the original radicular bone scan image, the jawbone segmentation image records the distribution area of ​​the jawbone and can be displayed as follows: Figure 17 The selection box for each image in the original jawbone segmentation image sequence set02.

[0255] Based on the regions representing the jawbone area determined by the original jawbone segmentation image, and the correspondence between the original jawbone segmentation image and the original radicular bone scan image, the radicular bone scan image can be cropped (e.g., ...). Figure 17 The first cropping in the image increases the proportion of the jawbone region in the radicular bone scan image, or makes the radicular bone scan image include only the region representing the jawbone region.

[0256] The cropped radicular bone scan images can be used to form a radicular bone scan image sequence set1. The radicular bone scan images in the processed radicular bone scan image sequence set1 can be used to perform steps S11 to S15, for example, to perform jawbone segmentation to obtain a jawbone segmentation image with a larger proportion of the jawbone area, or as input to a neural network to obtain better jawbone feature images, cancellous bone feature images, and cortical bone feature images.

[0257] Taking the mandible as an example, the original root bone scan image sequence set012 and the original jawbone segmentation image sequence set022 of the corresponding mandible can be obtained. The latter is used to determine the region representing the jawbone area, and the former is cropped to obtain the cropped root bone scan image sequence set12 of the corresponding mandible.

[0258] The procedure for the maxilla is similar and will not be repeated here.

[0259] The region representing the jawbone can also be replaced with other regions of interest.

[0260] In one embodiment, the method for determining jawbone features provided in this application may include the steps of: determining the region representing the jawbone area in a segmented jawbone image; and determining the region representing the jawbone area in a root bone scan image based on the region representing the jawbone area in the segmented jawbone image.

[0261] In one specific embodiment, the region representing the jawbone can be characterized using a selection box. The selection box can be a two-dimensional selection box, or it can be... Figure 17 The three-dimensional selection box shown.

[0262] In one specific embodiment, the method for determining jawbone features provided in this application may include the steps of: determining the region representing the jawbone area in the jawbone segmentation image and obtaining a first selection box corresponding to the jawbone area; adjusting the size of the first selection box according to a preset expansion value to obtain a second selection box; determining the region representing the jawbone area in the root bone scan image according to the second selection box, and cropping the root bone scan image accordingly.

[0263] Adjusting the size of the first selection box can expand it to create a second selection box with a larger volume or area than the first selection box.

[0264] When the first selection box is a two-dimensional rectangle, it can be determined based on the coordinates of its diagonal vertices. Adjusting the size of the first selection box can be achieved by adjusting the coordinates of at least one of its two diagonal vertices.

[0265] When the first selection box is a 3D rectangle, it can be determined based on the coordinates of its diagonal vertices. Adjusting the size of the first selection box can be achieved by adjusting the coordinates of at least one of its two diagonal vertices.

[0266] For example, the first selection box includes a first vertex v1 and a second vertex v2. The coordinates of the first vertex v1 are (x1, y1, z1), and the coordinates of the second vertex v2 are (x2, y2, z2). Based on this, the coordinates of the two vertices can be adjusted to expand the first selection box into a second selection box. The coordinates of the new first vertex v1' are (x1-margin_x, y1-margin_y, z1-margin_z), and the coordinates of the new second vertex v2' are (x2+margin_x, y2+margin_y, z2+margin_z).

[0267] The reason for adjusting the size of the selection box to expand it is to include part of the area around the jawbone (background), which helps improve the recognition accuracy of the jawbone (foreground) area.

[0268] The magnitude of the expansion (i.e., the aforementioned margin_x, margin_y, and margin_z) can be preset. In one embodiment, the preset expansion value is set as follows: the magnitude by which the first selection box is expanded is a preset multiple of the corresponding side length of the first selection box. Specifically, the preset value is 0.2.

[0269] For example, when adjusting the size of the x-coordinate direction, the expansion is equal to 0.2 times the side length of the x-coordinate direction of the first x-selection box (e.g., |x2-x1|). The same applies to other coordinate directions.

[0270] For example, the default extended value can be set as follows:

[0271] margin_x = 0.2 × (x2 - x1);

[0272] margin_y = 0.2 × (y2 - y1);

[0273] margin_z = 0.2 × (z2 - z1).

[0274] Once the second selection box is determined, it can characterize the region of the jawbone formed after the boundary expansion. Based on the second selection box, the region of the jawbone can be determined in the radicular bone scan image, and then a first cropping can be performed on the radicular bone scan image based on the determined region.

[0275] In some embodiments, the segmented jawbone image may also be cropped. By performing the first and second cropping, the resulting processed radicular bone scan image and jawbone segmentation image can be directly used in the aforementioned step S13 to directly determine the jawbone feature image and cancellous bone feature image.

[0276] In one specific embodiment, the method for determining jawbone features provided in this application may include the steps of: determining the region representing the jawbone area in a segmented jawbone image; cropping the segmented jawbone image; and determining the region representing the jawbone area in a root bone scan image based on the region representing the jawbone area in the segmented jawbone image.

[0277] The same bounding box method described above can be used to determine the regions representing the jawbone area in a segmented jawbone image. These bounding boxes can be obtained through connected component analysis.

[0278] Based on the determined second selection box, the original jawbone segmentation image can be cropped a second time, and the generated jawbone segmentation image is used to form the jawbone segmentation image sequence set2. The jawbone segmentation images in the processed jawbone segmentation image sequence set2 can be used to perform steps S11 to S15.

[0279] Taking the mandible as an example, the original mandibular segmentation image sequence set022 of the corresponding mandible can be obtained. The second selection box is determined using it, and the second cropping is performed on the mandibular segmentation image sequence set022 of the corresponding mandible to obtain the cropped mandibular segmentation image sequence set22 of the corresponding mandible.

[0280] The procedure for the maxilla is similar and will not be repeated here.

[0281] like Figure 18 As shown, one embodiment of this application provides a display method.

[0282] The application or instructions corresponding to this method can be mounted on an electronic device, a device for determining jawbone features and / or a storage medium, or on a carrier for implementing the display method, to achieve the corresponding technical effect.

[0283] The display method may specifically include at least one of the following steps.

[0284] Step S21: Present the jawbone feature image in the graphical user interface.

[0285] Jawbone feature images can be three-dimensional models or two-dimensional images.

[0286] When the jawbone feature image is a three-dimensional model, it can be as follows: Figure 12 The three-dimensional model 3d-31 corresponding to the maxillary bone features shown can also be as follows: Figure 13 The three-dimensional model 3d-32 shown corresponds to the jawbone features of the mandible, and can also be a combination of the corresponding three-dimensional models of the upper and lower jaws.

[0287] When the jawbone feature image is a three-dimensional model, it can also be as follows: Figure 12 or Figure 13 A three-dimensional model formed by combining multiple jawbone feature images in the midjawbone feature image sequence set3.

[0288] When the jawbone feature image is a two-dimensional image, it can be as follows: Figure 12 or Figure 13 The set3 contains one or more jawbone feature images from the midjaw feature image sequence. These jawbone feature images can be masked images, and particularly binary images.

[0289] The presented jawbone feature image can be information contained in the image, the image itself, or a combination of image and information. The jawbone feature image may include portions indicating the jawbone morphology, and / or portions indicating other feature information of the corresponding jawbone; other feature information may be size information, etc.

[0290] Jawbone feature images can be determined by a neural network based on both root bone scan images representing the same jawbone location and jawbone segmentation images as input.

[0291] Cancellous bone feature images can be used to determine cortical bone feature images based on the differences between cancellous bone feature images and jawbone feature images.

[0292] When performing step S21, the corresponding root bone scan image, jaw segmentation image, cancellous bone feature image, or cortical bone feature image is not necessarily displayed.

[0293] Jawbone feature images can also be presented together with other two-dimensional images or three-dimensional models. Two-dimensional images or three-dimensional models are used to present more complete structural information within the oral cavity. In this case, jawbone feature images can be presented as part of the two-dimensional image or the three-dimensional model to indicate the features of the jawbone region in the two-dimensional image or the three-dimensional model.

[0294] The other three-dimensional model can be an oral scan model. The oral scan model and the jawbone feature image correspond to the same test object.

[0295] In the two-dimensional image or the three-dimensional model, the jawbone feature image can be distinguished from other parts by changing the color, edge lines, strobe, etc., so as to indicate the features of the jawbone in the two-dimensional image or the three-dimensional model.

[0296] In one embodiment, the display method provided in this application may include the steps of: presenting an oral scan model and a jawbone feature image corresponding to the oral scan model in a graphical user interface.

[0297] Jawbone feature images are used to characterize the jawbone region. Specifically, the jawbone feature images can be displayed at the locations corresponding to the intraoral scan model.

[0298] This step can be included in step S21; when implementing step S21, this step can be implemented in detail.

[0299] In one embodiment, the display method provided in this application may include the step of presenting a selection box surrounding the maxillary region in a graphical user interface. This step may be included in step S21; when implementing step S21, this step may be specifically implemented.

[0300] In one embodiment, the display method provided in this application may include the step of presenting a selection box surrounding the jaw region in a graphical user interface. This step may be included in step S21; when implementing step S21, this step may be specifically implemented.

[0301] The selection box can be a two-dimensional selection box or a three-dimensional selection box.

[0302] refer to Figure 17 Two-dimensional selection boxes can be represented as the rectangular boxes in the original jawbone segmentation image in the original jawbone segmentation image sequence set022. Three-dimensional selection boxes can be represented as the first selection box corresponding to diagonal vertices v1 and v2, or as the second selection box corresponding to diagonal vertices v1' and v2'.

[0303] The selection box can be determined based on the region representing the jawbone area (e.g., the maxilla or mandible) in the segmented jawbone image. The jawbone segmentation image can be determined based on a root bone scan image. Jawbone segmentation can be performed using a neural network.

[0304] When the graphical user interface displays images of jawbone features, if the jawbone feature image corresponds to either the maxilla or the mandible, the selection box will surround the area where the jawbone is located in the image; if the jawbone feature image includes both the maxilla and the mandible, the selection box is equivalent to dividing the jawbone area into upper and lower jaws.

[0305] Step S22: Present the bone spongy features image in the graphical user interface.

[0306] Images of cancellous bone features can be three-dimensional models or two-dimensional images.

[0307] When the image of cancellous bone features is a three-dimensional model, it can be as follows: Figure 14 The three-dimensional model 3d-41 corresponding to the cancellous bone features of the maxilla shown can also be as follows: Figure 15 The three-dimensional model 3d-42 shown corresponds to the cancellous bone features of the mandible, and can also be a combination of the corresponding three-dimensional models of the upper and lower jaws.

[0308] When the image of cancellous bone features is a three-dimensional model, it can also be as follows: Figure 14 or Figure 15 A three-dimensional model formed by combining multiple cancellous bone feature images from the set4 sequence of cancellous bone feature images.

[0309] When the image of cancellous bone features is a two-dimensional image, it can be as follows: Figure 14 or Figure 15The sequence set4 contains one or more cancellous bone feature images. These cancellous bone feature images can be masked images, and particularly binary images.

[0310] The presented images of cancellous bone features can be information contained in the image, the image itself, or a combination of image and information.

[0311] The feature image of cancellous bone can be determined by a neural network based on both a root bone scan image representing the same jawbone location and a segmented jawbone image as input.

[0312] Cancellous bone feature images can be used to determine cortical bone feature images based on the differences between cancellous bone feature images and jawbone feature images.

[0313] When performing step S22, the corresponding root bone scan image, jaw segmentation image, jaw feature image, or bone cortex feature image is not necessarily displayed.

[0314] Images of cancellous bone features can also be presented together with other two-dimensional images or three-dimensional models.

[0315] The other three-dimensional model can be an oral scan model.

[0316] In one embodiment, the display method provided in this application may include the steps of: presenting an oral scan model and a bone trabecular feature image corresponding to the oral scan model in a graphical user interface.

[0317] The cancellous bone feature image is used to characterize the cancellous bone region. Specifically, the cancellous bone feature image can be displayed at the location corresponding to the intraoral scan model.

[0318] This step can be included in step S22; when implementing step S22, this step can be implemented in detail.

[0319] In one embodiment, the display method provided in this application may include the step of presenting a selection box surrounding the maxillary region in a graphical user interface. This step may be included in step S22; when implementing step S22, this step may be specifically implemented.

[0320] In one embodiment, the display method provided in this application may include the step of presenting a selection box surrounding the jaw region in a graphical user interface. This step may be included in step S22; when implementing step S22, this step may be specifically implemented.

[0321] The selection box can be a two-dimensional selection box or a three-dimensional selection box.

[0322] The selection box can be determined based on the region representing the jawbone area (e.g., the maxilla or mandible) in the segmented jawbone image. The jawbone segmentation image can be determined based on a root bone scan image. Jawbone segmentation can be performed using a neural network.

[0323] Step S23: Present the cortical bone feature image in the graphical user interface.

[0324] Bone cortical feature images can be three-dimensional models or two-dimensional images.

[0325] When the cortical bone feature image is a three-dimensional model, it can be a three-dimensional model of the cortical bone features corresponding to the maxilla, a three-dimensional model of the cortical bone features corresponding to the mandible, or a combination of corresponding three-dimensional models of the maxilla and mandible.

[0326] When a bone cortical feature image is a three-dimensional model, it can also be a three-dimensional model formed by combining multiple bone cortical feature images in a sequence of bone cortical feature images.

[0327] When the cortical bone feature image is a two-dimensional image, it can be a single or multiple cortical bone feature images in a sequence. The cortical bone feature image can be a masked image, and especially a binary image.

[0328] The presented images of bone cortical features can be information contained in the image, the image itself, or a combination of image and information.

[0329] Cortical bone feature images can be determined by comparing the differences between jawbone feature images and cancellous bone feature images.

[0330] Jawbone feature images can be determined by a neural network based on both root bone scan images representing the same jawbone location and jawbone segmentation images as input.

[0331] The feature image of cancellous bone can be determined by a neural network based on both a root bone scan image representing the same jawbone location and a segmented jawbone image as input.

[0332] When performing step S22, the corresponding root bone scan image, jaw segmentation image, jaw feature image, or cancellous bone feature image is not necessarily displayed.

[0333] Bone cortical feature images can also be presented together with other two-dimensional images or three-dimensional models.

[0334] The other three-dimensional model can be an oral scan model.

[0335] In one embodiment, the display method provided in this application may include the steps of: presenting an oral scan model and a bone cortical feature image corresponding to the oral scan model in a graphical user interface.

[0336] Cortical bone feature images are used to characterize the cortical bone region. Specifically, the cortical bone feature images can be displayed at the locations corresponding to the intraoral scan model.

[0337] This step can be included in step S23; when implementing step S23, this step can be implemented in detail.

[0338] In one embodiment, the display method provided in this application may include the step of presenting a selection box surrounding the maxillary region in a graphical user interface. This step may be included in step S23; when implementing step S23, this step may be specifically implemented.

[0339] In one embodiment, the display method provided in this application may include the step of presenting a selection box surrounding the jaw region in a graphical user interface. This step may be included in step S23; when implementing step S23, this step may be specifically implemented.

[0340] The selection box can be a two-dimensional selection box or a three-dimensional selection box.

[0341] The selection box can be determined based on the region representing the jawbone area (e.g., the maxilla or mandible) in the segmented jawbone image. The jawbone segmentation image can be determined based on a root bone scan image. Jawbone segmentation can be performed using a neural network.

[0342] The parts of the display method provided in this application that are not fully described can be implemented as corresponding parts in other technical solutions of this application, such as the method for determining jawbone features. Similarly, the various technical solutions, implementation methods, and embodiments provided in this application can be combined with each other or used to explain and illustrate each other.

[0343] In summary, the method for determining jawbone features provided in this application uses a segmented jawbone image obtained by segmenting the radicular bone scan image, and the radicular bone scan image itself as a dual-channel input to a neural network. This enhances the feature extraction capability of the neural network, enabling accurate determination of overall jawbone features and cancellous bone features. Furthermore, the method provided in this application determines cortical bone features based on the differences between cancellous bone features and overall jawbone features. Compared to existing technologies, this method achieves higher accuracy in cortical bone feature extraction and is more computationally efficient.

[0344] It should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This way of describing the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0345] The detailed descriptions listed above are merely specific descriptions of feasible implementation methods of this application and are not intended to limit the scope of protection of this application. All equivalent implementation methods or modifications made without departing from the spirit of the art of this application should be included within the scope of protection of this application.

Claims

1. A method for determining jawbone features, characterized in that, include: Obtain radicular bone scan images; Based on the radicular bone scan image, the jawbone is segmented to determine the segmented jawbone image; Using a neural network, the jawbone feature image and the cancellous bone feature image are determined by taking both the root bone scan image and the jawbone segmentation image representing the same jawbone location as input. Compare jawbone feature images with cancellous bone feature images, and determine cortical bone feature images based on the differences; Determine and output the bone cortex feature information based on the bone cortex feature image.

2. The method according to claim 1, characterized in that, include: The cortical bone feature image is determined by pixel-by-pixel subtraction between the jawbone feature image and the cancellous bone feature image.

3. The method according to claim 1, characterized in that, include: Using a neural network, feature extraction is performed on the root bone scan image by referring to the segmented image of the jawbone, and the characteristic images of the jawbone and cancellous bone are determined.

4. The method according to claim 1, characterized in that, Includes at least one of the following: An oral scan model is obtained, and the cortical bone feature information is transformed by coordinate transformation to display the cortical bone feature information at the oral scan model. Based on the bone trabecular feature image, determine the bone trabecular feature information, obtain the oral scanning model, and perform coordinate transformation on the bone trabecular feature information to display the bone trabecular feature information at the oral scanning model; Determine and output the size information of the bone cortex based on the feature image of the bone cortex; Determine and output bone density information based on the characteristic images of cancellous bone; A three-dimensional model of the jawbone is established based on several jawbone feature images corresponding to several jawbone locations. A three-dimensional model of cancellous bone is established based on several cancellous bone feature images corresponding to several jawbone locations; A three-dimensional model of the bone cortex is established based on several cortical bone feature images corresponding to several jawbone locations.

5. The method according to claim 1, characterized in that, include: Obtain a root bone scan image and a jaw segmentation image representing the same jawbone position in a first direction, wherein the first direction is perpendicular to the display plane of the root bone scan image and the jaw segmentation image; Based on the segmented images of the jawbone, determine the regions representing the jawbone area in the radicular bone scan images; The pedicle scan image is cropped.

6. The method according to claim 5, characterized in that, include: Determine the regions representing the jawbone area in the segmented jawbone image; Cropping segmented jawbone images; Based on the regions representing the jawbone area in the segmented jawbone image, determine the regions representing the jawbone area in the root bone scan image.

7. The method according to claim 1, characterized in that, The calcaneal scan images include cone-beam computed tomography (CBCT) images.

8. The method according to claim 1, characterized in that, include: Using a neural network, the maxilla and mandible are segmented based on the root bone scan image to determine the segmented images of the maxilla and mandible.

9. A display method, characterized in that, Includes at least one of the following: A jawbone feature image is presented in a graphical user interface. The jawbone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input. The jawbone feature image is used to determine a cortical bone feature image based on its difference from a cancellous bone feature image. A cancellous bone feature image is presented in a graphical user interface. The cancellous bone feature image is determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input. The cancellous bone feature image is used to determine a cortical bone feature image based on its difference from the jawbone feature image. The graphical user interface presents a cortical bone feature image, which is determined by comparing the differences between a jawbone feature image and a cancellous bone feature image. The jawbone feature image and the cancellous bone feature image are determined by a neural network based on both a root bone scan image representing the same jawbone location and a jawbone segmentation image as input.

10. The display method according to claim 9, characterized in that, Includes at least one of the following: The jawbone feature images, cancellous bone feature images, and cortical bone feature images are three-dimensional models; Jawbone feature images, cancellous bone feature images, and cortical bone feature images are two-dimensional images.

11. The display method according to claim 9, characterized in that, Includes at least one of the following: The oral scan model and the corresponding cortical bone feature image are presented in the graphical user interface. The cortical bone feature image is used to characterize the cortical bone region. The oral scan model and the corresponding cancellous bone feature image are presented in the graphical user interface. The cancellous bone feature image is used to characterize the cancellous bone region. The graphical user interface presents an oral scan model and a corresponding jawbone feature image, which is used to characterize the jawbone region.

12. The display method according to claim 9, characterized in that, Includes at least one of the following: A selection box surrounding the upper jaw area is displayed in the graphical user interface; A selection box surrounding the jawline is displayed in the graphical user interface; The selection box can be a two-dimensional selection box or a three-dimensional selection box; The selection box is determined based on the region representing the jawbone in the segmented jawbone image, which is determined based on the root bone scan image using a neural network for jawbone segmentation.

13. A device for determining jawbone features, characterized in that, include: The first module is used to obtain pedicle scan images; The second module is used to segment the jawbone based on the root bone scan image and determine the segmented jawbone image; The third module is used to determine the jawbone feature image and the cancellous bone feature image by using a neural network, taking both the root bone scan image and the jawbone segmentation image representing the same jawbone location as input. The fourth module is used to compare jawbone feature images and cancellous bone feature images, and determine the cortical bone feature images based on the differences; The fifth module is used to determine and output the bone cortex feature information based on the bone cortex feature image.

14. The apparatus according to claim 13, characterized in that, The device is connected to a first device, which is used to implement a cone-beam ring headgear to obtain radicular bone scanning images, which are used to obtain jawbone feature images and / or cancellous bone feature images.

15. An electronic device comprising a processor, a memory, and a communication bus, characterized in that, The processor and the memory communicate with each other via the communication bus; The memory is used to store application programs; The processor is configured to, when executing an application stored in the memory, implement the steps of the method for determining jawbone features as described in any one of claims 1-8, or the steps of the display method as described in any one of claims 9-12.

16. A storage medium having an application program stored thereon, characterized in that, When the application is executed, it implements the steps of the method for determining jawbone features as described in any one of claims 1-8, or the steps of the display method as described in any one of claims 9-12.

Images