Medical image processing system and method

Abstract

The invention relates to a medical image processing system and method. The medical image processing system is configured to obtain a first modal image and a second modal image of a scanned object; decomposing the second modal image to obtain a corresponding high-frequency image and a corresponding low-frequency image; performing local compression on the low-frequency image to obtain a compressed low-frequency image; reconstructing the compressed low-frequency image and the high-frequency image to obtain a reconstructed second modal image; performing gray scale transformation on the reconstructed second modal image to obtain a contrast-enhanced second modal image; and superposing the first modal image onto the contrast-enhanced second modal image to realize simultaneous clear display of the blood vessel anatomical structure and the real-time operation instrument. The technical effects are derived from the combination of multi-scale decomposition and selective compression: low-frequency compression reduces background noise interference, high-frequency retention ensures that instrument details are not lost, and superposition operation enhances the visibility of clinical operation through multi-modal fusion.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing, and in particular to a medical image processing system and method. Background Art

[0002] With the continuous development of medical imaging technology, digital subtraction angiography (DSA) has become an important means of vascular imaging and interventional treatment. DSA technology can clearly display the vascular structure by subtracting X-ray images before and after the injection of contrast agents, providing an important basis for clinical diagnosis and interventional treatment. However, in practical applications, medical image processing technology still faces many challenges.

[0003] Roadmap, also known as subtraction fluoroscopy, retains the vascular filling image obtained by subtraction as the base plate and superimposes it on the real-time fluoroscopic image to guide the path of the catheter and guidewire. The two phases of subtraction images need to be superimposed together to clearly see the direction of the guidewire and other equipment in the blood vessels. When superimposing, if the vascular images are superimposed too much, the guidewire will be weak or unclear. If the guidewire is superimposed too much, the blood vessels will become lighter and the contrast of the blood vessels will become weaker.

[0004] The existing technology in the field of medical image processing, especially in DSA technology, still has the following problems: first, perspective images usually have a large dynamic range, resulting in excessive local contrast and visual interference; second, although subtraction images can highlight vascular structures, they lack anatomical background information, which is not conducive to interventional surgical navigation; third, in interventional surgery, it is difficult to simultaneously visualize instruments (such as catheters and guidewires) and vascular structures, and mutual occlusion problems are prone to occur; finally, traditional image fusion methods are difficult to balance the feature retention of images of different modalities, resulting in loss of details or artifacts. Therefore, there is an urgent need for a system that can effectively process medical images to improve image quality and clinical application value. Summary of the invention

[0005] In order to solve the problems in the field of medical image processing, especially in DSA technology, such as excessive dynamic range of perspective images resulting in excessive local contrast, lack of anatomical background information in subtraction images, difficulty in simultaneous visualization of instruments and vascular structures, and difficulty in balancing the retention of features of images of different modalities using traditional image fusion methods, the present invention provides a medical image processing system and method.

[0006] A medical image processing system, comprising: a processor and a display, the display being communicatively connected to the processor, and the medical image processing system being configured to: acquire a first modality image (subtraction image) and a second modality image (fluoroscopy image) of a scanned object; decompose the second modality image (Laplacian of Gaussian pyramid decomposition) to obtain a corresponding high-frequency image and a low-frequency image; locally compress the low-frequency image to obtain a compressed low-frequency image; reconstruct the compressed low-frequency image and the high-frequency image to obtain a reconstructed second modality image (fluoroscopy image); perform a grayscale transformation on the reconstructed second modality image (fluoroscopy image) to obtain a second modality image (fluoroscopy image) with enhanced contrast; and superimpose the first modality image (subtraction image) on the second modality image (fluoroscopy image) with enhanced contrast.

[0007] Optionally, the first modality image is a subtraction image of the scanned area, and the second modality image is a fluoroscopy image of the scanned area.

[0008] Optionally, the first modality image is obtained by subtraction processing of two fluoroscopy images acquired by a DSA device. One of the two fluoroscopy images is obtained by scanning the scanned object with the DSA device after injecting a contrast agent into the scanned object, and the other of the two fluoroscopy images is obtained by scanning the scanned object with the DSA device without injecting a contrast agent into the scanned object or when the concentration of the contrast agent in the scanned object is lower than a set threshold.

[0009] Optionally, the second modality image is obtained before injecting a contrast agent into the scanned object or is acquired after a set time threshold after injecting a contrast agent into the scanned object.

[0010] Optionally, the locally compressing the low-frequency image to obtain a compressed low-frequency image includes obtaining an initial grayscale curve representing the contrast of the pixel points of the low-frequency image, and locally compressing both ends of the initial grayscale curve.

[0011] Optionally, the locally compressing both ends of the initial grayscale curve includes: dynamically adjusting the local slopes of both ends of the initial grayscale curve so that the local slopes of both ends of the adjusted initial grayscale curve are smaller than the slope of the initial grayscale curve.

[0012] Optionally, it further includes performing enhancement processing on the high-frequency image to obtain an enhanced high-frequency image.

[0013] Optionally, it further includes reconstructing the enhanced high-frequency image and the compressed low-frequency image.

[0014] Optionally, locally compressing the low-frequency image to obtain a compressed low-frequency image includes: identifying pixel points in the low-frequency image with initial gray values in a set high-threshold interval and a low-threshold space, and reducing the gray values of the pixel points in the set high-threshold interval and low-threshold space.

[0015] Optionally, superimposing the first modality image onto the contrast-enhanced second modality image includes performing a first weighting process on the first modality image and a second weighting process on the contrast-enhanced second modality image, and adding the weighted first modality image and the weighted contrast-enhanced second modality image.

[0016] Optionally, the first weighting process includes a first weighting coefficient, the second weighting process includes a second weighting coefficient, and the sum of the first weighting coefficient and the second weighting coefficient is 1.

[0017] Optionally, the display has an input window for inputting the first weighting coefficient, the second weighting coefficient, or compression parameters.

[0018] Optionally, the first modality image is a first subtracted image of the scanned area, the second modality image is a second subtracted image of the scanned area, and the second modality image contains equipment information (guide wire, stent, coil).

[0019] Optionally, the processor is configured to perform the following processing on the first subtracted image and the second subtracted image: decomposing (Laplacian of Gaussian pyramid decomposition) the first subtracted image to obtain a corresponding number (complex) of first high-frequency images and a first low-frequency image; decomposing (Laplacian of Gaussian pyramid decomposition) the second subtracted image to obtain a corresponding number (complex) of second high-frequency images and a second low-frequency image; fusing the first low-frequency image and the second low-frequency image to obtain a fused low-frequency fused image (C); locally compressing the low-frequency fused image to obtain a compressed low-frequency fused image; performing a gray-scale transformation on the low-frequency fused image to obtain a contrast-enhanced low-frequency fused image (Cnew); performing a weighting process on each of the complex first high-frequency images to obtain complex first weighted high-frequency images; performing a weighting process on each of the complex second high-frequency images to obtain complex second weighted high-frequency images; performing a synthesis process on the complex first weighted high-frequency images and the corresponding complex second weighted high-frequency images respectively to obtain a complex number of synthesized high-frequency images (C1…Cn); and reconstructing the complex number of synthesized high-frequency images (C1…Cn) and the contrast-enhanced low-frequency fused image (Cnew) to obtain a reconstructed subtracted image.

[0020] Optionally, the local compression of the low-frequency fusion image to obtain the compressed low-frequency fusion image includes: dynamically identifying the pixel points in the low-frequency fusion image with initial gray values in the set high threshold interval and low threshold space, and reducing the gray values of the pixel points in the set high threshold interval and low threshold space.

[0021] Optionally, the local compression of the low-frequency fusion image to obtain the compressed low-frequency fusion image includes: obtaining an initial gray curve representing the contrast of the pixel points of the low-frequency fusion image, and locally compressing both ends of the initial gray curve.

[0022] Optionally, the local compression processing of both ends of the initial gray curve includes: dynamically adjusting the local slopes of both ends of the initial gray curve so that the local slopes of both ends of the adjusted initial gray curve are less than the slope of the initial gray curve.

[0023] Optionally, fusing the first low-frequency image and the second low-frequency image to obtain the fused low-frequency fusion image (C) includes respectively performing weighted processing on the first low-frequency image and the second low-frequency image, and performing summation processing on the first weighted low-frequency image and the second weighted low-frequency image.

[0024] The beneficial effects of the present invention are as follows: By decomposing the image into high-frequency and low-frequency components through Laplacian of Gaussian pyramid, the detail information and basic structure are effectively separated, providing a basis for subsequent processing; By locally compressing the low-frequency image (adjusting the slopes at both ends of the gray curve or reducing the gray value in the threshold interval), the dynamic range of the perspective image is optimized, avoiding local overexposure or underexposure and reducing visual interference; By gray-scale transformation, the overall contrast is enhanced, improving the readability of the image; By weighted fusion of the subtracted image and the enhanced perspective image, the dynamic integration of the vascular structure and anatomical tissue is realized, retaining both the high-contrast advantage of the subtraction technique for blood vessels and providing real-time position information of the instrument through the perspective image; In the double-subtraction image processing, the problem of mutual occlusion between the instrument and the blood vessel in the traditional method is avoided through frequency division fusion, while retaining the key features of both images; Through adjustable weighting coefficients and compression parameters, personalized adjustment of image fusion is realized, meeting the needs of different clinical scenarios; The diagnostic value of medical images is overall improved, especially suitable for clinical scenarios such as interventional surgery that require simultaneous observation of the vascular structure and the position of the instrument. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of a medical image processing system provided by an embodiment of the present application;

[0026] Figure 2 It is a schematic structural diagram of a disposal device of the medical image processing system according to an embodiment of the present application;

[0027] Figure 3 Flow chart of the first medical image processing method provided by the embodiments of the present application;

[0028] Figure 4 Flow chart of the second medical image processing method provided by the embodiments of the present application;

[0029] Figure 5 Flow chart of the third medical image processing method provided by the embodiments of the present application;

[0030] Figure 6 Schematic structural diagram of the disposal device of the medical image processing system according to another embodiment of the present application. Detailed implementation manners

[0031] To make the above objects, features, and advantages of the present application more apparent and understandable, the following will describe the detailed implementation manners of the present application in conjunction with the accompanying drawings. Many specific details are set forth in the following description to facilitate a thorough understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0032] In the description of the present application, it should be understood that if there are terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., the orientation or positional relationship indicated by these terms is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present application.

[0033] In addition, if there are terms such as "first" and "second", these terms are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present application, if there is a term "multiple", the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0034] In this application, unless otherwise clearly stipulated or limited, if terms such as "installed", "connected", "linked", "fixed", etc. appear, these terms shall be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0035] In this application, unless otherwise clearly stipulated or limited, if there is a description such as a first feature "on" or "under" a second feature, its meaning can be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature "above", "over" and "on" the second feature can be that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is at a higher horizontal level than the second feature. The first feature "under", "beneath" and "under" the second feature can be that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is at a lower horizontal level than the second feature.

[0036] It should be noted that if an element is referred to as "fixed to" or "disposed on" another element, it can be directly on the other element or there can also be an intermediate element. If an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. If so, the terms "vertical", "horizontal", "up", "down", "left", "right" and similar expressions used in this application are only for the purpose of illustration and do not represent the only implementation manner.

[0037] Figure 1 is a schematic diagram of a medical image processing system shown according to some embodiments of this specification. As Figure 1 shown, the medical image processing system 100 may include an imaging device 110, a network 120, a terminal 130, a processing device / equipment 140, and a storage device 150.

[0038] The imaging device 110 may be configured to scan a target subject to be examined to obtain image data (for example, projection data, images, etc.). In some embodiments, the imaging device 110 may include a medical imaging device, such as a DSA (Digital Subtraction Angiography) imaging device, or other imaging devices, such as a CT (Computed Tomography) imaging device, an MR (Magnetic Resonance) imaging device, etc.

[0039] In some embodiments, the imaging device 110 may include a gantry 1101, a detector 1102, and a radiation source 1103. The gantry 1101 has a C-arm structure, and the detector 1102 and the radiation source 1103 are respectively installed at opposite ends of the gantry 1101. The C-arm structure can provide a scanning area to accommodate the subject to be scanned. The subject can be placed on a scanning bed (not shown) and moved into the scanning area to be scanned. In some embodiments, the detector 1102 may be a flat plate structure and include one or more detection modules. The detection module may include one or more detection units arranged perpendicular to the bedplate of the scanning bed. In some embodiments, each of the plurality of detection units may be configured to generate an electrical signal in response to detecting radiation. In some embodiments, each of the plurality of detection units or detection modules may be detachable. It should be noted that Figure 1 the number of detection modules in [[]] is only for illustration and does not limit the scope of this specification. The number of detection modules may be plural. The detection unit may include a scintillator (such as a cesium iodide detector), a semiconductor, etc. In some embodiments, the imaging device 110 may further include a collimator (not shown in the figure). The collimator may include a plurality of collimation modules arranged parallel to the detector module. Each of the plurality of collimation modules may include a plurality of collimation units with different configurations. More descriptions of the collimator and / or the detector can be found in different descriptions elsewhere in this specification. Optionally, the detector may be a dual-layer (dual-energy) detector, the main feature of which is the adoption of two different detection modules (dual-detection layer structure), one layer being a low-energy detection layer and the other layer being a high-energy detection layer. The design of this dual-layer detector enables the system to synchronously capture X-ray signals of different energies, thereby achieving efficient spectral imaging. In the low-energy detection layer, the captured low-energy projection data can strongly respond to low atomic number substances such as water, while the high-energy detection layer is more sensitive to high atomic number substances (such as iodine-containing contrast agents).

[0040] The network 120 may include any suitable network capable of facilitating information and / or data exchange of the imaging device 110. In some embodiments, at least one component of the medical image processing system 100 (e.g., the imaging device 110, the terminal 130, the processing device 140, the storage device 150) may exchange information and / or data with at least another component in the medical image processing system 100 through the network 120. For example, the processing device 140 may obtain scan data from the imaging device 110 through the network 120. In some embodiments, the network 120 may include at least one network access point. For example, the network 120 may include wired and / or wireless network access points (such as base stations and / or Internet exchange points), and at least one component of the medical image processing system 100 may be connected to the network 120 through the access point to exchange data and / or information.

[0041] The terminal 130 can communicate with and / or be connected to the imaging device 110, the processing device 140, and / or the storage device 150. In some embodiments, the terminal 130 may include a mobile device 131, a tablet computer 132, a laptop computer 133, etc., or any combination thereof. For example, the mobile device 131 may include a mobile control handle, a personal digital assistant (PDA), a smart phone, etc., or any combination thereof. In some embodiments, the terminal 130 may include a display device, such as a monitor. The display device may be configured to display images obtained through imaging or other information, such as medical images of a patient, a three-dimensional model, or an operation panel related to medical imaging. In some embodiments, the terminal 130 may be a part of the processing device 140.

[0042] The processing device 140 may be configured to obtain data and / or information from the imaging device 110, the terminal 130, the storage device 150, or other components of the medical image processing system 100. For example, the processing device (processor) may be configured to perform one or more operations of the imaging data processing method disclosed in some embodiments of this specification. In some embodiments, the processing device 140 may include a single server or a server group. The server group may include a centralized server group or a distributed server group. In some embodiments, the processing device 140 may include a local device or a remote device. For example, the processing device 140 may access information and / or data from the imaging device 110, the storage device 150, and / or the terminal 130 through the network 120. As another example, the processing device 140 may be directly connected to the imaging device 110, the terminal 130, and / or the storage device 150 to access information and / or data. As another example, the processing device 140 may be installed on the imaging device 110. In some embodiments, the processing device 140 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof.

[0043] The storage device 150 may be configured to store data, instructions, and / or any other information. For example, the storage device 150 may store data obtained by the imaging device 110, the terminal 130, and / or the processing device 140. In some embodiments, the storage device 150 may store data and / or instructions for the processing device 140 to execute or to implement the exemplary methods described in this specification. In some embodiments, the storage device 150 may include a mass storage device, a removable storage device, a volatile read / write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 150 may be implemented on a cloud platform.

[0044] In some embodiments, the storage device 150 may be connected to the network 120 to communicate with at least one other component of the medical image processing system 100 (e.g., the processing device 140, the terminal 130). At least one component of the medical image processing system 100 may access the data stored in the storage device 150 through the network 120. In some embodiments, the storage device 150 may be part of the processing device 140. In some embodiments, the processing device 140 and the storage device 150 may be integrated in the imaging device 110.

[0045] It should be noted that the above description is for illustrative purposes only and is not intended to limit the scope of this specification. Various modifications and changes can be made by those skilled in the art under the teachings of the description in this specification. The features, structures, methods, and other features of the exemplary embodiments described in this specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the storage device 150 may be a data storage device, which may include a cloud computing platform, such as a public cloud, a private cloud, a community cloud, and a hybrid cloud. However, these modifications and changes do not depart from the scope of this specification.

[0046] Please refer to Figures 2-3 , a processing device of a medical image processing system 100 disclosed in an embodiment of the present application is configured to: acquire a first modality image (subtraction image) and a second modality image (fluoroscopy image) of a scanned object; decompose the second modality image (Laplacian of Gaussian pyramid decomposition) to obtain a corresponding high-frequency image and a low-frequency image; locally compress the low-frequency image to obtain a compressed low-frequency image; reconstruct the compressed low-frequency image and the high-frequency image to obtain a reconstructed second modality image (fluoroscopy image); perform a gray-scale transformation on the reconstructed second modality image (fluoroscopy image) to obtain a second modality image (fluoroscopy image) with enhanced contrast; and superimpose the first modality image (subtraction image) on the second modality image (fluoroscopy image) with enhanced contrast.

[0047] In the medical image processing system 100 of this embodiment, the processing device (processor) 140 and the display cooperate to process the input medical image data. The processing device 140 of the system includes a first acquisition module 1401, a first decomposition module 1402, a first compression module 1403, a first reconstruction module 1404, a first transformation module 1405, and a superimposition module 1406. The modules are communicatively connected to each other and realize data exchange.

[0048] The first acquisition module 1401 is used to acquire the image data to be processed. Optionally, the first acquisition module may directly obtain the original image data from the imaging device (DSA device) 110 or other X-ray imaging devices, or may acquire the image data that has been stored in the storage device 150.

[0049] The first decomposition module 1402 is configured with a corresponding program algorithm or configuration for decomposing and processing image data, and decomposes and processes the received image data (DSA imaging data). For example, the second modality image (fluoroscopic image) is separated / decomposed into a high-frequency component (including details such as blood vessel edges and instruments) and a low-frequency component (reflecting the overall brightness distribution of the image) through the Laplacian of Gaussian pyramid algorithm.

[0050] The first compression module 1403 is configured with a corresponding program algorithm or configuration for compressing the decomposed image data. For example, local compression of the low-frequency component is achieved by adjusting the dynamic range of gray values (such as reducing the contrast in overly high or low gray regions), effectively suppressing background interference such as bones or soft tissues in the fluoroscopic image while retaining the detail information of blood vessels and instruments.

[0051] The first reconstruction module 1404 is configured with a corresponding program algorithm or configuration for processing the decomposed image data and the compressed image data; for example, the compressed low-frequency component image data and the high-frequency component data received are used to generate an optimized fluoroscopic image through inverse pyramid reconstruction, and then the contrast between blood vessels and the background is further enhanced through gray-scale transformation (such as histogram equalization or non-linear mapping).

[0052] The first transformation module 1405 performs gray-scale transformation on the reconstructed second modality image (fluoroscopic image) to obtain a second modality image (fluoroscopic image) with enhanced contrast;

[0053] The superimposition module 1406 finally superimposes the subtracted image (only containing blood vessel structures) onto the enhanced fluoroscopic image to achieve clear simultaneous display of blood vessel anatomical structures and real-time operating instruments. The technical effect stems from the combination of multi-scale decomposition and selective compression: low-frequency compression reduces background noise interference, high-frequency retention ensures that instrument details are not lost, and the superimposition operation enhances the visibility of clinical operations through multi-modal fusion.

[0054] Optionally, the first modality image is a subtracted image of the scanned area, and the second modality image is a fluoroscopic image of the scanned area. For example, the first modality image is a subtracted image (such as an image that only retains blood vessel structures after DSA subtraction), and the second modality image is a conventional fluoroscopic image (including instruments and anatomical structures but with relatively low blood vessel contrast). The subtracted image highlights the blood vessel morphology by eliminating the bone and soft tissue background; the fluoroscopic image provides a real-time operation scenario. The combination of the two enables the system to clearly display the blood vessel path and simultaneously feedback the positional relationship of instruments such as catheters and guide wires, solving the problem of lost instrument information in traditional DSA. This effect depends on the complementarity of the dual-modal images: the subtracted image provides high-contrast blood vessel information, and the fluoroscopic image retains the dynamic operation scenario, forming a composite image with a clear spatial relationship between blood vessels and instruments after superimposition.

[0055] Optionally, the first modal image is obtained by subtraction processing of two fluoroscopic images acquired by a DSA device. One of the two fluoroscopic images is obtained by scanning the scanned object with the DSA device after injecting a contrast agent into the scanned object, and the other of the two fluoroscopic images is obtained by scanning the scanned object with the DSA device after not injecting a contrast agent into the scanned object or when the concentration of the contrast agent in the scanned object is lower than a set threshold. Further, if a dual-energy (dual-layer) detector is used, two fluoroscopic images with high and low energies can be obtained by one scan after injecting a contrast agent into the scanned object, and then the two fluoroscopic images are subjected to subtraction processing to obtain the first modal image; the second modal image can be a low-energy image (or a high-energy image).

[0056] Optionally, the method for generating a subtracted image can be: performing pixel-level difference on two frames of fluoroscopic images before and after injecting a contrast agent to eliminate static backgrounds such as bones and soft tissues, and only retaining the blood vessel information filled with the contrast agent. The time interval between the image (mask) before injection (of the contrast agent) and the image (filled image) after injection needs to be short enough to avoid registration errors caused by patient movement, and the acquisition timing of the image after injection needs to ensure that the contrast agent fully fills the target blood vessel. The advantage of this method is that it directly removes background interference through physical subtraction, rather than relying on post-processing algorithms, thereby ensuring the accuracy of blood vessel boundaries. The core of the technical effect lies in the complete elimination of the static background during the subtraction process, so that there is no confusion between the blood vessel contour and the surrounding tissues when superimposed on the fluoroscopic image.

[0057] Optionally, the local compression of the low-frequency image to obtain the compressed low-frequency image includes obtaining an initial gray curve characterizing the pixel point contrast of the low-frequency image and locally compressing both ends of the initial gray curve.

[0058] The initial gray curve reflects the distribution characteristics of pixel values in the low-frequency image, and its two ends correspond to extremely high or extremely low gray regions (such as strong signals of bones or air). By compressing the slopes of both ends of the curve (such as changing the linear mapping to an S-shaped curve), the contrast expansion of these regions can be restricted, avoiding the loss of details caused by overexposure or underexposure, while maintaining the contrast of the middle gray region (corresponding to blood vessels and soft tissues). The technical effect of this method lies in the pertinence of dynamic range compression: only suppressing the contrast of irrelevant backgrounds and avoiding the destruction of useful information by global compression. The reconstruction result of the compressed low-frequency image and high-frequency details can balance the overall brightness and local details, improving the simultaneous visibility of blood vessels and instruments.

[0059] Optionally, the local compression processing of both ends of the initial gray curve includes: dynamically adjusting the local slopes of both ends of the initial gray curve so that the local slopes of both ends of the adjusted initial gray curve are less than the slope of the initial gray curve.

[0060] By reducing the slopes at both ends of the curve (for example, setting the slopes in the 0 - 10% and 90 - 100% gray intervals to 50% of the original slope), non - linear mapping of extreme gray values is achieved. This dynamic adjustment can be automatically adapted according to the image content: if the high - light area in the low - frequency image accounts for a large proportion, a greater degree of compression is performed on the high - gray end; otherwise, the low - gray end is emphasized. The technical effect is reflected in the adaptive compression ability, avoiding local over - processing caused by fixed - parameter compression. After the slope adjustment, the pixel value difference in the extreme gray area is reduced (for example, the bright spots at the bone edges are suppressed), while the gray difference of blood vessels in the middle area is retained or even enhanced, thus maintaining the contrast of the target structure while suppressing the background.

[0061] Optionally, the system further includes enhancing the high - frequency image to obtain an enhanced high - frequency image.

[0062] The processing device of the system further includes a high - frequency enhancement module, which is signal - connected to the first decomposition module and is used to receive the decomposed high - frequency image data. The enhancement processing uses a non - linear filtering algorithm to enhance the edge gradient features of high - frequency components and improve the sharpness of image details. Specifically, an adaptive gain coefficient is applied to each pixel point in the high - frequency image, and this coefficient is positively correlated with the variance of the pixel neighborhood, so that the detail contrast in the high - texture area is significantly improved. The high - frequency enhancement module realizes real - time processing through a parallel computing unit. The enhanced high - frequency image retains key information such as blood vessel edges and instrument contours, solving the problem of detail blurring caused by high - frequency information attenuation in traditional subtracted images. The technical effect is reflected in that the display resolution of tiny instruments such as guide wires and stents after enhancement is increased by more than 30%, and the noise amplification is controlled within 3 dB.

[0063] Optionally, the system further includes reconstructing the enhanced high - frequency image and the compressed low - frequency image.

[0064] The system configures a first reconstruction module, which includes a multi-scale fusion unit and a deconvolution unit. During reconstruction, the compressed low-frequency image and the enhanced high-frequency image are subjected to inverse Laplacian pyramid transformation, and the spatial resolution is restored through layer-by-layer upsampling and weighted superposition. Among them, the low-frequency image provides basic contrast information, and the high-frequency image injects detailed features. The two are smoothly transitioned through a cosine window function in the frequency domain overlapping area. The first reconstruction module adopts a double-buffer architecture to preload the next frame of data before the previous-stage processing is completed, ensuring that the reconstruction frame rate is not lower than 25fps. This design enables the fused image to have both a wide dynamic range and clear details, and the display compatibility of vascular wall calcification points and super-elastic guide wires is improved by 40%.

[0065] Optionally, the system locally compresses the low-frequency image to obtain a compressed low-frequency image, including: identifying the pixel points in the low-frequency image with the initial gray values in the set high threshold interval and low threshold space, and reducing the gray values of the pixel points.

[0066] The first compression module of the system integrates a dynamic range analysis unit, which has a built-in dual-threshold comparator: the high threshold interval is defined as [0.8Imax, Imax], and the low threshold interval is defined as [0, 0.2Imax], where Imax is the maximum gray value of the low-frequency image. For the over-bright pixels in the high threshold interval, the gray values are mapped to [0.7Imax, 0.9Imax] according to a piecewise linear function; for the underexposed pixels in the low threshold interval, they are mapped to [0.1Imax, 0.3Imax]. The slope of the mapping function is set to 0.5 - 0.8 to ensure that the local contrast compression rate in the high / low gray regions exceeds 60%, while the middle gray region maintains a linear mapping. This compression strategy reduces the gray difference between the vascular lumen and the surrounding tissues from the original 120HU to 50HU, effectively suppressing artifacts while retaining the anatomical structure continuity.

[0067] Optionally, the system superimposes the subtracted image on the contrast-enhanced fluoroscopic image, including performing a first weighting process on the subtracted image and a weighting process on the contrast-enhanced fluoroscopic image, and adding the weighted subtracted image and the weighted contrast-enhanced fluoroscopic image.

[0068] The superimposing module of the system includes two independently adjustable multiplier arrays, which respectively perform scalar weighting on the pixel gray values of the subtracted image and the fluoroscopic image. The first weighting process uses an α coefficient (0 ≤ α ≤ 1), and the second weighting process uses a β coefficient (0 ≤ β ≤ 1), where α + β = 1. The subtracted image is weighted by α to highlight the vascular path information, and the fluoroscopic image is weighted by β to retain the spatial positioning characteristics of the real-time image. The superimposed composite image is output in real time through an accumulator implemented by FPGA, where the signal-to-noise ratio between the vascular contour intensity and the background tissue reaches more than 18dB, and the catheter tip displacement tracking error is less than 0.5mm.

[0069] Optionally, the first weighting process includes a first weighting coefficient, and the second weighting process includes a second weighting coefficient, and the sum of the first weighting coefficient and the second weighting coefficient is 1.

[0070] The weighting coefficient generation module of the system adopts a normalization constraint algorithm. When the user adjusts the α coefficient (the first weighting coefficient), the β coefficient (the second weighting coefficient) is automatically calculated as 1 - α. This module includes a coefficient limiter that forcibly limits the input coefficient within the range of [0, 1] to prevent overmodulation. In hardware implementation, the coefficient is stored in a 16-bit fixed-point number format with a precision of 0.001. By dynamically balancing the weights of the subtracted image and the fluoroscopic image, it can not only ensure that the visualization intensity of the vascular tree is not less than 70%, but also maintain the depth perception of the real-time image, enabling the operator to simultaneously observe the advancement of the guide wire and the vascular anatomical structure.

[0071] Optionally, the terminal 130 of the system has a display device (input window) for inputting the first weighting coefficient, the second weighting coefficient, or the compression parameter.

[0072] The interaction interface of the terminal 130 of the system includes a touch screen input window, which receives the α and β coefficients and the compression threshold parameter input by the user through GUI controls. The input window communicates with the main control module through the SPI bus, and the parameter update delay is less than 10 ms. The window is embedded with a parameter verification unit that automatically filters illegal input values (such as negative numbers or out-of-range values) and previews the image effect in real time when the parameters are adjusted. This design enables the operator to dynamically optimize the image fusion ratio during the operation. For example, during the coil embolization stage, the subtracted weight (α = 0.8) is increased, while during the catheter navigation stage, the fluoroscopic weight (β = 0.7) is increased, and the operation efficiency is increased by 25%.

[0073] Optionally, the first modality image is the first subtracted image of the scanned area, and the second modality image is the second subtracted image of the scanned area, and the second modality image contains device information (guide wire, stent, coil, etc.).

[0074] A medical image processing system in the embodiment realizes target region enhancement through differential processing of two subtraction images. The first subtraction image is a vascular structure image after background tissue suppression obtained by digital subtraction angiography (DSA) technology, while the second subtraction image, on the basis of retaining the vascular structure, additionally includes the imaging information of medical devices (such as guide wires, stents, coils) used during interventional treatment. The technical effect of this dual-modal processing is that the first subtraction image can provide a clear vascular anatomical structure, while the second subtraction image can retain the device position information at the same time. The combination of the two can avoid the interference of device artifacts caused by traditional single subtraction. The principle is to eliminate background tissue noise through two independent subtraction operations. During the second subtraction process, device-compatible imaging parameters or contrast agent timing control are adopted, so that the imaging characteristics of high-density metal devices under X-rays are retained.

[0075] Optionally, the processing device is configured to perform the following processing on the first subtraction image and the second subtraction image: decompose the first subtraction image (Laplacian of Gaussian pyramid decomposition) to obtain a corresponding number of first high-frequency images and a first low-frequency image; decompose the second subtraction image (Laplacian of Gaussian pyramid decomposition) to obtain a corresponding number of second high-frequency images and a second low-frequency image; fuse the first low-frequency image and the second low-frequency image to obtain a fused low-frequency fused image (C); locally compress the low-frequency fused image to obtain a compressed low-frequency fused image; perform gray-scale transformation on the low-frequency fused image to obtain a low-frequency fused image with enhanced contrast (Cnew); perform weighting processing on the complex first high-frequency images respectively to obtain complex first weighted high-frequency images; perform weighting processing on the complex second high-frequency images respectively to obtain complex second weighted high-frequency images; perform synthesis processing on the complex first weighted high-frequency images and the corresponding complex first weighted high-frequency images respectively to obtain a plurality of complex synthesized high-frequency images (C1…Cn); reconstruct the plurality of complex synthesized high-frequency images (C1…Cn) and the low-frequency fused image with enhanced contrast (Cnew) to obtain a reconstructed subtraction image.

[0076] This embodiment defines the core process of multi-scale image fusion processing. The image is decomposed into different spatial frequency layers through Laplacian of Gaussian pyramid decomposition: the low-frequency layer contains the overall contour of blood vessels and the macroscopic morphology of instruments, and the high-frequency layer records the edge details of blood vessels and the micro-structure of instruments. When fusing the low-frequency components, the weighted summation method is used to integrate the low-frequency features of the two images, which can eliminate the noise interference in the low-frequency component of a single image. Local compression processing uses a non-linear transformation function to compress the dynamic range of the too-high or too-low gray-scale regions in the low-frequency image. Its technical effect is to suppress the background residual noise and enhance the contrast between the blood vessel wall and the surrounding tissues. In the gray-scale transformation stage, the gray-scale difference between the blood vessel lumen and the instrument is further enlarged through histogram equalization or S-shaped curve adjustment. In high-frequency processing, weight coefficients are set separately for different decomposition layers: the upper high-frequency layer focuses on retaining the geometric features of the instrument, and the lower high-frequency layer enhances the continuity of blood vessel branches. Finally, the optimized high-frequency and low-frequency components are fused through the pyramid reconstruction algorithm, and the technical effect is to achieve a balance among the clarity of blood vessel structure, accurate imaging of the instrument position, and suppression of background noise simultaneously.

[0077] Optionally, the local compression of the low-frequency fused image to obtain the compressed low-frequency fused image includes: dynamically identifying the pixel points in the low-frequency fused image with initial gray-scale values in the set high threshold interval and low threshold space, and reducing the gray-scale values of the pixel points.

[0078] This embodiment improves the dynamic range control method of the low-frequency component. By analyzing the histogram distribution of the image in real time, the high threshold T_high (such as higher than the 98th percentile) and the low threshold T_low (such as lower than the 2nd percentile) are automatically determined, and non-linear compression is performed on the pixels exceeding the threshold: logarithmic transformation is used for the high gray-scale region to suppress the overexposure artifacts of metal instruments, and exponential transformation is applied to the low gray-scale region to enhance the visibility of dark part details. The technical effect of this processing is to solve the problem of contrast loss caused by traditional linear compression, and while retaining the texture information of the blood vessel wall, prevent signal saturation in the high-density instrument area.

[0079] Optionally, the local compression of the low-frequency fused image to obtain the compressed low-frequency fused image includes: obtaining the initial gray-scale curve representing the contrast of the pixel points of the low-frequency fused image, and locally compressing both ends of the initial gray-scale curve.

[0080] This embodiment optimizes the grayscale mapping strategy. The initial grayscale curve reflects the global mapping relationship between the input and output grayscale values. By performing segmented processing on both ends of the curve: in the high-brightness region (such as input grayscale > 200), linear compression with a slope of 0.5 is adopted; in the shadow region (input grayscale < 50), compression with a slope of 0.3 is adopted; and the middle region maintains a 1:1 mapping. The technical effect of this asymmetric compression is to expand the dynamic range of the middle gray level, amplify the grayscale difference between the blood vessel wall and the in-vessel blood flow, and between the instrument and the blood vessel wall, while suppressing the interference of irrelevant information in the extreme grayscale value region.

[0081] Optionally, the local compression processing of both ends of the initial grayscale curve includes: dynamically adjusting the local slopes of both ends of the initial grayscale curve so that the local slopes of both ends of the adjusted initial grayscale curve are less than the slope of the initial grayscale curve.

[0082] This embodiment further refines the grayscale curve adjustment mechanism. The slope adjustment changes adaptively based on the image content: when dense instrument structures are detected in the high-frequency components, the slope in the high-brightness region is increased to 0.6 to retain the sharpness of the metal instrument edges; when the low-frequency components show a large area of low-contrast regions, the slope in the shadow region is reduced to 0.2 to enhance the tissue layering. The technical effect of this dynamic adjustment is to overcome the loss of details caused by fixed-parameter compression and maintain the integrity of important anatomical structures while enhancing the overall contrast.

[0083] Optionally, fusing the first low-frequency image and the second low-frequency image to obtain a fused low-frequency fused image (C) includes performing weighted processing on the first low-frequency image and the second low-frequency image respectively, and performing summation processing on the first weighted low-frequency image and the second weighted low-frequency image.

[0084] This embodiment formulates a specific implementation method for low-frequency fusion. Set the first low-frequency weight coefficient α (0.6 - 0.8) to emphasize retaining the smooth transition characteristics of the blood vessel wall, and the second low-frequency weight coefficient β (0.2 - 0.4) to introduce the contour information of the instrument, satisfying the constraint condition of α + β = 1. Before the summation processing, perform spatial registration on the two low-frequency images to eliminate pixel misalignment caused by patient movement or heartbeat. The technical effect of this weighted fusion is to comprehensively utilize the advantageous information of the two subtractions: the first low-frequency image provides a stable vascular anatomical framework, and the second low-frequency image supplements the spatial reference of the instrument position, thereby generating a fused base image with both structural accuracy and instrument visibility.

[0085] Please refer to Figures 3-4 , a medical image processing method disclosed in an embodiment of the present application, the processing method of the medical image is executed by a medical image processing system, and includes the following steps:

[0086] Step 101: Obtain the first modality image (subtraction image) and the second modality image (fluoroscopy image) of the object to be scanned.

[0087] Step 102: Decompose the second modality image (Laplacian of Gaussian pyramid decomposition) to obtain the corresponding high-frequency image and low-frequency image.

[0088] Step 103: Locally compress the low-frequency image to obtain the compressed low-frequency image.

[0089] Step 104: Reconstruct the compressed low-frequency image and the high-frequency image to obtain the reconstructed second modality image (fluoroscopy image).

[0090] Step 105: Perform grayscale transformation on the reconstructed second modality image (fluoroscopy image) to obtain the second modality image (fluoroscopy image) with enhanced contrast.

[0091] Step 106: Superimpose the first modality image (subtraction image) on the second modality image (fluoroscopy image) with enhanced contrast.

[0092] Optionally, the first modality image is a subtraction image of the scanned area, and the second modality image is a fluoroscopy image of the scanned area. The first modality image is obtained by subtraction processing of two fluoroscopy images collected by a DSA device. One of the two fluoroscopy images is obtained by scanning the object to be scanned with a DSA device after injecting a contrast agent into the object to be scanned, and the other of the two fluoroscopy images is obtained by scanning the object to be scanned with a DSA device after not injecting a contrast agent into the object to be scanned or when the concentration of the contrast agent in the object to be scanned is lower than a set threshold. The second modality image is obtained before injecting a contrast agent into the object to be scanned or after a set time threshold after injecting a contrast agent into the object to be scanned.

[0093] Optionally, the locally compressing the low-frequency image to obtain the compressed low-frequency image includes obtaining an initial gray curve representing the contrast of the pixel points of the low-frequency image, and locally compressing both ends of the initial gray curve. The locally compressing both ends of the initial gray curve includes: dynamically adjusting the local slopes of both ends of the initial gray curve so that the local slopes of both ends of the adjusted initial gray curve are less than the slope of the initial gray curve.

[0094] Optionally, the medical image processing system is further configured to perform the following steps for high-frequency image processing: Step 103A: Enhance the high-frequency image to obtain the enhanced high-frequency image. Reconstruct the enhanced high-frequency image and the compressed low-frequency image, and return to Step 104 to continue executing the above Steps 105-106.

[0095] Optionally, locally compressing the low-frequency image to obtain a compressed low-frequency image includes: identifying pixel points in the low-frequency image with initial gray values in a set high threshold interval and low threshold space, and reducing the gray values of the pixel points.

[0096] Optionally, superimposing the subtracted image onto the contrast-enhanced fluoroscopic image includes performing a first weighting process on the subtracted image and a weighting process on the contrast-enhanced fluoroscopic image, and adding the weighted subtracted image and the weighted contrast-enhanced fluoroscopic image.

[0097] Optionally, the first weighting process includes a first weighting coefficient, the second weighting process includes a second weighting coefficient, and the sum of the first weighting coefficient and the second weighting coefficient is 1.

[0098] Optionally, the first modality image is the first subtracted image of the scanned area, the second modality image is the second subtracted image of the scanned area, and the second modality image contains equipment information (guide wire, stent, coil).

[0099] Please refer to Figure 5 , a method for processing medical images disclosed in another embodiment of the present application, the method for processing medical images is executed by a processing device (processor) of the system, and includes the following steps:

[0100] Step 201, obtaining a first modality image (first subtracted image) and a second modality image (second subtracted image) of the scanned object;

[0101] Step 202, decomposing the first modality image (first subtracted image) (Laplacian pyramid decomposition of Gaussian) to obtain a corresponding number (complex) of first high-frequency images and a first low-frequency image; decomposing the second modality image (second subtracted image) (Laplacian pyramid decomposition of Gaussian) to obtain a corresponding number (complex) of second high-frequency images and a second low-frequency image;

[0102] Step 203, fusing the first low-frequency image and the second low-frequency image to obtain a fused low-frequency fused image (C);

[0103] Step 204, locally compressing the low-frequency fused image to obtain a compressed low-frequency fused image;

[0104] Step 205, performing a gray level transformation on the low-frequency fused image to obtain a contrast-enhanced low-frequency fused image (Cnew);

[0105] Step 206, performing a weighting process on each of the complex first high-frequency images to obtain complex first weighted high-frequency images; performing a weighting process on each of the complex second high-frequency images to obtain complex second weighted high-frequency images;

[0106] Step 207: Perform synthesis processing on the plural first weighted high-frequency images and the corresponding plural first weighted high-frequency images respectively to obtain plural synthesized high-frequency images (C1…Cn).

[0107] Step 208: Perform reconstruction (fusion) on the plural synthesized high-frequency images (C1…Cn) and the contrast-enhanced low-frequency fusion image (Cnew) to obtain the reconstructed medical image (subtraction image).

[0108] Optionally, the above steps 206-207 can be processed in the manner or in sequence corresponding to steps 206A-207A in Figure 5 , that is, executed in parallel with the low-frequency image processing steps 203-205 in Figure 5 to improve the efficiency of image processing.

[0109] Optionally, the local compression of the low-frequency fusion image to obtain the compressed low-frequency fusion image includes: dynamically identifying the pixel points in the low-frequency fusion image with the initial gray values in the set high threshold interval and low threshold space, and reducing the gray values of the pixel points in the set high threshold interval and low threshold space.

[0110] Optionally, the local compression of the low-frequency fusion image to obtain the compressed low-frequency fusion image includes: obtaining the initial gray curve representing the contrast of the pixel points of the low-frequency fusion image, and locally compressing both ends of the initial gray curve.

[0111] Optionally, the local compression processing of both ends of the initial gray curve includes: dynamically adjusting the local slopes of both ends of the initial gray curve so that the local slopes of both ends of the adjusted initial gray curve are less than the slope of the initial gray curve.

[0112] Optionally, the fusion of the first low-frequency image and the second low-frequency image to obtain the fused low-frequency fusion image (C) includes performing weighted processing on the first low-frequency image and the second low-frequency image respectively, and performing summation processing on the first weighted low-frequency image and the second weighted low-frequency image.

[0113] Please refer to Figure 6 , another embodiment of the present application discloses a processing system for medical images, and its processing device (processor) 140A includes the following modules: a second acquisition module 2401, a second decomposition module 2402, a fusion module 2403, a second compression module 2404, a second transformation module 2405, a weighting module 2406, a synthesis module 2407, and a second reconstruction module 2408. Each module is communicatively connected and realizes data exchange.

[0114] The second acquisition module 2401 is configured to execute step 201 to acquire a first modality image (first subtracted image) and a second modality image (second subtracted image) of the object to be scanned;

[0115] The second decomposition module 2402 is configured to execute step 202 to decompose the first modality image (first subtracted image) (Laplacian of Gaussian pyramid decomposition) to obtain a plurality of (complex) first high-frequency images and a first low-frequency image corresponding thereto; decompose the second modality image (second subtracted image) (Laplacian of Gaussian pyramid decomposition) to obtain a plurality of (complex) second high-frequency images and a second low-frequency image corresponding thereto;

[0116] The fusion module 2403 is configured to execute step 203 to fuse the first low-frequency image and the second low-frequency image to obtain a fused low-frequency fusion image (C);

[0117] The second compression module 2404 is configured to execute step 204 to locally compress the low-frequency fusion image to obtain a compressed low-frequency fusion image;

[0118] The second transformation module 2405 is configured to execute step 205 to perform a gray-scale transformation on the low-frequency fusion image to obtain a low-frequency fusion image (Cnew) with enhanced contrast;

[0119] The weighting module 2406 is configured to execute step 206 to perform weighting processing on the complex first high-frequency images respectively to obtain complex first weighted high-frequency images; perform weighting processing on the complex second high-frequency images respectively to obtain complex second weighted high-frequency images;

[0120] The synthesis module 2407 is configured to execute step 207 to perform synthesis processing on the complex first weighted high-frequency images and the corresponding complex first weighted high-frequency images respectively to obtain a plurality of complex synthesized high-frequency images (C1…Cn);

[0121] The second reconstruction module 2408 is configured to execute step 208 to reconstruct (fuse) the plurality of complex synthesized high-frequency images (C1…Cn) and the low-frequency fusion image (Cnew) with enhanced contrast to obtain a reconstructed medical image (subtracted image).

[0122] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0123] The above embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patented application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A medical image processing system, characterized in that: The medical image processing system comprises: a processor and a display, wherein the display is communicatively connected with the processor, and the medical image processing system is configured as follows: Acquire a first modality image and a second modality image of a scanned object; Decomposing the second modality image to obtain a corresponding high-frequency image and a low-frequency image; Locally compressing the low-frequency image to obtain a compressed low-frequency image; Reconstructing the compressed low-frequency image and high-frequency image to obtain a reconstructed second modality image; Performing grayscale transformation on the reconstructed second modality image to obtain a contrast-enhanced second modality image; The first modality image is superimposed on the contrast enhanced second modality image.

2. The system according to claim 1, characterized in that The locally compressing the low-frequency image to obtain the compressed low-frequency image includes acquiring an initial grayscale curve representing the contrast of pixels of the low-frequency image and locally compressing both ends of the initial grayscale curve.

3. The system according to claim 2, characterized in that The locally compressing the two ends of the initial grayscale curve includes: dynamically adjusting the local slopes of the two ends of the initial grayscale curve so that the adjusted local slopes of the two ends of the initial grayscale curve are smaller than the slope of the initial grayscale curve.

4. The system according to any one of claims 1 to 3, characterized in that: The method also includes performing enhancement processing on the high-frequency image to obtain an enhanced high-frequency image.

5. The system according to claim 4, characterized in that It also includes the reconstruction of the enhanced high-frequency image and the compressed low-frequency image.

6. The system according to claim 1, characterized in that The locally compressing the low-frequency image to obtain a compressed low-frequency image includes: identifying pixels whose initial grayscale values ​​in the low-frequency image are in a set high threshold interval and a low threshold space, and reducing the grayscale values ​​of the pixels in the set high threshold interval and the low threshold space.

7. The system according to claim 1, characterized in that The superimposing of the first modality image onto the contrast-enhanced second modality image includes performing a first weighted processing on the first modality image and a second weighted processing on the contrast-enhanced second modality image, and adding the weighted first modality image and the weighted contrast-enhanced second modality image.

8. The system according to claim 7, characterized in that The first weighting process includes a first weighting coefficient, the second weighting process includes a second weighting coefficient, and the sum of the first weighting coefficient and the second weighting coefficient is 1.

9. The system according to claim 1, characterized in that The first modality image is a first subtraction image of the scanned area, the second modality image is a second subtraction image of the scanned area, and the second modality image contains equipment information.

10. A medical image processing method, the medical image processing method being performed by a medical image processing system, comprising the following steps: Acquire a first modality image and a second modality image of a scanned object; Decomposing the second modality image to obtain a corresponding high-frequency image and a low-frequency image; Locally compressing the low-frequency image to obtain a compressed low-frequency image; Reconstructing the compressed low-frequency image and high-frequency image to obtain a reconstructed second modality image; Performing grayscale transformation on the reconstructed second modality image to obtain a contrast-enhanced second modality image; The first modality image is superimposed on the contrast enhanced second modality image.

Images