Ultrasound imaging method based on image fusion

Abstract

The application discloses an ultrasonic imaging method based on image fusion, and belongs to the field of assisted reproductive technology.The method comprises the following steps: collecting image data of a uterus by using uterine cavity ultrasonic and abdominal ultrasonic; preprocessing the collected uterine cavity ultrasonic image and abdominal ultrasonic image; extracting features and matching features of the two preprocessed images; transforming and aligning the two images after feature extraction and feature matching; and distributing weight of the two aligned images according to a fusion weight, and fusing the two images into a comprehensive image.The method combines the high-resolution characteristics of uterine cavity ultrasonic with the wide field of view of abdominal ultrasonic, and provides more comprehensive anatomical information by fusing the two ultrasonic images, overcoming the limitations of single imaging technology. The method provides clearer and more comprehensive ultrasonic imaging, improves the definition of the abdominal ultrasonic image, and makes the evaluation of the endometrium and embryo implantation site more accurate.

Description

Technical Field

[0001] This application relates to the field of assisted reproductive technology, and in particular to an ultrasound imaging method based on image fusion. Background Technology

[0002] In assisted reproductive technology, the success rate of embryo transfer is influenced by a variety of factors, among which the application of ultrasound imaging technology is crucial. While traditional abdominal ultrasound images can provide basic information about the uterus, they often lack detail and clarity, especially in assessing the condition of the endometrium and the location of embryo implantation, potentially leading to misdiagnosis or missed diagnosis. Transvaginal ultrasound (EVE) is widely used in gynecological examinations, providing higher resolution images that clearly show the uterine structure and surrounding tissues. However, using transvaginal ultrasound images alone (images of the uterus obtained through vaginal ultrasound) also has limitations; for example, patient comfort and the acceptability of the examination may be affected in some cases. Therefore, effectively combining these two ultrasound imaging techniques to improve image quality and diagnostic accuracy during embryo transfer has become a major challenge in the field. Summary of the Invention

[0003] This application aims to overcome the shortcomings of the prior art and provide an image fusion-based ultrasound imaging method that can effectively combine abdominal ultrasound and transvaginal ultrasound to improve image quality and diagnostic accuracy during embryo transfer.

[0004] To achieve the above objectives, the technical solution of this application is as follows:

[0005] An image fusion-based ultrasound imaging method includes,

[0006] Image data of the uterus were acquired using transvaginal ultrasound and abdominal ultrasound, respectively.

[0007] Preprocessing was performed on the acquired transvaginal ultrasound images of the uterus and abdominal ultrasound images;

[0008] Feature extraction and feature matching are performed on the preprocessed transvaginal ultrasound image of the uterus and the abdominal ultrasound image;

[0009] The transvaginal ultrasound image of the uterus after feature extraction and feature matching is transformed and aligned with the abdominal ultrasound image. The aligned transvaginal ultrasound image of the uterus and the abdominal ultrasound image are then weighted according to the fusion weight and fused into a single composite image.

[0010] Optionally, the acquisition of uterine image data via transvaginal ultrasound and abdominal ultrasound includes: performing the transvaginal ultrasound examination using a high-frequency probe and performing the abdominal ultrasound examination using a low-frequency probe, thereby acquiring high-resolution and wide-field-of-view transvaginal ultrasound images and abdominal ultrasound images.

[0011] Optionally, the preprocessing of the acquired transvaginal ultrasound image and abdominal ultrasound image includes: noise reduction, contrast enhancement, and image correction; the noise reduction includes,

[0012] Wavelet decomposition was performed on the acquired transvaginal ultrasound images of the uterus and the abdominal ultrasound images to obtain sub-images of different frequencies;

[0013] For high-frequency sub-images, thresholding is applied to remove noise;

[0014] Wavelet reconstruction is performed on the sub-images of different frequencies after noise removal to obtain the denoised image.

[0015] Optionally, the enhanced contrast includes,

[0016] The transvaginal ultrasound image of the uterus and the abdominal ultrasound image are divided into multiple small blocks, and histogram equalization is performed on each small block.

[0017] The equalization result of each small block is calculated and then merged into a complete image;

[0018] Following the enhancement of contrast, the method further includes: smoothing and merging regions using linear interpolation.

[0019] Optionally, the image correction includes,

[0020] After selecting a set of feature points, an affine transformation model is used for correction.

[0021] The parameters of the affine transformation model are estimated using the least squares method.

[0022] Optionally, after preprocessing the acquired transvaginal ultrasound image and abdominal ultrasound image, the method further includes: adjusting the size of the transvaginal ultrasound image and abdominal ultrasound image using interpolation to make the transvaginal ultrasound image and abdominal ultrasound image have the same resolution in the same coordinate system.

[0023] Optionally, the feature extraction includes,

[0024] The transvaginal ultrasound image of the uterus and the abdominal ultrasound image were subjected to Gaussian blurring.

[0025] Construct a pyramid structure between the transvaginal ultrasound image of the uterus and the abdominal ultrasound image, and extract feature points at different scales;

[0026] Calculate the orientation and descriptor of each feature point to form a set of feature points.

[0027] Optionally, the feature matching includes,

[0028] The extracted descriptors are matched, and the Euclidean distance between the descriptors is calculated;

[0029] Set a distance threshold to filter out feature points with high matching degree;

[0030] A random sampling consensus algorithm is used to further eliminate incorrect matches.

[0031] Optionally, the process of transforming and aligning the uterine transvaginal ultrasound image and the abdominal ultrasound image after feature extraction and matching, and then weighting the aligned uterine transvaginal ultrasound image and the abdominal ultrasound image according to fusion weights to fuse them into a single composite image, includes:

[0032] Based on the selected feature points with high matching degree, the transformation matrix between the transvaginal ultrasound image and the abdominal ultrasound image is calculated;

[0033] The calculated transformation matrix is ​​used to transform either the transvaginal ultrasound image of the uterus or the abdominal ultrasound image, so that it is aligned with the other image of the transvaginal ultrasound image of the uterus or the abdominal ultrasound image, resulting in two aligned ultrasound images;

[0034] The two aligned ultrasound images are fused together according to the fusion weight to obtain the composite image. The fusion weight is adjusted according to the clarity and detail of the composite image. The higher the value of the fusion weight, the higher the clarity and the more detail the composite image has.

[0035] Optionally, after fusing the images into a single composite image, the method further includes: post-processing the composite image to further improve image quality; the post-processing includes: using image sharpening technology to enhance the edge details of the image. This application provides a method for combining transvaginal ultrasound images of the uterus with abdominal ultrasound images into a clear and comprehensive ultrasound imaging scheme to assist in the embryo transfer process.

[0036] This application provides a clear and comprehensive ultrasound imaging scheme that combines transvaginal ultrasound images of the uterus with abdominal ultrasound images to assist in the embryo transfer process. This scheme improves the clarity of abdominal ultrasound images, enabling more accurate assessment of the endometrium and embryo implantation location. Utilizing the high-resolution characteristics of transvaginal ultrasound, it overcomes the limitations of single imaging techniques, while combining it with the wide field of view of abdominal ultrasound to provide more comprehensive anatomical information. By fusing the two ultrasound images, a new ultrasound imaging technique is formed, providing a clearer and more comprehensive ultrasound imaging scheme, enhancing the physician's decision-making ability during embryo transfer, improving the success rate of transfer, reducing the psychological and physiological burden on patients, and providing more reliable support for clinical practice.

[0037] To make the above-mentioned features and advantages of the application more apparent and understandable, specific embodiments are provided below, and detailed descriptions are given in conjunction with the accompanying drawings. Attached Figure Description

[0038] Figure 1 This is a flowchart of the image fusion-based ultrasound imaging method of this application. Detailed Implementation

[0039] To make the objectives and technical solutions of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the described embodiments of this application without creative effort are within the scope of protection of this application.

[0040] In one embodiment, please refer to Figure 1 This application provides an image fusion-based ultrasound imaging method to offer clinicians more accurate and reliable decision support. The image fusion-based ultrasound imaging method includes the following steps: S10~S30.

[0041] S10: Acquire uterine image data using transvaginal ultrasound and abdominal ultrasound respectively.

[0042] S20: Preprocess the acquired transvaginal ultrasound images of the uterus and the abdominal ultrasound images.

[0043] S30: Perform feature extraction and feature matching on the preprocessed transvaginal ultrasound image of the uterus and the abdominal ultrasound image.

[0044] S40: The transvaginal ultrasound image of the uterus after feature extraction and feature matching is transformed and aligned with the abdominal ultrasound image. The aligned transvaginal ultrasound image of the uterus and the abdominal ultrasound image are weighted according to the fusion weight and fused into a comprehensive image.

[0045] This application provides an image fusion-based ultrasound imaging method to assist in the embryo transfer process. The proposed method improves the clarity of abdominal ultrasound images, enabling more accurate assessment of the endometrium and embryo implantation location. Utilizing the high-resolution characteristics of transvaginal ultrasound, it overcomes the limitations of single imaging techniques and, combined with the wide field of view of abdominal ultrasound, provides more comprehensive anatomical information. By fusing the two ultrasound images, a novel ultrasound imaging technique is formed, providing a clearer and more comprehensive ultrasound imaging approach, enhancing physicians' decision-making ability during embryo transfer, improving transfer success rates, reducing the psychological and physiological burden on patients, and providing more reliable support for clinical practice.

[0046] In step S10, please refer to Figure 1 In step S10, uterine image data is acquired using transvaginal ultrasound and abdominal ultrasound, respectively.

[0047] As an example, transvaginal ultrasound of the uterus uses a high-frequency probe, typically 5-7.5 MHz, to provide higher image resolution, suitable for observing details of the endometrium and ovarian structure. During the examination, the operator gently inserts the probe into the vagina and adjusts the probe angle to obtain the best view. The system then displays cross-sectional and longitudinal images of the uterus in real time, clearly showing the uterine shape, endometrial thickness, and any abnormal structures.

[0048] As an example, abdominal ultrasound is performed using a low-frequency probe, typically 2-5 MHz, suitable for observing a wider range of anatomical structures and providing an overall view of the uterus and surrounding tissues. During an abdominal ultrasound, the operator places the probe on the patient's abdomen, adjusts its position and angle, and obtains a complete view of the uterus and the relative positions of surrounding organs. The system then displays the ultrasound image of the abdomen, helping the doctor assess the overall condition of the uterus.

[0049] In step S20, please refer to Figure 1 Step S20 involves preprocessing the acquired transvaginal ultrasound image of the uterus and the abdominal ultrasound image. Image preprocessing ensures the quality of subsequent image operations, providing high-quality input for subsequent image combination and analysis. The preprocessing includes noise removal, contrast enhancement, and image correction.

[0050] As an example, wavelet transform is used to denoise the transvaginal ultrasound image of the uterus and the abdominal ultrasound image. Wavelet decomposition is performed on the images to obtain sub-images of different frequencies, effectively separating high-frequency noise and low-frequency signals. The low-frequency sub-images, represented as a general background frame in the image, are not over-processed. The high-frequency sub-images, containing rich edge and texture details, are processed using a soft thresholding method to remove noise, using the following formula:

[0051]

[0052] in, These are wavelet coefficients. For the threshold, For symbolic functions, max It is a function for maximizing the value.

[0053] Furthermore, wavelet decomposition is followed by wavelet reconstruction, which reconstructs the denoised image from the decomposed sub-images of different frequencies after noise removal.

[0054] As an example, adaptive histogram equalization is used to enhance the contrast of an image. The image is divided into multiple small blocks, such as 8x8 pixel blocks, and histogram equalization is performed on each block. The equalization result of each block is calculated. By adjusting the contrast in local areas and merging them into a complete image, the detail of the complete image is improved.

[0055] Furthermore, to avoid edge effects, bilinear interpolation can be used to smooth merged regions, thereby improving image detail by adjusting contrast within local areas.

[0056] As an example, geometric correction is used to correct the transvaginal ultrasound image of the uterus and the abdominal ultrasound image to eliminate image distortion caused by changes in probe position or angle. The geometric correction includes: first, selecting a set of feature points, such as corner points or feature edges in the image, and recording their coordinates in the original image; then, using an affine transformation model for correction. The affine transformation model performs operations such as rotation, translation, scaling, and shearing on the image to achieve a transformation from one two-dimensional coordinate system to another, maintaining the parallelism of parallel lines and the angular relationships within the image. Specifically, after obtaining a reliable set of matching points, the transformation matrix parameters are calculated. The transformation matrix includes a 2×3 parameter containing information such as rotation, scaling, and translation; perspective transformation requires calculating a 3×3 homography matrix. Taking perspective transformation as an example, a 3×3 homography matrix is ​​calculated based on a direct linear transformation algorithm combined with the least squares method.

[0057] As an example, the feature points selected on the transvaginal ultrasound image of the uterus are: Feature points selected on abdominal ultrasound images are By taking the two selected feature points as a pair of matching points, and based on the mathematical model of perspective transformation, two linear equations can be established for each pair of matching points:

[0058]

[0059] in, Let H be the element of the perspective transformation matrix. Since this system of equations is nonlinear, it can be transformed into a linear system of equations for solution. Multiplying both sides of the above equations by the denominator and simplifying, we get:

[0060]

[0061] By simultaneously solving the equations corresponding to multiple pairs of matching points, an overdetermined linear system of equations, Ah = b, is formed, where A is the coefficient matrix, h is a column vector containing elements of the perspective transformation matrix H, and b is a constant vector. The least squares method is then used to solve this system of equations, i.e., to find the error vector... The minimum value of the L2 norm, h, is used as the parameter estimate for the perspective transformation matrix H. This method enables the calculation of the transformation matrix as accurately as possible, even in the presence of noise and errors, achieving precise alignment between images and providing strong support for the effective integration of multi-source image information.

[0062] As an example, after the preprocessing of the transvaginal ultrasound image of the uterus and the abdominal ultrasound image, the method further includes: preparing for the fusion of the transvaginal ultrasound image of the uterus and the abdominal ultrasound image using an interpolation method, the interpolation method including bilinear interpolation, by adjusting the image size so that the two images have the same resolution in the same coordinate system.

[0063] In step S30, please refer to Figure 1 In step S30, feature extraction and feature matching are performed on the preprocessed transvaginal ultrasound image of the uterus and the abdominal ultrasound image.

[0064] As an example, scale-invariant feature transformation or accelerated robust feature extraction algorithms are used to extract key points and their descriptors from transvaginal and abdominal ultrasound images, performing feature extraction on these images. First, Gaussian blurring is applied to the transvaginal and abdominal ultrasound images to reduce the impact of residual noise on feature extraction. Next, a Gaussian pyramid structure is constructed for the transvaginal and abdominal ultrasound images to extract feature points at different scales. Starting from the preprocessed transvaginal and abdominal ultrasound images, Gaussian kernel convolution and downsampling operations are repeatedly applied to generate multi-layered image sequences with decreasing resolution. During this process, high-frequency details in the transvaginal and abdominal ultrasound images are gradually stripped away, while low-frequency contour information is highlighted, laying the foundation for subsequent layered fusion. Finally, the orientation and descriptor of each feature point are calculated to form a feature point set.

[0065] As an example, after feature extraction, the process further includes: performing feature matching on the features extracted from the transvaginal ultrasound image and the abdominal ultrasound image using nearest neighbor matching or the FLANN algorithm. First, the extracted feature descriptors are matched, and the Euclidean distance between the descriptors is calculated. A distance threshold is set, with the value ranging from the absolute value of the high-frequency waveform to the absolute value of the low-frequency waveform. Feature points with high matching degrees are selected to ensure matching accuracy. Finally, a random sampling consensus algorithm is used to further eliminate incorrect matches, ensuring the reliability of the matching results.

[0066] In step S40, please refer to Figure 1 In step S40, the transvaginal ultrasound image of the uterus after feature extraction and feature matching is transformed and aligned with the abdominal ultrasound image. The aligned transvaginal ultrasound image of the uterus and the abdominal ultrasound image are then weighted according to the fusion weight and fused into a comprehensive image.

[0067] As an example, based on the feature points of feature matching, affine transformation or perspective transformation is used to calculate the transformation matrix between the two images. Further, the calculated transformation matrix is ​​used to transform either the transvaginal ultrasound image or the abdominal ultrasound image, aligning it with the other image from the transvaginal ultrasound image and the abdominal ultrasound image, resulting in aligned ultrasound images. Further, a weighted average method is used to fuse the transvaginal ultrasound image and the abdominal ultrasound image according to the fusion weights. When the doctor operates the instrument to acquire images, the highest priority is localization, followed by details; therefore, weight allocation is used. The fusion weights can be system-controlled or adjusted by the doctor.

[0068] As an example, at the beginning of abdominal ultrasound acquisition, The image shows the aligned transvaginal ultrasound image of the uterus. For the aligned abdominal ultrasound image, the transvaginal ultrasound image is used as the primary base, with a relatively high weight, while the abdominal ultrasound image has a lower weight, primarily for localization. When a precise placement point is needed after approximate localization, the abdominal ultrasound image is used as the primary base, with a correspondingly higher weight. The formula for image fusion of the transvaginal and abdominal ultrasound images is as follows:

[0069]

[0070] in, For the merged image, and These are two aligned images. The coordinates after alignment. The fusion weight has a value between 0 and 1.

[0071] Furthermore, by adjusting the fusion weights The value controls the sharpness and detail of the merged image; the fusion weight. The higher the value, the clearer the image and the more detailed it is.

[0072] As an example, this application employs an image fusion algorithm based on feature extraction and matching to combine the preprocessed transvaginal ultrasound image of the uterus with the abdominal ultrasound image, identify matching features, and fuse them into a clearer and more informative comprehensive image.

[0073] In some embodiments, aligned transvaginal ultrasound images and abdominal color Doppler ultrasound images can be fused. The fusion method may include, but is not limited to, pixel-level fusion, feature-level fusion, and decision-level fusion. For example, in some embodiments, applying a pixel-level fusion method may refer to a spatial domain fusion method: specifically, it involves directly performing simple processing on corresponding pixels in the transvaginal ultrasound image and abdominal color Doppler ultrasound image to fuse them into a clear image for the doctor's use. As another example, in some embodiments, applying a pixel-level fusion method may also refer to a frequency domain fusion method: specifically, it involves using methods such as pyramid decomposition and wavelet transform to process the high and low frequency information of the transvaginal ultrasound image and abdominal color Doppler ultrasound image respectively.

[0074] It should be noted that the specific methods for fusing the aligned transvaginal ultrasound image and abdominal color Doppler ultrasound image may include, but are not limited to, the fusion methods described above.

[0075] As an example, after the image is fused into a single composite image, post-processing is further performed to improve image quality. Image sharpening techniques, such as Laplacian sharpening, are used to enhance edge details, resulting in a clearer fused image.

[0076] In another example, after the image post-processing, the method further includes: feeding back the processed image and analysis results to the clinician to assist the clinician in making more accurate decisions during the embryo transfer process, and collecting feedback information from clinical applications to continuously optimize the processing and fusion algorithm based on the combination of transvaginal ultrasound images and abdominal ultrasound images, including the following steps S501~S504.

[0077] In step S501, after completing the image fusion algorithm for feature extraction and matching, a result feedback mechanism is adopted for the application results of the embryo transfer method based on the combined processing of transvaginal ultrasound images and abdominal ultrasound images. The system will automatically generate a detailed report, which includes the processed fused image, endometrial thickness, morphological characteristics, and other key indicators. This information will be transmitted to clinicians in real time through an electronic medical record system or a dedicated medical software platform to ensure that doctors can obtain the latest analysis results in a timely manner.

[0078] In step S502, after the system generates a detailed report, a decision support system is employed. To assist doctors in making more accurate decisions, the system integrates decision support algorithms. These algorithms, based on historical data and clinical guidelines, can provide doctors with personalized recommendations. For example, the system can assess the success rate of embryo transfer based on the thickness and morphological characteristics of the endometrium, combined with the patient's medical history, and provide corresponding suggestions. This process can be achieved through machine learning models, which need to be trained on a large amount of clinical data to improve their predictive accuracy.

[0079] In step S503, after the doctor makes and applies the decision, the system collects feedback information. Doctor feedback is crucial in clinical application; the system is designed with a feedback collection module that allows doctors to evaluate the effectiveness of image processing and fusion algorithms. Doctors can use simple questionnaires or rating systems to provide feedback on aspects such as image clarity, feature extraction accuracy, and the effectiveness of decision support. This feedback will be recorded and analyzed by the system to identify potential areas for improvement.

[0080] In step S504, after collecting the feedback information, the collected feedback information will be used to continuously optimize the image processing and fusion algorithm. Specifically, the development team can periodically analyze the feedback data to identify the reasons for poor algorithm performance in specific situations, and adjust the algorithm parameters or improve the processing flow accordingly. For example, if doctors report insufficient image clarity in certain situations, the development team can consider introducing more advanced noise reduction techniques or image enhancement methods to improve image quality.

[0081] In another embodiment, in a clinical application, a doctor needs to combine a transvaginal ultrasound image of the uterus with an abdominal ultrasound image. First, the system uses a scale-invariant feature transform algorithm to extract feature points from both images, obtaining their respective feature descriptors. Next, the system performs feature matching using the FLANN algorithm, selecting feature point pairs with high matching scores and using a random sampling consensus algorithm to remove incorrect matches. Subsequently, the matching feature point pairs are used to calculate the transformation matrix between the two images, and the transvaginal ultrasound image is aligned to the abdominal ultrasound image using this calculated transformation matrix. Finally, the two images are fused into a clear composite image using a weighted average method. After image post-processing, the fused image obtained by the doctor is not only clearly visible but also contains key information from both images, providing a more reliable basis for embryo transfer. This image fusion algorithm based on feature extraction and matching improves the usability and accuracy of ultrasound images. After receiving the processed fused image and analysis results, the doctor found that the endometrial thickness was 8 mm and the morphology was normal. The system also provides a success rate prediction based on historical data, showing that at this thickness, the success rate of embryo transfer is 75%. Based on this information, the doctor decided to proceed with the embryo transfer and recorded this decision-making process. Subsequently, the doctor completed a feedback questionnaire in the system, noting that the image clarity was good but requesting more morphological feature analysis capabilities in future versions. After collecting this feedback, the development team began researching how to incorporate more morphological features into the analysis to further improve the system's usability and accuracy. Through this cycle of feedback and optimization, the system continuously evolves, ultimately providing clinicians with more precise and reliable decision support.

[0082] This application provides an image fusion-based ultrasound imaging method to assist in the embryo transfer process. The proposed method improves the clarity of abdominal ultrasound images, enabling more accurate assessment of the endometrium and embryo implantation location. Utilizing the high-resolution characteristics of transvaginal ultrasound, it overcomes the limitations of single imaging techniques and, combined with the wide field of view of abdominal ultrasound, provides more comprehensive anatomical information. By fusing the two ultrasound images, a novel ultrasound imaging technique is formed, providing a clearer and more comprehensive ultrasound imaging approach, enhancing physicians' decision-making ability during embryo transfer, improving transfer success rates, reducing the psychological and physiological burden on patients, and providing more reliable support for clinical practice.

[0083] Although this application has been disclosed above with reference to embodiments, it is not intended to limit this application. Anyone skilled in the art may make some modifications and refinements without departing from the spirit and scope of this application. Therefore, the scope of protection of this application shall be determined by the appended claims.

Claims

1. An ultrasound imaging method based on image fusion, characterized in that, The application relates to an image processing method and device. The preprocessed uterine and abdominal ultrasound images are subjected to feature extraction and feature matching; the feature extraction comprises: the uterine and abdominal ultrasound images are subjected to Gaussian blur processing; the pyramid structure of the uterine and abdominal ultrasound images is constructed, and feature points in different scales are extracted; the direction and descriptor of each feature point are calculated to form a feature point set; the feature matching comprises: the extracted descriptors are matched, and the Euclidean distance between the descriptors is calculated; a distance threshold is set to screen out feature points with high matching degrees; the random sample consensus algorithm is used to further remove false matches; The uterine and abdominal ultrasound images after the feature extraction and feature matching are subjected to transformation alignment; the uterine and abdominal ultrasound images after the alignment are subjected to weight distribution according to a fusion weight, and are fused into a comprehensive image, which comprises: the transformation matrix between the uterine and abdominal ultrasound images is calculated according to the screened feature points with high matching degrees; the calculated transformation matrix is used to transform any one of the uterine and abdominal ultrasound images, so that the any one of the uterine and abdominal ultrasound images is aligned with the other one of the uterine and abdominal ultrasound images, thereby obtaining two aligned ultrasound images; the two aligned ultrasound images are fused according to the fusion weight, thereby obtaining the comprehensive image; the fusion weight is adjusted according to the definition and details of the comprehensive image; the higher the value of the fusion weight is, the higher the definition of the comprehensive image is, and the more details the comprehensive image has. ​ The fusing into a comprehensive image further comprises: post-processing the comprehensive image to further improve the image quality; and the post-processing comprises: using an image sharpening technique to enhance the edge details of the image.

2. The image fusion based ultrasound imaging method of claim 1, wherein, The interpolation method comprises bilinear interpolation.

3. The image fusion based ultrasound imaging method as claimed in claim 1, wherein, The image sharpening technique is Laplace sharpening.

Images