Medical image segmentation method based on KAN operator and diffusion mechanism

Abstract

The present invention discloses a medical image segmentation method based on a diffusion mechanism and a KAN operator, comprising constructing a diffusion segmentation model based on the diffusion mechanism and the KAN operator; the model comprises a denoising module, the denoising module comprising a denoising encoder, a semantic encoder, a KAN module, and a denoising decoder; the original medical image to be processed is input into the model and processed as follows: the semantic encoder is used to extract semantic information from the original medical image to obtain a first feature; each layer output of the semantic encoder is input into the corresponding level of the denoising encoder, and the denoising encoder is used to extract local detail information in the noisy image to obtain a second feature; the KAN module is used to optimize and refine the second feature to obtain a third feature; the first, second, and third features are fused and input into the denoising decoder, and each layer output of the denoising encoder is input into the corresponding level of the denoising decoder to output a segmentation result. This method can significantly improve segmentation accuracy.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image processing, and in particular relates to a KAN operator medical image segmentation method based on a diffusion mechanism. Background Art

[0002] Medical image segmentation primarily addresses the segmentation of various images used in the medical field, such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging). Its primary task is to segment regions of interest (ROIs) from these medical images, such as specific organ sites or targets of interest (e.g., brain tumors).

[0003] Traditional medical image segmentation methods mainly rely on manual judgment, which is limited by factors such as human experience, energy, and emotional fluctuations, and the judgment accuracy is unstable. At this stage, medical image analysis is often achieved with the help of deep learning methods. For example, Patent Document 1 (application number CN202410313700.X) discloses a brain MRI tumor segmentation method based on a GAN-UNet variant network, and proposes an innovative brain MRI tumor segmentation technology. This technology uses the generator and discriminator under the generative adversarial network (GAN) framework to extract and analyze semantic features from low-level pixels to high-order dimensions through the encoder and decoder structure, while introducing refined channel attention blocks and multi-scale pyramid fusion blocks to enhance feature extraction accuracy. In addition, the method also includes key data preprocessing steps, such as MRI image labeling, Z-score normalization, and size adjustment, to improve the accuracy of tumor area segmentation.

[0004] Patent Document 2 (Application Number CN202410023147.6) discloses a method for joint segmentation and registration of brain tumor images, and proposes a technique for improving the accuracy of brain tumor image processing by jointly training a segmentation model and a registration model. This technique uses multiple seed segmentation modules and evaluates the effect using the Dice score. It also uses an improved VTN network for registration training and achieves feature fusion through skip connections and dense connections. In addition, this method also specially designs a target loss function that takes into account the image dissimilarity terms and the loss of the segmentation model, as well as appearance-aware regularization, to improve segmentation accuracy and registration robustness.

[0005] However, while the GAN-UNet variant network-based approach in Patent Document 1 has made progress in improving segmentation accuracy, the technology has limitations in generalization and inference time. Further optimization may be needed to improve the model's adaptability and efficiency, particularly when dealing with tumors of varying types or morphologies. While the combined segmentation and registration approach in Patent Document 2 improves segmentation accuracy and registration robustness, it is insufficient when dealing with tumors with diverse morphologies and complex spatial distribution characteristics. In practical applications, more technological innovations may be needed to further enhance segmentation and registration accuracy, especially in complex clinical situations.

[0006] In summary, when faced with complex clinical environments that require rapid response, the existing deep learning-based medical image segmentation methods need to be further improved in segmentation accuracy, model robustness, and processing efficiency. Summary of the Invention

[0007] In order to solve the above problems existing in the prior art, the present invention provides a medical image segmentation method based on the KAN operator of the diffusion mechanism. The technical problem to be solved by the present invention is achieved through the following technical solutions:

[0008] In a first aspect, the present invention proposes a medical image segmentation method based on a diffusion mechanism KAN operator, comprising:

[0009] A diffusion segmentation Diff-KAN model is constructed based on the diffusion mechanism and the KAN operator. The diffusion segmentation Diff-KAN model includes a denoising module using an encoder-decoder structure. The denoising module includes a semantic encoder, a denoising encoder, a KAN module, and a denoising decoder.

[0010] The original medical image to be processed is input into the diffusion segmentation Diff-KAN model for the following processing:

[0011] Add random Gaussian noise to the label to generate a pure noise image; perform channel splicing on the original medical image and the pure noise image, and input the spliced ​​noise image into the denoising encoder;

[0012] The semantic encoder is used to extract semantic information from the original medical image to obtain the first feature. The output of each layer of the semantic encoder is input into the corresponding layer of the denoising encoder, and the denoising encoder is used to extract local detail information in the noisy image to obtain the second feature.

[0013] Use the KAN module to optimize and refine the first feature to obtain the third feature;

[0014] The first, second and third features are fused and the fused features are input into the denoising decoder. At the same time, the output of each layer of the denoising encoder is input into the layer of corresponding size in the denoising decoder through a jump connection, and the segmentation result is output.

[0015] In a second aspect, the present invention proposes a KAN operator medical image segmentation device based on a diffusion mechanism, which is used to implement the KAN operator medical image segmentation method based on a diffusion mechanism proposed in the first aspect of the present invention. The device includes:

[0016] A model building module is used to build a diffusion segmentation Diff-KAN model based on the diffusion mechanism and the KAN operator. The diffusion segmentation Diff-KAN model includes a denoising module using an encoder-decoder structure. The denoising module includes a semantic encoder, a denoising encoder, a KAN module, and a denoising decoder.

[0017] The image processing module is used to input the original medical image to be processed into the diffusion segmentation Diff-KAN model for the following processing:

[0018] Add random Gaussian noise to the label to generate a pure noise image; perform channel splicing on the original medical image and the pure noise image, and input the spliced ​​noise image into the denoising encoder;

[0019] The semantic encoder is used to extract semantic information from the original medical image to obtain the first feature. The output of each layer of the semantic encoder is input into the corresponding layer of the denoising encoder, and the denoising encoder is used to extract local detail information in the noisy image to obtain the second feature.

[0020] Use the KAN module to optimize and refine the second feature to obtain the third feature;

[0021] The first, second and third features are fused and the fused features are input into the denoising decoder. At the same time, the output of each layer of the denoising encoder is input into the layer of corresponding size in the denoising decoder through a jump connection, and the segmentation result is output.

[0022] In a third aspect, the present invention provides an electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0023] Memory for storing computer programs;

[0024] The processor is used to execute the program stored in the memory to implement the method proposed in the first aspect of the present invention.

[0025] In a fourth aspect, the present invention proposes a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method proposed in the first aspect of the present invention is implemented.

[0026] Beneficial effects of the present invention:

[0027] 1. The present invention constructs a diffusion segmentation Diff-KAN model based on the diffusion mechanism and the KAN operator. The diffusion segmentation Diff-KAN model includes a denoising module using an encoder-decoder structure. The denoising module includes a semantic encoder, a denoising encoder, a KAN module, and a denoising decoder. The semantic encoder is used to extract semantic information from the original medical image, the denoising encoder is used to extract local detail information from the noisy image corresponding to the original medical image, the KAN module is used to further optimize and refine the output features of the denoising encoder, and the denoising decoder processes the fusion features of the output features of the semantic encoder, denoising encoder, and KAN module to output the segmentation result. The diffusion segmentation Diff-KAN model constructed by the present invention, on the one hand, is based on the encoder-decoder structure and cleverly integrates the KAN operator into the diffusion model, achieving more refined and accurate image processing. The diffusion mechanism allows the model to simulate the physical diffusion process during processing, transferring information between different image regions and enhancing the global consistency of segmentation. The KAN operator, through specific mathematical operations, optimizes the model's ability to capture local features and simplifies the model structure. Furthermore, the algorithm employs a unique architecture consisting of a denoising encoder and a semantic encoder. The denoising encoder focuses on removing noise from the image and restoring clear features, while the semantic encoder extracts semantic information. The collaborative work of these two encoders enables the model to more comprehensively understand and process image content. By combining the diffusion model, the KAN operator, and a deep learning model, the algorithm's accuracy and robustness are significantly improved.

[0028] 2. The diffusion segmentation Diff-KAN model designed by this invention adopts a U-shaped encoder-decoder structure, which enables the model to gradually abstract and refine features from the bottom up when processing images. At the same time, it combines dense skip residual connections technology, which not only enhances the model's ability to segment complex images, but also significantly improves the model's processing efficiency. Residual connections allow the model to directly transfer information within the deep network, reducing information loss and improving the model's learning ability and generalization.

[0029] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 1 is a flow chart of a medical image segmentation method using a KAN operator based on a diffusion mechanism according to an embodiment of the present invention;

[0031] Figure 2 2 is a framework diagram of the diffusion segmentation Diff-KAN model provided by an embodiment of the present invention;

[0032] Figure 3 Schematic diagram of the structure of the word segmentation KAN network provided by an embodiment of the present invention;

[0033] Figure 4 Schematic diagram of the structure of the KAN layer provided by an embodiment of the present invention;

[0034] Figure 5 This is a structural block diagram of a medical image segmentation device using a KAN operator based on a diffusion mechanism provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] The core idea of ​​the diffusion mechanism is to simulate a continuous random process, gradually transforming a complex data distribution into a simple distribution (such as the standard normal distribution), and then gradually restoring the original data distribution from this simple distribution. This process can be viewed as a process of "noising" and "denoising." During the diffusion process, noise is first gradually added to the data until the data becomes sufficiently blurred to be approximately sampled from a simple distribution (such as the standard normal distribution). Then, through the reverse process, the noise is gradually removed, and the original data is finally restored. By gradually removing noise from the image, the recognition and segmentation accuracy of key information in the image is significantly improved, and the visual effect of the image is improved, making the image features clearer. The robustness of this model enables it to maintain high segmentation accuracy in the face of noise and image degradation. Its multi-scale feature fusion capability ensures that both global and local information are considered during the segmentation process, further improving segmentation accuracy.

[0037] The Kolmogorov-Arnold Network (KAN) is a neural network architecture based on the Kolmogorov-Arnold representation theorem, designed to replace traditional multilayer perceptrons. The KAN operator utilizes learnable and parameterized activation functions on edges as weights, eliminating the reliance on linear weight matrices and simplifying the model structure while maintaining or improving performance. This design not only improves the model's generalization and adaptability, enabling it to flexibly handle different types of images and noise patterns, but also enhances the model's interpretability, which is particularly important for medical image analysis.

[0038] Therefore, the first aspect of the present invention proposes a diffusion-based medical image segmentation method based on the diffusion mechanism and the KAN operator.

[0039] See Figure 1 , Figure 1 FIG. 1 is a flow chart of a diffusion-based medical image segmentation method provided by an embodiment of the present invention. The method mainly includes:

[0040] Step 1: Construct a diffusion segmentation Diff-KAN model based on the diffusion mechanism and the KAN operator. The diffusion segmentation Diff-KAN model includes a denoising module with an encoder-decoder structure, and the denoising module includes a semantic encoder, a denoising encoder, a KAN module, and a denoising decoder.

[0041] Specifically, see Figure 2 , Figure 2 This is a framework diagram of the diffusion segmentation Diff-KAN model provided by an embodiment of the present invention. The semantic encoder includes multiple first convolutional blocks, each of which includes a convolutional layer (Conv), a batch normalization layer (BN), and a ReLU activation function. Each first convolutional block is followed by a maximum pooling layer with a pooling window size of 2x2. The output of each convolutional block can be written as:

[0042] X L =Pool(Conv(X L-1 ));

[0043] Where, X L Represents the output feature map of the Lth convolution block, Pool represents the pooling operation, Conv represents the convolution operation, X L-1 represents the output feature map of the L-1th convolutional layer, then the final output of the semantic encoder is X L .

[0044] Optionally, as an implementation manner, the semantic encoder in this embodiment may include 3 convolution blocks, that is, L=3, and the kernel size of each convolution block is set to 3x3, the stride is 1, and the padding amount is 1.

[0045] It should be noted that since the diffusion model generates images from a random Gaussian noise, ∈~N(0,1)∈~N(0,1), this process can be achieved by predicting the noise given the noise input, that is:

[0046] ∈ t =DiffKAN(I t ,t);

[0047] Where, I t is the label image corrupted by Gaussian noise, and t is the time step I that controls the noise intensity t =N(0,1).

[0048] The diffusion model can be used to inject learnable temporal information into each convolutional block, giving the network the ability to perceive temporal dynamics.

[0049] For further information, please see Figure 2 , wherein the denoising encoder includes multiple second convolution blocks, each of which includes a convolution layer, a batch normalization layer and a ReLU activation function; wherein the number of second convolution blocks is the same as the number of first convolution blocks, and each first convolution block is connected to a second convolution block of corresponding size to fuse features of different scales in the semantic encoder with features of corresponding scales in the denoising encoder.

[0050] Optionally, in this embodiment, the denoising encoder also includes three second convolution blocks and adopts the same convolution processing technology as the semantic encoder, that is, each second convolution block has three key components: convolution layer (Conv), batch normalization layer (BN) and ReLU activation function. This structure not only deepens the network's ability to capture local features, but also ensures the stability and efficiency of network training.

[0051] Specifically, the semantic encoder receives raw, unprocessed medical images as input and extracts and generates multi-scale features that contain rich semantic information from the original data. Furthermore, by cleverly combining these different-scale features with the corresponding-size features generated by the denoising encoder, a comprehensive multi-scale feature set is obtained through a splicing operation. This fusion process not only enhances the model's ability to capture image details but also significantly improves the recognition and segmentation accuracy of complex structures such as brain tumors by integrating information from different levels.

[0052] This embodiment utilizes a unique architecture consisting of a denoising encoder and a semantic encoder. The denoising encoder focuses on removing noise from images and restoring clear features, while the semantic encoder extracts semantic information from the image. The collaborative work of these two encoders enables the model to more comprehensively understand and process image content, particularly excelling in multi-scale feature fusion.

[0053] Furthermore, the KAN module includes a plurality of word segmentation KAN networks, which are connected in series in sequence, and the output end of the first word segmentation KAN network is connected to the input end of the last word segmentation KAN network; wherein,

[0054] The input of the first word segmentation KAN network is connected to the output of the denoising encoder as the input of the entire KAN module;

[0055] The output of the last word segmentation KAN network is connected to the input of the denoising decoder as the output of the entire KAN module.

[0056] Optionally, as an implementation, such as Figure 2 As shown, this embodiment designs a KAN module including four word segmentation KAN networks.

[0057] See Figure 3 , Figure 3 Schematic diagram of the structure of the word segmentation KAN network provided by the embodiment of the present invention. Specifically, each word segmentation KAN network includes a word segmentation module, a mapping module, multiple KAN layers and layer normalization connected in sequence; wherein,

[0058] The word segmentation module is used to reshape the input features into a 2D image block sequence through the word segmentation algorithm;

[0059] The mapping module is used to map the 2D image block sequence to the D-dimensional embedding space to obtain high-dimensional features and pass them to multiple KAN layers;

[0060] Multiple KAN layers are connected in series to optimize and refine the high-dimensional features of the input;

[0061] Layer normalization is used to process the output features of the last KAN layer to obtain the output of the current word segmentation KAN network.

[0062] For example, for the first word segmentation KAN network, its input is the output X of the denoising encoder L , through the word segmentation algorithm, X L Reshape into a sequence of flat 2D image patches Among them, the size of each image block is P×P, and the number of image blocks generated is H L For X L Length, WL For X L The vectorized image blocks are then transformed using a trainable linear projection E (i.e., a convolutional layer with a kernel size of 3). Mapped to a potential D-dimensional embedding space, namely:

[0063]

[0064] Where Z0 is the E high-dimensional feature obtained after mapping.

[0065] Next, the high-dimensional features obtained above are transferred to multiple KAN layers for processing. In this embodiment, three KAN layers are preferred. The structure of each KAN layer is as follows: Figure 4 shown.

[0066] It should be noted that each KAN layer of multiple KAN layers also includes a Batch normalization layer and a ReLU activation function.

[0067] Finally, layer normalization (LN) is applied and the output features are passed to the next block.

[0068] The principle of the entire word segmentation KAN network can be expressed as follows:

[0069] Z k =LN(KAN(Z k-1 ));

[0070] Where Z k and Z k-1 They represent the output feature maps of the kth and k-1th word segmentation KAN networks respectively.

[0071] The word segmentation KAN network designed in the present invention uses feature segmentation and high-dimensional mapping technology to convert the features output by the convolution block into a flat 2D image block sequence through word segmentation technology, and applies trainable linear projection to map these image blocks into a high-dimensional embedding space (D dimension), greatly enriching the expressive power of the features. Finally, these high-dimensional features are passed to the KAN layer. This step further refines the features, enabling the model to more accurately capture and respond to key information of brain tumor images.

[0072] For further information, please see Figure 2The denoising decoder maintains structural consistency and symmetry with the denoising encoder and also includes three convolutional blocks. This structure cleverly utilizes the previous word segmentation KAN block to process features. At the same time, each decoder block has the ability to double the resolution of the input features. This design not only accelerates the feature upsampling process, but also effectively enhances the model's ability to reconstruct the fine structure of the original data by gradually restoring the details of the image. In this way, the denoising decoder not only improves the image resolution but also ensures the richness and integrity of the feature information, providing a solid foundation for achieving high-precision brain tumor segmentation.

[0073] In addition, for the diffusion segmentation Diff-KAN model constructed by the present invention, its denoising module specifically adopts a U-shaped structure and an encoder-decoder structure with dense jump connections. The denoising encoder, KAN module and denoising decoder form a classic U-shaped structure as a whole.

[0074] The model constructed in the present invention adopts a classic U-shaped structure, supplemented by dense skip connection technology, to carefully construct the Diff-KAN model. This structural design draws on the hierarchical processing mechanism of the biological visual system, and cleverly bypasses the information loss problem in traditional deep networks through skip connections, effectively transferring low-level detail information directly to the high-level layers of the model. Such a design not only retains the key details in the image, but also achieves in-depth extraction of high-level semantic information through the collaborative work of the encoder-decoder structure. The encoder part is responsible for capturing and encoding the essential features of the input data, while the decoder part focuses on converting these features into accurate segmentation results. The use of this structure enables the Diff-KAN model to achieve more refined and accurate segmentation effects when processing complex brain tumor images, significantly improving the performance and application value of the model.

[0075] Specifically, given the skip connection feature Z of the kth network in the word segmentation KAN network k and the feature Z' of the last loaded block k+1 , then the input feature Z' of the kth upsampling block k for:

[0076] Z' k =Cat(Z' k+1 ,(Z k ));

[0077] Where Cat() represents the feature concatenation operation. Similarly, given the skip feature X of the lth layer in the convolution part of the encoder, l , and the feature X of the last upsampling block l ' +1 , then the input feature X of the lth upsampling block l 'for:

[0078] X l '=Cat(X l ' +1 ,(X l )).

[0079] At this point, the construction of the diffusion segmentation Diff-KAN model is completed.

[0080] This paper proposes a diffusion segmentation model, Diff-KAN, based on the diffusion mechanism and the KAN operator. By introducing the diffusion mechanism and the KAN operator, this model achieves more refined and accurate image processing. The diffusion mechanism allows the model to simulate the physical diffusion process during processing, thereby transferring information between different regions of the image and enhancing the global consistency of the segmentation. The KAN operator, through specific mathematical operations, optimizes the model's ability to capture local features.

[0081] Furthermore, in terms of model design, the present invention utilizes a unique architecture consisting of a denoising encoder and a semantic encoder. The design of these two encoders enables the model to simultaneously process both local image details and global semantic information. The denoising encoder focuses on removing noise and restoring clear features, while the semantic encoder is responsible for extracting semantic information from the image. The collaborative work of these two encoders enables the model to more comprehensively understand and process image content, particularly excelling in multi-scale feature fusion.

[0082] Furthermore, this model utilizes a U-shaped structural design, which mimics the processing flow of the human visual system, enabling the model to gradually abstract and refine features from the bottom up when processing images. Incorporating residual connections, this U-shaped structure not only enhances the model's ability to segment complex images, such as brain tumor images, but also significantly improves its processing efficiency. Residual connections allow the model to directly transfer information within deep networks, reducing information loss and improving the model's learning and generalization capabilities.

[0083] By combining the diffusion mechanism, the KAN operator and the U-shaped structure, the diffusion segmentation Diff-KAN model obtained in the present invention exhibits excellent performance in segmentation accuracy, model robustness and processing speed.

[0084] Step 2: Input the original image of the medical image to be processed into the diffusion segmentation Diff-KAN model and perform the following processing:

[0085] Add random Gaussian noise to the label to generate a pure noise image; perform channel splicing on the original medical image and the pure noise image, and input the spliced ​​noise image into the denoising encoder;

[0086] The semantic encoder is used to extract semantic information from the original medical image to obtain the first feature. The output of each layer of the semantic encoder is input into the corresponding layer of the denoising encoder, and the denoising encoder is used to extract local detail information in the noisy image to obtain the second feature.

[0087] Use the KAN module to optimize and refine the second feature to obtain the third feature;

[0088] The first feature, the second feature, and the third feature are fused, and the fused features are input into the denoising decoder. At the same time, each layer output of the denoising encoder is input into the layer of corresponding size in the denoising decoder through a jump connection, and the segmentation result is output.

[0089] It should be noted that before the original medical image to be processed is input into the diffusion segmentation Diff-KAN model for processing, the diffusion segmentation Diff-KAN model is trained using a training set.

[0090] In this embodiment, the training set is constructed using the following method:

[0091] Collect existing medical imaging data, analyze the effective attributes in the medical imaging data based on principal component analysis, and generate a usable data set;

[0092] The dataset is preprocessed and divided into training set, validation set and test set; the training set is used to train the diffusion segmentation Diff-KAN model, and the validation set and test set are used to verify and evaluate the generalization ability of the diffusion segmentation Diff-KAN model.

[0093] As an optional implementation approach, we first collected extensive raw medical imaging data on brain tumors, including key attributes such as scan date, image type, tumor location, size, pathology, patient age, and gender. By collaborating closely with domain experts and applying advanced data analysis methods such as principal component analysis, we extracted the most effective attributes from the raw data and constructed a high-quality dataset suitable for deep learning model training.

[0094] The raw medical imaging data in the dataset was then subjected to a series of preprocessing operations to ensure data quality. These preprocessing operations included image standardization and data augmentation using techniques such as rotation, flipping, and random cropping, thereby increasing the diversity and robustness of model training.

[0095] Specifically, the brain tumor region and its adjacent tissues were defined as primary regions of interest (ROIs) and marked as foreground objects. The pixel intensities in these regions were carefully analyzed to determine their mean and standard deviation. Based on this, the entire dataset was normalized by centering and scaling the pixel intensities to eliminate intensity variations between images.

[0096] A variety of enhancement techniques were implemented on the standardized dataset, including but not limited to image rotation, flipping, random cropping, etc. These operations are designed to simulate various variations that may be encountered during clinical image acquisition, thereby enhancing the model's ability to recognize these variations.

[0097] Finally, the processed dataset is precisely divided into training, test, and validation sets according to a specific ratio. This strategy is crucial for developing a high-performance segmentation model. This division not only avoids overfitting due to the lack of a validation step, but also enables continuous model iteration through repeated adjustment and optimization of attribute information to achieve optimal segmentation results. The rigor and foresight of this methodology provide a solid foundation for achieving high-precision segmentation of brain tumor images.

[0098] The obtained training set is input into the constructed diffusion segmentation Diff-KAN model for training. It should be noted that in the context of medical brain tumor segmentation tasks, the final segmentation map can be obtained from the output feature map, that is, Among them, C Y is the number of semantic categories, and Y is the ground-truth of the segmentation. Therefore, in order to measure the accuracy of the segmentation result, this embodiment designs a comprehensive loss function, which consists of three parts: Dice loss, binary cross entropy loss, and mean square error loss, namely:

[0099]

[0100] Where, L total Represents the total loss function, L dice (DiffKAN(I),Y) represents the Dice loss, L bce (DiffKAN(I),Y) represents the binary cross entropy loss, L mse (DiffKAN(I),Y) represents the mean squared error loss.

[0101] This loss function comprehensively considers the contour consistency, category balance, and pixel-level accuracy of the segmentation, ensuring that the model can be fully optimized during training, thereby achieving higher accuracy and reliability in brain tumor segmentation tasks.

[0102] After the training is completed, the original medical images can be input into the trained diffusion segmentation Diff-KAN model for processing.

[0103] First, random Gaussian noise is added to the label to generate a pure noise image; then the original medical image and the pure noise image are channel-joined to generate a noise image.

[0104] The original medical image is then used as input to the semantic encoder, where convolution operations are performed to extract semantic information from the original medical image, generating the first feature. Simultaneously, the output of each layer of the semantic encoder is fed into a correspondingly sized layer of the denoising encoder, and the concatenated noisy image is used as input to the denoising encoder, where convolution operations are performed to extract local detail information from the noisy image, generating the second feature.

[0105] Next, the second feature output by the denoising encoder is input into the KAN module for optimization and refinement to obtain the third feature.

[0106] Finally, the first, second, and third features are fused, and the fused features are input into the denoising decoder. At the same time, the output of each layer of the denoising encoder is input into the layer of corresponding size in the denoising decoder through a jump connection, and the segmentation result is output.

[0107] It should be noted that before the original medical images are input into the trained diffusion segmentation Diff-KAN model for processing, they also need to be subjected to data enhancement operations such as rotation, flipping, and random cropping.

[0108] This paper proposes a diffusion-based medical image segmentation method designed to overcome the limitations of existing technologies in brain tumor segmentation accuracy and model generalization. This method first performs meticulous preprocessing on the original medical images, including uniform slice intervals, pixel intensity normalization, and data augmentation techniques, to reduce image variability and improve model generalization. Subsequently, a Diff-KAN model, incorporating an encoder-decoder architecture and a diffusion mechanism, is constructed. This model further enhances the accuracy of brain tumor region recognition and segmentation by introducing the KAN operator. The model is systematically trained using training data and rigorously evaluated using validation and test sets, ensuring robustness and accuracy across diverse data sets. Finally, post-processing the segmentation output of the model yields highly accurate brain tumor segmentation images. This method not only significantly improves segmentation accuracy but also optimizes the model's learning efficiency and processing speed, providing clinicians with an efficient and accurate tool for brain tumor image analysis, with significant clinical application value and broad market prospects.

[0109] Based on the same inventive concept, the second aspect of the present invention also provides a medical image segmentation device using a KAN operator based on a diffusion mechanism. Figure 5 , Figure 5 : This is a structural block diagram of a medical image segmentation device using a KAN operator based on a diffusion mechanism provided by an embodiment of the present invention. The device specifically includes:

[0110] A model building module is used to build a diffusion segmentation Diff-KAN model based on the diffusion mechanism and the KAN operator. The diffusion segmentation Diff-KAN model includes a denoising module using an encoder-decoder structure. The denoising module includes a semantic encoder, a denoising encoder, a KAN module, and a denoising decoder.

[0111] The image processing module is used to input the original medical image to be processed into the diffusion segmentation Diff-KAN model for the following processing:

[0112] Add random Gaussian noise to the label to generate a pure noise image; perform channel splicing on the original medical image and the pure noise image, and input the spliced ​​noise image into the denoising encoder;

[0113] The semantic encoder is used to extract semantic information from the original medical image to obtain the first feature. The output of each layer of the semantic encoder is input into the corresponding layer of the denoising encoder, and the denoising encoder is used to extract local detail information in the noisy image to obtain the second feature.

[0114] Use the KAN module to optimize and refine the second feature to obtain the third feature;

[0115] The first feature, the second feature, and the third feature are fused, and the fused features are input into the denoising decoder. At the same time, each layer output of the denoising encoder is input into the layer of corresponding size in the denoising decoder through a jump connection, and the segmentation result is output.

[0116] Based on the same inventive concept, a third aspect of the present invention further provides an electronic device, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0117] Memory for storing computer programs;

[0118] The processor is used to execute the program stored in the memory to implement the method proposed in the first aspect of the present invention.

[0119] Based on the same inventive concept, the third aspect of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method proposed in the first aspect of the present invention is implemented.

[0120] As for the device provided in the second aspect, the electronic device provided in the third aspect, and the storage medium embodiment provided in the fourth aspect of the present invention, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0121] It should be noted that the device, electronic device and storage medium of the embodiments of the present invention are respectively the device, electronic device and storage medium that apply the above-mentioned diffusion-based medical image segmentation method. All embodiments of the above-mentioned XX method are applicable to the device, electronic device and storage medium, and can achieve the same or similar beneficial effects.

[0122] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices (equipment), or computer program products. Therefore, the application can adopt the form of complete hardware embodiment, complete software embodiment, or the embodiment in combination with software and hardware, which are all collectively referred to as "module" or "system" herein. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The computer program is stored / distributed in a suitable medium, provided together with other hardware or as a part of hardware, or other distribution forms can be adopted, such as by the Internet or other wired or wireless telecommunication systems.

[0123] The above is a further detailed description of the present invention in conjunction with specific preferred embodiments, and the specific implementation of the present invention should not be considered to be limited to these descriptions. For those skilled in the art of the present invention, without departing from the concept of the present invention, several simple deductions or substitutions can be made, which should be considered to fall within the scope of protection of the present invention.

Claims

1. A KAN operator medical image segmentation method based on diffusion mechanism, characterized in that: include: A diffusion segmentation Diff-KAN model is constructed based on the diffusion mechanism and the KAN operator; the diffusion segmentation Diff-KAN model includes a denoising module using an encoder-decoder structure, and the denoising module includes a semantic encoder, a denoising encoder, a KAN module, and a denoising decoder; The original medical image to be processed is input into the diffusion segmentation Diff-KAN model for the following processing: Adding random Gaussian noise to the label to generate a pure noise image; performing channel splicing on the original medical image and the pure noise image, and inputting the spliced ​​noise image into the denoising encoder; Extracting semantic information from the original medical image using the semantic encoder to obtain a first feature; Inputting the output of each layer of the semantic encoder into a layer of corresponding size in the denoising encoder, and using the denoising encoder to extract local detail information in the noisy image to obtain a second feature; Utilizing the KAN module to optimize and refine the second feature to obtain a third feature; The first feature, the second feature, and the third feature are fused, and the fused features are input into the denoising decoder. At the same time, each layer output of the denoising encoder is input into the layer of corresponding size in the denoising decoder through a jump connection, and the segmentation result is output.

2. The KAN operator medical image segmentation method based on the diffusion mechanism according to claim 1 is characterized in that: The semantic encoder includes multiple first convolution blocks, each of which includes a convolution layer, a batch normalization layer and a ReLU activation function.

3. The KAN operator medical image segmentation method based on the diffusion mechanism according to claim 2 is characterized in that: The denoising encoder includes multiple second convolution blocks, each of which includes a convolution layer, a batch normalization layer and a ReLU activation function; wherein the number of the second convolution blocks is the same as the number of the first convolution blocks, and each second convolution block is connected to the first convolution block of the corresponding size to fuse features of different scales in the semantic encoder with features of corresponding scales in the denoising encoder.

4. The KAN operator medical image segmentation method based on diffusion mechanism according to claim 1, characterized in that: The KAN module includes several word segmentation KAN networks, which are connected in series in sequence, and the output end of the first word segmentation KAN network is connected to the input end of the last word segmentation KAN network; wherein, The input end of the first word segmentation KAN network is connected to the output of the denoising encoder as the input of the entire KAN module; The output end of the last word segmentation KAN network is connected to the input of the denoising decoder as the output of the entire KAN module.

5. The KAN operator medical image segmentation method based on diffusion mechanism according to claim 4, characterized in that: The word segmentation KAN network includes a word segmentation module, a mapping module, multiple KAN layers and layer normalization connected in sequence; The word segmentation module is used to reshape the input features into a 2D image block sequence through a word segmentation algorithm; The mapping module is used to map the 2D image block sequence to a D-dimensional embedding space to obtain high-dimensional features and pass them to the multiple KAN layers; The multiple KAN layers are connected in series in sequence to optimize and refine the input high-dimensional features; The layer normalization is used to process the output features of the last KAN layer to obtain the output of the current word segmentation KAN network; Each of the multiple KAN layers further includes a Batch normalization layer and a ReLU activation function.

6. The KAN operator medical image segmentation method based on diffusion mechanism according to claim 1, characterized in that: The denoising module specifically adopts a U-shaped structure and an encoder-decoder structure with dense skip connections, and the denoising decoder adopts a structure symmetrical to the denoising encoder.

7. The KAN operator medical image segmentation method based on diffusion mechanism according to claim 1, characterized in that: Before the original medical image to be processed is input into the diffusion segmentation Diff-KAN model for processing, the method further includes: Using the training set to train the diffusion segmentation Diff-KAN model; The training set is constructed using the following method: Collect existing medical imaging data, analyze the effective attributes in the medical imaging data based on principal component analysis, and generate a usable data set; Preprocessing the data set and dividing the preprocessed data set into a training set, a validation set, and a test set; the training set is used to train the diffusion segmentation Diff-KAN model, and the validation set and the test set are used to verify and evaluate the generalization ability of the diffusion segmentation Diff-KAN model; The loss function used in training is a comprehensive loss function consisting of Dice loss, binary cross entropy loss and mean square error loss.

8. A KAN operator medical image segmentation device based on a diffusion mechanism, used to implement the KAN operator medical image segmentation method based on a diffusion mechanism according to any one of claims 1 to 7, characterized in that: The device comprises: A model construction module is used to construct a diffusion segmentation Diff-KAN model based on the diffusion mechanism and the KAN operator; the diffusion segmentation Diff-KAN model includes a denoising module using an encoder-decoder structure, and the denoising module includes a semantic encoder, a noise encoder, a KAN module, and a denoising decoder; The image processing module is used to input the original medical image to be processed into the diffusion segmentation Diff-KAN model for the following processing: Adding random Gaussian noise to the label to generate a pure noise image; performing channel splicing on the original medical image and the pure noise image, and inputting the spliced ​​noise image into the denoising encoder; Extracting semantic information from the original medical image using the semantic encoder to obtain a first feature; inputting each layer output of the semantic encoder into a layer of corresponding size in the denoising encoder, and extracting local detail information from the noisy image using the denoising encoder to obtain a second feature; Utilizing the KAN module to optimize and refine the first feature to obtain a third feature; The first feature, the second feature, and the third feature are fused, and the fused features are input into the denoising decoder. At the same time, each layer output of the denoising encoder is input into the layer of corresponding size in the denoising decoder through a jump connection, and the segmentation result is output.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to execute a program stored in a memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 can be implemented.

Images