Lesion location recognition method and system based on fusion of MRI and CT images

Abstract

The present invention discloses a method and system for identifying the position of a lesion based on the fusion of nuclear magnetic resonance (NMR) and CT images, which belongs to the field of image recognition technology. The method includes the following steps: S1, image acquisition and preprocessing: acquiring the patient's nuclear magnetic resonance (NMR) and CT real-time images, and preprocessing the patient's nuclear magnetic resonance (NMR) and CT real-time images; S2, image registration and fusion: registering and fusing the patient's nuclear magnetic resonance (NMR) and CT real-time images to generate a patient's nuclear magnetic resonance (NMR) and CT fusion image; S3, lesion position identification: performing image recognition on the generated patient's nuclear magnetic resonance (NMR) and CT fusion image according to a lesion position identification model to determine the patient's lesion position. The present invention solves the existing problem that the patient's lesion position cannot be effectively identified, resulting in low accuracy and efficiency in identifying the patient's lesion position. The present invention can effectively identify the patient's lesion position based on the fusion of nuclear magnetic resonance (NMR) and CT images, improve the accuracy and efficiency of identifying the patient's lesion position, and provide strong support for clinical diagnosis.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a method and system for identifying lesion locations based on the fusion of MRI and CT images. Background Art

[0002] Medical imaging provides increasingly diverse image modalities for clinical medical diagnosis. Due to different imaging principles, multimodal medical images enable medical images of different modalities to have different characteristics and advantages. Therefore, fusing images with different characteristics and advantages can reduce the error rate of clinical diagnosis.

[0003] Chinese patent publication number CN115471432A discloses a method and system for fusing MRI images and CT images, wherein the method comprises: performing wavelet decomposition on MRI images and CT images and calculating information gradient values ​​of the decomposed images; constructing fusion coefficients based on the information gradient values; calculating information values ​​of the MRI wavelet images and the CT wavelet images; constructing a fusion formula based on the information values; constructing an image fusion model based on the fusion formula and the fusion coefficients; fusing the MRI image and the CT image using the image fusion model to obtain a fused image; constructing an image fusion model based on the information gradient values ​​and information values ​​of the images to be fused, and fusing the MRI image and the CT image based on the image fusion model. This method not only improves image clarity, but also compensates for the defect of insufficient information content of a single MRI image or CT image, greatly improves the doctor's interpretation of the image, and provides a favorable imaging basis for subsequent lesion localization. However, the patent has the following defects:

[0004] Existing technologies cannot effectively identify the location of patient lesions based on the fusion of MRI and CT images, resulting in low accuracy and efficiency in identifying the location of patient lesions and failing to provide strong support for clinical diagnosis. Summary of the Invention

[0005] The purpose of the present invention is to provide a lesion location identification method and system based on the fusion of MRI and CT images, which can effectively identify the patient's lesion location based on the fusion of MRI and CT images, improve the accuracy and efficiency of patient lesion location identification, provide strong support for clinical diagnosis, and solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The lesion location recognition method based on fusion of MRI and CT images includes the following steps:

[0008] S1. Image acquisition and preprocessing: The image acquisition terminal is used to acquire real-time MRI and CT images of the patient, and the acquired MRI and CT images are preprocessed to remove noise from the images, adjust the brightness and contrast of the images, and enhance the images.

[0009] S2. Image registration and fusion: A transformation-based registration method is used to register the patient's MRI and real-time CT images. A transform-domain-based image fusion method is used to generate a fused image of the patient's MRI and CT images, which includes both the patient's real-time MRI and CT images.

[0010] S3. Lesion location recognition: Based on machine learning technology, a lesion location recognition model based on the fusion of MRI and CT images is trained. Image recognition is performed on the generated patient MRI and CT fusion images according to the lesion location recognition model based on the fusion of MRI and CT images to determine the patient lesion location.

[0011] Preferably, in S1, acquiring the patient's real-time MRI and CT images based on the image acquisition terminal includes:

[0012] Patient MRI image acquisition: Real-time monitoring and continuous acquisition of the patient's lesion site based on the MRI device to obtain the patient's real-time MRI image;

[0013] Patient CT image acquisition: Based on the CT machine, the patient's lesion area is monitored in real time and continuously acquired to obtain the patient's real-time CT image;

[0014] The real-time MRI and CT images of the patient based on the image acquisition terminal are determined based on the real-time MRI and CT images of the patient.

[0015] Preferably, in S1, preprocessing the collected patient MRI and CT real-time images includes:

[0016] Image denoising: Based on filters, the system performs filtering processing on the real-time MRI and CT images of patients based on the image acquisition terminal to remove noise from the real-time MRI and CT images of patients based on the image acquisition terminal.

[0017] Image brightness and contrast adjustment: Based on image segmentation technology, the system adjusts the brightness and contrast of the patient's MRI and CT real-time images based on the image acquisition terminal. Interpolation or reconstruction technology is used to keep the brightness of the patient's MRI and CT real-time images based on the image acquisition terminal consistent. Based on the adaptive adjustment method of global contrast and the relationship between adjacent pixels, the system automatically adjusts the pixel contrast to ensure high-definition patient MRI and CT real-time images.

[0018] Image enhancement: Based on image enhancement technology, high-definition patient MRI and real-time CT images are enhanced. The edges of high-definition patient MRI and real-time CT images are identified based on edge detection algorithms. The edges of patient MRI and real-time CT images are detected and enhanced by calculating the gradient values ​​of neighboring pixels to highlight the edges in high-definition patient MRI and real-time CT images.

[0019] Preferably, in S1, preprocessing the collected patient MRI and CT real-time images includes:

[0020] Extract the patient's MRI and CT real-time images after edge enhancement as the target image;

[0021] Extracting grayscale values ​​corresponding to edge pixel blocks in the target image to form a first grayscale value set;

[0022] Extracting grayscale values ​​corresponding to non-edge pixel blocks in the target image to form a second grayscale value set;

[0023] Obtaining a grayscale relative coefficient using the first grayscale value set and the second grayscale value set;

[0024] The grayscale relative coefficient is obtained by the following formula:

[0025]

[0026] Wherein, W represents the grayscale relative coefficient; n represents the number of grayscale values ​​included in the first grayscale value set; m represents the number of grayscale values ​​included in the second grayscale value set; H ni represents the corresponding value of the i-th grayscale value contained in the first grayscale value set; H mi represents the corresponding value of the i-th grayscale value contained in the second grayscale value set; H z Represents the central grayscale value of the target image; H nz represents the grayscale intermediate value corresponding to the n grayscale values ​​contained in the first grayscale value set; H mz represents the grayscale intermediate value corresponding to the m grayscale values ​​contained in the second grayscale value set;

[0027] Comparing the grayscale relative coefficient with a preset relative coefficient threshold;

[0028] When the grayscale relative coefficient exceeds a preset relative coefficient threshold, no contrast adjustment is performed on the target image;

[0029] When the grayscale relative coefficient does not exceed a preset relative coefficient threshold, contrast adjustment is performed on the target image.

[0030] Preferably, when the grayscale relative coefficient does not exceed a preset relative coefficient threshold, contrast adjustment is performed on the target image, including:

[0031] When the grayscale relative coefficient does not exceed a preset relative coefficient threshold, retrieving the grayscale values ​​included in the second grayscale value set of the target image;

[0032] Obtaining a contrast adjustment coefficient using the grayscale values ​​included in the second grayscale value set;

[0033] The contrast adjustment coefficient is obtained by the following formula:

[0034]

[0035] Wherein, R represents the contrast adjustment coefficient; m represents the number of grayscale values ​​contained in the second grayscale value set; H mi represents the corresponding value of the i-th grayscale value contained in the second grayscale value set; H z Represents the central grayscale value of the target image; H nz represents the grayscale intermediate value corresponding to the n grayscale values ​​contained in the first grayscale value set; H np represents the grayscale average value corresponding to the n grayscale values ​​contained in the first grayscale value set; W represents the grayscale relative coefficient;

[0036] Adjusting the contrast of the target image using the contrast adjustment coefficient to obtain the contrast-adjusted target image as an enhanced image highlighting the edges in the high-definition patient MRI and CT real-time images;

[0037] The adjusted contrast value is obtained by the following formula:

[0038]

[0039] Among them, D t represents the contrast value after adjustment; D represents the contrast value before adjustment; R represents the contrast adjustment coefficient; W represents the grayscale relative coefficient; n represents the number of grayscale values ​​contained in the first grayscale value set; H ni represents the corresponding value of the i-th grayscale value contained in the first grayscale value set; H mz Represents the grayscale intermediate value corresponding to the m grayscale values ​​included in the second grayscale value set.

[0040] Preferably, in S2, registering and fusing the patient's MRI and CT real-time images includes:

[0041] Image registration: Register the patient's MRI and real-time CT images, using a transformation-based registration method to ensure that the patient's MRI and real-time CT images have a spatial correspondence;

[0042] Image fusion: The registered patient MRI and real-time CT images are fused. A transform-domain-based image fusion method is used to decompose the source image into sub-bands of different scales using wavelet transform. The sub-bands are then fused to generate a fused image of the patient's MRI and CT real-time images.

[0043] Preferably, in S3, based on machine learning technology, training a lesion location recognition model based on fusion of MRI and CT images includes:

[0044] Collect data sources: Based on the need for lesion location identification based on MRI and CT image fusion, collect historical MRI and CT images of patients to determine the data source for model training;

[0045] Data source division: The collected patient MRI and CT historical images were divided into training and test sets in a ratio of 7:3;

[0046] Model training: Based on the training set, the machine learning model is trained to determine the lesion location recognition model based on the fusion of MRI and CT images. Based on the test set, the performance of the trained lesion location recognition model based on the fusion of MRI and CT images is tested to determine whether the lesion location recognition model based on the fusion of MRI and CT images can achieve the expected effect and to determine the optimal lesion location recognition model based on the fusion of MRI and CT images.

[0047] Preferably, in S3, performing image recognition on the generated fusion image of the patient's MRI and CT images according to a lesion location recognition model based on fusion of MRI and CT images includes:

[0048] Obtain the optimal lesion location recognition model based on MRI and CT image fusion;

[0049] Deploy the optimal lesion location recognition model based on MRI and CT image fusion in the actual lesion location recognition environment;

[0050] The generated patient MRI and CT fusion images are subjected to image recognition according to the optimal lesion location recognition model based on MRI and CT image fusion, and the patient lesion location is identified to determine the patient lesion location.

[0051] Preferably, in said S3, after the patient's lesion position is identified, the patient's lesion position is marked and displayed in a visual form on the user interface.

[0052] According to another aspect of the present invention, a lesion location recognition system based on MRI and CT image fusion is provided, which is used to implement the above-mentioned lesion location recognition method based on MRI and CT image fusion, including:

[0053] An image acquisition unit is used to acquire real-time MRI images and CT images of patients, and determine real-time MRI and CT images of patients;

[0054] Image preprocessing unit, used to perform denoising, brightness and contrast adjustment, and image enhancement on the collected patient MRI and CT real-time images;

[0055] An image fusion unit is used to fuse the patient's MRI and CT real-time images to generate a fused image of the patient's MRI and CT;

[0056] a lesion location recognition unit, configured to perform image recognition on the generated fusion image of the patient's MRI and CT and identify the location of the patient's lesion, thereby determining the location of the patient's lesion;

[0057] The user interface display unit is used to display the patient's lesion location to the user in a visual form.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] 1. The present invention collects patient nuclear magnetic resonance (NMR) and CT real-time images based on an image acquisition terminal, and preprocesses the collected patient nuclear magnetic resonance (NMR) and CT real-time images to remove noise from the patient nuclear magnetic resonance (NMR) and CT real-time images, adjusts the brightness and contrast of the patient nuclear magnetic resonance (NMR) and CT real-time images, and enhances the patient nuclear magnetic resonance (NMR) and CT real-time images. A transformation-based registration method is used to register the patient nuclear magnetic resonance (NMR) and CT real-time images, and a transform-domain-based image fusion method is used to generate a patient nuclear magnetic resonance and CT fusion image containing the patient nuclear magnetic resonance (NMR) and CT real-time images, thereby facilitating subsequent accurate recognition of the patient nuclear magnetic resonance and CT fusion image.

[0060] 2. The present invention is based on machine learning technology to train a lesion location recognition model based on the fusion of MRI and CT images. According to the lesion location recognition model based on the fusion of MRI and CT images, image recognition is performed on the generated patient MRI and CT fusion images and the patient lesion location is identified. The patient lesion location is determined and marked, and the patient lesion location is displayed in a visual form on the user interface. The patient lesion location can be effectively identified based on the fusion of MRI and CT images, the accuracy and efficiency of patient lesion location recognition can be improved, and strong support can be provided for clinical diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a flow chart of the lesion location identification method based on MRI and CT image fusion of the present invention;

[0062] Figure 2 This is a process diagram of the lesion location identification method based on MRI and CT image fusion of the present invention;

[0063] Figure 3 This is a module diagram of the lesion location recognition system based on MRI and CT image fusion of the present invention. DETAILED DESCRIPTION

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0065] To address the problem that existing technologies cannot effectively identify the location of patient lesions based on MRI and CT image fusion, resulting in low accuracy and efficiency in identifying the location of patient lesions and failing to provide strong support for clinical diagnosis, please refer to Figure 1-Figure 3 , this embodiment provides the following technical solutions: Example 1

[0066] The lesion location recognition method based on fusion of MRI and CT images includes the following steps:

[0067] S1. Image acquisition and preprocessing: The image acquisition terminal is used to acquire real-time MRI and CT images of the patient, and the acquired MRI and CT images are preprocessed to remove noise from the images, adjust the brightness and contrast of the images, and enhance the images.

[0068] In this embodiment, as a preferred technical solution of the present invention, the patient's real-time MRI and CT images are acquired based on the image acquisition terminal, including:

[0069] Patient MRI image acquisition: Real-time monitoring and continuous acquisition of the patient's lesion site based on the MRI device to obtain the patient's real-time MRI image;

[0070] Patient CT image acquisition: Based on the CT machine, the patient's lesion area is monitored in real time and continuously acquired to obtain the patient's real-time CT image;

[0071] The real-time MRI and CT images of the patient based on the image acquisition terminal are determined based on the real-time MRI and CT images of the patient.

[0072] It should be noted that nuclear magnetic resonance (NMR) is a biological magnetic spin imaging technology that utilizes the characteristics of atomic nucleus spin motion. In an external magnetic field, after being stimulated by radio frequency pulses, a signal is generated, which is detected by a detector and input into a computer, and then processed and converted to display an image on the screen. The amount of information provided by NMR is not only greater than many other imaging technologies in medical imaging, but also different from existing imaging technologies. Therefore, it has great potential advantages in the diagnosis of diseases. It can directly produce cross-sectional, sagittal, coronal and various oblique tomographic images without the artifacts seen in CT detection, without the need for contrast agent injection, and without ionizing radiation, and has no adverse effects on the body. Therefore, by using a nuclear magnetic resonance imager to monitor and continuously acquire the patient's lesion site in real time, real-time NMR images of the patient can be obtained, which can provide high-resolution soft tissue contrast.

[0073] It should be noted that CT, or computed tomography, is a medical imaging technology that uses X-ray beams to perform layered scans of the human body and uses computer processing to produce detailed images of the body's internal structures. CT scanning is widely used in the diagnosis of various diseases due to its fast and clear imaging capabilities. CT images reflect the degree of X-ray absorption by organs and tissues in different grayscales, have high-density resolution, and can clearly display soft tissue and bone structures. Therefore, by using a CT machine to monitor and continuously acquire the patient's lesion site in real time, obtaining real-time CT images of the patient, and providing detailed information on bone and calcification structures.

[0074] In this embodiment, as a preferred technical solution of the present invention, the collected patient MRI and CT real-time images are preprocessed, including:

[0075] Image denoising: Based on filters, the system performs filtering processing on the real-time MRI and CT images of patients based on the image acquisition terminal to remove noise from the real-time MRI and CT images of patients based on the image acquisition terminal.

[0076] It should be noted that the filter is a filtering circuit composed of capacitors, inductors and resistors. The filter can effectively filter out a specific frequency point in the power line or frequencies other than the frequency point to obtain a power signal of a specific frequency, or eliminate a power signal after eliminating a specific frequency; therefore, the filter can be used to filter the patient's nuclear magnetic resonance and CT real-time images based on the image acquisition terminal, remove noise in the patient's nuclear magnetic resonance and CT real-time images based on the image acquisition terminal, and reduce interference.

[0077] Image brightness and contrast adjustment: Based on image segmentation technology, the system adjusts the brightness and contrast of the patient's MRI and CT real-time images based on the image acquisition terminal. Interpolation or reconstruction technology is used to keep the brightness of the patient's MRI and CT real-time images based on the image acquisition terminal consistent. Based on the adaptive adjustment method of global contrast and the relationship between adjacent pixels, the system automatically adjusts the pixel contrast to ensure high-definition patient MRI and CT real-time images.

[0078] Image enhancement: Based on image enhancement technology, high-definition patient MRI and real-time CT images are enhanced. The edges of high-definition patient MRI and real-time CT images are identified based on edge detection algorithms. The edges of patient MRI and real-time CT images are detected and enhanced by calculating the gradient values ​​of neighboring pixels to highlight the edges in high-definition patient MRI and real-time CT images.

[0079] Specifically, in S1, preprocessing the collected patient MRI and CT real-time images includes:

[0080] Extract the patient's MRI and CT real-time images after edge enhancement as the target image;

[0081] Extracting grayscale values ​​corresponding to edge pixel blocks in the target image to form a first grayscale value set;

[0082] Extracting grayscale values ​​corresponding to non-edge pixel blocks in the target image to form a second grayscale value set;

[0083] Obtaining a grayscale relative coefficient using the first grayscale value set and the second grayscale value set;

[0084] The grayscale relative coefficient is obtained by the following formula:

[0085]

[0086] Wherein, W represents the grayscale relative coefficient; n represents the number of grayscale values ​​included in the first grayscale value set; m represents the number of grayscale values ​​included in the second grayscale value set; H ni represents the corresponding value of the i-th grayscale value contained in the first grayscale value set; H mi represents the corresponding value of the i-th grayscale value contained in the second grayscale value set; H z Represents the central grayscale value of the target image; H nz represents the grayscale intermediate value corresponding to the n grayscale values ​​contained in the first grayscale value set; H mz represents the grayscale intermediate value corresponding to the m grayscale values ​​contained in the second grayscale value set;

[0087] Comparing the grayscale relative coefficient with a preset relative coefficient threshold;

[0088] When the grayscale relative coefficient exceeds a preset relative coefficient threshold, no contrast adjustment is performed on the target image;

[0089] When the grayscale relative coefficient does not exceed a preset relative coefficient threshold, contrast adjustment is performed on the target image.

[0090] The technical solution described above has the following technical effects: By extracting edge-enhanced patient MRI and real-time CT images as target images, this solution can fully utilize the improved image clarity brought about by edge enhancement technology. Edge enhancement helps highlight key structures or lesions in the image, providing more valuable information for subsequent analysis and processing. The solution extracts the grayscale values ​​corresponding to edge and non-edge pixel blocks in the target image, forming two grayscale value sets. This step enables a refined analysis of the image's grayscale characteristics. Grayscale values ​​are fundamental data in image analysis and are crucial for understanding image characteristics such as texture and contrast. By introducing a grayscale relative coefficient, the solution comprehensively considers the grayscale distribution characteristics of edge and non-edge areas, as well as the overall grayscale level of the target image. The calculation of this coefficient not only considers the number and specific values ​​of grayscale values, but also incorporates parameters such as the center grayscale value and the grayscale median value, making the evaluation results more comprehensive and accurate. Based on the comparison of the grayscale relative coefficient with a preset relative coefficient threshold, the solution intelligently determines whether to adjust the contrast of the target image. This processing method, which automatically adjusts based on image characteristics, avoids the subjectivity and uncertainty of human intervention, improving processing efficiency and accuracy. Because the technical solution adjusts contrast based on objective analysis of image grayscale values, the processing effect is relatively stable and does not fluctuate due to differences in personal experience or subjective judgment. This is of great significance for maintaining the consistency and reliability of medical image processing. This technical solution is not only applicable to the processing of real-time patient MRI and CT images, but can also be extended to other types of medical image processing. Furthermore, with the continuous development of image processing technology, the relevant parameters and algorithms in the technical solution can be further optimized and improved to adapt to a wider range of and more complex application scenarios.

[0091] In summary, the technical benefits of the above-mentioned technical solutions are primarily reflected in the evaluation and utilization of edge enhancement, refined grayscale value analysis, innovative application of grayscale relative coefficients, intelligent contrast adjustment, stable processing results, and adaptability and scalability. These technical benefits collectively enhance the efficiency and accuracy of medical image processing, providing doctors with more reliable and valuable diagnostic evidence.

[0092] Specifically, when the grayscale relative coefficient does not exceed a preset relative coefficient threshold, contrast adjustment is performed on the target image, including:

[0093] When the grayscale relative coefficient does not exceed a preset relative coefficient threshold, retrieving the grayscale values ​​included in the second grayscale value set of the target image;

[0094] Obtaining a contrast adjustment coefficient using the grayscale values ​​included in the second grayscale value set;

[0095] The contrast adjustment coefficient is obtained by the following formula:

[0096]

[0097] Wherein, R represents the contrast adjustment coefficient; m represents the number of grayscale values ​​contained in the second grayscale value set; H mi represents the corresponding value of the i-th grayscale value contained in the second grayscale value set; H z Represents the central grayscale value of the target image; H nz represents the grayscale intermediate value corresponding to the n grayscale values ​​contained in the first grayscale value set; H np represents the grayscale average value corresponding to the n grayscale values ​​contained in the first grayscale value set; W represents the grayscale relative coefficient;

[0098] Adjusting the contrast of the target image using the contrast adjustment coefficient to obtain the contrast-adjusted target image as an enhanced image highlighting the edges in the high-definition patient MRI and CT real-time images;

[0099] The adjusted contrast value is obtained by the following formula:

[0100]

[0101] Among them, D t represents the contrast value after adjustment; D represents the contrast value before adjustment; R represents the contrast adjustment coefficient; W represents the grayscale relative coefficient; n represents the number of grayscale values ​​contained in the first grayscale value set; H ni represents the corresponding value of the i-th grayscale value contained in the first grayscale value set; H mz Represents the grayscale intermediate value corresponding to the m grayscale values ​​included in the second grayscale value set.

[0102] The technical effect of the above-mentioned technical solution is as follows: by introducing a contrast adjustment coefficient R, this coefficient integrates multiple factors of the second grayscale value set (i.e., the grayscale values ​​in the non-edge area), including the number of grayscale values, the specific grayscale values, the target image's central grayscale value Hz, the grayscale median value Hnz and grayscale mean value Hnp of the first grayscale value set, and the grayscale relative coefficient W. This comprehensive consideration makes contrast adjustment more precise and enables personalized processing based on the characteristics of different images. The contrast adjustment coefficient R and the adjusted contrast value Dt of the target image in the technical solution are both dynamically calculated based on multiple factors, meaning that the degree and method of contrast adjustment will vary for different target images. This dynamic adjustment capability enables the technical solution to adapt to a wider range of image processing needs. Through contrast adjustment, especially when the grayscale relative coefficient does not exceed a preset threshold, the technical solution can significantly enhance the edges in the target image, making them clearer and more prominent. This is particularly important for medical images, as edge information often contains important clues to lesions or critical structures. This technical solution comprehensively considers multiple factors to calculate the contrast adjustment coefficient and the adjusted contrast value, making it robust and adaptable to different types of medical images (such as MRI and CT images). Regardless of changes in the image background, brightness, or contrast, the technical solution can effectively process and achieve satisfactory edge highlighting. Ultimately, through contrast adjustment and edge highlighting, the technical solution can significantly improve the clarity and legibility of medical images, providing doctors with more accurate and reliable diagnostic evidence. This is of great significance for improving medical standards and protecting patient health.

[0103] In summary, the technical effects of this technical solution in terms of performance indicators are mainly reflected in the accuracy of contrast adjustment, dynamic adjustment capability, edge highlighting effect, computational efficiency, robustness and adaptability. These effects together improve the processing quality and diagnostic accuracy of medical images.

[0104] S2. Image registration and fusion: A transformation-based registration method is used to register the patient's MRI and real-time CT images. A transform-domain-based image fusion method is used to generate a fused image of the patient's MRI and CT images, which includes both the patient's real-time MRI and CT images.

[0105] In this embodiment, as a preferred technical solution of the present invention, the patient's MRI and CT real-time images are registered and fused, including:

[0106] Image registration: Register the patient's MRI and real-time CT images, using a transformation-based registration method to ensure that the patient's MRI and real-time CT images have a spatial correspondence;

[0107] Image fusion: The registered patient MRI and real-time CT images are fused. A transform-domain-based image fusion method is used to decompose the source image into sub-bands of different scales using wavelet transform. The sub-bands are then fused to generate a fused image of the patient MRI and CT that contains both the patient's real-time MRI and CT images, preserving the superior information of both images.

[0108] S3. Lesion location recognition: Based on machine learning technology, a lesion location recognition model based on the fusion of MRI and CT images is trained. Image recognition is performed on the generated patient MRI and CT fusion images according to the lesion location recognition model based on the fusion of MRI and CT images to determine the patient lesion location.

[0109] In this embodiment, as a preferred technical solution of the present invention, a lesion location recognition model based on fusion of MRI and CT images is trained based on machine learning technology, including:

[0110] Collect data sources: Based on the need for lesion location identification based on MRI and CT image fusion, collect historical MRI and CT images of patients to determine the data source for model training;

[0111] Data source division: The collected patient MRI and CT historical images were divided into training and test sets in a ratio of 7:3;

[0112] Model training: Based on the training set, the machine learning model is trained to determine the lesion location recognition model based on the fusion of MRI and CT images. Based on the test set, the performance of the trained lesion location recognition model based on the fusion of MRI and CT images is tested to determine whether the lesion location recognition model based on the fusion of MRI and CT images can achieve the expected effect and to determine the optimal lesion location recognition model based on the fusion of MRI and CT images.

[0113] In this embodiment, as a preferred technical solution of the present invention, image recognition is performed on the generated patient MRI and CT fusion images according to a lesion location recognition model based on MRI and CT image fusion, including:

[0114] Obtain the optimal lesion location recognition model based on MRI and CT image fusion;

[0115] Deploy the optimal lesion location recognition model based on MRI and CT image fusion in the actual lesion location recognition environment;

[0116] The generated patient MRI and CT fusion images are subjected to image recognition according to the optimal lesion location recognition model based on MRI and CT image fusion, and the patient lesion location is identified to determine the patient lesion location.

[0117] In this embodiment, as a preferred technical solution of the present invention, after the patient's lesion position is identified, the patient's lesion position is marked and displayed in a visual form on the user interface.

[0118] Example 2

[0119] To better demonstrate the principle of lesion location recognition based on MRI and CT image fusion, this embodiment provides a lesion location recognition system based on MRI and CT image fusion, which is used to implement the above-mentioned lesion location recognition method based on MRI and CT image fusion, including:

[0120] An image acquisition unit is used to acquire real-time MRI images and CT images of patients, and determine real-time MRI and CT images of patients;

[0121] Image preprocessing unit, used to perform denoising, brightness and contrast adjustment, and image enhancement on the collected patient MRI and CT real-time images;

[0122] An image fusion unit is used to fuse the patient's MRI and CT real-time images to generate a fused image of the patient's MRI and CT;

[0123] a lesion location recognition unit, configured to perform image recognition on the generated fusion image of the patient's MRI and CT and identify the location of the patient's lesion, thereby determining the location of the patient's lesion;

[0124] The user interface display unit is used to display the patient's lesion location to the user in a visual form.

[0125] It should be noted that the patient's MRI and CT real-time images are acquired by the image acquisition unit, and the acquired patient's MRI and CT real-time images are preprocessed by the image preprocessing unit to remove the noise of the patient's MRI and CT real-time images, adjust the brightness and contrast of the patient's MRI and CT real-time images, and enhance the patient's MRI and CT real-time images. The patient's MRI and CT real-time images are aligned by the image fusion unit, and a transform domain-based image fusion method is used to generate a patient's MRI and CT fusion image containing the patient's MRI real-time image and the patient's CT real-time image. The generated patient's MRI and CT fusion image is recognized by the lesion position recognition unit to determine the patient's lesion position. The patient's lesion position is displayed to the user in a visual form through the user interface display unit. The patient's lesion position can be effectively identified based on the fusion of MRI and CT images, the accuracy and efficiency of patient lesion position identification can be improved, and strong support can be provided for clinical diagnosis.

[0126] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0127] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A lesion location recognition method based on fusion of MRI and CT images, characterized in that: The steps include: S1. Image acquisition and preprocessing: The image acquisition terminal is used to acquire real-time MRI and CT images of the patient, and the acquired MRI and CT images are preprocessed to remove noise from the images, adjust the brightness and contrast of the images, and enhance the images. S2. Image registration and fusion: A transformation-based registration method is used to register the patient's MRI and real-time CT images. A transform-domain-based image fusion method is used to generate a fused image of the patient's MRI and CT images, which includes both the patient's real-time MRI and CT images. S3. Lesion location identification: Based on machine learning technology, a lesion location identification model based on MRI and CT image fusion is trained. Image recognition is performed on the generated patient MRI and CT fusion images using the lesion location identification model to determine the patient's lesion location. In S1, the collected real-time MRI and CT images of the patient are preprocessed, including: Extract the patient's MRI and CT real-time images after edge enhancement as the target image; Extracting grayscale values ​​corresponding to edge pixel blocks in the target image to form a first grayscale value set; Extracting grayscale values ​​corresponding to non-edge pixel blocks in the target image to form a second grayscale value set; Obtaining a grayscale relative coefficient using the first grayscale value set and the second grayscale value set; The grayscale relative coefficient is obtained by the following formula: Wherein, W represents the grayscale relative coefficient; n represents the number of grayscale values ​​included in the first grayscale value set; m represents the number of grayscale values ​​included in the second grayscale value set; H ni represents the corresponding value of the i-th grayscale value contained in the first grayscale value set; H mi represents the corresponding value of the i-th grayscale value contained in the second grayscale value set; H z Represents the central grayscale value of the target image; H nz represents the grayscale intermediate value corresponding to the n grayscale values ​​contained in the first grayscale value set; H mz represents the grayscale intermediate value corresponding to the m grayscale values ​​contained in the second grayscale value set; Comparing the grayscale relative coefficient with a preset relative coefficient threshold; When the grayscale relative coefficient exceeds a preset relative coefficient threshold, no contrast adjustment is performed on the target image; When the grayscale relative coefficient does not exceed a preset relative coefficient threshold, contrast adjustment is performed on the target image.

2. The method for lesion location recognition based on MRI and CT image fusion according to claim 1, characterized in that: In S1, the real-time MRI and CT images of the patient are collected based on the image acquisition terminal, including: Patient MRI image acquisition: Real-time monitoring and continuous acquisition of the patient's lesion site based on the MRI device to obtain the patient's real-time MRI image; Patient CT image acquisition: Based on the CT machine, the patient's lesion area is monitored in real time and continuously acquired to obtain the patient's real-time CT image; The real-time MRI and CT images of the patient based on the image acquisition terminal are determined based on the real-time MRI and CT images of the patient.

3. The method for lesion location recognition based on fusion of MRI and CT images according to claim 2, characterized in that: In S1, the collected real-time MRI and CT images of the patient are preprocessed, including: Image denoising: Based on filters, the system performs filtering processing on the real-time MRI and CT images of patients based on the image acquisition terminal to remove noise from the real-time MRI and CT images of patients based on the image acquisition terminal. Image brightness and contrast adjustment: Based on image segmentation technology, the system adjusts the brightness and contrast of the patient's MRI and CT real-time images based on the image acquisition terminal. Interpolation or reconstruction technology is used to keep the brightness of the patient's MRI and CT real-time images based on the image acquisition terminal consistent. Based on the adaptive adjustment method of global contrast and the relationship between adjacent pixels, the system automatically adjusts the pixel contrast to ensure high-definition patient MRI and CT real-time images. Image enhancement: Based on image enhancement technology, high-definition patient MRI and real-time CT images are enhanced. The edges of high-definition patient MRI and real-time CT images are identified based on edge detection algorithms. The edges of patient MRI and real-time CT images are detected by calculating the gradient values ​​of neighboring pixels and enhanced to highlight the edges in high-definition patient MRI and real-time CT images.

4. The method for lesion location recognition based on fusion of MRI and CT images according to claim 3, characterized in that: When the grayscale relative coefficient does not exceed a preset relative coefficient threshold, contrast adjustment is performed on the target image, including: When the grayscale relative coefficient does not exceed a preset relative coefficient threshold, retrieving the grayscale values ​​included in the second grayscale value set of the target image; Obtaining a contrast adjustment coefficient using the grayscale values ​​included in the second grayscale value set; The contrast adjustment coefficient is obtained by the following formula: Wherein, R represents the contrast adjustment coefficient; m represents the number of grayscale values ​​contained in the second grayscale value set; H mi represents the corresponding value of the i-th grayscale value contained in the second grayscale value set; H z Represents the central grayscale value of the target image; H nz represents the grayscale intermediate value corresponding to the n grayscale values ​​contained in the first grayscale value set; H np represents the grayscale average value corresponding to the n grayscale values ​​contained in the first grayscale value set; W represents the grayscale relative coefficient; Adjusting the contrast of the target image using the contrast adjustment coefficient to obtain the contrast-adjusted target image as an enhanced image highlighting the edges in the high-definition patient MRI and CT real-time images; The adjusted contrast value is obtained by the following formula: Among them, D t represents the contrast value after adjustment; D represents the contrast value before adjustment; R represents the contrast adjustment coefficient; W represents the grayscale relative coefficient; n represents the number of grayscale values ​​contained in the first grayscale value set; H ni represents the corresponding value of the i-th grayscale value contained in the first grayscale value set; H mz Represents the grayscale intermediate value corresponding to the m grayscale values ​​included in the second grayscale value set.

5. The method for lesion location recognition based on fusion of MRI and CT images according to claim 4, characterized in that: In S2, the patient's MRI and CT real-time images are registered and fused, including: Image registration: Register the patient's MRI and real-time CT images, using a transformation-based registration method to ensure that the patient's MRI and real-time CT images have a spatial correspondence; Image fusion: The registered patient MRI and real-time CT images are fused. A transform-domain-based image fusion method is used to decompose the source image into sub-bands of different scales using wavelet transform. The sub-bands are then fused to generate a fused image of the patient's MRI and CT real-time images.

6. The method for identifying lesion locations based on fusion of MRI and CT images according to claim 5, characterized in that: In S3, based on machine learning technology, a lesion location recognition model based on fusion of MRI and CT images is trained, including: Collect data sources: Based on the need for lesion location identification based on MRI and CT image fusion, collect historical MRI and CT images of patients to determine the data source for model training; Data source division: The collected patient MRI and CT historical images were divided into training and test sets in a ratio of 7:3; Model training: Based on the training set, the machine learning model is trained to determine the lesion location recognition model based on the fusion of MRI and CT images. Based on the test set, the performance of the trained lesion location recognition model based on the fusion of MRI and CT images is tested to determine whether the lesion location recognition model based on the fusion of MRI and CT images can achieve the expected effect and to determine the optimal lesion location recognition model based on the fusion of MRI and CT images.

7. The method for identifying lesion locations based on fusion of MRI and CT images according to claim 6, wherein: In S3, image recognition is performed on the generated fusion image of the patient's MRI and CT images according to a lesion location recognition model based on fusion of MRI and CT images, including: Obtain the optimal lesion location recognition model based on MRI and CT image fusion; Deploy the optimal lesion location recognition model based on MRI and CT image fusion in the actual lesion location recognition environment; The generated patient MRI and CT fusion images are subjected to image recognition according to the optimal lesion location recognition model based on MRI and CT image fusion, and the patient lesion location is identified to determine the patient lesion location.

8. The method for identifying lesion locations based on fusion of MRI and CT images according to claim 7, wherein: In S3, after the patient's lesion position is identified, the patient's lesion position is marked and displayed in a visual form on the user interface.

9. A lesion location recognition system based on fusion of MRI and CT images, used to implement the lesion location recognition method based on fusion of MRI and CT images as claimed in claim 8, characterized in that: include: An image acquisition unit is used to acquire real-time MRI images and CT images of patients, and determine real-time MRI and CT images of patients; Image preprocessing unit, used to perform denoising, brightness and contrast adjustment, and image enhancement on the collected patient MRI and CT real-time images; An image fusion unit is used to fuse the patient's MRI and CT real-time images to generate a fused image of the patient's MRI and CT; a lesion location recognition unit, configured to perform image recognition on the generated fusion image of the patient's MRI and CT and identify the location of the patient's lesion, thereby determining the location of the patient's lesion; The user interface display unit is used to display the patient's lesion location to the user in a visual form.

Images