Medical ultrasonic image quality control system based on multi-modal fusion

Abstract

The invention discloses a medical ultrasonic image quality control system based on multi-modal fusion. The medical ultrasonic image quality control system comprises a data preprocessing module used for collecting medical ultrasonic image data of different modals from different crowds in real time and preprocessing the medical ultrasonic image data; the dynamic self-adaptive fusion module is used for dynamically adjusting a fusion strategy according to the medical ultrasonic image data acquired in real time and introducing a self-adaptive mechanism to dynamically adjust weights of different modal data; the image enhancement module combines medical ultrasonic image data with a three-dimensional anatomical structure of a human body by utilizing an augmented reality technology to generate a visual and three-dimensional diagnostic image; the visualization module adopts a dynamic image display mode to present the change process of the diagnosis image in real time; a complete medical ultrasonic image quality control system is constructed by integrating a data preprocessing module, a dynamic adaptive fusion module, an image enhancement module, a visualization module and the like, the system can automatically process and analyze medical ultrasonic image data, and the quality control efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to a medical ultrasonic image processing system, and in particular to a medical ultrasonic image quality control system based on multi-modal fusion. Background Art

[0002] Medical ultrasound imaging technology is an advanced medical diagnostic method that uses ultrasound to penetrate human tissue and reflect images, allowing doctors to clearly observe the structure, morphology and functional status of tissues, thereby diagnosing and monitoring diseases. This technology is widely used in many fields such as prenatal examinations, visceral organ evaluation and tumor detection. Medical ultrasound image quality control uses automated image analysis technology to compare ultrasound images with standard images of normal people, accurately detect and identify abnormalities or defects in the images, and ensure that the quality of medical ultrasound images meets diagnostic requirements. In recent years, multimodal fusion technology has been increasingly used in the medical field. It combines different medical imaging technologies with clinical data to provide more comprehensive and accurate information support for medical imaging diagnosis and quality control.

[0003] However, since medical ultrasound image data comes from a wide range of people and a variety of modalities, it shows a high degree of diversity and complexity, making it difficult for traditional processing methods to effectively deal with it. At the same time, the information contained in various modal ultrasound image data has different focuses. How to efficiently and accurately integrate this information constitutes a major challenge in the current technical field. In addition, medical ultrasound image data is usually presented in a two-dimensional form, which greatly limits doctors' intuitive understanding of the three-dimensional anatomical structure of the human body, thereby affecting the accuracy and efficiency of diagnosis.

[0004] Therefore, there is an urgent need for a medical ultrasound image quality control system based on multimodal fusion to solve the technical problems existing in the above-mentioned prior art. Summary of the invention

[0005] The present invention overcomes the deficiencies of the prior art and provides a medical ultrasound image quality control system based on multimodal fusion.

[0006] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a medical ultrasound image quality control system based on multimodal fusion, comprising: a data preprocessing module, a dynamic adaptive fusion module, an image enhancement module, and a visualization module;

[0007] The data preprocessing module is used to collect medical ultrasound image data of different modalities from different groups of people in real time and perform preprocessing;

[0008] The dynamic adaptive fusion module is used to dynamically adjust the fusion strategy according to the medical ultrasound image data acquired in real time, and introduce an adaptive mechanism to dynamically adjust the weights of different modality data;

[0009] The image enhancement module uses augmented reality technology to combine medical ultrasound image data with the three-dimensional anatomical structure of the human body to generate intuitive and three-dimensional diagnostic images;

[0010] The visualization module uses a dynamic image display method to present the changing process of the diagnostic image in real time.

[0011] In a preferred embodiment of the present invention, the preprocessing includes denoising, image resampling, normalization and contrast stretching of the medical ultrasound image data. The algorithm expression formula of the preprocessing is:

[0012]

[0013] In the formula, I preprocessed (x, y) is the image pixel value at the coordinate (x, y) after preprocessing; I resamled (x, y) represents the pixel value of the image after denoising and image resampling at the coordinate (x, y); min(I resampled ) is I resampled The overall minimum pixel value of the image; max(I resampled ) is I resampled The overall maximum pixel value of the image;

[0014] The preprocessing algorithm expression formula is resampled The pixel values ​​of the image are linearly mapped to the range [0,255] so that I resampled The contrast of the image is stretched, and the denominator of the preprocessing algorithm expression formula max(I resampled )-min(I resampled ) will I resampled The pixel values ​​of the image are stretched to the entire [0,255] range, and the numerator I resampled (x,y)-min(I resampled ) will I resampled The minimum pixel value of the image is mapped to 0, and the maximum pixel value is mapped to 255.

[0015] In a preferred embodiment of the present invention, the fusion strategy uses a multi-scale decomposition algorithm to decompose medical ultrasound image data of different modalities into images of multiple scales, fuses the decomposed images according to actual application scenarios and data features, and reconstructs the fused images at multiple scales to generate new image data; the algorithm expression formula of the fusion strategy is:

[0016] W j (I) = DWT(I)

[0017]

[0018] Ifused =IDWT(F j )

[0019] Where, I is the original image data; W j (I) represents the wavelet coefficient at the jth scale; DWT(I) represents the discrete wavelet transform function; F j Represents the fused wavelet coefficients; I A and I B They represent medical ultrasound image data from different modalities; and They represent the wavelet coefficients of medical ultrasound image data of different modalities at the jth scale; α and β are weighted coefficients, and satisfy α+β=1; I fused represents the fused image data; IDWT(·) represents the inverse discrete wavelet transform function.

[0020] In a preferred embodiment of the present invention, based on different groups of people, different modalities, actual application scenarios and data characteristics, the adaptive mechanism is introduced to dynamically adjust the weights of different modal data. The algorithm expression formula of the adaptive mechanism is:

[0021]

[0022] In the formula, Represents the weighted wavelet coefficients; W(F j ) represents the calculated adaptive weight matrix; Represents an element-by-element multiplication operation; F j represents the fused wavelet coefficients; Represents the image data obtained by fusion after the introduction of the adaptive mechanism.

[0023] In a preferred embodiment of the present invention, the image enhancement module uses computer graphics and medical image processing technology to construct a three-dimensional anatomical model of the patient's body based on medical ultrasound image data or other medical image data of the human body, and uses augmented reality technology to superimpose the virtual medical ultrasound image data onto the human body or anatomical model in the real world to generate an enhanced diagnostic image.

[0024] In a preferred embodiment of the present invention, the process expression formula of superimposing virtual medical ultrasound image data onto a human body or anatomical model in the real world by using the augmented reality technology is:

[0025]

[0026] Where M represents the three-dimensional anatomical model; f model (·) represents a function for constructing a three-dimensional anatomical model, which accepts the original medical image data as input and outputs a three-dimensional anatomical model M; I represents medical ultrasound image data of different modalities of different populations collected in real time by the data preprocessing module without preprocessing; enhanced F stands for diagnostic imaging; AR (·) represents a composite function, which accepts the medical ultrasound image data of different modalities of different populations collected in real time by the data preprocessing module without preprocessing and the image data fused after introducing the adaptive mechanism as input, and outputs the diagnostic image I enhanced .

[0027] In a preferred embodiment of the present invention, the visualization module includes an interactive interface, allowing the user to interact with the displayed dynamic image through touch, gesture or voice command to achieve image zooming in, zooming out, rotating, cutting, and marking and analysis of specific areas.

[0028] In a preferred embodiment of the present invention, a method for using a medical ultrasound image quality control system based on multimodal fusion is applied to the medical ultrasound image quality control system based on multimodal fusion described above:

[0029] The medical ultrasound image quality control system based on multimodal fusion is started. The data preprocessing module collects medical ultrasound image data of different modalities from different populations in real time and preprocesses them by denoising, image resampling, normalization and contrast stretching. The pixel values ​​of medical ultrasound images are linearly mapped to

[0030] In the range [0,255];

[0031] Based on the medical ultrasound image data acquired in real time, the system uses a multi-scale decomposition algorithm to decompose the medical ultrasound image data from different modalities into images of multiple scales, and fuses the decomposed images according to the actual application scenario and data characteristics. At the same time, an adaptive mechanism is introduced in the fusion process to dynamically adjust the weights of different modal data to implement a dynamic adjustment strategy, and then new image data is generated through scale reconstruction technology;

[0032] The system again uses computer graphics and medical image processing technology, combined with augmented reality technology, to construct a three-dimensional anatomical model of the human body, and superimposes virtual medical ultrasound image data onto the human body or anatomical model in the real world to generate intuitive and three-dimensional diagnostic images;

[0033] The visualization module uses dynamic image display technology to present the changing process of the diagnostic image, and users can interact with the diagnostic image through an interactive interface to zoom in, zoom out, rotate, cut the image, and mark and analyze specific areas.

[0034] In a preferred embodiment of the present invention, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the system or method when executing the computer program.

[0035] In a preferred embodiment of the present invention, a computer-readable storage medium stores a computer program, which implements the steps or method steps when executed by a processor.

[0036] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0037] (1) The present invention uses a data preprocessing module to perform denoising, image resampling, normalization, and contrast stretching on medical ultrasound image data collected in real time, thereby improving the availability and consistency of the data. The preprocessing algorithm linearly maps the image pixel values ​​to the range of [0, 255], thereby enhancing the image contrast and providing a clearer image basis for subsequent analysis.

[0038] (2) The present invention adopts a dynamic adaptive fusion module and a multi-scale decomposition algorithm to decompose data of different modalities into images of multiple scales, and fuses them according to the actual application scenario and data features. In addition, by introducing an adaptive mechanism, the weights of data of different modalities are dynamically adjusted, thereby achieving more accurate and flexible multi-modal data fusion.

[0039] (3) The present invention uses an image enhancement module, computer graphics and medical image processing technology to construct a three-dimensional anatomical model, and combines it with augmented reality technology to superimpose virtual medical ultrasound image data onto a human body or anatomical model in the real world to generate intuitive and three-dimensional diagnostic images, thereby not only improving the intuitiveness of the image, but also enhancing the doctor's understanding and judgment of the disease.

[0040] (4) The present invention uses a visualization module to present the changing process of diagnostic images in real time using a dynamic image display method. At the same time, an interactive interface is provided to allow users to interact with the image by touch, gesture or voice command, to achieve image zooming in, zooming out, rotating, cutting, and marking and analyzing specific areas, thereby greatly improving the doctor's diagnostic efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 It is a system flow chart of a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0045] like Figure 1 As shown, a medical ultrasound image quality control system based on multimodal fusion includes: a data preprocessing module, a dynamic adaptive fusion module, an image enhancement module, and a visualization module;

[0046] The data preprocessing module is used to collect and preprocess medical ultrasound image data of different modalities from different populations in real time;

[0047] It should be explained that the types of distinctions between different groups of people include:

[0048] Age differences, children, teenagers, adults and the elderly, etc. People of different age groups have differences in physiological structure, metabolic level, etc., which leads to different medical ultrasound imaging performances.

[0049] Gender differences: Men and women differ in physiological structure, hormone levels, etc., which will also affect the performance of medical ultrasound images.

[0050] Disease status: There will be significant differences in medical ultrasound images between healthy people and people with different diseases. In addition, even people with the same disease may show different imaging characteristics due to factors such as the severity of the disease and the duration of the disease.

[0051] Genetic background: Differences in genetic background may also lead to differences in the performance of medical ultrasound images among people.

[0052] In medical ultrasound imaging, different modalities usually refer to different types of ultrasound imaging techniques or methods, which can provide different information about the internal structure of the human body. Common medical ultrasound imaging modalities include:

[0053] B-mode ultrasound: This is the most common ultrasound imaging modality, used to display two-dimensional images of the internal structures of the human body.

[0054] Doppler ultrasound: used to detect the speed and direction of blood flow, which helps to evaluate the functional status of organs such as the heart and blood vessels.

[0055] 3D ultrasound: provides three-dimensional images of the internal structure of the human body, helping doctors to understand the condition of the disease more intuitively.

[0056] Elastography: Elastography helps diagnose certain diseases, such as breast cancer, by assessing tissue stiffness.

[0057] Contrast-enhanced ultrasound (CEUS): The contrast of ultrasound images is enhanced by intravenous injection of contrast agents, which helps to show the lesion more clearly.

[0058] Furthermore, the preprocessing includes denoising, image resampling, normalization and contrast stretching of medical ultrasound image data. The algorithm expression formula of the preprocessing is:

[0059]

[0060] In the formula, I preprocessed (x, y) is the image pixel value at the coordinate (x, y) after preprocessing; I resamled (x, y) represents the pixel value of the image after denoising and image resampling at the coordinate (x, y); min(I resampled ) is I resampled The overall minimum pixel value of the image; max(I resampled ) is I resampled The overall maximum pixel value of the image;

[0061] The preprocessing algorithm expression formula is I resampled The pixel values ​​of the image are linearly mapped to the range [0,255] so that I resampled The contrast of the image is stretched, and the denominator of the preprocessing algorithm expression formula

[0062] max(I resampled )-min(I resampled ) will I resampled The pixel values ​​of the image are stretched to the entire [0,255] range, and the numerator I resampled (x,y)-min(I resampled ) will I resampledThe minimum pixel value of the image is mapped to 0, and the maximum pixel value is mapped to 255.

[0063] The dynamic adaptive fusion module is used to dynamically adjust the fusion strategy according to the medical ultrasound image data acquired in real time, and introduce an adaptive mechanism to dynamically adjust the weights of different modality data;

[0064] Furthermore, the fusion strategy uses a multi-scale decomposition algorithm to decompose medical ultrasound image data of different modalities into images of multiple scales, fuses the decomposed images according to the actual application scenario and data characteristics, reconstructs the fused images at multiple scales, and generates new image data; the algorithm expression formula of the fusion strategy is:

[0065] W j (I) = DWT(I)

[0066]

[0067] I fused =IDWT(F j )

[0068] Where, I is the original image data; W j (I) represents the wavelet coefficient at the jth scale; DWT(I) represents the discrete wavelet transform function; F j Represents the fused wavelet coefficients; I A and I B They represent medical ultrasound image data from different modalities; and They represent the wavelet coefficients of medical ultrasound image data of different modalities at the jth scale; α and β are weighted coefficients, and satisfy α+β=1; I fused represents the fused image data; IDWT(·) represents the inverse discrete wavelet transform function.

[0069] Furthermore, based on different populations, different modalities, actual application scenarios and data characteristics, an adaptive mechanism is introduced to dynamically adjust the weights of different modal data. The algorithm expression formula of the adaptive mechanism is:

[0070]

[0071] In the formula, Represents the weighted wavelet coefficients; W(F j ) represents the calculated adaptive weight matrix; Represents an element-by-element multiplication operation; F j represents the fused wavelet coefficients; Represents the image data obtained by fusion after the introduction of the adaptive mechanism.

[0072] It should be noted that the specific implementation of the adaptive weight function W(·) depends on the criteria and algorithm used. For example, if the weights are calculated based on local energy, then W(·) involves calculating the local energy map of the wavelet coefficients and assigning weights based on the energy map. If the weights are calculated based on clarity or contrast, then W(·) involves calculating statistics such as the gradient or standard deviation of the wavelet coefficients and assigning weights based on these statistics.

[0073] In addition, the adaptive mechanism can be applied not only to the multi-scale reconstruction stage, but also to the multi-scale fusion stage. For example, adaptive weights can be introduced into the fusion function to dynamically adjust the contribution of different modal data in the fusion process. In this way, the entire fusion strategy will be more flexible and robust, and can better adapt to different application scenarios and data characteristics.

[0074] The image enhancement module uses augmented reality technology to combine medical ultrasound image data with the three-dimensional anatomical structure of the human body to generate intuitive and three-dimensional diagnostic images;

[0075] The image enhancement module uses computer graphics and medical image processing technology to construct a three-dimensional anatomical model of the patient's body based on the medical ultrasound image data or other medical image data of the human body. It uses augmented reality technology to superimpose the virtual medical ultrasound image data onto the human body or anatomical model in the real world to generate an enhanced diagnostic image.

[0076] Furthermore, the process expression formula of superimposing virtual medical ultrasound image data onto a human body or anatomical model in the real world by using augmented reality technology is:

[0077]

[0078] Where M represents the three-dimensional anatomical model; f model (·) represents a function for constructing a three-dimensional anatomical model, which accepts the original medical image data as input and outputs a three-dimensional anatomical model M; It represents the medical ultrasound image data of different modalities of different populations collected in real time by the data preprocessing module without preprocessing;

[0079] I enhanced F stands for diagnostic imaging; AR (·) represents a composite function, which accepts the medical ultrasound image data of different modalities of different populations collected in real time by the data preprocessing module without preprocessing and the image data fused after the introduction of the adaptive mechanism as input, and outputs the diagnostic image I enhanced .

[0080] What needs to be further explained here is that, first, the processing of the three-dimensional anatomical model and the medical ultrasound image data is respectively performed by two functions M and To indicate that f model (·) A function for constructing a three-dimensional anatomical model, which accepts raw medical imaging data (including data of multiple modalities, such as CT, MRI, US, etc.) as input and outputs a three-dimensional anatomical model M.

[0081] Let f peprocess (·) Function used to process the post-medical ultrasound image data, accepting the original medical ultrasound image data As input, it performs denoising, contrast enhancement and other processing, and outputs the processed medical ultrasound image data I us , its formula expression is:

[0082]

[0083] Afterwards, the overlay process of augmented reality technology is refined into multiple steps, such as registration, fusion and rendering. registration (·) represents the registration function, which accepts the 3D anatomical model M and the processed medical ultrasound image data I us As input, and output the registered data pair (M registered , I us ), its formula expression is:

[0084] (M registered , I us ) = f registration (M,I us ).

[0085] Then, let f fusion (·) represents the fusion function, accepting the registered data pair (M registered , I us ) as input, and fuse the medical ultrasound image into the 3D anatomical model, and output the fused data Its formula expression is:

[0086] I fused =f fusion (M regeistered ,I us ).

[0087] The visualization module uses dynamic image display to present the changes of diagnostic images in real time.

[0088] The visualization module includes an interactive interface that allows users to interact with the displayed dynamic images through touch, gestures or voice commands to zoom in, zoom out, rotate, cut the images, and mark and analyze specific areas.

[0089] A method for using a medical ultrasound image quality control system based on multimodal fusion is applied to the above-mentioned medical ultrasound image quality control system based on multimodal fusion:

[0090] The medical ultrasound image quality control system based on multimodal fusion is started. The data preprocessing module collects medical ultrasound image data of different modalities from different populations in real time and preprocesses them by denoising, image resampling, normalization and contrast stretching. The pixel values ​​of medical ultrasound images are linearly mapped to

[0091] In the range [0,255];

[0092] Based on the medical ultrasound image data acquired in real time, the system uses a multi-scale decomposition algorithm to decompose the medical ultrasound image data from different modalities into images of multiple scales, and fuses the decomposed images according to the actual application scenario and data characteristics. At the same time, an adaptive mechanism is introduced in the fusion process to dynamically adjust the weights of different modal data to implement a dynamic adjustment strategy, and then new image data is generated through scale reconstruction technology;

[0093] The system again uses computer graphics and medical image processing technology, combined with augmented reality technology, to construct a three-dimensional anatomical model of the human body, and superimposes virtual medical ultrasound image data onto the human body or anatomical model in the real world to generate intuitive and three-dimensional diagnostic images;

[0094] The visualization module uses dynamic image display technology to present the changing process of the diagnostic image, and users can interact with the diagnostic image through an interactive interface to zoom in, zoom out, rotate, cut the image, and mark and analyze specific areas.

[0095] Furthermore, the system supports cloud storage and remote access functions. All processed image data and analysis results can be securely uploaded to the cloud server, and authorized users can access and view them anytime and anywhere through any Internet-connected device, promoting the sharing of medical resources and the development of telemedicine services.

[0096] The system also integrates data encryption and secure transmission mechanisms to ensure the security and privacy protection of imaging data during transmission and storage, in compliance with relevant regulations and standards for medical information security.

[0097] The present invention constructs a complete medical ultrasound image quality control system by integrating modules such as data preprocessing, dynamic adaptive fusion, image enhancement and visualization. The system can automatically process and analyze medical ultrasound image data, improving the efficiency and accuracy of quality control. At the same time, the present invention also provides a computer device and a computer-readable storage medium, so that the system can run in different hardware and software environments, further enhancing the versatility and practicality of the system.

[0098] The above is based on the ideal embodiment of the present invention. Through the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention. The technical scope of the present invention is not limited to the content in the specification, and the technical scope must be determined according to the scope of the claims.

Claims

1. A medical ultrasound image quality control system based on multimodal fusion, characterized in that: include: Data preprocessing module, dynamic adaptive fusion module, image enhancement module, and visualization module; The data preprocessing module is used to collect medical ultrasound image data of different modalities from different groups of people in real time and perform preprocessing; The dynamic adaptive fusion module is used to dynamically adjust the fusion strategy according to the medical ultrasound image data acquired in real time, and introduce an adaptive mechanism to dynamically adjust the weights of different modality data; The image enhancement module uses augmented reality technology to combine medical ultrasound image data with the three-dimensional anatomical structure of the human body to generate intuitive and three-dimensional diagnostic images; The visualization module uses a dynamic image display method to present the changing process of the diagnostic image in real time.

2. The medical ultrasound image quality control system based on multimodal fusion according to claim 1, characterized in that: The preprocessing includes denoising, image resampling, normalization and contrast stretching of the medical ultrasound image data. The algorithm expression formula of the preprocessing is: In the formula, I preprocessed (x, y) is the image pixel value at the coordinate (x, y) after preprocessing; I resamled (x, y) represents the pixel value of the image after denoising and image resampling at the coordinate (x, y); min(I resampled ) is I resampled The overall minimum pixel value of the image; max(I resampled ) is I resampled The overall maximum pixel value of the image; The preprocessing algorithm expression formula is resampled The pixel values ​​of the image are linearly mapped to the range [0,255] so that I resampled The contrast of the image is stretched, and the denominator of the preprocessing algorithm expression formula max(I resampled )-min(I resampled ) will I resampled The pixel values ​​of the image are stretched to the entire [0,255] range, and the numerator I resampled (x,y)-min(I resampled ) will I resampled The minimum pixel value of the image is mapped to 0, and the maximum pixel value is mapped to 255.

3. The medical ultrasound image quality control system based on multimodal fusion according to claim 1, characterized in that: The fusion strategy uses a multi-scale decomposition algorithm to decompose medical ultrasound image data of different modalities into images of multiple scales, fuses the decomposed images according to actual application scenarios and data features, and reconstructs the fused images at multiple scales to generate new image data; the algorithm expression formula of the fusion strategy is: W j (I)=DWT(I) I fused =IDWT(F j ) Where, I is the original image data; W j (I) represents the wavelet coefficient at the jth scale; DWT(I) represents the discrete wavelet transform function; F j Represents the fused wavelet coefficients; I A and I B They represent medical ultrasound image data from different modalities; and They represent the wavelet coefficients of medical ultrasound image data of different modalities at the jth scale; α and β are weighted coefficients, and satisfy α+β=1; I fused represents the fused image data; IDWT(·) represents the inverse discrete wavelet transform function.

4. A medical ultrasound image quality control system based on multimodal fusion according to claims 1 and 3, characterized in that: Based on different groups of people, different modalities, actual application scenarios and data characteristics, the adaptive mechanism is introduced to dynamically adjust the weights of different modal data. The algorithm expression formula of the adaptive mechanism is: In the formula, Represents the weighted wavelet coefficients; W(F j ) represents the calculated adaptive weight matrix; Represents an element-by-element multiplication operation; F j represents the fused wavelet coefficients; Represents the image data obtained by fusion after the introduction of the adaptive mechanism.

5. The medical ultrasound image quality control system based on multimodal fusion according to claim 1, characterized in that: The image enhancement module uses computer graphics and medical image processing technology to construct a three-dimensional anatomical model of the patient's body based on the medical ultrasound image data or other medical image data of the human body, and uses augmented reality technology to superimpose the virtual medical ultrasound image data onto the human body or anatomical model in the real world to generate an enhanced diagnostic image.

6. A medical ultrasound image quality control system based on multimodal fusion according to claims 1 and 5, characterized in that: The process expression formula of superimposing virtual medical ultrasound image data onto a human body or anatomical model in the real world by using the augmented reality technology is: Where M represents the three-dimensional anatomical model; f model (·) represents a function for constructing a three-dimensional anatomical model, which accepts the original medical image data as input and outputs a three-dimensional anatomical model M; I represents medical ultrasound image data of different modalities of different populations collected in real time by the data preprocessing module without preprocessing; enhanced F stands for diagnostic imaging; AR (·) represents a composite function, which accepts the medical ultrasound image data of different modalities of different populations collected in real time by the data preprocessing module without preprocessing and the image data fused after introducing the adaptive mechanism as input, and outputs the diagnostic image I enhanced .

7. The medical ultrasound image quality control system based on multimodal fusion according to claim 1, characterized in that: The visualization module includes an interactive interface, which allows the user to interact with the displayed dynamic image by means of touch, gesture or voice command, so as to achieve image zooming in, zooming out, rotating, cutting, and marking and analysis of specific areas.

8. A method for using a medical ultrasound image quality control system based on multimodal fusion, applied to a medical ultrasound image quality control system based on multimodal fusion as described in any one of claims 1 to 7, characterized in that: Start the medical ultrasound image quality control system based on multimodal fusion, collect and preprocess medical ultrasound image data of different modalities from different populations in real time through the data preprocessing module by means of denoising, image resampling, normalization and contrast stretching, and linearly map the pixel values ​​of medical ultrasound images to the range of [0,255]; Based on the medical ultrasound image data acquired in real time, the system uses a multi-scale decomposition algorithm to decompose the medical ultrasound image data from different modalities into images of multiple scales, and fuses the decomposed images according to the actual application scenario and data characteristics. At the same time, an adaptive mechanism is introduced in the fusion process to dynamically adjust the weights of different modal data to implement a dynamic adjustment strategy, and then new image data is generated through scale reconstruction technology; The system again uses computer graphics and medical image processing technology, combined with augmented reality technology, to construct a three-dimensional anatomical model of the human body, and superimposes virtual medical ultrasound image data onto the human body or anatomical model in the real world to generate intuitive and three-dimensional diagnostic images; The visualization module uses dynamic image display technology to present the changing process of the diagnostic image, and users can interact with the diagnostic image through an interactive interface to zoom in, zoom out, rotate, cut the image, and mark and analyze specific areas.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the system or method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps or method steps of any one of claims 1 to 8 are implemented.

Images