A multi-plane reconstruction method, apparatus, device and readable storage medium

Abstract

The specification discloses a multi-plane reconstruction method, device, equipment and readable storage medium. According to a preset standard value range of a specified parameter, an original value range is adjusted to obtain a target value range. Then, for each original image, the specified parameter of the original image is updated and normalized according to the target value range, so as to obtain a gray image corresponding to the original image. Each compressed image is obtained by compressing each gray image. A target file is generated according to each compressed image and the target value range. Then, a target cross-sectional image is obtained by multi-plane reconstruction according to the target file. It can be seen that, by adjusting the target value range, the specified parameter of the original image is updated and normalized to obtain the gray image, and the target file is generated by compressing the gray image. In this way, the data storage and data transmission of the target file can be reduced, and the efficiency of multi-plane reconstruction can be improved.

Description

Technical Field

[0001] This specification relates to the field of medical technology, and in particular to a multiplanar reconstruction method, apparatus, device, and readable storage medium. Background Technology

[0002] With the development of medical imaging technology, multi-planar reformation (MPR) technology has attracted increasing attention. MPR technology can reconstruct images in specific directions or at arbitrary angles to generate two-dimensional planes, such as coronal, sagittal, and transverse planes, so that doctors can view information about the patient's tissues and organs.

[0003] Currently, doctors typically need to perform MPR operations based on a large amount of raw image data in order to reconstruct a more accurate two-dimensional plane.

[0004] However, due to the large amount of raw image data, the efficiency of data storage and transmission is limited, which may result in low MPR efficiency in the above scheme. Summary of the Invention

[0005] This specification provides a multi-plane reconstruction method, apparatus, device, and readable storage medium to partially solve the aforementioned problems existing in the prior art.

[0006] The following technical solution is adopted in this specification:

[0007] This specification provides a multi-plane reconstruction method, including:

[0008] Obtain the original medical image file, and determine the original value range of the specified parameter based on each original image in the original medical image file;

[0009] The target value range of the specified parameter is determined based on the preset standard value range and the original value range of the specified parameter;

[0010] For each original image, the specified parameters of the original image are updated according to the target value range, and the updated specified parameters are normalized to determine the grayscale image corresponding to the original image.

[0011] Based on the preset image compression rate, each grayscale image is compressed to obtain a compressed image.

[0012] Based on the compressed images and the target value range, a target file is generated;

[0013] In response to a reconstruction request input by the user, multi-plane reconstruction is performed based on the target file to obtain a target cross-sectional image.

[0014] Optionally, the target value range of the specified parameter is determined based on the preset standard value range and the original value range, specifically including:

[0015] Determine whether the upper limit of the parameter in the original value range is greater than the upper limit of the parameter in the standard value range;

[0016] If so, the original value range shall be used as the target value range of the specified parameter;

[0017] If not, the standard value range shall be used as the target value range for the specified parameter.

[0018] Optionally, the specified parameters of the original image are updated according to the target value range, specifically including:

[0019] Determine whether the specified parameters of the original image fall within the target value range;

[0020] If so, do not update the specified parameters of the original image;

[0021] If not, update the specified parameters of the original image according to the upper and lower limits of the target value range.

[0022] Optionally, the updated specified parameters are normalized to determine the grayscale image corresponding to the original image, specifically including:

[0023] Based on the upper and lower limits of the target value range, the updated specified parameters are normalized to obtain the grayscale value of the original image.

[0024] Based on the grayscale values ​​of the original image, determine the corresponding grayscale image.

[0025] Optionally, the original image in the original medical image file is an oral cavity image;

[0026] In response to a user-inputted reconstruction request, multi-plane reconstruction is performed based on the target file to obtain a target cross-sectional image, specifically including:

[0027] In response to a user-inputted reconstruction request, the system retrieves and displays a pre-generated 3D model of the oral cavity corresponding to the original medical image file.

[0028] In response to the point selected by the user in the oral cavity 3D model, the target tooth selected by the user is determined;

[0029] Based on the oral cavity three-dimensional model, the target point corresponding to the target tooth is determined;

[0030] Determine the target file corresponding to the oral cavity 3D model, and determine the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file;

[0031] Multi-plane reconstruction is performed based on the target location to obtain a cross-sectional image of the target.

[0032] Optionally, based on the oral cavity 3D model, the target point corresponding to the target tooth is determined, and the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file is determined, specifically including:

[0033] The centroid of the target tooth is determined based on the crown mesh data in the oral cavity 3D model;

[0034] The centroid of the target tooth is taken as the target point corresponding to the target tooth, and the position of the target point in the coordinate system corresponding to the crown mesh data is determined.

[0035] By using the coordinate transformation matrix corresponding to the oral cavity 3D model, the position of the target point in the coordinate system corresponding to the crown mesh data is transformed to the coordinate system corresponding to the compressed image contained in the target file, and the position of the target point in the coordinate system corresponding to the compressed image is obtained, which is used as the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file.

[0036] Optionally, the method further includes:

[0037] Based on the crown mesh data and root mesh data in the oral cavity three-dimensional model, the first candidate point corresponding to each maxillary tooth and the second candidate point corresponding to each mandibular tooth are determined respectively.

[0038] Using the coordinate system transformation matrix in the oral cavity 3D model, the first candidate point and the second candidate point are respectively transformed to the coordinate system corresponding to the compressed image;

[0039] The designated point is determined based on the first and second candidate points in the coordinate system corresponding to the compressed image.

[0040] Using the position of the specified point in the coordinate system corresponding to the compressed image as the initial position, multi-plane reconstruction is performed to obtain the initial cross-sectional image.

[0041] Optionally, a three-dimensional oral cavity model is generated in advance, specifically including:

[0042] Pre-acquire crown mesh data using a scanning device;

[0043] Based on the crown mesh data, the original images in the original medical image file are segmented to obtain the root mesh data;

[0044] The coordinate system corresponding to the tooth root mesh data is determined as the coordinate system corresponding to the compressed image;

[0045] The coordinate system corresponding to the crown mesh data is registered with the coordinate system corresponding to the compressed image to obtain the coordinate system transformation matrix;

[0046] A three-dimensional oral cavity model is generated based on the crown mesh data, the root mesh data, and the coordinate system transformation matrix.

[0047] Optionally, the oral cavity 3D model stores a first identifier code, and the target file stores a second identifier code;

[0048] Determining the target file corresponding to the oral cavity 3D model specifically includes:

[0049] Determine the first identifier code corresponding to the oral cavity three-dimensional model;

[0050] Determine the second identifier stored in each target file;

[0051] The target file with the same second identifier as the first identifier is used as the target file corresponding to the oral cavity three-dimensional model.

[0052] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described multiplane reconstruction method.

[0053] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described multiplane reconstruction method.

[0054] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects:

[0055] The multi-planar reconstruction method provided in this specification determines the original value range of specified parameters from each original image in the original medical image file. The original value range is then adjusted according to a preset standard value range to obtain a target value range. For each original image, the specified parameters are updated according to the target value range, and the updated parameters are normalized to obtain a corresponding grayscale image. This grayscale image is then compressed according to a preset image compression rate to obtain compressed images. Finally, a target file is generated based on the compressed images and the target value range. When a user inputs a reconstruction request, multi-planar reconstruction of the target file yields the target cross-sectional image. Therefore, by adjusting the original value range of the original image to obtain the target value range, updating and normalizing the specified parameters of the original image using the target value range to obtain grayscale images, and then compressing the grayscale images to generate the target file, the data storage and data transmission volume of the target file used in multi-planar reconstruction can be greatly reduced, thereby improving the efficiency of multi-planar reconstruction. Attached Figure Description

[0056] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and their descriptions, serving to explain this specification and do not constitute an undue limitation thereof.

[0057] In the picture:

[0058] Figure 1 This is a flowchart illustrating a multi-plane reconstruction method described in this specification.

[0059] Figure 2 This is a flowchart illustrating a multi-plane reconstruction method described in this specification.

[0060] Figure 3 This is a flowchart illustrating a multi-plane reconstruction method described in this specification.

[0061] Figure 4 This is a flowchart illustrating a multi-plane reconstruction method described in this specification.

[0062] Figure 5 This is a schematic diagram of a multi-plane reconstruction device provided in this specification;

[0063] Figure 6 The corresponding information provided in this specification Figure 1 A schematic diagram of an electronic device. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0065] Additionally, it should be noted that all actions involving the acquisition of signals, information, or data in this invention are carried out in compliance with the relevant data protection laws and regulations of the country where the invention is located, and with authorization from the owner of the corresponding device.

[0066] With the development of medical imaging technology, MPR (Multi-Plan Reconstruction) technology has attracted increasing attention. MPR technology can reconstruct images into two-dimensional planes, such as coronal, sagittal, and transverse planes, from specific directions or arbitrary angles, allowing users to view tissue and organ information in a two-dimensional plane. Currently, users need a large amount of raw image data to obtain a relatively accurate reconstructed image when performing MPR operations. However, the size of the raw image data in the original medical image file is related to the spatial resolution and field of view; higher spatial resolution and a larger field of view result in a larger storage space occupied by the raw image data. To obtain an accurate reconstructed image, the amount of raw image data is usually large, which not only requires more storage space but may also lead to low efficiency in MPR operations.

[0067] In one application scenario, when a doctor opens raw image data on their local operating system and performs MPR operations, the loading time and MPR reconstruction computation time are considerable. When the operating system's hardware memory is limited, lag can easily occur, reducing MPR efficiency. In another application scenario, users can remotely process raw image data for MPR operations via a remote workstation, or transfer raw image data stored on a remote workstation to their local machine via digital transmission methods such as network transmission before performing MPR operations. This scenario involves data transmission issues. Due to the large amount of raw image data, both MPR operations and data transmission are constrained by transmission bandwidth, increasing the user's time cost and reducing MPR efficiency.

[0068] Based on this, this specification provides a multi-plane reconstruction method. By performing image compression on the preprocessed original image to obtain a compressed image, and generating a target file based on the compressed image, the user can perform multi-plane reconstruction using the target file containing the compressed image during MPR operations to obtain the target cross-sectional image. The above scheme can reduce the data storage and data transmission volume of the target file, thereby improving the efficiency of multi-plane reconstruction.

[0069] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0070] Figure 1 This is a flowchart illustrating a multi-plane reconstruction method provided in this specification.

[0071] S100: Obtain the original medical image file, and determine the original value range of the specified parameter based on each original image in the original medical image file.

[0072] This specification provides a multi-plane reconstruction method in its embodiments. The execution process of this multi-plane reconstruction method can be performed by an electronic device such as a server used for multi-plane reconstruction. The electronic device executing the file generation process involved in the multi-plane reconstruction can be the same as or different from the electronic device executing the multi-plane reconstruction method; this specification does not impose any limitations on this.

[0073] In the embodiments of this specification, the acquired original medical image file may be a Digital Imaging and Communications in Medicine (DICOM) file, or a file storing the patient's medical image data in other existing file formats. The original images in the original medical image file may be stored and arranged as an image sequence, with each original image arranged sequentially according to the order of image acquisition. Alternatively, they may be stored and arranged in other formats. This specification does not limit the file type of the original medical image file or the storage and arrangement format of the original images. The original images contained in the original medical image file may be images obtained through computed tomography (CT), magnetic resonance imaging (MRI), low-dose positron emission tomography / magnetic resonance imaging (PET), or images obtained through other modalities of medical image acquisition. This embodiment does not specifically limit the modality used to acquire the original images contained in the original medical image file.

[0074] In addition, depending on the application scenario, the original image in the original medical image file may show different parts of the patient's body. The original image may be an image of the oral cavity, a chest cavity, or a brain, etc. This manual does not limit this.

[0075] For ease of explanation, this manual uses the original medical image file as a DICOM file, with the original image in the original medical image file originating from a CT scan, as an example to elaborate on the specific technical solution.

[0076] Optionally, the original medical image files may be obtained from a Picture Archiving and Communication Systems (PACS) or from medical image acquisition equipment in real time; this specification does not limit this.

[0077] Furthermore, in addition to storing multiple original images, DICOM files also store various types of attribute information for these original images, such as spatial resolution (voxel size), field of view size (voxel count), window width and level, and CT values ​​of volume data. Window width and level are attributes used in CT examinations to observe normal tissues or lesions of different densities. Since various tissue structures or lesions have different CT values, when displaying details of a particular tissue structure, a suitable window width and level should be selected for optimal display. However, the original window width and level stored in the original medical image file may not necessarily present an ideal visual effect, potentially causing a lack of contrast between different tissues, making it difficult for users to intuitively observe the different tissues presented in the image. Therefore, the original value range of specified parameters can be extracted from the original medical image file for subsequent adaptive adjustment, enabling the image to better display the details of different tissue structures.

[0078] The original medical image may store the original window width and original window level, or it may directly store the original value range; this manual does not limit this.

[0079] It should be noted that the specified parameter here refers to the CT value. The CT value describes the density of a CT image. The CT value is a relative value obtained by mathematically transforming the X-ray attenuation coefficient measured by the detector. Generally, different human tissues correspond to different CT values. For example, -1000 HU is the CT value of air, and 3300 HU is the CT value between that of metal and dental porcelain.

[0080] S102: Determine the target value range of the specified parameter based on the preset standard value range and the original value range.

[0081] Furthermore, to obtain images with high contrast and good visual effects, a standard range of values ​​for specified parameters can be preset, and the standard range can be compared with the original range to obtain a target range with ideal visual effects. Specifically, the upper and lower limits of the parameters in the standard range can be compared with the upper and lower limits of the parameters in the original range, and the range of values ​​with more reasonable upper and lower limits can be used as the target range.

[0082] S104: For each original image, update the specified parameters of the original image according to the target value range, and normalize the updated specified parameters to determine the grayscale image corresponding to the original image.

[0083] In practical applications, there may be objects made of metal or other materials in the patient's oral cavity, resulting in a large range of variations in the actual CT values. Direct normalization would lead to grayscale compression, which in turn affects the image's clarity, making it difficult for users to distinguish different tissue structures when viewing the original image. Therefore, the specified parameters of the original image can be updated based on the target value range determined in step S102 above. The specific update processing method can be existing methods such as truncation or nonlinear mapping, which are not limited in this specification.

[0084] Furthermore, the updated specified parameters are normalized according to the upper and lower limits of the target value range. The normalization method can be any existing normalization method, and this specification does not limit it.

[0085] Optionally, this specification provides an optional normalization method for specified parameters, as shown in the following formula:

[0086]

[0087] Among them, pixel_value ′ The specified parameter is the normalized value, and pixel_value is the original specified parameter. CT max and CT min These are the upper and lower limits of the parameter, respectively, for the target value range.

[0088] Then, the grayscale image corresponding to the original image is determined based on the specified parameters after normalization of the original image.

[0089] Optionally, the specified parameters after normalization can be used as the grayscale values ​​of each pixel in the original image. Further, based on each grayscale value, the corresponding grayscale image of the original image can be determined.

[0090] S106: Based on the preset image compression rate, compress each grayscale image to obtain each compressed image.

[0091] Specifically, the pixel grayscale values ​​in the grayscale image obtained through step S104 above are between 0 and 1. These floating-point grayscale values ​​between 0 and 1 can be converted into 8-bit integer values, ranging from 0 to 255, through image compression. The image compression rate can be a preset fixed value or determined based on the pixel size stored in the original medical image file. The image compression rate can be positively correlated with the pixel size; the smaller the pixel size, the lower the image compression rate. Through the above operations, the data storage space is reduced while ensuring that the tissue structure information in the CT image is not significantly distorted. Furthermore, the image compression method can be JPEG compression or other encoding compression methods; this specification does not limit this.

[0092] Optionally, the image compression ratio can be related to other parameters related to image quality, such as field of view size, number of voxels, and resolution of the original image, in addition to pixel size. Therefore, the image compression ratio can be determined based on several different types of attribute values, which are not limited in this specification.

[0093] S108: Generate a target file based on the compressed images and the target value range.

[0094] Specifically, the target file can be obtained by writing the compressed image and the target value range into a file using any existing serialized structured data format such as protobuf.

[0095] Optionally, other types of attribute information from the original medical image file, such as pixel size, field of view, and shooting direction, can also be written into the target file.

[0096] S110: In response to the user's input reconstruction request, perform multi-plane reconstruction based on the target file to obtain the target cross-sectional image.

[0097] In practical applications, after obtaining the target file, the user can use a file parser corresponding to the file's generation method to parse it, thereby obtaining the compressed image and attribute values ​​such as the target value range stored in the file. During this process, when using the file parser to parse the target file, access conditions can be set to verify the validity of the user's parsing of the target file, confirming that the user can obtain the compressed image and attribute values ​​contained in the target file. This prevents the leakage of patients' medical privacy information. Verification of validity can be done using any existing verification method, such as encrypting the target file and having the user provide a decryption key for verification; this manual does not limit this method.

[0098] The multi-plane reconstruction method provided in this manual determines the original value range of specified parameters from each original image in the original medical image file, and adjusts the original value range according to the preset standard value range of the specified parameters to obtain the target value range. Then, for each original image, the specified parameters of the original image are updated according to the target value range, and the updated specified parameters are normalized to obtain the corresponding grayscale image of the original image. In order to compress each grayscale image according to the preset image compression rate, each compressed image is obtained. Then, a target file is generated based on each compressed image and the target value range. When the user inputs a reconstruction request, the target cross-sectional image can be obtained by performing multi-plane reconstruction based on the target file. As can be seen, by adjusting the original value range of the original image to obtain the target value range, updating and normalizing the specified parameters of the original image with the target value range to obtain a grayscale image, and then compressing the grayscale image to generate a target file, the image and attribute values ​​required for multi-plane reconstruction can be extracted as the target file. This eliminates the need to use a large original data file to achieve multi-plane reconstruction, which can greatly reduce the data storage and data transmission volume of the target file used in multi-plane reconstruction, thereby improving the efficiency of multi-plane reconstruction.

[0099] In one or more embodiments of this specification, in such Figure 1 Step S102 shows that, based on the preset standard value range and the original value range of the specified parameter, the target value range of the specified parameter is determined. The original value range can be adjusted according to the relationship between the upper limit of the parameter in the original value range and the upper limit of the parameter in the standard value range, as detailed below:

[0100] Determine whether the upper limit of the parameter in the original value range is greater than the upper limit of the parameter in the standard value range.

[0101] Specifically, the upper limit of the parameter's original value range is original_CT. max The upper limit of the parameter within the standard value range is default_CT. max If original_CT max Less than default_Ct maxThis results in compressed CT values, potentially leading to poor contrast between different tissue types. For example, with a window width of 4300 and a window level of 1150, the calculated CT value range is [-1000, 3300], where -1000 is the CT value for air and 3300 is the CT value between metal and dental porcelain. In practice, most CT data from a patient's oral cavity are close to this range, showing good contrast between various tissues. However, if the original window width is only 2300 and the original window level is 0, the calculated original value range is [-1150, 1150]. In this case, the CT value for some areas of the teeth is greater than 1150, resulting in almost no contrast in those areas, with grayscale compressed and appearing as a white mass.

[0102] In response to the above situation, in the embodiments of this specification, the method of comparing the upper limit of the parameter in the original value range with the upper limit of the parameter in the standard value range is adopted, and the original value range is adjusted according to the comparison result.

[0103] If so, the original value range shall be used as the target value range of the specified parameter.

[0104] Specifically, if original_CT max Greater than default_CT max If the original value range is not adjusted, then the original value range is the target value range of the specified parameter.

[0105] If not, the standard value range shall be used as the target value range for the specified parameter.

[0106] If original_CT max Not greater than default_CT max If so, the standard value range will be directly used as the target value range of the specified parameter.

[0107] In one or more embodiments of this specification, in such Figure 1 Step S104 shows updating the specified parameters of the original image according to the target value range. The update process can be performed based on the relationship between the target value range and the specified parameters of the original image, as detailed below:

[0108] Determine whether the specified parameters of the original image fall within the target value range.

[0109] To prevent the CT values ​​of metal or other materials in the patient's mouth from having an excessive impact on the contrast between other tissues in the image, the specified parameters of the original image are truncated according to the target value range. That is, if the specified parameters of the original image are within the target value range, the specified parameters of the original image will not be updated.

[0110] If so, do not update the specified parameters of the original image;

[0111] If not, update the specified parameters of the original image according to the upper and lower limits of the target value range.

[0112] If the specified parameter of the original image is not within the target value range, then when the specified parameter is greater than the upper limit of the target value range, the specified parameter is updated to the upper limit of the target value range; when the specified parameter is less than the lower limit of the target value range, the specified parameter is updated to the lower limit of the target value range.

[0113] In one or more embodiments of this specification, in such Figure 1 In step S110, in response to a user-inputted reconstruction request, multi-plane reconstruction is performed based on the target file to obtain a target cross-sectional image. Simultaneously, a three-dimensional oral cavity model can be acquired, allowing the user to select target points under the guidance of this model, thereby improving the accuracy of the target point selection. The specific steps are as follows: Figure 2 As shown:

[0114] S200: In response to the user's input reconstruction request, obtain the oral cavity 3D model corresponding to the pre-generated original medical image file, and display the oral cavity 3D model.

[0115] In oral CT images, a single tooth occupies only a small portion of the overall 2D image field of view. To view the specific appearance of a particular tooth, a user must first determine the jaw position, then browse through a sequence of images to find the center point of the tooth, and then zoom in, rotate, and switch planes. If each tooth requires detailed examination, the time consumed by the initial localization and MPR (Multi-Level Preview) operations is considerable. Furthermore, during observation, the user lacks intuitive guidance from a 3D oral model, leading to frequent switching of the center point position and rotation direction.

[0116] Based on this, in the embodiments of this specification, by obtaining and displaying a pre-generated three-dimensional oral cavity model, the user can select the target point of the MPR operation under the guidance of the three-dimensional oral cavity model, thereby improving the efficiency and accuracy of target point selection.

[0117] S202: In response to the point selected by the user in the oral cavity 3D model, determine the target tooth selected by the user.

[0118] In the embodiments of this specification, a complete three-dimensional tooth surface image can be constructed based on the crown mesh data and root mesh data in the three-dimensional oral cavity model. This three-dimensional tooth surface image is divided into the maxilla and mandible. Users can select the teeth that need to be reconstructed in multiple planes according to specific application needs. Each tooth in the maxilla and mandible has an independent number, and there is a correspondence between the tooth number and the corresponding crown mesh data and root mesh data. That is, after the user selects a target point on the three-dimensional model, the location of the target point can be used to determine which tooth the user has selected.

[0119] Specifically, while displaying a 3D image of the tooth surface to the user, the user can input a target point based on the displayed 3D tooth surface image using an input device. Typically, the user needs to observe a reconstructed cross-sectional image of a specific tooth; therefore, the target point is usually located on the tooth surface. Of course, if the target point selected by the user is not on the tooth, a multi-planar reconstruction operation can also be performed.

[0120] When a user selects a target point on a tooth, the system can determine which tooth the user has selected based on the correspondence between the tooth's crown mesh data and the tooth root mesh data, and then use that tooth as the target tooth.

[0121] S204: Determine the target file corresponding to the oral cavity 3D model.

[0122] Optionally, the oral cavity 3D model can be stored in a 3D model file, and the 3D model file can also use a parsing method similar to that of the target file, as described above. Figure 1 Step S110 is similar and will not be repeated here.

[0123] Furthermore, since multiplanar reconstruction requires compressed images contained in the target file, it is also necessary to obtain the corresponding target file of the oral cavity 3D model while acquiring the oral cavity 3D model. Specifically, the correspondence between the oral cavity 3D model and the target file can be stored in advance, such as by establishing the correspondence through patient identification.

[0124] In an optional embodiment of this specification, since the 3D model data in the oral cavity 3D model can originate from the patient's original medical image file, and the original image in the original medical image file can be an oral cavity image, a first identifier code can be generated and stored in the oral cavity 3D model. Correspondingly, a second identifier code can also be generated when the target file is generated. When determining the target file corresponding to the oral cavity 3D model, the target file whose second identifier code is the same as the first identifier code of the oral cavity 3D model can be selected by matching the first and second identifier codes. It should be noted that for oral cavity 3D models and target files with a corresponding relationship, the generation method and basis of their first and second identifier codes should be the same to generate the same identifier code. The generation basis of the first identifier code (or second identifier code) can be the serial number of the original medical image file, or the patient's identity information, etc., which is not specifically limited in this specification. Furthermore, the generation method of the first identifier code (or second identifier code) can be any existing identifier code generation method, which is not limited in this specification.

[0125] S206: Based on the oral cavity three-dimensional model, determine the target point corresponding to the target tooth, and determine the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file.

[0126] Specifically, the 3D model file can also store the coordinate system transformation matrix corresponding to the 3D oral cavity model, which is then converted to the coordinate system of the image contained in the target file. When a user selects a target tooth on the displayed 3D oral cavity model, the target points corresponding to the target tooth can be transformed to the coordinate system of the image contained in the target file for subsequent multi-plane reconstruction.

[0127] S208: Perform multi-plane reconstruction based on the target location to obtain the target cross-sectional image.

[0128] After obtaining the target location for MPR deployment, coronal, sagittal, and transverse cross-sectional views can be obtained from this target location. The operation method of MPR mentioned in this manual is the same as the existing MPR operation method, and will not be described in detail in this manual.

[0129] Through such Figure 2The proposed solution involves acquiring a 3D model of the oral cavity, determining and parsing the corresponding target file, allowing the user to select points based on the 3D model, and then identifying the target tooth. The target point is then transformed from the coordinate system of the 3D model to the coordinate system of the compressed image contained in the target file to obtain its position. Multi-plane reconstruction is then performed based on the target position to obtain the target cross-sectional image. As can be seen, when using a target file containing a compressed image for multi-plane reconstruction, the user can select the target points for multi-plane reconstruction under the guidance of the 3D model of the oral cavity. This reduces both data storage and data transmission volume while improving the accuracy of multi-plane reconstruction.

[0130] In one or more embodiments of this specification, in such Figure 2 Step S206 shows determining the target point corresponding to the target tooth based on the oral cavity 3D model, and determining the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file, such as... Figure 3 As shown, this can be obtained through the following steps:

[0131] S300: Determine the centroid of the target tooth based on the crown mesh data corresponding to the target tooth.

[0132] In practical applications, in addition to determining the center of gravity of the target tooth, the position of the centroid of the target tooth or the center of the crown surface can also be determined. This manual does not limit this. This manual only describes the specific technical solution by taking the determination of the center of gravity of the target tooth as an example, and does not mean that this solution can only be achieved by determining the center of gravity of the target tooth.

[0133] S302: Using the centroid of the target tooth as the target point corresponding to the target tooth, determine the position of the target point in the coordinate system corresponding to the crown mesh data.

[0134] The reason for using the centroid of the target tooth as the target point, instead of directly using a user-selected point, is that if the tooth occupies only a small portion of the entire 3D tooth surface image's field of view, the small field of view reduces the accuracy of point selection when the user chooses the target point for MPR operations. This results in a significant discrepancy between the obtained cross-sectional image and the image the user needs, increasing the time spent on MPR operations. By using the centroid of the target tooth as the target point in this solution, the user only needs to roughly select a point to locate the tooth to be observed, obtaining a more accurate target cross-sectional image without the need for multiple fine selections, thus improving the efficiency of MPR.

[0135] S304: Using the coordinate system transformation matrix corresponding to the oral cavity 3D model, the position of the target point in the coordinate system corresponding to the crown mesh data is transformed to the coordinate system corresponding to the compressed image contained in the target file, so as to obtain the position of the target point in the coordinate system corresponding to the compressed image, which is used as the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file.

[0136] Specifically, after determining the target point, its position in the coordinate system corresponding to the crown mesh data can be determined. Further, based on the coordinate transformation matrix corresponding to the 3D oral cavity model, the position of the target point in the coordinate system corresponding to the crown mesh data can be transformed to the coordinate system corresponding to the compressed image, obtaining the position of the target point in the coordinate system corresponding to the compressed image. The target position in the coordinate system corresponding to the image contained in the target file is then used as the center point of the MPR operation, resulting in a target cross-sectional image in any direction.

[0137] Optionally, after acquiring the target cross-sectional image of MPR, the user can switch between different coronal, sagittal, and transverse plane positions by panning the mouse and scrolling the scroll wheel; or obtain reconstruction results of other planes by rotating the crosshair formed by the X and Y axes. The specific interpolation method is similar to the existing interpolation method, and this manual does not limit it.

[0138] In an optional embodiment of this specification, since the occlusal relationship of the upper and lower jaws in a patient's oral cavity is constantly changing, the crown mesh data and root mesh data may not be collected at the same time period, or the collection devices may be different, which may cause changes in the occlusal relationship of the patient's upper and lower jaws. Therefore, the coordinate system transformation matrix corresponding to the three-dimensional oral cavity model can be divided into a maxillary coordinate system transformation matrix and a mandibular coordinate system transformation matrix. After determining the target tooth, it can be further determined whether the target tooth is in the maxilla or mandible, and the position of the target point can be transformed using the corresponding jaw position coordinate system transformation matrix.

[0139] In an optional embodiment of this specification, when a user first opens a 3D oral cavity model for MPR reconstruction, or when, after obtaining the target cross-sectional image through reconstruction, it is necessary to redetermine the target point and perform MPR reconstruction again, the initial position of the initial point and the initial cross-sectional image can be displayed to the user based on the crown mesh data and root mesh data contained in the 3D oral cavity model. This facilitates the user in reselecting the target point based on the initial position. The specific solution is as follows:

[0140] First, based on the crown mesh data and root mesh data of the oral cavity 3D model, the first candidate points corresponding to each maxillary tooth and the second candidate points corresponding to each mandibular tooth are determined respectively.

[0141] In practical applications, when a user performs an MPR operation for the first time, or when the target point for the MPR needs to be covered, the distance between the currently displayed position (the current target point position) and the target point position for the user's next MPR operation may be too large, making it difficult for the user to select the target point and easily leading to selection errors. Therefore, when the user first opens the oral cavity 3D model for MPR reconstruction, or when the target point needs to be redefined for MPR reconstruction after the target section image has been reconstructed, the position of the target point can be reset to a preset initial position, and the initial section image obtained by the MPR operation corresponding to the initial position can be displayed.

[0142] Specifically, since the oral cavity is divided into the maxilla and mandible, the average coordinates can be determined based on the crown and root mesh data of each maxillary tooth to obtain the first candidate points corresponding to each maxillary tooth. The same principle applies to the mandible, yielding the second candidate points corresponding to each mandibular tooth.

[0143] Optionally, in addition to coordinate averaging, the first and second candidate points can be obtained by determining the weights of different teeth and performing a weighted average of the coordinates. Of course, other existing methods can also be used, which are not limited in this specification.

[0144] Secondly, by using the coordinate transformation matrix in the parsed oral cavity 3D model, the first candidate point and the second candidate point are transformed to the coordinate system corresponding to the compressed image.

[0145] Furthermore, since it is necessary to obtain the cross-sectional image at the initial position, the positions of the first candidate point and the second candidate point in the coordinate system corresponding to the crown mesh data must also be transformed to the coordinate system corresponding to the compressed image, so as to obtain the positions of the first candidate point and the second candidate point in the coordinate system corresponding to the compressed image.

[0146] Since the first candidate point corresponds to the maxilla and the second candidate point corresponds to the mandible, a maxillary coordinate system transformation matrix can be used to transform the position of the first candidate point, and a mandibular coordinate system transformation matrix can be used to transform the position of the second candidate point. The specific maxillary and mandibular coordinate system transformation matrices are as described above. Figure 3 Step S310 is similar and will not be repeated here.

[0147] Then, the designated point is determined based on the first candidate point and the second candidate point in the coordinate system corresponding to the compressed image.

[0148] Specifically, the position of the designated point can be determined by averaging the positions of the first candidate point and the second candidate point in the coordinate system corresponding to the compressed image. Alternatively, existing methods such as weighted averaging can be used to determine the position of the designated point based on these coordinates; this specification does not limit this approach.

[0149] Finally, using the position of the specified point in the coordinate system corresponding to the compressed image as the initial position, multi-plane reconstruction is performed to obtain the initial cross-sectional image.

[0150] The method of multiplanar reconstruction here is the same as the existing multiplanar reconstruction method, and will not be described in detail in this manual.

[0151] In one or more embodiments of this specification, in such Figure 3 Before obtaining the pre-generated oral cavity 3D model as shown in step S300, an oral cavity 3D model can be generated. The data contained in the oral cavity 3D model can come from the original medical image file or data obtained by rescanning a specified part of the patient. The specific oral cavity 3D model generation process is as follows: Figure 4 As shown:

[0152] S400: Pre-acquire crown mesh data using a scanning device.

[0153] In practical applications, although the original images in the original medical image files contain crown and root data, the crown mesh data obtained by an oral scanning probe or other direct scanning devices is more accurate. Therefore, in an optional embodiment of this specification, crown mesh data can be obtained by scanning devices to improve the accuracy of the crown data in the oral cavity three-dimensional model.

[0154] S402: Segment each original image in the original medical image file according to the crown mesh data to obtain root mesh data.

[0155] Since the crown portion uses crown mesh data obtained from scanning equipment, the crown data in the original images can be appropriately deleted, retaining only the root data. Specifically, the crown portion in each original image can be registered based on the crown mesh data obtained from the scanning equipment, segmenting the crown portion in each original image, and then the crown portion can be deleted to obtain the root data in each original image. Then, the root data in each original image can be reconstructed to obtain the root mesh data.

[0156] S404: Determine the coordinate system corresponding to the root mesh data as the coordinate system corresponding to the compressed image.

[0157] S406: Register the coordinate system corresponding to the crown mesh data with the coordinate system corresponding to the compressed image to obtain a coordinate transformation matrix.

[0158] The specific registration method between the coordinate system corresponding to the crown mesh data and the coordinate system corresponding to the compressed image can be any existing medical image registration method, such as aligning the mesh vertices of the crown mesh data with the mesh vertices of the root mesh data, registering by extracting feature descriptors based on deep learning and iteratively optimizing the objective function, or registering by deep reinforcement learning. This specification does not limit the specific registration method.

[0159] For example, features are extracted from crown mesh data and root mesh data respectively. A suitable affine transformation model is selected to transform the features of crown mesh data. The similarity between the transformed crown mesh data features and root mesh data features is determined. The parameters of the affine transformation model are adjusted with the goal of maximizing the similarity.

[0160] In addition, when determining the target file corresponding to the oral cavity 3D model, the target file whose second identifier code is the same as the first identifier code of the oral cavity 3D model can be selected by matching the identifier code.

[0161] In an optional embodiment of this specification, since the 3D model data in the oral cavity 3D model originates from the patient's original medical image file, a first identifier code can be generated based on the serial number of the original medical image file. Correspondingly, when the target file is generated, a second identifier code can also be generated based on the serial number of the original medical image file corresponding to the compressed image.

[0162] Of course, other attribute values ​​can also be used to determine the first and second identifier codes, such as the patient's identifier code, as long as the generation rules for the first and second identifier codes are the same. This manual does not limit this.

[0163] S408: Generate a three-dimensional oral cavity model based on the crown mesh data, the root mesh data, and the coordinate system transformation matrix.

[0164] Figure 5 This specification provides a schematic diagram of a multi-plane reconstruction device, which specifically includes:

[0165] The original value range determination module 500 is used to acquire the original medical image file and determine the original value range of the specified parameter based on each original image in the original medical image file.

[0166] The target value range determination module 502 is used to determine the target value range of the specified parameter based on the preset standard value range and the original value range of the specified parameter;

[0167] The grayscale image determination module 504 is used to update the specified parameters of each original image according to the target value range, and to normalize the updated specified parameters to determine the grayscale image corresponding to the original image.

[0168] Compression module 506 is used to compress each grayscale image according to a preset image compression rate to obtain each compressed image;

[0169] The target file generation module 508 is used to generate a target file based on the compressed images and the target value range;

[0170] The reconstruction module 510 is used to respond to a reconstruction request input by the user, perform multi-plane reconstruction based on the target file, and obtain a target cross-sectional image.

[0171] Optionally, the target value range determination module 502 is specifically used to determine whether the upper limit of the parameter in the original value range is greater than the upper limit of the parameter in the standard value range; if so, the original value range is used as the target value range of the specified parameter; if not, the standard value range is used as the target value range of the specified parameter.

[0172] Optionally, the grayscale image determination module 504 is specifically used to determine whether the specified parameters of the original image fall within the target value range; if yes, the specified parameters of the original image are not updated; if no, the specified parameters of the original image are updated according to the upper and lower limits of the target value range.

[0173] Optionally, the grayscale image determination module 504 is specifically used to: normalize the updated specified parameters according to the upper and lower limits of the target value range to obtain the grayscale value of the original image; and determine the grayscale image corresponding to the original image based on the grayscale value of the original image.

[0174] Optionally, the original image in the original medical image file is an oral cavity image;

[0175] Optionally, the reconstruction module 510 is specifically configured to: in response to a reconstruction request input by a user, acquire a pre-generated three-dimensional oral cavity model corresponding to the original medical image file, and display the three-dimensional oral cavity model; in response to a point selected by the user in the three-dimensional oral cavity model, determine the target tooth selected by the user; determine the target file corresponding to the three-dimensional oral cavity model; based on the three-dimensional oral cavity model, determine the target point corresponding to the target tooth, and determine the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file; and perform multi-plane reconstruction based on the target position to obtain a target cross-sectional image.

[0176] Optionally, the reconstruction module 510 is specifically used to: determine the centroid of the target tooth based on the crown mesh data in the oral cavity three-dimensional model; take the centroid of the target tooth as the target point corresponding to the target tooth, and determine the position of the target point in the coordinate system corresponding to the crown mesh data; transform the position of the target point in the coordinate system corresponding to the crown mesh data to the coordinate system corresponding to the compressed image contained in the target file through the coordinate system transformation matrix corresponding to the oral cavity three-dimensional model, and obtain the position of the target point in the coordinate system corresponding to the compressed image, which is used as the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file.

[0177] Optionally, the device further includes:

[0178] The initial cross-sectional image determination module 512 is specifically used to determine, based on the crown mesh data and root mesh data in the oral cavity 3D model, the first candidate points corresponding to each maxillary tooth and the second candidate points corresponding to each mandibular tooth, respectively; transform the first candidate points and the second candidate points to the coordinate system corresponding to the compressed image through the coordinate system transformation matrix in the oral cavity 3D model; determine a designated point based on the first candidate points and the second candidate points in the coordinate system corresponding to the compressed image; and use the position of the designated point in the coordinate system corresponding to the compressed image as the initial position to perform multi-plane reconstruction to obtain the initial cross-sectional image.

[0179] Optionally, the device further includes:

[0180] The oral cavity 3D model generation module 514 is specifically used for: acquiring crown mesh data in advance through a scanning device; segmenting each original image in the original medical image file according to the crown mesh data to obtain root mesh data; determining the coordinate system corresponding to the root mesh data as the coordinate system corresponding to the compressed image; registering the coordinate system corresponding to the crown mesh data with the coordinate system corresponding to the compressed image to obtain a coordinate system transformation matrix; and generating an oral cavity 3D model according to the crown mesh data, the root mesh data, and the coordinate system transformation matrix.

[0181] Optionally, the oral cavity 3D model stores a first identifier code, and the target file stores a second identifier code;

[0182] Optionally, the reconstruction module 510 is specifically used to: determine the first identifier code corresponding to the oral cavity three-dimensional model; determine the second identifier code stored in each target file; and use the target file with the same second identifier code as the first identifier code as the target file corresponding to the oral cavity three-dimensional model.

[0183] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The multi-plane reconstruction method is shown.

[0184] This instruction manual also provides Figure 6 The diagram shows a schematic structural representation of the electronic device. Figure 6 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for the business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The multi-plane reconstruction method is shown. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0185] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0186] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0187] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0188] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0189] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0190] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0191] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0192] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0193] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0194] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0195] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0196] It should also be noted that the terms "comprising," "including," or any other variations thereof are 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 a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0197] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0198] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0199] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0200] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A multi-plane reconstruction method, characterized in that, The method includes: Obtain the original medical image file, and determine the original value range of a specified parameter based on each original image in the original medical image file; wherein, the specified parameter includes: CT value; Based on the preset standard value range and the original value range of the specified parameter, the target value range of the specified parameter is determined; wherein, if the upper limit of the parameter in the original value range is greater than the upper limit of the parameter in the preset standard value range of the specified parameter, then the original value range is taken as the target value range of the specified parameter; otherwise, the standard value range is taken as the target value range of the specified parameter. For each original image, if the specified parameters of the original image do not fall within the target value range, the specified parameters of the original image are updated according to the target value range, and the updated specified parameters are normalized to determine the grayscale image corresponding to the original image. Based on the preset image compression rate, each grayscale image is compressed to obtain a compressed image. Based on the compressed images and the target value range, a target file is generated; In response to a reconstruction request input by the user, multi-plane reconstruction is performed based on the target file to obtain a target cross-sectional image.

2. The method as described in claim 1, characterized in that, Update the specified parameters of the original image according to the target value range, specifically including: Determine whether the specified parameters of the original image fall within the target value range; If so, do not update the specified parameters of the original image; If not, update the specified parameters of the original image according to the upper and lower limits of the target value range.

3. The method as described in claim 1, characterized in that, The updated specified parameters are normalized to determine the grayscale image corresponding to the original image, specifically including: Based on the upper and lower limits of the target value range, the updated specified parameters are normalized to obtain the grayscale value of the original image. Based on the grayscale values ​​of the original image, determine the corresponding grayscale image.

4. The method as described in claim 1, characterized in that, The original image in the original medical image file is an oral cavity image; In response to a user-inputted reconstruction request, multi-plane reconstruction is performed based on the target file to obtain a target cross-sectional image, specifically including: In response to a user-inputted reconstruction request, the system retrieves and displays a pre-generated 3D model of the oral cavity corresponding to the original medical image file. In response to the point selected by the user in the oral cavity 3D model, the target tooth selected by the user is determined; Determine the target file corresponding to the oral cavity 3D model; Based on the oral cavity 3D model, the target point corresponding to the target tooth is determined, and the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file is determined; Multi-plane reconstruction is performed based on the target location to obtain a cross-sectional image of the target.

5. The method as described in claim 4, characterized in that, Based on the oral cavity 3D model, the target point corresponding to the target tooth is determined, and the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file is determined, specifically including: The centroid of the target tooth is determined based on the crown mesh data in the oral cavity 3D model; The centroid of the target tooth is taken as the target point corresponding to the target tooth, and the position of the target point in the coordinate system corresponding to the crown mesh data is determined. By using the coordinate transformation matrix corresponding to the oral cavity 3D model, the position of the target point in the coordinate system corresponding to the crown mesh data is transformed to the coordinate system corresponding to the compressed image contained in the target file, and the position of the target point in the coordinate system corresponding to the compressed image is obtained, which is used as the target position of the target point in the coordinate system corresponding to the compressed image contained in the target file.

6. The method as described in claim 4, characterized in that, The method further includes: Based on the crown mesh data and root mesh data in the oral cavity three-dimensional model, the first candidate point corresponding to each maxillary tooth and the second candidate point corresponding to each mandibular tooth are determined respectively. Using the coordinate system transformation matrix in the oral cavity 3D model, the first candidate point and the second candidate point are respectively transformed to the coordinate system corresponding to the compressed image; The designated point is determined based on the first and second candidate points in the coordinate system corresponding to the compressed image. Using the position of the specified point in the coordinate system corresponding to the compressed image as the initial position, multi-plane reconstruction is performed to obtain the initial cross-sectional image.

7. The method as described in claim 4, characterized in that, Pre-generating a 3D model of the oral cavity, specifically including: Pre-acquire crown mesh data using a scanning device; Based on the crown mesh data, the original images in the original medical image file are segmented to obtain the root mesh data; The coordinate system corresponding to the tooth root mesh data is determined as the coordinate system corresponding to the compressed image; The coordinate system corresponding to the crown mesh data is registered with the coordinate system corresponding to the compressed image to obtain the coordinate system transformation matrix; A three-dimensional oral cavity model is generated based on the crown mesh data, the root mesh data, and the coordinate system transformation matrix.

8. The method as described in claim 4, characterized in that, The oral cavity 3D model stores a first identifier code, and the target file stores a second identifier code. Determining the target file corresponding to the oral cavity 3D model specifically includes: Determine the first identifier code corresponding to the oral cavity three-dimensional model; Determine the second identifier stored in each target file; The target file with the same second identifier as the first identifier is used as the target file corresponding to the oral cavity three-dimensional model.

9. A multi-plane reconstruction device, characterized in that, include: The original value range determination module is used to acquire the original medical image file and determine the original value range of a specified parameter based on each original image in the original medical image file; wherein, the specified parameter includes: CT value; The target value range determination module is used to determine the target value range of the specified parameter based on the preset standard value range and the original value range of the specified parameter; wherein, if the upper limit of the parameter in the original value range is greater than the upper limit of the parameter in the preset standard value range of the specified parameter, then the original value range is taken as the target value range of the specified parameter; otherwise, the standard value range is taken as the target value range of the specified parameter. The grayscale image determination module is used to, for each original image, update the specified parameters of the original image according to the target value range if the specified parameters of the original image do not fall within the target value range, and perform normalization processing on the updated specified parameters to determine the grayscale image corresponding to the original image. The compression module is used to compress each grayscale image according to a preset image compression ratio to obtain each compressed image. The target file generation module is used to generate a target file based on each compressed image and the target value range; The reconstruction module is used to respond to a reconstruction request input by the user, perform multi-plane reconstruction based on the target file, and obtain a target cross-sectional image.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 8.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 8.

Images