Soft and hard tissue collaborative orthodontic adjuvant therapy system based on CBCT and pseudo nuclear magnetic bimodal image

Abstract

A soft and hard tissue collaborative orthodontic adjuvant therapy system based on CBCT and pseudo nuclear magnetic bimodal images comprises: data acquisition and preprocessing: using CBCT equipment to obtain an oral cavity three-dimensional image, and performing standardization processing; the pseudo MRI image generation module is used for generating a pseudo nuclear magnetic image with high-contrast soft tissue information from the standardized CBCT image by using a deep learning model; multi-modal image fusion: combining the standardized CBCT image with the pseudo nuclear magnetic image based on a multi-modal fusion algorithm of feature enhancement to generate a soft and hard tissue collaborative image; the tooth segmentation and numbering module is used for segmenting teeth in the collaborative image by using a deep learning model, extracting a single tooth contour and numbering based on a spatial position and morphological characteristics; the orthodontic path planning module is used for formulating a tooth movement path by using a multi-objective optimization algorithm in combination with the tooth segmentation result and the collaborative image data; and the simulation and evaluation module simulates the tooth movement process in the three-dimensional simulation model and verifies the feasibility of the treatment path.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging and oral orthodontics, and in particular to an orthodontic auxiliary system for realizing collaborative diagnosis and treatment of hard and soft tissues through CBCT and pseudo-nuclear magnetic resonance dual-modality image fusion. Background Art

[0002] In orthodontic treatment, imaging technology is of great significance to the accuracy of diagnosis and the formulation of treatment plans. The widely used CBCT has high-resolution hard tissue imaging capabilities, but performs poorly in terms of soft tissue contrast, which limits the accurate diagnosis of complex cases. Although traditional MRI technology can provide high-contrast soft tissue images, it is difficult to popularize due to equipment cost and time constraints. Existing image processing technology cannot efficiently integrate the hard tissue advantages of CBCT with the detailed information of soft tissue. In addition, the formulation of existing treatment plans is mostly based on single-modality data, which makes it difficult to take into account the coordinated planning of hard and soft tissues. How to achieve dual-modality fusion on the basis of efficiently generating pseudo-nuclear magnetic resonance images and apply it to orthodontic treatment has become an urgent problem to be solved. Summary of the invention

[0003] The present invention aims to solve the problems of soft and hard tissue image separation and insufficient collaborative treatment planning in the prior art, and proposes an orthodontic auxiliary treatment system based on CBCT to reconstruct pseudo-nuclear magnetic resonance images and realize dual-modality fusion.

[0004] <Technical solution>

[0005] A soft and hard tissue coordinated orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality imaging, comprising:

[0006] Data acquisition and preprocessing, used to obtain oral three-dimensional images using CBCT equipment, and perform standardization processing to obtain standardized CBCT images;

[0007] A pseudo MRI image generation module is used to generate pseudo nuclear magnetic resonance images with high-contrast soft tissue information from standardized CBCT images using a deep learning model;

[0008] Multimodal image fusion is used to combine standardized CBCT images with pseudo-MRI images based on feature enhancement to generate soft and hard tissue synergistic images.

[0009] Preferably, the soft and hard tissue collaborative orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality images also includes: a tooth segmentation and numbering module, which is used to segment the teeth in the collaborative image using a deep learning model, extract the contours of single teeth, and number them based on spatial position and morphological characteristics.

[0010] Preferably, the soft and hard tissue collaborative orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality imaging also includes: an orthodontic path planning module, which is used to combine the tooth segmentation results with the collaborative imaging data and use a multi-objective optimization algorithm to formulate a tooth movement path.

[0011] Preferably, the path planning of the orthodontic path planning module supports real-time adjustment to dynamically adjust the path planning.

[0012] Preferably, the soft and hard tissue collaborative orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality imaging also includes: a simulation and evaluation module, which is used to simulate the tooth movement process in a three-dimensional simulation model, verify the feasibility of the treatment path, and provide quantitative data of the treatment effect through the evaluation module.

[0013] Preferably, the soft and hard tissue collaborative orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality imaging also includes: a central control module for monitoring the operating status of each module and optimizing system performance and processing efficiency through a feedback mechanism.

[0014] Preferably, the data storage module is used to record patient information and treatment data to support subsequent queries and program optimization.

[0015] Preferably, the data storage module uses an encryption algorithm to ensure the security and privacy protection of patient imaging data and treatment plans.

[0016] Preferably, multimodal image fusion combines CBCT and pseudo-MRI images to generate soft and hard tissue collaborative images while retaining the resolution information of CBCT and the contrast information of pseudo-MRI through pixel-level and feature-level fusion algorithms.

[0017] Preferably, the standardization processing of the data acquisition and preprocessing module includes denoising, correction, alignment and cropping.

[0018] <Beneficial Effects of the Invention>

[0019] The beneficial technical effects of the present invention include at least:

[0020] 1. Image fusion innovation: Combining CBCT and pseudo-MRI images, it provides high-quality images of soft and hard tissue synergy, significantly improving diagnostic accuracy.

[0021] 2. Personalized treatment plan: Through multi-objective optimization algorithm and real-time adjustment mechanism, more efficient orthodontic path planning can be achieved.

[0022] 3. Simulation and evaluation guarantee: Through three-dimensional simulation and quantitative evaluation, the treatment risk is reduced and the scientificity and applicability of the plan are improved.

[0023] 4. System module integration: From data collection to treatment output, a complete closed loop is formed to improve system work efficiency and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] A more complete understanding of the present invention and its attendant advantages and features will be more readily appreciated by reference to the following detailed description taken in conjunction with the accompanying drawings, in which:

[0025] Figure 1 The functional block diagram of the soft and hard tissue coordinated orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality imaging according to a preferred embodiment of the present invention is schematically shown.

[0026] Figure 2 An example of a real CBCT image is shown.

[0027] Figure 3 An example of a reference MR is shown.

[0028] Figure 4 An example of pseudo MR obtained by the present invention is shown.

[0029] Figure 5 An example of the soft and hard tissue coordinated imaging obtained by the present invention is shown.

[0030] It should be noted that the drawings are used to illustrate the present invention, rather than to limit the present invention. Note that the drawings showing the structures may not be drawn to scale. In addition, in the drawings, the same or similar elements are marked with the same or similar reference numerals. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0033] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0034] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0035] In general, the present invention provides an orthodontic auxiliary treatment system for coordinated hard and soft tissues based on CBCT and pseudo-MRI dual-modality imaging. The system utilizes multimodality image fusion technology to combine the high-resolution hard tissue imaging of CBCT with the high soft tissue contrast advantages of pseudo-MRI imaging to form a diagnosis and treatment plan for coordinated hard and soft tissues.

[0036] The innovations of the present invention include at least: 1) developing a multimodal image fusion algorithm to achieve accurate fusion of CBCT images and pseudo-MRI images, provide coordinated display of soft and hard tissues, and significantly improve image quality; 2) proposing a personalized orthodontic path planning algorithm, combining multi-objective optimization, and formulating a dynamically adjusted treatment plan; 3) through the simulation and evaluation module, the planned treatment plan is simulated in three dimensions and the effect is evaluated to improve the scientific nature and clinical applicability of the plan. While improving image clarity and diagnostic accuracy, the present invention optimizes the orthodontic treatment path, significantly reduces the cost of diagnosis and treatment, and provides efficient and accurate auxiliary treatment support for complex orthodontic cases, which has a wide range of clinical application value.

[0037] Figure 1 The functional block diagram of the soft and hard tissue coordinated orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality imaging according to a preferred embodiment of the present invention is schematically shown.

[0038] like Figure 1 As shown, the soft and hard tissue coordinated orthodontic auxiliary treatment system based on CBCT and pseudo nuclear magnetic resonance dual-modality imaging according to a preferred embodiment of the present invention includes:

[0039] Data acquisition and preprocessing 10, for acquiring oral three-dimensional images using a CBCT device, and performing standardized processing (such as denoising, correction, alignment and cropping, thereby optimizing the quality and consistency of CBCT image data), thereby obtaining standardized CBCT images;

[0040] A pseudo MRI image generation module 20, for generating a pseudo nuclear magnetic resonance image with high-contrast soft tissue information from a standardized CBCT image using a deep learning model;

[0041] Among them, the deep learning model uses a deep learning model based on a neural network DDPM model (preferably, the latest diffusion + transfer model) because it has high accuracy and performance in image recognition and processing. For example, the deep learning model includes but is not limited to any of the following: the diffusion model MC-IDDPM, which generates high-resolution images through iterative denoising; the boundary condition diffusion model (BBDM), which enhances image clarity and contrast through boundary guidance; the conditional generative adversarial network (cGAN), which generates pseudo images based on input images and conditions.

[0042] Among them, for the training of deep learning models, for example, the following specific methods can be adopted: use a large number of CBCT and real MRI images to train the model and establish a mapping relationship from CBCT to MRI. The training data set should include multiple types of oral images to ensure the generalization ability of the model; use data enhancement technology (such as rotation, flipping, scaling, etc.) to increase the diversity of training data and improve the robustness of the model; use cross-validation methods to evaluate model performance, adjust model parameters, and optimize model effects.

[0043] The process of generating pseudo images by the deep learning model can include: using a diffusion model to generate images through iterative denoising; using a conditional generative adversarial network (cGAN) to generate pseudo images based on input images and conditions; optimizing the generated images in combination with boundary conditions, such as optimizing the details and clarity of the generated images. In the image reconstruction process, through continuous iterative training, the generated pseudo MRI images can approach the characteristics of real MRI images, with both the high resolution of CBCT and the ability to clearly display soft tissue structures.

[0044] For example, refer to Figures 2 to 4 As shown, Figure 2 shows a real CBCT image, Figure 3 The corresponding reference MR is shown, Figure 4 The corresponding pseudo MR obtained by the present invention is shown.

[0045] Furthermore, the present invention also includes: multimodal image fusion 30, which is used to combine the standardized CBCT image with the pseudo nuclear magnetic resonance image based on the feature-enhanced multimodal fusion algorithm to generate a soft and hard tissue collaborative image.

[0046] For example, refer to Figures 2 to 5 As shown, Figure 2 shows a real CBCT image, Figure 3 The corresponding reference MR is shown, Figure 4The corresponding pseudo MR obtained by the present invention is shown. Figure 5 An example of corresponding soft and hard tissue synergistic images obtained by the present invention is shown.

[0047] In a specific embodiment, for example, the multimodal image fusion 30 uses a feature enhancement algorithm, such as a pixel-level and feature-level fusion algorithm, combining the high resolution of the CBCT image with the high contrast of the pseudo-MRI image (while retaining the high resolution information of the CBCT and the high contrast information of the pseudo-MRI), and combining the CBCT with the pseudo-MRI image to generate a soft and hard tissue collaborative image. The fusion result highlights the bone and tooth structure while showing high-contrast soft tissue details. Preferably, the multimodal image fusion module 30 also performs a quality assessment on the fused image data and enhances the key features to improve the diagnostic effect.

[0048] The tooth segmentation and numbering module 40 is used to segment the teeth in the collaborative image using a deep learning model, extract the contours of individual teeth, and number them based on spatial position and morphological features; for example, the tooth segmentation and numbering module automatically extracts the contours of individual teeth based on the collaborative image, and numbers them in combination with their spatial position information to generate a digital tooth file.

[0049] The orthodontic path planning module 50 is used to combine the tooth segmentation results with the collaborative image data and use a multi-objective optimization algorithm to formulate a tooth movement path, taking into account treatment time, patient comfort and final effect. The path planning supports real-time adjustment to dynamically adjust the path planning to meet the needs of different patients.

[0050] The simulation and evaluation module 60 is used to simulate the tooth movement process in the three-dimensional simulation model, verify the feasibility of the treatment path, and provide quantitative data of the treatment effect through the evaluation module, for example, the feasibility and effectiveness of the scheme are evaluated through quantitative indicators (such as tooth displacement error, treatment time, etc.).

[0051] The central control module 70 is used to coordinate all functional modules to ensure efficient operation of the data flow, monitor the operating status of each module and optimize system performance and processing efficiency through a feedback mechanism;

[0052] The data storage module 80 is used to record patient information and treatment data to support subsequent query and program optimization. Preferably, the data storage module 80 uses an encryption algorithm to ensure the security and privacy protection of patient imaging data and treatment programs.

[0053] Therefore, in specific operations, data acquisition involves collecting image data through CBCT equipment and performing preprocessing; when reconstructing pseudo MRI images, deep learning technology is used to convert standardized CBCT images into pseudo MRI images; during image fusion, the multimodal fusion module generates soft and hard tissue collaborative images; followed by segmentation and planning, segmenting teeth, and formulating personalized treatment paths; thereafter, simulation evaluation can be performed, and the treatment plan can be three-dimensionally simulated and optimized; finally, the plan is output, and the doctor can evaluate the simulation results and generate the final treatment plan.

[0054] It should be noted that, unless otherwise specified, the terms "first", "second", "third", etc. in the specification are only used to distinguish the various components, elements, steps, etc. in the specification, and are not used to indicate the logical relationship or sequential relationship between the various components, elements, steps, etc.

[0055] It is to be understood that, although the present invention has been disclosed as a preferred embodiment, the above embodiment is not intended to limit the present invention. For any person skilled in the art, without departing from the scope of the technical solution of the present invention, the technical content disclosed above can be used to make many possible changes and modifications to the technical solution of the present invention, or modified into equivalent embodiments of equivalent changes. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of protection of the technical solution of the present invention.

Claims

1. A soft and hard tissue coordinated orthodontic auxiliary treatment system based on CBCT and pseudo-MRI dual-modality imaging, characterized by include: Data acquisition and preprocessing, used to obtain oral three-dimensional images using CBCT equipment, and perform standardization processing to obtain standardized CBCT images; A pseudo MRI image generation module is used to generate pseudo nuclear magnetic resonance images with high-contrast soft tissue information from standardized CBCT images using a deep learning model; Multimodal image fusion is used to combine standardized CBCT images with pseudo-MRI images based on feature enhancement to generate soft and hard tissue synergistic images.

2. The system according to claim 1, characterized in that It also includes: a tooth segmentation and numbering module, which uses a deep learning model to segment teeth in collaborative images, extract the contours of individual teeth, and number them based on spatial position and morphological characteristics.

3. The system according to claim 1, characterized in that Also includes: The orthodontic path planning module is used to combine the tooth segmentation results with the collaborative image data and use a multi-objective optimization algorithm to formulate the tooth movement path.

4. The system according to claim 3, characterized in that The path planning of the orthodontic path planning module supports real-time adjustment to dynamically adjust the path planning.

5. The system according to claim 1, characterized in that It also includes: a simulation and evaluation module, which is used to simulate the tooth movement process in a three-dimensional simulation model, verify the feasibility of the treatment path, and provide quantitative data of the treatment effect through an evaluation module.

6. The system according to claim 1, characterized in that Also includes: The central control module is used to monitor the operating status of each module and optimize system performance and processing efficiency through feedback mechanism.

7. The system according to claim 6, characterized in that Also includes: The data storage module is used to record patient information and treatment data to support subsequent queries and program optimization.

8. The system according to claim 7, characterized in that The data storage module uses encryption algorithms to ensure the security and privacy protection of patient imaging data and treatment plans.

9. The system according to claim 1, characterized in that Multimodal image fusion uses pixel-level and feature-level fusion algorithms to combine CBCT and pseudo-MRI images to generate soft and hard tissue collaborative images while retaining the resolution information of CBCT and the contrast information of pseudo-MRI.

10. The system according to claim 1, characterized in that The standardized processing of the data acquisition and preprocessing module includes denoising, correction, alignment and cropping.

Images