Image acquisition processing method and system based on AR technology

Abstract

The invention discloses an image acquisition processing method and system based on an AR technology, relates to the technical field of augmented reality, and effectively solves the problems of image noise and artifacts through an image enhancement module and a dynamic artifact correction module. The image enhancement module highlights key areas, adjusts details and weakens metal artifacts in combination with an artifact removal algorithm, and the artifact correction module captures tiny movement of a patient in real time by using a posture tracking algorithm, calculates a correction coefficient Jyz, compensates and eliminates motion artifacts according to the correction coefficient Jyz and outputs a high-quality medical image; multi-frame fusion and detail compensation are carried out by adopting a super-resolution reconstruction algorithm of an AR technology, the resolution is improved, recognition of tiny lesions is enhanced, and missed diagnosis is avoided; the data standardization processing module unifies different device formats through a data bridging interface to ensure compatibility; whether image enhancement is triggered or not is determined by gradually calculating the image quality Ylzz and the image anomaly evaluation index Yjz, it is ensured that the image meets the diagnostic standard, and cross-platform sharing is achieved.

Description

Technical Field

[0001] The present invention relates to the field of augmented reality technology, and in particular to an image acquisition and processing method and system based on AR technology. Background Art

[0002] The image acquisition and processing system originated from early photography and video technology, and has gradually improved with the development of digital image processing technology. The earliest image acquisition and processing system was used to acquire and store static images. With the advancement of technology, it has gradually expanded to video surveillance, satellite remote sensing, industrial detection and other fields. In recent years, the introduction of computer vision, artificial intelligence and deep learning has made the application of image acquisition and processing systems in image analysis, feature recognition, target detection and other aspects more accurate and efficient. The development of this system has greatly improved the acquisition speed and processing capabilities of image information, providing a rich data foundation and technical support for various industries.

[0003] Image acquisition and processing systems are widely used in various fields, including medical image analysis, but in practical applications, the following technical problems often exist: 1. Image noise and artifacts: Medical images may be affected by various noises and artifacts during the acquisition process, such as motion artifacts, metal artifacts, etc. These factors will reduce image quality and affect subsequent analysis and diagnosis.

[0004] 2. Resolution limitation: The resolution of some imaging acquisition devices is low and may not be able to clearly display fine structures, resulting in missed or misdiagnosis of early lesions, especially in the early screening of diseases such as tumors.

[0005] 3. Data standardization and interoperability: Inconsistent data formats and standards between different devices and systems may lead to compatibility and portability issues for imaging data, making cross-platform analysis and sharing difficult. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides an image acquisition and processing method and system based on AR technology, which solves the technical shortcomings of image noise and artifacts, resolution limitations, and data standardization and interoperability in the background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an image acquisition and processing system based on AR technology, including an image enhancement module, a dynamic artifact correction module, a resolution optimization module, a data standardization processing module and a comprehensive evaluation module; The image enhancement module is used to enhance the image appearing in the medical image acquisition process in real time by using AR technology, by superimposing multiple layers of virtual information to highlight key areas, adjusting the detail visibility and artifacts of the image, and finally obtaining a first medical image; The dynamic artifact correction module is used to automatically identify motion artifacts caused by patient movement or device jitter in the first medical image, use a posture tracking algorithm to capture the patient's tiny movements in real time, calculate and evaluate the correction coefficient Jyz in real time, compensate and correct the image in real time based on the evaluation content of the correction coefficient Jyz, and finally obtain the second medical image; The resolution optimization module is used to combine the super-resolution reconstruction algorithm of AR technology, perform pixel detail compensation and image reconstruction on the acquired second medical image, adjust the image resolution and the recognition ability of subtle lesions, including the imaging effect of early tumor screening, and finally obtain a third medical image; The data standardization processing module is used to convert all collected third medical images into a unified format, and through AR technology and data bridging interface, make the data of different collection devices and systems have cross-platform compatibility and interoperability, share image data in real time and conduct comprehensive analysis; The comprehensive evaluation module is used to calculate the image quality coefficient Ylzz for the third medical image and perform a comprehensive analysis, and then further generate an image abnormality evaluation index Yjz; pre-set the noise tolerance threshold N and the quality evaluation threshold R, and compare the image quality coefficient Ylzz with the noise tolerance threshold N to determine whether the noise level of the current image is within an acceptable range, and compare and evaluate the image abnormality evaluation index Yjz with the quality evaluation threshold R, and formulate subsequent image processing and diagnosis recommendations based on the evaluation content.

[0008] Preferably, the image enhancement module uses imaging equipment to perform preliminary acquisition of medical images to obtain original images; then activates AR technology to analyze image data in real time and identify key areas and artifact interference areas in the image; through multi-layer virtual information superposition, the enhancement algorithm is applied to key areas to highlight fine structures and adjust detail visibility; Then, for the artifacts caused by metal tools, image segmentation and artifact removal algorithms are used to automatically filter and weaken the interference of metal artifacts on the image; finally, the image processed with detail enhancement and artifact correction will be superimposed on the original image to achieve a real-time preview effect after enhancement, and finally the real-time enhanced image will be marked as the first medical image.

[0009] Preferably, the dynamic artifact correction module includes a motion detection unit and a correction compensation unit; The motion detection unit is used to automatically identify motion artifacts caused by patient movement or device jitter in the first medical image, and obtain the patient's posture tracking information in real time through a posture tracking algorithm, including the patient's slight movement; the posture tracking information generates motion trajectory data corresponding to the image, including the patient's movement amplitude parameter Md, the device jitter frequency parameter Df, the image clarity change parameter Iq and the image time series parameter Tt; After extracting the motion trajectory data and performing dimensionless processing, the correction coefficient Jyz is calculated in real time using the following formula: Then, the preset correction threshold Q and correction coefficient Jyz are used for evaluation, and the image is compensated and corrected in real time. The specific evaluation contents are as follows: If the correction coefficient Jyz ≤ the correction threshold Q, it indicates that the motion artifact in the current image has a normal effect and no additional compensation processing is required. The original image quality is directly retained and the current image is directly marked as the second medical image for resolution adjustment; If the correction coefficient Jyz>correction threshold Q, it indicates that the motion artifact in the current image has an abnormal effect. In this case, additional compensation processing is performed on the current image, and after the compensation processing is completed on the current image, it is marked as the second medical image.

[0010] Preferably, the correction and compensation unit is used to perform image correction on the image with abnormal motion artifacts generated by the motion detection unit, by extracting the patient's movement trajectory data in real time, and combining it with the posture tracking information, using the inverse correction algorithm to correct the area in the image affected by the motion artifacts pixel by pixel, and compensate in real time for the image distortion caused by the patient's movement or the device shaking; Subsequently, the correction and compensation unit eliminates the edge transition discontinuity phenomenon in the correction process by performing a smoothing process; finally, the image after the compensation process is completed is marked and a second medical image is output.

[0011] Preferably, the resolution optimization module is used to receive and import a second medical image, and perform denoising and artifact removal operations on the second medical image through a preprocessing step; then call a super-resolution reconstruction algorithm based on AR technology, and compensate and reconstruct the lost details in the low-resolution image through multi-frame image fusion and detail reconstruction technology to form a high-resolution image; finally, output an optimized high-resolution image and mark it as a third medical image.

[0012] Preferably, the data standardization processing module first receives the third medical image, and automatically detects the original format and related parameters in the third medical image through a built-in format recognition algorithm; then, the data bridging interface enhanced by AR technology is used to perform format conversion on the third medical image, and uniformly converts it into a standardized medical imaging format; finally, a multi-layer data protocol verification mechanism is established to prevent the loss of key details or image quality during the conversion process.

[0013] Preferably, the comprehensive evaluation module includes a noise analysis unit, a quality analysis unit and an evaluation decision unit; The noise analysis unit is used to detect and analyze the noise level of the third medical image, obtain the noise feature related data in the image in real time and perform dimensionless processing; wherein the noise feature related data includes the spatial frequency Sf, the texture roughness Tr, the contrast fluctuation value Cw and the edge gradient variation value Eg, and the image quality coefficient Ylzz is calculated by the following formula: The preset noise tolerance threshold N is compared with the image quality coefficient Ylzz for evaluation. The specific contents are as follows: If the image quality coefficient Ylzz ≤ threshold N, it indicates that the noise level of the image is within an acceptable range, the image quality meets the diagnostic requirements, and can be directly used for subsequent analysis and clinical diagnosis; If the image quality coefficient Ylzz>noise tolerance threshold N, it indicates that the noise level in the image exceeds the acceptable range, but the impact on the image detail resolution and diagnostic reliability is unknown, and further analysis is performed at this time.

[0014] Preferably, the quality analysis unit is used to further analyze and calculate the image whose noise level exceeds the acceptable range according to the evaluation content of the image quality coefficient Ylzz, and generate the image abnormality evaluation index Yjz; By deploying sensors near the imaging equipment, including acceleration sensors, illumination sensors, RF interference sensors, and built-in thermal noise sensors, the environmental acquisition interference related data is obtained in real time. After extracting the environmental acquisition interference related data and performing dimensionless processing, the image anomaly assessment index Yjz is calculated using the following formula: Wherein, Mv is the micro-vibration interference value in the environmental collection interference related data, Lu is the light source unevenness value in the environmental collection interference related data, Ei is the electronic interference value in the environmental collection interference related data, and Tn is the thermal noise value in the environmental collection interference related data.

[0015] Preferably, the evaluation decision unit is used to compare the image abnormality evaluation index Yjz with a preset quality evaluation threshold R, and formulate a subsequent image processing plan and diagnostic suggestion, the specific contents of which are as follows: If the image abnormality assessment index Yjz ≤ the quality assessment threshold R, it means that the noise and interference level of the image is within an acceptable range, indicating that the image meets the quality standard. At this time, the current image is directly used for diagnosis, and conventional diagnostic analysis is performed on this basis; If the image abnormality assessment index Yjz>quality assessment threshold R, it means that the noise and interference levels of the image are beyond the acceptable range, indicating that the image does not meet the quality standards. At this time, the image enhancement or denoising program is started; the image processing solution should include high-frequency filtering, image smoothing and artifact removal algorithms; diagnostic recommendations include re-evaluating the image quality after processing.

[0016] An image acquisition and processing method based on AR technology includes the following steps: Step 1: Use AR technology to enhance the images that appear during the medical image acquisition process in real time, by superimposing multiple layers of virtual information to highlight key areas, adjust the detail visibility and artifacts of the image, and finally obtain the first medical image; Step 2: automatically identify motion artifacts in the first medical image caused by patient movement or device jitter, use a posture tracking algorithm to capture the patient's tiny movements in real time, calculate and evaluate the correction coefficient Jyz in real time, compensate and correct the image in real time based on the evaluation content of the correction coefficient Jyz, and finally obtain the second medical image; Step 3: Combine the AR technology’s super-resolution reconstruction algorithm to perform pixel detail compensation and image reconstruction on the acquired second medical image, adjust the image resolution and the ability to identify subtle lesions, including the imaging effect of early tumor screening, and finally obtain the third medical image; Step 4: Convert all collected third-party medical images into a unified format, and use AR technology and data bridging interface to make data from different acquisition devices and systems cross-platform compatible and interoperable, so that image data can be shared in real time and comprehensive analysis can be performed; Step 5. Calculate and obtain the image quality coefficient Ylzz for the third medical image and conduct a comprehensive analysis, and then further generate the image abnormality assessment index Yjz; pre-set the noise tolerance threshold N and the quality assessment threshold R, and compare the image quality coefficient Ylzz with the noise tolerance threshold N to determine whether the noise level of the current image is within an acceptable range, and compare the image abnormality assessment index Yjz with the quality assessment threshold R to obtain the diagnostic reliability level of the image, and formulate subsequent image processing and diagnosis recommendations based on the assessment level.

[0017] The present invention provides an image acquisition and processing method and system based on AR technology, which has the following beneficial effects: (1) This image acquisition and processing method and system based on AR technology effectively solves the problems of image noise and artifacts through an image enhancement module and a dynamic artifact correction module. The image enhancement module highlights the key areas in the image by superimposing multiple layers of virtual information and adjusts the visibility of details. At the same time, it combines image segmentation and artifact removal algorithms to weaken the interference of metal artifacts on the image. The dynamic artifact correction module uses a posture tracking algorithm to capture the patient's tiny movements in real time, generate the patient's movement amplitude parameter Md, the device jitter frequency parameter Df, the image clarity change parameter Iq and the image time series parameter Tt, and eliminates or reduces the motion artifacts caused by patient movement or device jitter by calculating the correction coefficient Jyz in real time and performing evaluation and compensation, and finally outputs high-quality medical images. (2) This is an image acquisition and processing method and system based on AR technology. The resolution optimization module adopts the super-resolution reconstruction algorithm of AR technology, and compensates and reconstructs the pixel details of the second medical image through multi-frame image fusion and detail reconstruction technology, which significantly improves the image resolution and enhances the ability to identify subtle lesions, especially the early screening effect for diseases such as tumors. The image quality is stable through pre-processing denoising and artifact correction. The module finally outputs an optimized high-resolution third medical image to ensure that subtle structures are clearly presented and avoid the risk of missed diagnosis or misdiagnosis due to low resolution. (3) In this image acquisition and processing method and system based on AR technology, the data standardization processing module and the comprehensive evaluation module jointly solve the problems of data standardization and cross-platform compatibility. The data standardization processing module converts the image data of different acquisition devices and systems into a unified format through the data bridging interface and multi-layer data protocol verification mechanism enhanced by AR technology, avoiding the compatibility and portability problems caused by inconsistent formats; the comprehensive evaluation module detects the image quality coefficient Ylzz in real time through the noise analysis unit and the quality analysis unit, extracts and analyzes the environmental acquisition interference related data, such as the micro-vibration interference value Mv, the light source unevenness value Lu, the electronic interference value Ei, and the thermal noise value Tn, calculates the image abnormality evaluation index Yjz, and compares it with the preset quality evaluation threshold R to ensure that the image meets the standard during diagnosis or trigger the image enhancement and denoising program, thereby realizing cross-platform sharing and comprehensive analysis of medical image data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a structural block diagram of an image acquisition and processing system based on AR technology in the present invention; Figure 2 The present invention is a flowchart of an image acquisition and processing method based on AR technology. DETAILED DESCRIPTION

[0019] 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.

[0020] Example 1 See also Figure 1 , the present invention provides an image acquisition and processing system based on AR technology, including an image enhancement module, a dynamic artifact correction module, a resolution optimization module, a data standardization processing module and a comprehensive evaluation module; The image enhancement module is used to enhance the image appearing in the medical image acquisition process in real time by using AR technology, by superimposing multiple layers of virtual information to highlight key areas, adjusting the detail visibility and artifacts of the image, and finally obtaining a first medical image; The dynamic artifact correction module is used to automatically identify motion artifacts caused by patient movement or device jitter in the first medical image, use a posture tracking algorithm to capture the patient's tiny movements in real time, calculate and evaluate the correction coefficient Jyz in real time, compensate and correct the image in real time based on the evaluation content of the correction coefficient Jyz, and finally obtain the second medical image; The resolution optimization module is used to combine the super-resolution reconstruction algorithm of AR technology, perform pixel detail compensation and image reconstruction on the acquired second medical image, adjust the image resolution and the recognition ability of subtle lesions, including the imaging effect of early tumor screening, and finally obtain a third medical image; The data standardization processing module is used to convert all collected third medical images into a unified format, and through AR technology and data bridging interface, make the data of different collection devices and systems have cross-platform compatibility and interoperability, share image data in real time and conduct comprehensive analysis; The comprehensive evaluation module is used to calculate the image quality coefficient Ylzz for the third medical image and perform a comprehensive analysis, and then further generate an image abnormality evaluation index Yjz; pre-set the noise tolerance threshold N and the quality evaluation threshold R, and compare the image quality coefficient Ylzz with the noise tolerance threshold N to determine whether the noise level of the current image is within an acceptable range, and compare and evaluate the image abnormality evaluation index Yjz with the quality evaluation threshold R, and formulate subsequent image processing and diagnosis recommendations based on the evaluation content.

[0021] In this embodiment, the image enhancement module uses AR technology to enhance the medical image in real time, highlights the key areas through multi-layer virtual information superposition, adjusts the detail visibility and artifacts of the image, and finally obtains a clear first medical image to improve the diagnostic effectiveness of the image; the dynamic artifact correction module captures the patient's tiny movements through the posture tracking algorithm and calculates the correction coefficient Jyz, compensates for motion artifacts in real time, obtains the artifact-free second medical image, and reduces the image distortion caused by movement or jitter; the resolution optimization module uses the super-resolution reconstruction algorithm of AR technology to compensate for pixel details and reconstruct the second medical image, improve the image resolution and enhance the recognition ability of subtle lesions, especially to obtain a clearer third medical image in early tumor screening; the data standardization processing module converts the third medical image into a unified format through AR technology and a data bridging interface, ensures the cross-platform compatibility and interoperability of data between different devices and systems, and realizes real-time sharing and comprehensive analysis of image data; the comprehensive evaluation module calculates the image quality coefficient Ylzz and generates the image abnormality evaluation index Yjz, and ensures that the image noise level and quality meet the diagnostic requirements by comparing the noise tolerance threshold N with the quality evaluation threshold R, formulates further image processing and diagnostic suggestions, and improves the overall diagnostic reliability and consistency.

[0022] Example 2 The image enhancement module uses imaging equipment to perform preliminary acquisition of medical images to obtain original images; then activates AR technology to analyze image data in real time and identify key areas and artifact interference areas in the image; through multi-layer virtual information superposition, the enhancement algorithm is applied to key areas to highlight fine structures and adjust detail visibility; Then, for the artifacts caused by metal tools, image segmentation and artifact removal algorithms are used to automatically filter and weaken the interference of metal artifacts on the image; finally, the image processed with detail enhancement and artifact correction will be superimposed on the original image to achieve a real-time preview effect after enhancement, and finally the real-time enhanced image will be marked as the first medical image.

[0023] In this embodiment, the imaging device is used to initially collect medical images and the AR technology is activated for real-time analysis to identify key areas and artifact interference areas, thereby achieving accurate processing of details and artifacts in the early stage of image acquisition; by superimposing multiple layers of virtual information and applying enhancement algorithms to highlight key areas and fine structures, adjusting the visibility of details, and significantly improving the clarity of the image and diagnostic details; this module uses image segmentation and artifact removal algorithms, especially for artifacts caused by metal tools, to effectively and automatically filter and weaken artifact interference, thereby ensuring the accuracy and availability of medical images; the image after detail enhancement and artifact correction is superimposed on the original image to achieve an enhanced real-time preview effect, and the first medical image finally output has a higher level of visualization and reliability; this module is of great significance in the system. As a pre-processing step, it not only improves the quality of the original image, but also provides high-quality basic data for subsequent modules such as dynamic artifact correction, resolution optimization and comprehensive evaluation, thereby improving the overall performance and diagnostic accuracy of the entire image acquisition and processing system.

[0024] Example 3 The dynamic artifact correction module includes a motion detection unit and a correction compensation unit; The motion detection unit is used to automatically identify motion artifacts caused by patient movement or device jitter in the first medical image, and obtain the patient's posture tracking information in real time through a posture tracking algorithm, including the patient's slight movement; the posture tracking information generates motion trajectory data corresponding to the image, including the patient's movement amplitude parameter Md, the device jitter frequency parameter Df, the image clarity change parameter Iq and the image time series parameter Tt; After extracting the motion trajectory data and performing dimensionless processing, the correction coefficient Jyz is calculated in real time using the following formula: Then, the preset correction threshold Q and correction coefficient Jyz are used for evaluation, and the image is compensated and corrected in real time. The specific evaluation contents are as follows: If the correction coefficient Jyz ≤ the correction threshold Q, it indicates that the motion artifact in the current image has a normal effect and no additional compensation processing is required. The original image quality is directly retained and the current image is directly marked as the second medical image for resolution adjustment; If the correction coefficient Jyz>correction threshold Q, it indicates that the motion artifact in the current image has an abnormal effect. In this case, additional compensation processing is performed on the current image, and after the compensation processing is completed on the current image, it is marked as the second medical image.

[0025] The correction and compensation unit is used to perform image correction on the image with abnormal motion artifacts generated by the motion detection unit, by extracting the patient's movement trajectory data in real time, and combining it with the posture tracking information, using the inverse correction algorithm to correct the area affected by the motion artifacts in the image pixel by pixel, and compensate in real time for the image distortion caused by the patient's movement or the device shaking; Subsequently, the correction and compensation unit eliminates the edge transition discontinuity phenomenon in the correction process by performing a smoothing process; finally, the image after the compensation process is completed is marked and a second medical image is output.

[0026] The resolution optimization module is used to receive and import the second medical image, and perform denoising and artifact removal operations on the second medical image through a preprocessing step; then call the super-resolution reconstruction algorithm based on AR technology, and compensate and reconstruct the lost details in the low-resolution image through multi-frame image fusion and detail reconstruction technology to form a high-resolution image; finally output the optimized high-resolution image and mark it as the third medical image.

[0027] The data standardization processing module first receives the third medical image, and automatically detects the original format and related parameters in the third medical image through a built-in format recognition algorithm; then, the data bridging interface enhanced by AR technology is used to perform format conversion on the third medical image, and uniformly converts it into a standardized medical imaging format; finally, a multi-layer data protocol verification mechanism is established to prevent the loss of key details or image quality during the conversion process.

[0028] In this embodiment, the motion detection unit and the correction and compensation unit work together to realize automatic identification and correction of motion artifacts caused by patient movement or device jitter in the first medical image; the motion detection unit obtains the patient's posture tracking information in real time through the posture tracking algorithm and generates the patient's movement amplitude parameter Md, the device jitter frequency parameter Df, the image clarity change parameter Iq and the image time series parameter Tt, these parameters can fully reflect the impact of motion artifacts on the image and are used to calculate the correction coefficient Jyz in real time after dimensionless processing, and are compared and evaluated with the preset correction threshold Q to determine whether the image needs compensation; when the correction coefficient Jyz exceeds the correction threshold Q, the correction and compensation unit is started, and the artifact-affected area is corrected pixel by pixel by using the inverse correction algorithm by extracting motion trajectory data and posture tracking information, so as to realize real-time image compensation and output the second medical image, which ensures the image quality stability and diagnostic accuracy; The resolution optimization module receives and imports the second medical image, ensures image clarity through denoising and artifact removal preprocessing, and then calls the super-resolution reconstruction algorithm of AR technology to compensate and reconstruct pixel details through multi-frame image fusion and detail reconstruction technology, making up for the missing details in the low-resolution image and generating a high-resolution image, which is finally marked as the third medical image; this module significantly improves the image resolution in the system, which is especially important in identifying small lesions such as early screening of tumors, ensuring detail presentation and diagnostic reliability.

[0029] The data standardization processing module detects the original format and related parameters of the third medical image through the built-in format recognition algorithm, standardizes the image format using the data bridging interface enhanced by AR technology, and establishes a multi-layer data protocol verification mechanism to ensure that key details or image quality are not lost during the format conversion process. The significance of this module is to ensure the cross-platform compatibility and interoperability of data from different devices and systems, and to achieve real-time sharing and comprehensive analysis of medical images; the parameters collected by the comprehensive evaluation module include the noise tolerance threshold N and the quality assessment threshold R, which are used to compare and evaluate the image quality coefficient Ylzz and the image abnormality assessment index Yjz, to ensure that the output image meets the diagnostic requirements in terms of noise level and overall quality, thereby improving the overall diagnostic consistency and data availability of the system.

[0030] Example 4 The comprehensive evaluation module includes a noise analysis unit, a quality analysis unit and an evaluation decision unit; The noise analysis unit is used to detect and analyze the noise level of the third medical image, obtain the noise feature related data in the image in real time and perform dimensionless processing; wherein the noise feature related data includes the spatial frequency Sf, the texture roughness Tr, the contrast fluctuation value Cw and the edge gradient variation value Eg, and the image quality coefficient Ylzz is calculated by the following formula: The preset noise tolerance threshold N is compared with the image quality coefficient Ylzz for evaluation. The specific contents are as follows: If the image quality coefficient Ylzz ≤ threshold N, it indicates that the noise level of the image is within an acceptable range, the image quality meets the diagnostic requirements, and can be directly used for subsequent analysis and clinical diagnosis; If the image quality coefficient Ylzz>noise tolerance threshold N, it indicates that the noise level in the image exceeds the acceptable range, but the impact on the image detail resolution and diagnostic reliability is unknown, and further analysis is performed at this time.

[0031] The quality analysis unit is used to further analyze and calculate the image whose noise level exceeds the acceptable range according to the evaluation content of the image quality coefficient Ylzz, and generate the image abnormality evaluation index Yjz; By deploying sensors near the imaging equipment, including acceleration sensors, illumination sensors, RF interference sensors, and built-in thermal noise sensors, the environmental acquisition interference related data is obtained in real time. After extracting the environmental acquisition interference related data and performing dimensionless processing, the image anomaly assessment index Yjz is calculated using the following formula: Wherein, Mv is the micro-vibration interference value in the environmental collection interference related data, Lu is the light source unevenness value in the environmental collection interference related data, Ei is the electronic interference value in the environmental collection interference related data, and Tn is the thermal noise value in the environmental collection interference related data.

[0032] The evaluation decision unit is used to compare the image abnormality evaluation index Yjz with the preset quality evaluation threshold R, and formulate subsequent image processing plans and diagnostic suggestions, the specific contents of which are as follows: If the image abnormality assessment index Yjz ≤ the quality assessment threshold R, it means that the noise and interference level of the image is within an acceptable range, indicating that the image meets the quality standard. At this time, the current image is directly used for diagnosis, and conventional diagnostic analysis is performed on this basis; If the image abnormality assessment index Yjz>quality assessment threshold R, it means that the noise and interference levels of the image are beyond the acceptable range, indicating that the image does not meet the quality standards. At this time, the image enhancement or denoising program is started; the image processing solution should include high-frequency filtering, image smoothing and artifact removal algorithms; diagnostic recommendations include re-evaluating the image quality after processing.

[0033] In this embodiment, the noise analysis unit, the quality analysis unit and the evaluation and decision unit work together to achieve a comprehensive quality evaluation of the third medical image; the noise analysis unit is used to detect and analyze the noise level in the image, collect the spatial frequency parameter Sf, the texture roughness parameter Tr, the contrast fluctuation value Cw and the edge gradient variation value Eg, these parameters are used to quantify the clarity of image details, the complexity of texture, the stability of local contrast and the change of edge intensity respectively; these parameters after dimensionless processing are used to generate an image quality coefficient Ylzz through a calculation formula, which is used to preliminarily determine whether the image noise level is within the noise tolerance threshold N; the significance of this unit in the system is to provide real-time detection and preliminary evaluation of the noise level to ensure that the quality of the diagnostic image meets the requirements; The quality analysis unit is used to further analyze images with noise levels beyond the acceptable range and generate an image anomaly assessment index Yjz. The unit collects micro-vibration interference values ​​Mv, light source unevenness values ​​Lu, electronic interference values ​​Ei and thermal noise values ​​Tn in real time through acceleration sensors, light intensity sensors, RF interference sensors and built-in thermal noise sensors. These parameters reflect the interference of external and internal environments on the image. The image anomaly assessment index Yjz is evaluated through dimensionless processing and calculation formulas to identify whether the image needs further compensation processing and diagnostic optimization. The unit ensures a comprehensive evaluation of the image under multiple interference factors and improves the accuracy of diagnosis. The evaluation and decision-making unit formulates image processing and diagnosis recommendations based on the comparison between the image abnormality evaluation index Yjz and the quality assessment threshold R. If the image abnormality evaluation index Yjz is within the quality assessment threshold R, it means that the image meets the quality standards and can be used directly for diagnosis. If the image abnormality evaluation index Yjz exceeds the quality assessment threshold R, enhancement programs such as high-frequency filtering, image smoothing and artifact removal algorithms are started to ensure that the image achieves the best quality in subsequent diagnosis. The significance of this unit in the system is to provide reliable decision support for noise and interference, ensuring that medical images always maintain high quality and diagnostic effectiveness under different acquisition conditions.

[0034] Example 5 See also Figure 2 , an image acquisition and processing method based on AR technology, comprising the following steps: Step 1: Use AR technology to enhance the images that appear during the medical image acquisition process in real time, by superimposing multiple layers of virtual information to highlight key areas, adjust the detail visibility and artifacts of the image, and finally obtain the first medical image; Step 2: automatically identify motion artifacts in the first medical image caused by patient movement or device jitter, use a posture tracking algorithm to capture the patient's tiny movements in real time, calculate and evaluate the correction coefficient Jyz in real time, compensate and correct the image in real time based on the evaluation content of the correction coefficient Jyz, and finally obtain the second medical image; Step 3: Combine the AR technology’s super-resolution reconstruction algorithm to perform pixel detail compensation and image reconstruction on the acquired second medical image, adjust the image resolution and the ability to identify subtle lesions, including the imaging effect of early tumor screening, and finally obtain the third medical image; Step 4: Convert all collected third-party medical images into a unified format, and use AR technology and data bridging interface to make data from different acquisition devices and systems cross-platform compatible and interoperable, so that image data can be shared in real time and comprehensive analysis can be performed; Step 5. Calculate and obtain the image quality coefficient Ylzz for the third medical image and conduct a comprehensive analysis, and then further generate the image abnormality assessment index Yjz; pre-set the noise tolerance threshold N and the quality assessment threshold R, and compare the image quality coefficient Ylzz with the noise tolerance threshold N to determine whether the noise level of the current image is within an acceptable range, and compare the image abnormality assessment index Yjz with the quality assessment threshold R to obtain the diagnostic reliability level of the image, and formulate subsequent image processing and diagnosis recommendations based on the assessment level.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An image acquisition and processing system based on AR technology, characterized in that: It includes image enhancement module, dynamic artifact correction module, resolution optimization module, data standardization processing module and comprehensive evaluation module; The image enhancement module is used to enhance the image appearing in the medical image acquisition process in real time by using AR technology, by superimposing multiple layers of virtual information to highlight key areas, adjusting the detail visibility and artifacts of the image, and finally obtaining a first medical image; The dynamic artifact correction module is used to automatically identify motion artifacts caused by patient movement or device jitter in the first medical image, use a posture tracking algorithm to capture the patient's tiny movements in real time, calculate and evaluate the correction coefficient Jyz in real time, compensate and correct the image in real time based on the evaluation content of the correction coefficient Jyz, and finally obtain the second medical image; The resolution optimization module is used to combine the super-resolution reconstruction algorithm of AR technology, perform pixel detail compensation and image reconstruction on the acquired second medical image, adjust the image resolution and the recognition ability of subtle lesions, including the imaging effect of early tumor screening, and finally obtain a third medical image; The data standardization processing module is used to convert all collected third medical images into a unified format, and through AR technology and data bridging interface, make the data of different collection devices and systems have cross-platform compatibility and interoperability, share image data in real time and conduct comprehensive analysis; The comprehensive evaluation module is used to calculate the image quality coefficient Ylzz for the third medical image and perform a comprehensive analysis, and then further generate an image abnormality evaluation index Yjz; pre-set the noise tolerance threshold N and the quality evaluation threshold R, and compare the image quality coefficient Ylzz with the noise tolerance threshold N to determine whether the noise level of the current image is within an acceptable range, and compare and evaluate the image abnormality evaluation index Yjz with the quality evaluation threshold R, and formulate subsequent image processing and diagnosis recommendations based on the evaluation content.

2. The image acquisition and processing system based on AR technology according to claim 1, characterized in that: The image enhancement module uses imaging equipment to perform preliminary acquisition of medical images to obtain original images; then activates AR technology to analyze image data in real time and identify key areas and artifact interference areas in the image; through multi-layer virtual information superposition, the enhancement algorithm is applied to key areas to highlight fine structures and adjust detail visibility; Then, for the artifacts caused by metal tools, image segmentation and artifact removal algorithms are used to automatically filter and weaken the interference of metal artifacts on the image; finally, the image processed with detail enhancement and artifact correction will be superimposed on the original image to achieve a real-time preview effect after enhancement, and finally the real-time enhanced image will be marked as the first medical image.

3. The image acquisition and processing system based on AR technology according to claim 1, characterized in that: The dynamic artifact correction module includes a motion detection unit and a correction compensation unit; The motion detection unit is used to automatically identify motion artifacts caused by patient movement or device jitter in the first medical image, and obtain the patient's posture tracking information in real time through a posture tracking algorithm, including the patient's slight movement; the posture tracking information generates motion trajectory data corresponding to the image, including the patient's movement amplitude parameter Md, the device jitter frequency parameter Df, the image clarity change parameter Iq and the image time series parameter Tt; After extracting the motion trajectory data and performing dimensionless processing, the correction coefficient Jyz is calculated in real time using the following formula: Then, the preset correction threshold Q and correction coefficient Jyz are used for evaluation, and the image is compensated and corrected in real time. The specific evaluation contents are as follows: If the correction coefficient Jyz ≤ the correction threshold Q, it indicates that the motion artifact in the current image has a normal effect and no additional compensation processing is required. The original image quality is directly retained and the current image is directly marked as the second medical image for resolution adjustment; If the correction coefficient Jyz>correction threshold Q, it indicates that the motion artifact in the current image has an abnormal effect. In this case, additional compensation processing is performed on the current image, and after the compensation processing is completed on the current image, it is marked as the second medical image.

4. The image acquisition and processing system based on AR technology according to claim 3, characterized in that: The correction and compensation unit is used to perform image correction on the image with abnormal motion artifacts generated by the motion detection unit, by extracting the patient's movement trajectory data in real time, and combining it with the posture tracking information, using the inverse correction algorithm to correct the area affected by the motion artifacts in the image pixel by pixel, and compensate in real time for the image distortion caused by the patient's movement or the device shaking; Subsequently, the correction and compensation unit eliminates the edge transition discontinuity phenomenon in the correction process by performing a smoothing process; finally, the image after the compensation process is marked and a second medical image is output.

5. The image acquisition and processing system based on AR technology according to claim 1, characterized in that: The resolution optimization module is used to receive and import the second medical image, and perform denoising and artifact removal operations on the second medical image through a preprocessing step; then call the super-resolution reconstruction algorithm based on AR technology, and compensate and reconstruct the lost details in the low-resolution image through multi-frame image fusion and detail reconstruction technology to form a high-resolution image; finally output the optimized high-resolution image and mark it as the third medical image.

6. The image acquisition and processing system based on AR technology according to claim 1, characterized in that: The data standardization processing module first receives the third medical image, and automatically detects the original format and related parameters in the third medical image through a built-in format recognition algorithm; then, the data bridging interface enhanced by AR technology is used to perform format conversion on the third medical image, and uniformly converts it into a standardized medical imaging format; finally, a multi-layer data protocol verification mechanism is established to prevent the loss of key details or image quality during the conversion process.

7. The image acquisition and processing system based on AR technology according to claim 1, characterized in that: The comprehensive evaluation module includes a noise analysis unit, a quality analysis unit and an evaluation decision unit; The noise analysis unit is used to detect and analyze the noise level of the third medical image, obtain the noise feature related data in the image in real time and perform dimensionless processing; wherein the noise feature related data includes the spatial frequency Sf, the texture roughness Tr, the contrast fluctuation value Cw and the edge gradient variation value Eg, and the image quality coefficient Ylzz is calculated by the following formula: The preset noise tolerance threshold N is compared with the image quality coefficient Ylzz for evaluation. The specific contents are as follows: If the image quality coefficient Ylzz ≤ threshold N, it indicates that the noise level of the image is within an acceptable range, the image quality meets the diagnostic requirements, and can be directly used for subsequent analysis and clinical diagnosis; If the image quality coefficient Ylzz>noise tolerance threshold N, it indicates that the noise level in the image exceeds the acceptable range, but the impact on the image detail resolution and diagnostic reliability is unknown, and further analysis is performed at this time.

8. The image acquisition and processing system based on AR technology according to claim 7, characterized in that: The quality analysis unit is used to further analyze and calculate the image whose noise level exceeds the acceptable range according to the evaluation content of the image quality coefficient Ylzz, and generate the image abnormality evaluation index Yjz; By deploying sensors near the imaging equipment, including acceleration sensors, illumination sensors, RF interference sensors, and built-in thermal noise sensors, the environmental acquisition interference related data is obtained in real time. After extracting the environmental acquisition interference related data and performing dimensionless processing, the image anomaly assessment index Yjz is calculated using the following formula: Wherein, Mv is the micro-vibration interference value in the environmental collection interference related data, Lu is the light source unevenness value in the environmental collection interference related data, Ei is the electronic interference value in the environmental collection interference related data, and Tn is the thermal noise value in the environmental collection interference related data.

9. The image acquisition and processing system based on AR technology according to claim 7, characterized in that: The evaluation decision unit is used to compare the image abnormality evaluation index Yjz with the preset quality evaluation threshold R, and formulate subsequent image processing plans and diagnostic suggestions, the specific contents of which are as follows: If the image abnormality assessment index Yjz ≤ the quality assessment threshold R, it means that the noise and interference level of the image is within an acceptable range, indicating that the image meets the quality standard. At this time, the current image is directly used for diagnosis, and conventional diagnostic analysis is performed on this basis; If the image abnormality assessment index Yjz>quality assessment threshold R, it means that the noise and interference levels of the image are beyond the acceptable range, indicating that the image does not meet the quality standards. At this time, the image enhancement or denoising program is started; the image processing solution should include high-frequency filtering, image smoothing and artifact removal algorithms; diagnostic recommendations include re-evaluating the image quality after processing.

10. An image acquisition and processing method based on AR technology, according to the image acquisition and processing system based on AR technology according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Use AR technology to enhance the images that appear during the medical image acquisition process in real time, by superimposing multiple layers of virtual information to highlight key areas, adjust the detail visibility and artifacts of the image, and finally obtain the first medical image; Step 2: automatically identify motion artifacts in the first medical image caused by patient movement or device jitter, use a posture tracking algorithm to capture the patient's tiny movements in real time, calculate and evaluate the correction coefficient Jyz in real time, compensate and correct the image in real time based on the evaluation content of the correction coefficient Jyz, and finally obtain the second medical image; Step 3: Combine the AR technology’s super-resolution reconstruction algorithm to perform pixel detail compensation and image reconstruction on the acquired second medical image, adjust the image resolution and the ability to identify subtle lesions, including the imaging effect of early tumor screening, and finally obtain the third medical image; Step 4: Convert all collected third-party medical images into a unified format, and use AR technology and data bridging interface to make data from different acquisition devices and systems cross-platform compatible and interoperable, so that image data can be shared in real time and comprehensive analysis can be performed; Step 5. Calculate and obtain the image quality coefficient Ylzz for the third medical image and conduct a comprehensive analysis, and then further generate the image abnormality assessment index Yjz; pre-set the noise tolerance threshold N and the quality assessment threshold R, and compare the image quality coefficient Ylzz with the noise tolerance threshold N to determine whether the noise level of the current image is within an acceptable range, and compare the image abnormality assessment index Yjz with the quality assessment threshold R to obtain the diagnostic reliability level of the image, and formulate subsequent image processing and diagnosis recommendations based on the assessment level.

Images