Jaw internal hemangioma recognition system based on CBCT data source

Abstract

The invention discloses a jaw hemangioma identification system based on CBCT data source, which is applied to detection and discrimination of a jaw hemangioma, and comprises an identification module and a data and preprocessing module, the identification module is used for carrying out model processing on an original image from CBCT to generate a structure model, and the data and preprocessing module is used for carrying out data processing on the structure model; marking a target tumor body on the structure model to assist a user in distinguishing; the data acquisition and preprocessing module is used for preprocessing data of each input stage and acquiring original data and real-time data of a user in an operation process; through the data acquisition and preprocessing module and the identification module, informatization labeling and showing of the target tumor body are realized, and medical personnel are assisted to accurately judge the target tumor body.

Description

Technical Field

[0001] The present invention relates to the field of machine learning, and in particular to a jaw hemangioma recognition system based on CBCT data sources. Background Art

[0002] Mandibular hemangioma is a rare benign lesion with abnormal proliferation of blood vessels in the jaw, also known as central mandibular hemangioma or mandibular intraosseous arteriovenous malformation. At present, due to the limitations of pathological examination, the diagnosis of mandibular hemangioma mainly depends on clinical and imaging manifestations. Cone beam computed tomography (CBCT) is an imaging examination technology widely used in the field of oral medicine. It has the characteristics of high resolution, low radiation dose, and short data acquisition time. It is the most commonly used imaging method for mandibular hemangioma. However, mandibular hemangioma is difficult to distinguish from benign maxillofacial tumors (such as ameloblastoma, odontogenic cyst, etc.) due to the non-specificity of imaging manifestations and the lack of obvious early symptoms. It mainly depends on the experience and clinical judgment of surgeons; the main difficulties lie in two aspects. The first aspect is that the early symptoms are not obvious. Since mandibular hemangioma may have no obvious symptoms and signs in the early stage, loose teeth, malocclusion, repeated bleeding of gums (aggravated at night), facial swelling, local numbness or pain may occur in the later stage. These symptoms are similar to those of some benign tumors, which increases the difficulty of identification. The second aspect is that the imaging manifestations are non-specific. Intramandibular hemangioma may show multicystic honeycomb-like changes in imaging, with clear or unclear boundaries in the lesion area, thin intervals between honeycombs, and very fine light-blocking lines in the bone tissue at the edge of each cyst. These manifestations are not unique to hemangioma. Other benign tumors such as ameloblastoma and odontogenic cyst may also have similar manifestations, leading to difficulties in identification. It is also worth noting that intramandibular hemangioma is one of the more dangerous diseases in oral and maxillofacial surgery due to its rarity and potential risk of massive bleeding. If the doctor performs surgery on a benign maxillofacial tumor, it is likely to cause massive bleeding during the operation, which may endanger the patient's life in severe cases. Therefore, a hemangioma recognition system is needed to distinguish intramandibular hemangioma from benign maxillofacial tumors through imaging manifestations at an early stage, which plays an important role in reducing surgical risks, reducing surgical trauma, and improving the quality of life of patients. Summary of the invention

[0003] In view of the technical problem that there is no suitable solution for identifying intramandibular hemangioma in the clinical detection of intramandibular hemangioma in the prior art, the present invention aims to provide an intramandibular hemangioma identification system based on CBCT data source, which can help surgeons to distinguish it from benign maxillofacial tumors through imaging manifestations at an early stage and choose appropriate treatment measures to achieve the purpose of reducing the risk of massive bleeding, reducing surgical trauma, etc., and restoring the patient's function and quality of life to the greatest extent.

[0004] To achieve the above object, the present invention provides a system for identifying intramandibular hemangioma based on CBCT data source, the system comprising: A recognition module, used for performing multi-model processing on the original image to generate a structural model, and marking the target tumor on the structural model; It also includes a data acquisition and preprocessing module, which is used to preprocess the data at each input stage and to collect the original data and the real-time data of the user during the operation; The real-time reasoning and feedback module is used to associate the recognition module with the data acquisition and preprocessing module to provide real-time feedback of the target tumor information to the user.

[0005] Among them, before the original image is input into the model for processing, it needs to be preprocessed. The preprocessing steps include: Image normalization: obtain the original image and perform normalization on the original image to obtain a primary image; Image enhancement: Perform data enhancement on the primary image to obtain the secondary image; Image annotation: Label the secondary images and ensure spatial consistency to obtain training data.

[0006] Among them, the data enhancement method includes at least one of geometric transformation, color and brightness adjustment, noise addition and local deformation.

[0007] The generation of the structural model includes the following steps: The training data is input into the YOLO model for modeling processing to generate a structural model.

[0008] Among them, the YOLO model training process is: A1. Data preprocessing: adjust the training data to a fixed size to achieve standardized input; A2. Target detection: The YOLO model extracts image features through a convolutional neural network to generate the bounding box of the target tumor and the probability of its corresponding category; A3. Optimize training: Use the cross entropy loss function and IoU loss function to optimize the model to ensure that the convolutional network can produce positioning and classification results during detection; A4. Data output: The output includes the location information of each target tumor and the corresponding classification probability.

[0009] After the structural model is obtained, the following steps are also included: The ResNet model is used to receive the output data of the YOLO model, classify and refine the target tumor location to output classification information.

[0010] Among them, the ResNet model training process is: B1. Feature extraction and classification: Input at least one location information, perform multi-layer convolution and pooling layer operations on the ResNet model to extract higher-level image features, and use the fully connected layer to further classify the anatomical structure so that each target tumor will be assigned a probability value; B2. Cross entropy loss function: Use the cross entropy loss function to optimize the ResNet model; B3. Training optimization: Use the Adam optimizer for training and adjust the weight parameters in the model to minimize the loss function; B4. Data output: The ResNet model outputs the category of each target tumor and the confidence of the category as classification information.

[0011] Among them, it also includes an integration module, which integrates the data acquisition and preprocessing module, the recognition module and the real-time reasoning and feedback module as sub-modules, and also includes an auxiliary sub-module, which is associated with the recognition module.

[0012] The beneficial effects of the present invention are as follows: compared with the prior art, the present invention provides a jaw hemangioma identification system based on CBCT data source, characterized in that the system includes an identification module and a data and preprocessing module, wherein the identification module is used to perform model processing on the original image derived from CBCT to generate a structural model, and mark the target tumor on the structural model to assist the user in making a judgment; the data acquisition and preprocessing module is used to preprocess the data at each input stage, and to collect the original data and the real-time data of the user during the operation; through the data acquisition and preprocessing module and the identification module, the target tumor is annotated and displayed in an informationized manner, so as to assist medical staff in making an accurate judgment on the target tumor. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of module connection of the present invention; Figure 2 A schematic diagram of module connection according to another embodiment of the present invention; Figure 3 is a schematic diagram of an identification module of the present invention; Figure 4 Schematic diagram of the training steps of the YOLO model of the present invention; Figure 5 Schematic diagram of the training steps of the ResNet model of the present invention; Figure 6 A diagram showing the training data processing steps of the present invention; Figure 7 This is a schematic diagram of the optimization means for labeling of the present invention; Figure 8Schematic diagram of data enhancement processing of the present invention. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with the accompanying drawings.

[0015] In the following description, the example details are given to provide a deeper understanding of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. It should be understood that the specific embodiments are only used to explain the present invention and are not used to limit the present invention.

[0016] It should be understood that when the terms "include" and / or "comprises" are used in this specification, they indicate the existence of the stated features, integers, steps, operations, elements or components, but do not exclude the existence or addition of one or more other features, integers, steps, operations, elements, components or combinations thereof.

[0017] In view of the technical problem that the existing clinical medical anatomy is extremely dependent on the experience and feeling of medical staff, which increases the risk and difficulty of surgery, and there is no suitable solution to assist medical staff in making judgments to reduce the risk and difficulty of surgery, this application provides a mandibular hemangioma recognition system based on CBCT data source, which is used to detect and identify tumors in the mandible. Please refer to the attached Figure 1 To Attachment Figure 8 The system includes a data acquisition and preprocessing module and an identification module; wherein the identification module is used to perform model processing on the original image from CBCT to generate a structural model, and mark the target tumor on the structural model to assist the user in making a judgment; the data acquisition and preprocessing module is used to preprocess the data at each input stage, and to collect the original data and the real-time data of the user during the operation; Through the cooperation of data acquisition and preprocessing module, recognition module and real-time reasoning, the target tumor can be labeled and displayed in an informationized manner, which can assist medical staff in making judgments on the target tumor. This greatly reduces the experience requirements for medical staff, and medical staff can more conveniently choose appropriate treatment measures, reduce subsequent surgical risks and reduce surgical trauma.

[0018] In order to better understand this solution, the following is combined with specific implementation details to further elaborate on the early data collection and processing, model construction and optimization, and implementation collection of user data. The user in this application is understood to be the surgeon, attending physician, surgeon, or medical staff assisting in the operation.

[0019] In terms of early data acquisition and processing, in the system of the present application, the original image is obtained through CBCT technology, which is cone beam CT. The projected image obtained is a two-dimensional image. After reconstruction, a three-dimensional image can be obtained. The data is highly representative and widely used in the fields of oral surgery and oral inspection. Due to the difficulty in obtaining the original image, the sample size limitation, and the differences between different patients during the operation, mainly due to the differences in different models, firmware versions, and different use angles when the machine collects the original image, the original image will appear more complicated. Therefore, the original image is preprocessed in particular, and the preprocessing steps include: Image standardization: obtain the original image and normalize it to obtain a first-level image; normalize the original images from different sources to ensure the consistency of the input data; Image augmentation: Perform data augmentation on primary images to obtain secondary images; use data augmentation techniques to process images to increase the diversity and robustness of the resulting training data, especially in the case of low-quality or missing data; Image annotation: Label the secondary images and ensure spatial consistency to obtain training data. Medical staff annotate the secondary images with the assistance of automated tools to ensure the accuracy of the labels of the target tumors, while optimizing the refinement and spatial consistency of the labels. The training data is highly representative and accurate. It can be seen that data enhancement and label annotation are important steps to ensure that the model is robust and accurate in surgical scenarios. Data enhancement and label annotation can improve the diversity and quality of training data, thereby enhancing the generalization ability of the model and ensuring that the model can cope with various situations and uncertainties.

[0020] It is worth noting that enhancing the original image through data enhancement can significantly be compatible with more sources and quantities of original data, making the subsequently produced model more referenceable; therefore, in this embodiment, the specific means of image enhancement include: Geometric transformation: Perform geometric transformations on the primary image, such as rotation, translation, scaling, and mirror flipping, to simulate different shooting angles and perspective changes, so that the subsequently generated structural model can adapt to different surgical perspectives and postures; Color and brightness adjustment: Taking into account the changes in lighting during the operation, use brightness, contrast, saturation adjustment and other methods to simulate image changes under different lighting conditions.

[0021] Noise addition: Simulate the noise in the original image (such as Gaussian noise, salt and pepper noise, etc.) to enhance the robustness of the model so that it can still accurately identify targets in unclear or low-quality images during surgery.

[0022] Local deformation: In order to simulate the deformation during surgery and the local deformation of tissues, the image can be elastically deformed or affine transformed to improve the adaptability of the subsequent structural model to the target tumor after morphological changes.

[0023] It can be seen that data enhancement can significantly improve the diversity of original images, adapt to different surgical scenarios and effectively optimize surgical scenarios; specifically, in terms of the diversity of data sources, by generating original images in different geometric states, data enhancement can expand the data set and reduce the risk of overfitting; in terms of adapting to different surgical scenarios, during surgery, conditions such as lighting, viewing angle, and image noise may change, and data enhancement can simulate these changes to improve the adaptability of the model; with emphasis on optimizing training effects, the enhanced data set enables the model to better learn the characteristics of target tumors in different situations, and improve the recognition ability of smaller target tumors and targets with blurred boundaries; Regarding label annotation processing, the target tumor in the original image is highly professional, and the accuracy of label annotation is crucial to the training of the model; label annotation helps ensure that each target tumor is correctly and accurately labeled in the data; for example, medical personnel accurately annotate the associated lesion area of ​​the mandibular hemangioma or the tissue in the lesion area (such as blood vessels, nerves, muscles, bones, etc.) based on the secondary image to ensure that the bounding box and category label of each structure are correct; in a better solution, the label annotation can be multi-layered, for example, considering the details and levels of certain structures (for example, the branches of nerves), the target tumor is annotated with multi-layer labels, so that the subsequent model can identify different parts of the target tumor (such as "superior branch of facial nerve", "inferior branch of facial nerve", etc.); The specific optimization methods for label annotation are: Label consistency check: Perform consistency check on the annotations in the secondary images to ensure that the labels and bounding boxes of each target tumor are accurate; optionally, reduce label bias through cross-validation and feedback from medical staff; Label expansion: Generate new labels for the same target tumor (for example, the target areas detected by the YOLO model can further generate refined labels for these areas) to supplement the deficiencies in the labels, especially in the annotation of subdivided anatomical structures (such as vascular branches, nerve branches, etc.).

[0024] Multi-label learning: In special cases, a target area may belong to multiple categories. For example, some target tumors can be classified as "trigeminal nerve" or as part of "facial nerve" due to their special location. Multi-label learning can optimize the performance of the model in such multiple classification tasks.

[0025] Associate three-dimensional space for label calibration: By combining 3D annotation tools (such as 3D reconstruction technology), the spatial consistency of label annotation is optimized to ensure that the annotation of each target tumor is accurate not only in the two-dimensional plane but also in the three-dimensional space.

[0026] In order to achieve more representative and accurate training data, it also includes: a. Data segmentation: The data set formed by the secondary images after data augmentation processing is divided into training set, validation set and test set to ensure the diversity and representativeness of each data set and prevent overfitting of the model.

[0027] b. Batch training and validation: Use the data-enhanced training set for batch training, and use the validation set to evaluate the model's performance on new data. Adjust the data enhancement strategy based on the validation results to further improve the accuracy of the model.

[0028] c. Label optimization and loss function: During the training process, label annotation and data enhancement are combined, and appropriate loss functions (such as Focal Loss) are used to improve the classification accuracy of difficult-to-identify samples (such as small target tumors and fuzzy boundaries of the target location).

[0029] As a partial summary, it is not difficult to know that the data acquisition and preprocessing module of the present application can effectively process the original image to generate training data with strong representativeness and accuracy as output; it is derived from a variety of original data as a data source, and can simulate the changing conditions in various types of operations, so that the subsequent structural model has strong adaptability and robustness; and it can ensure the accuracy of the label of each anatomical structure through label annotation and its optimization method, especially in the identification of subdivided anatomical structures, to enhance the classification accuracy of the model; and through data enhancement technology, it also further enhances the recognition ability of smaller blood vessels, nerves, etc.; associate three-dimensional space construction for label calibration, improve navigation accuracy in subsequent surgical processes, and ultimately achieve more complete and accurate data input into the structural model.

[0030] In the model construction and optimization part, this system will further process the training data obtained by the above processing through the model. The processed models are YOLO (You Only Look Once) model and ResNet (Residual Neural Network) model. First, the generation of the structural model includes the following steps: The training data is input into the YOLO model for modeling and processing to generate a structural model; by constructing the structural model as an important basis for auxiliary surgery, the YOLO model can first accept the training data input by the data acquisition and preprocessing module to construct a structural model. The obtained structural model can intuitively and quickly preliminarily represent the intramandibular situation and intuitively identify the target tumor. The aforementioned anatomical structure is the key structures such as blood vessels, nerves, bones, etc. associated with the target tumor; the version of the YOLO model is YOLOv8 or YOLOv11, and YOLOv11 is preferably used. Compared with YOLOv8, YOLOv11 uses a more efficient backbone network (Backbone) and a more sophisticated decoding method (Decoding), which is suitable for complex surgical scenarios and has more complete algorithm accuracy.

[0031] Specifically, the YOLO model training process is: A1. Data preprocessing: adjust the training data to a fixed size to achieve standardized input; A2. Target detection: The YOLO model extracts image features through a convolutional neural network (CNN) to generate the bounding box of the target tumor and the probability of its corresponding category; A3. Optimize training: Use the cross entropy loss function and IoU (Intersection over Union) loss function to optimize the model to ensure that the convolutional network can produce positioning and classification results during detection; A4. Data output: The output includes the location information of each target tumor and the corresponding classification probability.

[0032] It can be seen that the YOLO model extracts image features from the input medical images through convolutional neural networks, and can then effectively detect the target tumor. Its efficient feature extraction capability ensures real-time response during surgery and quickly provides the location and classification probability of important anatomical structures.

[0033] It is worth noting that the YOLO model does not just process the training data. During the operation, the data acquisition and preprocessing module will also transmit the images or video streams collected at all times to the YOLO model. The YOLO model continues to detect the target tumor in each frame of the image and displays relevant classification information for the target tumor. Medical staff can intuitively and quickly obtain relevant information feedback from the structural model and classification information to assist in the operation. The feedback can be in the form of a corresponding surgical navigation subsystem, which is displayed to medical staff through projection, display, etc., so that they can intuitively understand the anatomical structure in the lesion area and the spatial relationship between the target tumors. During the operation, medical staff can make operational adjustments based on the output of the YOLO model, and the system can also update the anatomical structure and classification results in real time according to environmental changes to ensure efficient and accurate completion of the operation.

[0034] It can be seen that the training data and real-time collected data processed by the YOLO model as described above can perform image analysis within milliseconds, ensuring the efficiency and safety of the operation, and also performs better in small anatomical structures and overlapping target tumors, and is more suitable for complex jaw surgery; on the other hand, the YOLO model is relatively lightweight, suitable for deployment on embedded hardware, and is suitable for real-time computing needs at the surgical site.

[0035] In a further solution, after obtaining the structural model, the following steps are also included: The ResNet model is used to receive the output data of the YOLO model, classify and refine the target tumor location to output classification information; after the YOLO model detects the structural target, the ResNet model is used to further classify and refine these target models. The residual connection of the ResNet model can solve the gradient vanishing problem in the deep network and improve the training efficiency and performance of the structural model; the basic principle is that the core of the ResNet model lies in its "residual block" design. This model structure can effectively solve the problem of information attenuation in the deep network through "jump connection", so that the model network can maintain stable training performance while increasing the depth; It can be seen that after the YOLO model is mainly responsible for detecting and locating anatomical structures and target tumors, the ResNet model uses its deep characteristics to classify images and refine the specific types of anatomical structures, such as distinguishing the subtle differences between "external carotid artery" and "internal jugular vein"; through the deep network layer, the ResNet model can extract high-order features from complex images, and can provide more accurate recognition and classification when dealing with complex and intertwined anatomical regions of the head and neck. The residual connection design of the ResNet module effectively solves the gradient vanishing problem that may occur in deep neural networks, ensuring that the structural model can train deeper network layers, thereby improving the accuracy of recognition; the ResNet model can improve the classification accuracy of the YOLO model output, especially when dealing with anatomical structures with smaller structures and high similarity, and can provide more accurate classification.

[0036] In the specific solution, the ResNet model training process is: B0. Input and preprocessing: After the YOLO model detects the location information of the target tumor, it generates a bounding box for each target tumor. This location information will be passed as input to the ResNet model; in the preferred solution, before passing it to the ResNet model, the target area image is resized and standardized to meet the input requirements of the ResNet model, and the consistency of the input data is ensured by standardization (such as mean subtraction and standard deviation division); B1. Feature extraction and classification: Input the location information of at least one target tumor, perform multi-layer convolution and pooling layer operations on the ResNet model to extract higher-level image features, and use a fully connected layer to further classify the anatomical structure so that each target tumor is assigned a probability value, indicating what type of nerve, blood vessel or other unit the target tumor is.

[0037] B2. Cross-entropy loss function: Use the cross-entropy loss function to optimize the ResNet model to ensure that the ReNest model can accurately classify and predict each target tumor.

[0038] B3. Training optimization: Use the Adam optimizer for training and adjust the weight parameters in the model to minimize the loss function; B4. Data output: The ResNet model outputs the category of each target tumor and the confidence of the category as classification information.

[0039] It can be seen that the RssNet model and the YOLO model work together to further improve the system's analytical capabilities, so as to achieve further detailed classification of target tumors. For example, after the YOLO model identifies the facial nerve, the RssNet model further distinguishes the different branches of the facial nerve. The ResNet model can extract more detailed features from the data through its deep network structure and adapt to the recognition tasks of more complex anatomical areas (such as vascular interlacing, nerve entanglement, etc.). In addition, since many anatomical structures in head and neck surgery are small and have complex spatial relationships, the ResNet model uses residual connections to solve the gradient vanishing problem in deep neural network training and enhance the recognition ability of smaller target tumors.

[0040] In terms of cooperating with the surgical navigation subsystem, during the operation, the YOLO model works together with the ResNet model. The YOLO model is responsible for quickly detecting the target and performing preliminary classification, while the ResNet model further classifies the anatomical structure more finely based on the target area output by YOLO, generating detailed surgical navigation information. Since the ResNet model outputs the category and confidence of each target tumor, the system can perform real-time navigation and feedback to help medical staff accurately locate the target tumor and avoid injury and misjudgment. Finally, the classification results and positioning information of each anatomical structure and target tumor during the operation are displayed through a visual interface, and medical staff are reminded of the risk level of the target area in real time to ensure efficient and safe surgical operations.

[0041] As an improved solution of the present invention, it also includes an integration module, which integrates the data acquisition and preprocessing module and the recognition module as submodules, and also includes an auxiliary submodule, which is commonly connected to the data acquisition and preprocessing module and the recognition module; all modules are efficiently integrated and collaborated, the system integration module ensures smooth collaboration of each subsystem, and provides intelligent auxiliary functions through the auxiliary submodule, so that the operation of the system is more efficient, accurate and sensitive; For example, the auxiliary submodule includes a surgical navigation subsystem: this subsystem can comprehensively process the processing flow of the recognition module and the real-time collected signal flow, generate accurate surgical navigation information for medical staff to use during the operation, and realize the visual interface to facilitate medical staff to obtain information intuitively. The specific detailed processes are mentioned in the aforementioned embodiments, so they are not elaborated here.

[0042] The auxiliary submodule also includes a surgical control feedback unit: this feedback unit adjusts the operating accuracy of the surgical robot based on the operational feedback from medical staff to ensure the efficiency and accuracy of the surgical process. At the same time, the system can adjust the surgical path based on real-time images to optimize the surgical process.

[0043] The auxiliary submodule also includes a postoperative recovery tracking unit: After the operation is completed, the postoperative recovery tracking unit continues to track the patient's recovery progress, compares subsequent imaging data with intraoperative data, evaluates the surgical effect and provides recovery suggestions.

[0044] This system realizes real-time recognition of anatomical structures, spatial relationship modeling and precise navigation during head and neck surgery through the collaboration of deep learning models and multiple AI algorithms. The system architecture includes multiple modules such as data acquisition and preprocessing, anatomical structure recognition, data enhancement and label optimization, real-time reasoning and feedback, and system integration. The modules work together to ensure accurate recognition and navigation of anatomical structures during surgery, and can be dynamically adjusted according to actual conditions to minimize surgical risks, reduce trauma, and improve the quality of postoperative recovery of patients.

[0045] The advantages of the present invention are: This system achieves real-time recognition of anatomical structures, spatial relationship modeling and precise navigation during head and neck surgery through the collaborative work of multiple deep learning models and multiple algorithms. The various modules of the system work together to ensure the accurate recognition and navigation of anatomical structures during surgery, and can be dynamically adjusted according to actual conditions to minimize surgical risks, reduce trauma, and improve the quality of patient recovery after surgery.

[0046] The above disclosures are only several specific embodiments of the present invention, but the present invention is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims

1. A system for identifying mandibular hemangiomas based on CBCT data, characterized in that: The system includes: A recognition module, used for performing model processing on the original image from CBCT to generate a structural model, and marking the target tumor on the structural model to assist the user in making a distinction; It also includes a data acquisition and preprocessing module, which is used to preprocess the data at each input stage and to collect the original data and the real-time data of the user during the operation.

2. The system for identifying mandibular hemangioma based on CBCT data according to claim 1, characterized in that: Before the original image is input into the model for processing, it needs to be preprocessed. The preprocessing steps include: Image normalization: obtain the original image and perform normalization on the original image to obtain a primary image; Image enhancement: Perform data enhancement on the primary image to obtain the secondary image; Image annotation: Label the secondary images and ensure spatial consistency to obtain training data.

3. The system for identifying mandibular hemangioma based on CBCT data source according to claim 2, characterized in that: The data enhancement method includes at least one of geometric transformation, color and brightness adjustment, noise addition and local deformation.

4. The system for identifying mandibular hemangioma based on CBCT data according to claim 2, characterized in that: After obtaining the training data, it also includes: a. Data segmentation: The data set formed by the secondary images after data augmentation is divided into training set, validation set and test set to ensure the diversity and representativeness of each data set to prevent overfitting of the model; b. Batch training and validation: Use the data-augmented training set for batch training, and use the validation set to evaluate the performance of the model on new data to adjust the data; c. Label optimization and loss function: During the training process, label annotation and data augmentation are combined, and loss functions are used to improve the classification accuracy of difficult-to-identify samples.

5. The system for identifying mandibular hemangioma based on CBCT data source according to claim 2, characterized in that: The generation of the structural model includes the following steps: The training data is input into the YOLO model for modeling processing to generate a structural model.

6. The system for identifying mandibular hemangioma based on CBCT data according to claim 4, characterized in that: The YOLO model training process is: A1. Data preprocessing: adjust the training data to a fixed size to achieve standardized input; A2. Target detection: The YOLO model extracts image features through a convolutional neural network to generate the bounding box of the target tumor and the probability of its corresponding category; A3. Optimize training: Use the cross entropy loss function and IoU loss function to optimize the model to ensure that the convolutional network can produce positioning and classification results during detection; A4. Data output: The output includes the location information of each target tumor and the corresponding classification probability.

7. The system for identifying mandibular hemangioma based on CBCT data according to claim 6, characterized in that: After obtaining the structural model, the following steps are also included: The ResNet model is used to receive the output data of the YOLO model, classify and refine the target tumor location to output classification information.

8. The system for identifying mandibular hemangioma based on CBCT data according to claim 7, characterized in that: The ResNet model training process is: B1. Feature extraction and classification: Input at least one location information, perform multi-layer convolution and pooling layer operations on the ResNet model to extract higher-level image features, and use the fully connected layer to further classify the anatomical structure so that each target tumor will be assigned a probability value; B2. Cross entropy loss function: Use the cross entropy loss function to optimize the ResNet model; B3. Training optimization: Use the Adam optimizer for training and adjust the weight parameters in the model to minimize the loss function; B4. Data output: The ResNet model outputs the category of each target tumor and the confidence of the category as classification information.

9. The system for identifying mandibular hemangioma based on CBCT data according to any one of claims 1 to 8, characterized in that: It also includes an integration module, which integrates the data acquisition and preprocessing module and the recognition module as submodules, and also includes an auxiliary submodule, which is commonly connected to the data acquisition and preprocessing module and the recognition module.

10. The system for identifying mandibular hemangioma based on CBCT data according to claim 9, characterized in that: The auxiliary submodule includes a surgical navigation subsystem, which is used to process the processing flow of the recognition module and the signal flow collected in real time, and generate accurate surgical navigation information for display in the visualization device.

Images