3D CBCT Tooth Image Segmentation Method, System and Storage Medium Based on State Space Modeling

Abstract

The present invention discloses a three-dimensional CBCT dental image segmentation method, system, and storage medium based on state-space modeling, relating to the field of medical image processing technology. The method comprises the following steps: acquiring a number of historical CBCT jaw region image data, preprocessing the image data to obtain sample jaw region images; manually labeling the sample jaw region images to generate a model training image set; establishing a CBCT image dental segmentation model, using the model training images as input and tooth contours as labels, performing state-space information modeling and multi-frequency domain analysis on the input images; performing multi-scale feature fusion on the feature output to generate a fused feature map, performing a decoding operation based on the fused feature map, restoring the full-size feature map, and processing the Softmax function to generate the final segmentation result; setting a loss function, continuously updating the model parameters through gradient backpropagation until the loss function converges, completing model training, and outputting the segmented tooth contour image.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a three-dimensional CBCT tooth image segmentation method, system and storage medium based on state space modeling. Background Art

[0002] Oral health is an important component of national health. With socioeconomic development and improved quality of life, more and more people are paying attention to dental health and seeking dental treatment to maintain oral function and improve facial appearance. The rapid advancement of artificial intelligence has driven the development of digital dental care, especially the widespread use of computer-assisted treatment systems, which has greatly improved the efficiency of dental treatment. In clinical dental treatment, 3D cone-beam computed tomography (CBCT) images are the only means of providing complete three-dimensional information of teeth and alveolar bone. Therefore, accurately segmenting teeth and alveolar bone structures from CBCT images to reconstruct three-dimensional models is crucial for digital dentistry.

[0003] However, dental CBCT image segmentation faces numerous challenges. Due to the similar strength of teeth and alveolar bone, misclassifications and omissions are prone to occur. The disordered and unstructured 3D data structure is prone to both misclassification and omission. Adhesions between adjacent teeth and the occlusal teeth can blur boundaries. Patients have complex dental conditions, including misplaced teeth, missing teeth, and teeth with brackets. Tooth distribution and arrangement vary significantly between patients. These difficulties pose significant challenges to digital 3D tooth segmentation in dental CBCT images. Traditional 3D tooth segmentation methods for dental CBCT images rely on extensive prior knowledge and require manual intervention, making them incapable of fully automatic and intelligent tooth segmentation. Existing deep learning-based dental CBCT image segmentation methods have limited ability to extract local detail features. Digital 3D tooth segmentation methods often perform poorly in cases of tooth misalignment and tooth-gingival boundaries, often over-segmenting or under-segmenting adjacent teeth and unclear boundary segmentation. Different tooth classes can exhibit large differences within the same category and small differences between them, leading to inter-class confusion. Furthermore, these methods are computationally demanding, making them difficult to process 3D CBCT data in real-time in practical applications.

[0004] In the prior art, publication number CN114972360A discloses a method for segmenting computed tomography images of teeth. The method comprises obtaining a first three-dimensional digital model representing the crown of an erupted tooth in a first jaw and a sequence of two-dimensional tomographic images of the first jaw; utilizing a local image classification model, based on the sequence of two-dimensional tomographic images of the first jaw, to select a starting segmented two-dimensional tomographic image for each erupted tooth from the sequence of two-dimensional tomographic images of the first jaw. The local image classification model is a trained deep neural network that is configured to classify the local two-dimensional tomographic images into categories including crown and root. Based on the first three-dimensional digital model, the method obtains position and range information for each erupted tooth; and for each erupted tooth, utilizing the position and range information and the local image segmentation model, segmenting the local image of the erupted tooth from the corresponding starting segmented two-dimensional tomographic image toward the crown and root, thereby obtaining a sequence of binary mask images. However, the deep neural network used in this method may not be able to fully extract important features when processing complex structures, particularly when the tooth structure is complex or ambiguous, which may result in reduced classification accuracy. Furthermore, despite the use of a three-dimensional digital model, the segmentation process primarily relies on the two-dimensional image sequence. The lack of effective utilization of 3D structural information may lead to inaccurate segmentation results.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a three-dimensional CBCT dental image segmentation method, system and storage medium based on state space modeling to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A three-dimensional CBCT tooth image segmentation method, system and storage medium based on state space modeling, specifically comprising the following steps:

[0009] S1, acquiring a number of historical CBCT jaw region image data, and preprocessing the acquired historical CBCT jaw region image data to obtain a sample jaw region image, wherein the preprocessing includes image denoising and image enhancement processing;

[0010] S2, based on the sample jaw region image, manually marking the sample jaw region image, marking the tooth contours in the sample jaw region image, recording the marked image as a model training image, and generating a model training image set;

[0011] S3, establishing a CBCT image tooth segmentation model based on the image data in the model training image set, using the image data in the model training image set as input and the tooth contours in the model training images as labels. The CBCT image tooth segmentation model performs state space information modeling and multi-frequency domain analysis on the input images to obtain state space information modeling branch output and multi-frequency domain analysis branch output. The CBCT image tooth segmentation model includes an encoder, a state-frequency domain joint enhancement layer, a multi-scale feature fusion layer, a decoder, and an output layer;

[0012] S4, performing multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output to generate a fused feature map, performing decoding operations based on the fused feature map to generate a feature map restored to the full size, inputting the full size feature map into the output layer of the CBCT image tooth segmentation model, and processing it through the Softmax function to generate the final segmentation result;

[0013] S5, setting the loss function, calculating the loss function value of the model based on the segmentation results, and continuously updating the model parameters through gradient backpropagation until the loss function converges to a value less than the pre-set loss threshold, completing the model training, and finally obtaining a trained CBCT image tooth segmentation model, and outputting the segmented tooth contour image;

[0014] S6, obtaining CBCT jaw region image data of the jaw to be detected, preprocessing the data, and then inputting the data into a CBCT image tooth segmentation model to obtain a tooth contour image of the jaw to be detected.

[0015] Furthermore, several historical CBCT jaw region image data collected are preprocessed, and the preprocessing includes image denoising and image enhancement processing, wherein the image is denoised by adopting a wavelet transform denoising method, and the image is enhanced by adopting a bilateral filtering method, and the preprocessed image is recorded as a sample jaw region image.

[0016] Furthermore, the sample jaw region image is manually labeled, and the method for marking the tooth contours in the sample jaw region image is as follows: the tooth contours in a single jaw region image are annotated using the LabelImg tool by manual labeling, and the labeled image is recorded as a model training image to generate a model training image set.

[0017] Furthermore, the step S3 further includes the following steps:

[0018] S31, performing state space information modeling on the input image to obtain a state space information modeling branch output;

[0019] S32, performing multi-frequency domain analysis to obtain multi-frequency domain analysis output;

[0020] Before performing state space information modeling and multi-frequency domain analysis on the input image, it is necessary to perform preliminary feature extraction on the model training image and use downsampling processing to obtain a preliminary feature map. The formula for obtaining the preliminary feature map is:

[0021]

[0022] Where, I is the image data before downsampling, I * is the downsampled image data, R is the multidimensional tensor space on the real number domain, C is the number of feature channels, H, W, D represent the height, width and depth of the image respectively, R C×H×W×D That is, it represents a multidimensional array with C channels, H height, W width and D depth. Conv represents the convolution operation, stride is the step size, and 3×3Conv (stride = 2) means using a 3×3 convolution kernel and convolving the input with a stride of 2.

[0023] Furthermore, the step S31 further includes the following steps:

[0024] S311, flattening the image data after preliminary feature extraction into a one-dimensional vector, specifically based on the formula:

[0025]

[0026] Where, X sequence is the flattened one-dimensional vector, HWD is the product of the length, width and depth of the model training image, and n2 represents the flattened one-dimensional vector X sequence The number of channels is n2;

[0027] S312, based on the flattened one-dimensional vector, the position embedding vector is added to compensate for the position information loss caused by the flattening operation to obtain a compensation vector, wherein the compensation vector is calculated based on the formula:

[0028]

[0029] Where, X pos represents the compensation vector, PE is the position embedding vector;

[0030] S313, based on the compensation vector, obtain an input vector of the state space model by performing forward and backward convolution, wherein the input vector of the state space model includes a forward convolution vector and a backward convolution vector, wherein the formulas based on which the input vector of the state space model is obtained are:

[0031]

[0032] Where, X for represents the forward convolution vector, Xback represents the backward convolution vector;

[0033] S314, forward convolution vector X for and the backward convolution vector X back Input into the state space model, model the global dependency information in the feature vector to obtain the forward state feature graph and the backward state feature graph, whose characteristic expressions are:

[0034]

[0035] Where, X forwarf represents the forward state feature map, X backward Represents the backward state feature map, ※ represents the global convolution, and Represent the structured convolution kernels in the forward and backward state space models respectively;

[0036] S315, based on the obtained forward state feature map and backward state feature map combined with the compensation vector, a tensor reshaping operation is performed, and an inverse flattening is performed to obtain the state space information modeling branch output, wherein the expression of the state space information modeling branch output is:

[0037]

[0038] Where, X state The output of the state space information modeling branch, Reshape represents the tensor reshaping operation, Concat represents the splicing operation, and σ is the SiLU activation function.

[0039] Furthermore, the step S32 further includes the following steps:

[0040] S321, input the feature map after preliminary feature extraction into the adaptive wavelet convolution layer to obtain a frequency domain information feature map, wherein the formula for obtaining the frequency domain information feature map is:

[0041]

[0042] Where, X w Represents the frequency domain information feature map, n3 represents the frequency domain information feature map X w The number of channels is n3;

[0043] S322, based on frequency domain information feature map X w Through convolution and activation operations, the feature information in the high and low frequency domains is fused and compressed, and nonlinear transformation is introduced to highlight high-frequency details. Finally, the inverse wavelet transform convolution is performed to obtain the output of the multi-frequency domain analysis branch. The formula for obtaining the output of the frequency domain analysis branch is:

[0044]

[0045] Where, X f is the output of the frequency domain analysis branch, PointConv represents point-by-point convolution, which is implemented by a convolution operation with a convolution kernel size of 1×1, σ is the SiLU activation function, and Conv represents the convolution operation.

[0046] Furthermore, step S4 includes the following steps:

[0047] S41, performing multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output, combining the preliminary feature map to generate a fused feature map, wherein the formula for generating the fused feature map is:

[0048]

[0049] Where, X o To fuse feature maps, Concat represents the concatenation operation. represents element-by-element multiplication, X score is the feature enhancement score map, n2 is the flattened one-dimensional vector X sequence The number of channels, that is, the state space information modeling branch output X state The number of channels, where the feature enhancement score map X score The formula is:

[0050] X score =Sigmoid(Conv(I * ))

[0051] Where, Sigmoid represents the Sigmoid activation function;

[0052] S42, fusion feature map X o Input decoder to generate feature map X restored to full size out ∈R N×H×W×D ;

[0053] S43, based on feature map X restored to full size out ∈R N×H×W×D , the formula for obtaining the final segmentation result after using the Softmax function is:

[0054]

[0055] Where Y j is the final segmentation result, X j represents the output corresponding to the semantics of the jth category, N represents the total number of categories, and j is the index of the category, where j = 1, 2, …, N.

[0056] Furthermore, a loss function is set, where the loss function of the model includes a multi-class Dice loss function and a wavelet loss function. The multi-class Dice loss and the wavelet loss are summed to obtain the total loss function of the model. The expression of the multi-class Dice loss function is:

[0057]

[0058] where Y c,i and g c,i Represents the category of the i-th pixel prediction and ground truth, w c represents the weight of the cth class, ∈ is a constant for numerical stability; ground truth represents the label data used to supervise the training process, that is, the tooth contour;

[0059] The wavelet loss function expression is:

[0060]

[0061] Where k represents the position index of the convolution operation, a0 and a1 are the analysis vectors in the adaptive wavelet convolution, and s0 and s1 are the reconstruction vectors in the inverse wavelet convolution;

[0062] The final loss function is the sum of the two:

[0063] L=L MCD +L wavelet

[0064] Where L represents the final loss function;

[0065] The model parameters are continuously updated through gradient back propagation until the loss function converges to a value less than the pre-set loss threshold yz, completing the model training. Finally, a trained CBCT image tooth segmentation model is obtained, and the segmented tooth contour image is output.

[0066] The present invention further provides a three-dimensional CBCT dental image segmentation system based on state-space modeling, wherein the three-dimensional CBCT dental image segmentation system is used to execute the above-mentioned three-dimensional CBCT dental image segmentation method based on state-space modeling, comprising:

[0067] An image preprocessing module is used to obtain a number of historical CBCT jaw region image data, and preprocess the collected historical CBCT jaw region image data to obtain a sample jaw region image, wherein the preprocessing includes image denoising and image enhancement processing;

[0068] A training sample acquisition module is used to manually mark the sample jaw region image based on the sample jaw region image, mark the tooth contours in the sample jaw region image, record the marked image as a model training image, and generate a model training image set;

[0069] A tooth segmentation model establishment module is used to establish a CBCT image tooth segmentation model based on the image data in the model training image set. The CBCT image tooth segmentation model uses the image data in the model training image set as input and the tooth contours in the model training image as labels. The CBCT image tooth segmentation model performs state space information modeling and multi-frequency domain analysis on the input image to obtain a state space information modeling branch output and a multi-frequency domain analysis branch output. The CBCT image tooth segmentation model includes an encoder, a state frequency domain joint enhancement layer, a multi-scale feature fusion layer, a decoder, and an output layer.

[0070] The feature fusion module is used to perform multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output to generate a fused feature map. The fused feature map is decoded to generate a feature map restored to its full size. The full-size feature map is input into the output layer of the CBCT image tooth segmentation model and processed through the Softmax function to generate the final segmentation result.

[0071] The loss analysis and adjustment module is used to set the loss function, calculate the loss function value of the model based on the segmentation results, and continuously update the model parameters through gradient backpropagation until the loss function converges to a value less than the pre-set loss threshold. This completes the model training and ultimately obtains a trained CBCT image tooth segmentation model and outputs the segmented tooth contour image.

[0072] The tooth image output module is used to obtain the CBCT jaw area image data of the jaw to be detected, pre-process it, and then input it into the CBCT image tooth segmentation model to obtain the tooth contour image in the jaw to be detected.

[0073] The present invention also provides a storage medium, which stores a computer program that can be executed by one or more processors. When the computer program is executed by the processor, it can implement the above-mentioned three-dimensional CBCT tooth image segmentation method based on state space modeling.

[0074] Compared with the prior art, the present invention has the following beneficial effects:

[0075] This paper employs a 3D convolutional-state-space hybrid neural network that combines a state-frequency domain joint enhancement module and a multiscale feature fusion module to segment dental CBCT images. This approach combines state-space information modeling with multi-frequency domain analysis to accurately model long-range relationships in the data at large scales and accurately restore high-frequency details at small scales. The multiscale fusion module integrates low-level features to preserve the effective semantics of the target. This effectively improves the segmentation and classification accuracy of dental CBCT images while reducing the computational burden. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 Schematic diagram of the overall method flow of the present invention;

[0077] Figure 2 Schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0078] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0079] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0080] Example:

[0081] See also Figure 1 , the present invention provides a technical solution:

[0082] A three-dimensional CBCT tooth image segmentation method based on state space modeling, comprising the following steps:

[0083] S1, acquiring a number of historical CBCT jaw region image data, and preprocessing the acquired historical CBCT jaw region image data to obtain a sample jaw region image, wherein the preprocessing includes image denoising and image enhancement processing;

[0084] Several historical CBCT jaw region image data collected were preprocessed, and the preprocessing included image denoising and image enhancement. The images were denoised by using a wavelet transform denoising method, and enhanced by using a bilateral filtering method. The preprocessed images were recorded as sample jaw region images.

[0085] The wavelet transform denoising method is used to denoise the jaw region image. The specific steps of the wavelet transform denoising method include: decomposing the jaw region image through wavelet transform to obtain wavelet coefficients of the image at different scales and directions; thresholding the wavelet coefficients to set the low-amplitude wavelet coefficients to zero and retain the high-amplitude wavelet coefficients; inverse transforming the thresholded wavelet coefficients and reconstructing the processed coefficients into an image to complete the image denoising;

[0086] Bilateral filtering is used to enhance the details of the jaw region image. The specific filter transformation is based on the formula:

[0087]

[0088] Where y is the coordinate vector in the image coordinate system, I y is the grayscale value at the coordinate vector y, B y is the gray value I y The gray value after bilateral filtering transformation, G d and G r are all Gaussian functions, where G d and G r The formula is:

[0089]

[0090] Where x is the coordinate vector in the image coordinate system, I x is the grayscale value at the coordinate vector x, σ d and σ r G d and G r The standard deviation of .

[0091] S2, based on the sample jaw region image, manually marking the sample jaw region image, marking the tooth contours in the sample jaw region image, recording the marked image as a model training image, and generating a model training image set;

[0092] The sample jaw region image is manually labeled, and the method for marking the tooth contours in the sample jaw region image is as follows: the tooth contours in a single jaw region image are manually labeled using the LabelImg tool, and the labeled image is recorded as a model training image to generate a model training image set. The LabelImg command is run through the Python software. After running LabelImg, a main window will appear on the interface, and labeling is performed through the main window.

[0093] S3, establishing a CBCT image tooth segmentation model based on the image data in the model training image set, using the image data in the model training image set as input and the tooth contours in the model training images as labels. The CBCT image tooth segmentation model performs state space information modeling and multi-frequency domain analysis on the input images to obtain state space information modeling branch output and multi-frequency domain analysis branch output. The CBCT image tooth segmentation model includes an encoder, a state-frequency domain joint enhancement layer, a multi-scale feature fusion layer, a decoder, and an output layer;

[0094] The step S3 further comprises the following steps:

[0095] S31, performing state space information modeling on the input image to obtain a state space information modeling branch output;

[0096] S32, performing multi-frequency domain analysis to obtain multi-frequency domain analysis output;

[0097] Before performing state space information modeling and multi-frequency domain analysis on the input image, it is necessary to perform preliminary feature extraction on the model training image and use downsampling processing to obtain a preliminary feature map. The formula for obtaining the preliminary feature map is:

[0098]

[0099] Where, I is the image data before downsampling, I * is the downsampled image data, R is the multidimensional tensor space on the real number domain, C is the number of feature channels, H, W, D represent the height, width and depth of the image respectively, R C×H×W×D That is, it represents a multidimensional array with C channels, H height, W width and D depth. Conv represents the convolution operation, stride is the step size, and 3×3Conv (stride = 2) means using a 3×3 convolution kernel and convolving the input with a stride of 2.

[0100] The step S31 further includes the following steps:

[0101] S311, flattening the image data after preliminary feature extraction into a one-dimensional vector, specifically based on the formula:

[0102]

[0103] Where, X sequence is the flattened one-dimensional vector, HWD is the product of the length, width and depth of the model training image, and n2 represents the flattened one-dimensional vector X sequence The number of channels is n2;

[0104] S312, based on the flattened one-dimensional vector, the position embedding vector is added to compensate for the position information loss caused by the flattening operation to obtain a compensation vector, wherein the compensation vector is calculated based on the formula:

[0105]

[0106] Where, X pos Denotes the compensation vector, and PE is the position embedding vector. The position embedding vector can be obtained and determined using fixed mathematical functions or training. Choosing the appropriate method depends on the specific application scenario and model requirements. Sine and cosine methods are suitable for capturing global positional relationships, while learnable embeddings offer greater flexibility. The specific steps are well-established and will not be detailed here.

[0107] S313, based on the compensation vector, obtain an input vector of the state space model by performing forward and backward convolution, wherein the input vector of the state space model includes a forward convolution vector and a backward convolution vector, wherein the formulas based on which the input vector of the state space model is obtained are:

[0108]

[0109] Where, X for represents the forward convolution vector, X back represents the backward convolution vector;

[0110] S314, forward convolution vector X for and the backward convolution vector X back Input into the state space model, model the global dependency information in the feature vector to obtain the forward state feature graph and the backward state feature graph, whose characteristic expressions are:

[0111]

[0112] Where, X forward represents the forward state feature map, X backward Represents the backward state feature map, ※ represents the global convolution, and denote the structured convolution kernels in the forward and backward state space models, respectively; they are composed of the parameter matrices in the discrete-time state equations:

[0113]

[0114] Among them, the state matrix A, control matrix B and output matrix D are parameter matrices that are updated as the model iterates, and Δ is a manually set hyperparameter that controls the discrete step size. Represents a form of state transition matrix, Where H represents the identity matrix, Represents the adjusted control matrix, and t represents the number of historical states contained in the structured convolution kernel.

[0115] S315, based on the obtained forward state feature map and backward state feature map combined with the compensation vector, a tensor reshaping operation is performed, and an inverse flattening is performed to obtain the state space information modeling branch output, wherein the expression of the state space information modeling branch output is:

[0116]

[0117] Where, X state The output of the state space information modeling branch, Reshape represents the tensor reshaping operation, Concat represents the splicing operation, and σ is the SiLU activation function.

[0118] The step S32 further includes the following steps:

[0119] S321, input the feature map after preliminary feature extraction into the adaptive wavelet convolution layer to obtain a frequency domain information feature map, wherein the formula for obtaining the frequency domain information feature map is:

[0120]

[0121] Where, X w Represents the frequency domain information feature map, n3 represents the frequency domain information feature map X w The number of channels is n3;

[0122] The adaptive wavelet convolution kernel is formed by combining the low-frequency, horizontal high-frequency, vertical high-frequency and diagonal high-frequency convolution operators generated by the analysis vector. It can give the model the ability to adaptively adjust the wavelet basis function and analyze and extract high-frequency detail features. Its specific expression is:

[0123] K w =cat(F ll ,F lh ,F hl ,F hh )

[0124] Where K wRepresents the adaptive wavelet convolution kernel, cat represents connecting multiple matrices or arrays along a specific dimension, where F ll ,F lh ,F hl ,F hh Represent the low frequency, horizontal high frequency, vertical high frequency and diagonal high frequency convolution operators respectively, and their specific expressions are:

[0125]

[0126] in and are the analysis vectors learned through supervised learning based on the optimal reconstruction principle. Their specific expressions are:

[0127]

[0128] Where ψ(·) and φ(·) represent the wavelet function and scaling function respectively, k represents the position index of the convolution operation, and t represents a continuous time or space variable, which is the input of the wavelet function and scaling function.

[0129] The expression of the optimal reconstruction principle is:

[0130] A0(-z)S0(z)+A1(-z)S1(z)=0

[0131] A0(z)S0(z)+A1(z)S1(z)=2

[0132] Where A0(z), A1(z), S0(z), and S1(z) are the analysis vectors and reconstruction vector The Z transform (Ztransform), the optimal reconstruction principle can be expressed as the wavelet loss function L wavelet Applying deep learning to supervise the analysis of vectors and reconstruction vector learning process.

[0133] S322, based on frequency domain information feature map X w Through convolution and activation operations, the feature information in the high and low frequency domains is fused and compressed, and nonlinear transformation is introduced to highlight high-frequency details. Finally, the inverse wavelet transform convolution is performed to obtain the output of the multi-frequency domain analysis branch. The formula for obtaining the output of the frequency domain analysis branch is:

[0134]

[0135] Where, X fis the output of the frequency domain analysis branch, PointConv represents point-by-point convolution, which is implemented by a convolution operation with a convolution kernel size of 1×1, σ is the SiLU activation function, and Conv represents the convolution operation.

[0136] S4, performing multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output to generate a fused feature map, performing decoding operations based on the fused feature map to generate a feature map restored to the full size, inputting the full size feature map into the output layer of the CBCT image tooth segmentation model, and processing it through the Softmax function to generate the final segmentation result;

[0137] The step S4 comprises the following steps:

[0138] S41, performing multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output, combining the preliminary feature map to generate a fused feature map, wherein the formula for generating the fused feature map is:

[0139]

[0140] Where, X o To fuse feature maps, Concat represents the concatenation operation. represents element-by-element multiplication, X score is the feature enhancement score map, where the feature enhancement score map X score The formula is:

[0141] X score =Sigmoid(Conv(I * ))

[0142] Where, Sigmoid represents the Sigmoid activation function;

[0143] S42, fusion feature map X o Input decoder to generate feature map X restored to full size out ∈R N×H×W×D ;

[0144] S43, based on feature map X restored to full size out ∈R N×H×W×D , the formula for obtaining the final segmentation result after using the Softmax function is:

[0145]

[0146] Where Y j is the final segmentation result, X j represents the output corresponding to the semantics of the jth category, N represents the total number of categories, and j is the index of the category, where j = 1, 2, …, N.

[0147] The resolution of the feature map can also be adjusted by performing multiple downsampling to obtain feature maps of different resolutions. State space information modeling and multi-frequency domain analysis are performed based on the feature maps of different resolutions. The output results of the analysis are upsampled to adjust the feature maps to the same length, width, and depth, and then the feature maps are fused to obtain a fused feature map.

[0148] S5, set the loss function, calculate the loss function value of the model based on the segmentation results, and continuously update the model parameters through gradient backpropagation until the loss function converges to a value less than the pre-set loss threshold. The model training is completed, and finally a trained CBCT image tooth segmentation model is obtained, and the segmented tooth contour image is output.

[0149] Set the loss function, where the loss function of the model includes the multi-class Dice loss function and the wavelet loss function. The multi-class Dice loss and the wavelet loss are summed to obtain the total loss function of the model. The expression of the multi-class Dice loss function is:

[0150]

[0151] where Y c,i and g c,i Represents the category of the i-th pixel prediction and ground truth, w c represents the weight of the cth class, ∈ is a constant for numerical stability; ground truth represents the label data used to supervise the training process, that is, the tooth contour;

[0152] The wavelet loss function expression is:

[0153]

[0154] Where k represents the position index of the convolution operation, a0 and a1 are the analysis vectors in the adaptive wavelet convolution, and s0 and s1 are the reconstruction vectors in the inverse wavelet convolution;

[0155] The final loss function is the sum of the two:

[0156] L=L MCD +L wavelet

[0157] Where L represents the final loss function;

[0158] The model parameters are continuously updated through gradient back propagation until the loss function converges to a value less than the pre-set loss threshold yz, completing the model training. Finally, a trained CBCT image tooth segmentation model is obtained, and the segmented tooth contour image is output.

[0159] The loss threshold yz can be set based on expert experience and adjusted according to actual needs.

[0160] S6, obtaining CBCT jaw region image data of the jaw to be detected, preprocessing the data, and then inputting the data into a CBCT image tooth segmentation model to obtain a tooth contour image of the jaw to be detected.

[0161] See also Figure 2 The present invention further provides a three-dimensional CBCT dental image segmentation system based on state-space modeling, wherein the three-dimensional CBCT dental image segmentation system is used to execute the above-mentioned three-dimensional CBCT dental image segmentation method based on state-space modeling, comprising:

[0162] An image preprocessing module is used to obtain a number of historical CBCT jaw region image data, and preprocess the collected historical CBCT jaw region image data to obtain a sample jaw region image, wherein the preprocessing includes image denoising and image enhancement processing;

[0163] A training sample acquisition module is used to manually mark the sample jaw region image based on the sample jaw region image, mark the tooth contours in the sample jaw region image, record the marked image as a model training image, and generate a model training image set;

[0164] A tooth segmentation model establishment module is used to establish a CBCT image tooth segmentation model based on the image data in the model training image set. The CBCT image tooth segmentation model uses the image data in the model training image set as input and the tooth contours in the model training image as labels. The CBCT image tooth segmentation model performs state space information modeling and multi-frequency domain analysis on the input image to obtain a state space information modeling branch output and a multi-frequency domain analysis branch output. The CBCT image tooth segmentation model includes an encoder, a state frequency domain joint enhancement layer, a multi-scale feature fusion layer, a decoder, and an output layer.

[0165] The feature fusion module is used to perform multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output to generate a fused feature map. The fused feature map is decoded to generate a feature map restored to its full size. The full-size feature map is input into the output layer of the CBCT image tooth segmentation model and processed through the Softmax function to generate the final segmentation result.

[0166] The loss analysis and adjustment module is used to set the loss function, calculate the loss function value of the model based on the segmentation results, and continuously update the model parameters through gradient backpropagation until the loss function converges to a value less than the pre-set loss threshold. This completes the model training and ultimately obtains a trained CBCT image tooth segmentation model and outputs the segmented tooth contour image.

[0167] The tooth image output module is used to obtain the CBCT jaw area image data of the jaw to be detected, pre-process it, and then input it into the CBCT image tooth segmentation model to obtain the tooth contour image in the jaw to be detected.

[0168] The present invention also provides a storage medium, which stores a computer program that can be executed by one or more processors. When the computer program is executed by the processor, it can implement the above-mentioned three-dimensional CBCT tooth image segmentation method based on state space modeling.

[0169] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0170] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0171] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0172] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A three-dimensional CBCT tooth image segmentation method based on state space modeling, characterized in that: The specific steps include: S1, acquiring a number of historical CBCT jaw region image data, and preprocessing the acquired historical CBCT jaw region image data to obtain a sample jaw region image, wherein the preprocessing includes image denoising and image enhancement processing; S2, based on the sample jaw region image, manually marking the sample jaw region image, marking the tooth contours in the sample jaw region image, recording the marked image as a model training image, and generating a model training image set; S3, establishing a CBCT image tooth segmentation model based on the image data in the model training image set, using the image data in the model training image set as input and the tooth contours in the model training images as labels. The CBCT image tooth segmentation model performs state space information modeling and multi-frequency domain analysis on the input images to obtain state space information modeling branch output and multi-frequency domain analysis branch output. The CBCT image tooth segmentation model includes an encoder, a state-frequency domain joint enhancement layer, a multi-scale feature fusion layer, a decoder, and an output layer; S4, performing multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output to generate a fused feature map, performing decoding operations based on the fused feature map to generate a feature map restored to the full size, inputting the full size feature map into the output layer of the CBCT image tooth segmentation model, and processing it through the Softmax function to generate the final segmentation result; S5, setting the loss function, calculating the loss function value of the model based on the segmentation results, and continuously updating the model parameters through gradient backpropagation until the loss function converges to a value less than the pre-set loss threshold, completing the model training, and finally obtaining a trained CBCT image tooth segmentation model, and outputting the segmented tooth contour image; S6, obtaining CBCT jaw region image data of the jaw to be detected, preprocessing the data, and then inputting the data into a CBCT image tooth segmentation model to obtain a tooth contour image of the jaw to be detected.

2. The three-dimensional CBCT tooth image segmentation method based on state space modeling according to claim 1, characterized in that: Several historical CBCT jaw region image data collected were preprocessed, and the preprocessing included image denoising and image enhancement. The images were denoised by using a wavelet transform denoising method, and enhanced by using a bilateral filtering method. The preprocessed images were recorded as sample jaw region images.

3. The 3D CBCT dental image segmentation method based on state-space modeling according to claim 1, characterized in that: The sample jaw region image is manually labeled, and the method for marking the tooth contours in the sample jaw region image is as follows: the tooth contours in a single jaw region image are manually labeled using the Label Img tool, and the labeled image is recorded as a model training image to generate a model training image set.

4. The 3D CBCT dental image segmentation method based on state space modeling according to claim 1, characterized in that: The step S3 further comprises the following steps: S31, performing state space information modeling on the input image to obtain a state space information modeling branch output; S32, performing multi-frequency domain analysis to obtain multi-frequency domain analysis output; Before performing state space information modeling and multi-frequency domain analysis on the input image, it is necessary to perform preliminary feature extraction on the model training image and use downsampling processing to obtain a preliminary feature map. The formula for obtaining the preliminary feature map is: Where, I is the image data before downsampling, I * is the downsampled image data, R is the multidimensional tensor space on the real number domain, C is the number of feature channels, H, W, D represent the height, width and depth of the image respectively, R C×H×W×D That is, it represents a multidimensional array with C channels, H height, W width and D depth, Conv represents the convolution operation, stride is the step size, 3× 3Conv (stride = 2) means using a 3×3 convolution kernel and convolving the input with a stride of 2.

5. The three-dimensional CBCT tooth image segmentation method based on state space modeling according to claim 4, characterized in that: The step S31 further includes the following steps: S311, flattening the image data after preliminary feature extraction into a one-dimensional vector, specifically based on the formula: Where, X sequence is the flattened one-dimensional vector, HWD is the product of the length, width and depth of the model training image, and n2 represents the flattened one-dimensional vector X sequence The number of channels is n2; S312, based on the flattened one-dimensional vector, the position embedding vector is added to compensate for the position information loss caused by the flattening operation to obtain a compensation vector, wherein the compensation vector is calculated based on the formula: Where, X pos represents the compensation vector, PE is the position embedding vector; S313, based on the compensation vector, obtain an input vector of the state space model by performing forward and backward convolution, wherein the input vector of the state space model includes a forward convolution vector and a backward convolution vector, wherein the formulas based on which the input vector of the state space model is obtained are: Where, X for represents the forward convolution vector, X back represents the backward convolution vector; S314, forward convolution vector X for and the backward convolution vector X back Input into the state space model, model the global dependency information in the feature vector to obtain the forward state feature graph and the backward state feature graph, whose characteristic expressions are: Where, X forward represents the forward state feature map, X backward Represents the backward state feature map, ※ represents the global convolution, and Represent the structured convolution kernels in the forward and backward state space models respectively; S315, based on the obtained forward state feature map and backward state feature map combined with the compensation vector, a tensor reshaping operation is performed, and an inverse flattening is performed to obtain the state space information modeling branch output, wherein the expression of the state space information modeling branch output is: Where, X state The output of the state space information modeling branch, Reshape represents the tensor reshaping operation, Concat represents the splicing operation, and σ is the SiLU activation function.

6. The method for 3D CBCT tooth image segmentation based on state space modeling according to claim 4, characterized in that: The step S32 further includes the following steps: S321, input the feature map after preliminary feature extraction into the adaptive wavelet convolution layer to obtain a frequency domain information feature map, wherein the formula for obtaining the frequency domain information feature map is: Where, X w Represents the frequency domain information feature map, n3 represents the frequency domain information feature map X w The number of channels is n3; S322, based on frequency domain information feature map X w Through convolution and activation operations, the feature information in the high and low frequency domains is fused and compressed, and nonlinear transformation is introduced to highlight high-frequency details. Finally, the inverse wavelet transform convolution is performed to obtain the output of the multi-frequency domain analysis branch. The formula for obtaining the output of the frequency domain analysis branch is: Where, X f is the output of the frequency domain analysis branch, PointConv represents point-by-point convolution, which is implemented by a convolution operation with a convolution kernel size of 1×1, σ is the SiLU activation function, and Conv represents the convolution operation.

7. The method for 3D CBCT tooth image segmentation based on state space modeling according to claim 6, characterized in that: The step S4 comprises the following steps: S41, performing multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output, combining the preliminary feature map to generate a fused feature map, wherein the formula for generating the fused feature map is: Where, X o To fuse feature maps, Concat represents the concatenation operation. represents element-by-element multiplication, X score is the feature enhancement score map, n2 is the flattened one-dimensional vector X sequence The number of channels, that is, the state space information modeling branch output X state The number of channels, where the feature enhancement score map X score The formula is: X score =Sigmoid(Conv(I * )) Where, Sigmoid represents the Sigmoid activation function; S42, fusion feature map X o Input decoder to generate feature map X restored to full size out ∈R N×H×W×D ; S43, based on feature map X restored to full size out ∈R N×H×W×D , the formula for obtaining the final segmentation result after using the Softmax function is: Where Y j is the final segmentation result, X j represents the output corresponding to the semantics of the jth category, N represents the total number of categories, and j is the index of the category, where j = 1, 2, …, N.

8. The three-dimensional CBCT tooth image segmentation method based on state space modeling according to claim 1, characterized in that: Set the loss function, where the loss function of the model includes the multi-class Dice loss function and the wavelet loss function. The multi-class Dice loss and the wavelet loss are summed to obtain the total loss function of the model. The expression of the multi-class Dice loss function is: where Y c,i and g c,i Represents the category of the i-th pixel prediction and ground truth, w c represents the weight of the cth class, ∈ is a constant for numerical stability; ground truth represents the label data used to supervise the training process, that is, the tooth contour; The wavelet loss function expression is: Where k represents the position index of the convolution operation, a0 and a1 are the analysis vectors in the adaptive wavelet convolution, and s0 and s1 are the reconstruction vectors in the inverse wavelet convolution; The final loss function is the sum of the two: L=L MCD +L wavelet Where L represents the final loss function; The model parameters are continuously updated through gradient back propagation until the loss function converges to a value less than the pre-set loss threshold yz, completing the model training. Finally, a trained CBCT image tooth segmentation model is obtained, and the segmented tooth contour image is output.

9. A 3D CBCT dental image segmentation system based on state-space modeling, characterized by: The three-dimensional CBCT tooth image segmentation system based on state-space modeling is used to execute the three-dimensional CBCT tooth image segmentation method based on state-space modeling according to any one of claims 1 to 8, comprising: An image preprocessing module is used to obtain a number of historical CBCT jaw region image data, and preprocess the collected historical CBCT jaw region image data to obtain a sample jaw region image, wherein the preprocessing includes image denoising and image enhancement processing; A training sample acquisition module is used to manually mark the sample jaw region image based on the sample jaw region image, mark the tooth contours in the sample jaw region image, record the marked image as a model training image, and generate a model training image set; A tooth segmentation model establishment module is used to establish a CBCT image tooth segmentation model based on the image data in the model training image set. The CBCT image tooth segmentation model uses the image data in the model training image set as input and the tooth contours in the model training image as labels. The CBCT image tooth segmentation model performs state space information modeling and multi-frequency domain analysis on the input image to obtain a state space information modeling branch output and a multi-frequency domain analysis branch output. The CBCT image tooth segmentation model includes an encoder, a state frequency domain joint enhancement layer, a multi-scale feature fusion layer, a decoder, and an output layer. The feature fusion module is used to perform multi-scale feature fusion processing on the state space information modeling branch output and the multi-frequency domain analysis output to generate a fused feature map. The fused feature map is decoded to generate a feature map restored to its full size. The full-size feature map is input into the output layer of the CBCT image tooth segmentation model and processed through the Softmax function to generate the final segmentation result. The loss analysis and adjustment module is used to set the loss function, calculate the loss function value of the model based on the segmentation results, and continuously update the model parameters through gradient backpropagation until the loss function converges to a value less than the pre-set loss threshold. This completes the model training and ultimately obtains a trained CBCT image tooth segmentation model and outputs the segmented tooth contour image. The tooth image output module is used to obtain the CBCT jaw area image data of the jaw to be detected, pre-process it, and then input it into the CBCT image tooth segmentation model to obtain the tooth contour image in the jaw to be detected.

10. A storage medium, characterized in that: The computer program stored in the storage medium can be executed by one or more processors. When the computer program is executed by the processor, it can implement the three-dimensional CBCT tooth image segmentation method based on state space modeling as described in any one of claims 1 to 8.

Images