Image processing methods, image processing devices and medical equipment

Abstract

This application provides an image processing method, an image processing apparatus, and a medical device. The image processing method includes: acquiring an image to be processed, wherein the image to be processed is a medical image; performing at least two iterations on the image to be processed based on a preset processing model to obtain an initial detail texture image and a denoised image in each iteration, wherein each iteration includes the following steps: acquiring image parameters of the image to be processed input to the processing model; extracting detail texture information from the corresponding image to be processed based on the image parameters to obtain an initial detail texture image, wherein the detail texture information includes at least one of the following: vascular information, nerve information, tissue texture information, and lesion texture information; performing denoising processing on the image to be processed based on the image parameters to obtain a denoised image after filtering; and fusing the denoised image and the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture.

Description

Technical Field

[0001] This invention relates generally to the field of image processing technology, and more specifically to an image processing method, an image processing device, and a medical device. Background Technology

[0002] With the widespread use of various digital instruments and products, images have become the most commonly used information carrier in human activities. However, during the acquisition, transmission, and storage of images, various noises often interfere with and affect the image quality, leading to degradation. Furthermore, the quality of image preprocessing algorithms directly impacts the effectiveness of subsequent image processing, such as image segmentation, target recognition, and edge extraction. Therefore, to obtain high-quality digital images, noise reduction is essential. The challenge of image noise reduction lies in reducing noise while preserving image details, which has always been a hot research topic in image processing and computer vision. On the other hand, it is also necessary to enhance image details to make them more easily perceived by the human eye. However, most common image processing algorithms currently separate image denoising and image enhancement, generally requiring significant computational resources to achieve good results. This makes these algorithms unsuitable for processing chips with limited computational resources, especially Field Programmable Gate Arrays (FPGAs).

[0003] In view of the above problems, this application proposes a new image processing method, image processing device and medical device. Summary of the Invention

[0004] The present invention is proposed to solve at least one of the above problems.

[0005] A first aspect of this application provides an image processing method, the method comprising:

[0006] Acquire an image to be processed, wherein the image to be processed is a medical image;

[0007] The image to be processed is subjected to at least two iterations based on a preset processing model, in order to obtain an initial detailed texture image and a denoised image in each iteration. Each iteration includes the following steps:

[0008] Obtain the image parameters of the image to be processed that are input into the processing model;

[0009] Based on the image parameters, extract the detailed texture information from the corresponding image to be processed to obtain an initial detailed texture image, wherein the detailed texture information includes at least one of the following: blood vessel information, nerve information, tissue texture information, and lesion texture information;

[0010] The image to be processed is denoised based on the image parameters to obtain a denoised image after filtering.

[0011] The denoised image is fused with the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture.

[0012] Optionally, the processing model processes the image to be processed through iterative parameters, the iterative parameters including at least one of a first parameter, a second parameter, and a third parameter, wherein the first parameter is used to control the contribution of the denoising intensity term to the denoised image, the second parameter is used to control the contribution of the denoising sharpening term to the denoised image, and the third parameter is used to control the contribution of the sharpening supplement term to the denoised image.

[0013] Optionally, the image parameters corresponding to the image to be processed in each iteration include the total gradient of the image to be processed and the gradient of the image to be processed in the normal direction.

[0014] Optionally, when the image to be processed is an image in the RGB color space, the method further includes:

[0015] The image to be processed is converted from the RGB color space to the first color space to obtain a converted image in the first color space;

[0016] Extract the image information of the transformed image, wherein the image information of the transformed image includes the pixel matrix of the luminance component and the pixel matrix of the chrominance component.

[0017] Optionally, the image to be processed based on the preset processing model undergoes at least two iterations, including:

[0018] The transformed image is input into the processing model as the image to be processed for the first iteration to obtain the initial iterative image;

[0019] The initial iterative image is used as the updated image to be processed and input into the processing model for a second iteration to obtain the secondary iterative image.

[0020] Optionally, fusing the denoised image and the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture includes:

[0021] Obtain the initial detail texture images corresponding to each iteration, and fuse the initial detail texture images to obtain a target detail image with clear texture;

[0022] The target detail image and the denoised image are fused together to obtain a processed medical image with clear texture.

[0023] Optionally, the image information of the target detail image includes a first pixel matrix containing a luminance component, and the image information of the denoised image includes a second pixel matrix containing a luminance component. The step of fusing the denoised image and the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture includes:

[0024] The first pixel matrix and the second pixel matrix are fused to obtain a fused pixel matrix of luminance components;

[0025] The fused pixel matrix and the pixel matrix of the chromaticity component of the transformed image are combined into a composite image matrix in the first color space;

[0026] The synthesized image matrix is ​​converted from the first color space to the RGB color space to obtain a processed medical image with clear texture.

[0027] A first aspect of this application provides an image processing method, the method comprising:

[0028] Acquire an image to be processed, including a medical image;

[0029] The image parameters of the image to be processed are obtained based on a preset processing model;

[0030] Based on the image parameters, the detailed texture information of the image to be processed is extracted to obtain a detailed texture image, wherein the detailed texture information includes at least one of the following: blood vessel information, nerve information, and tissue texture information;

[0031] The image to be processed is denoised based on the image parameters to obtain a denoised image after filtering.

[0032] The detailed texture image and the denoised image are fused together to obtain a processed medical image with clear texture.

[0033] A third aspect of this application provides an image processing apparatus, comprising:

[0034] Memory is used to store executable program instructions;

[0035] The processor is also configured to execute the program instructions stored in the memory, causing the processor to perform the image processing method described above.

[0036] Optionally, the image processing apparatus further includes a display for displaying the medical image.

[0037] A fourth aspect of this application provides a medical device, the medical device comprising:

[0038] An image acquisition device is used to acquire images of the parts of a target object to be observed, in order to obtain the original image to be processed.

[0039] The image processing device described above.

[0040] Specifically, the image processing methods provided in the first and second aspects of this application have the following advantages:

[0041] 1. This method extracts image parameters through a preset processing model and applies these image parameters to denoising and detail texture extraction, thereby integrating the image denoising process and the image detail texture enhancement process simultaneously, reducing the amount of computation, and achieving good denoising and detail texture enhancement effects.

[0042] 2. Since the noise reduction process and the detail texture enhancement process of this application are integrated and performed simultaneously, compared with the method of performing the noise reduction process and the detail texture enhancement process separately, the method of this application can be implemented without consuming too many computing resources, and can be deployed on some processing chips with limited computing resources, such as on a single FPGA chip.

[0043] A third aspect of this application provides an image processing apparatus that, since it is capable of performing the aforementioned image processing method, has substantially the same advantages as the aforementioned image processing method.

[0044] The fourth aspect of this application provides a medical device that, since the medical device includes the aforementioned image processing apparatus, which is capable of performing the aforementioned image processing method, has substantially the same advantages as the aforementioned image processing method. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A schematic block diagram of an image processing apparatus according to one embodiment of the present invention is shown;

[0047] Figure 2 A flowchart of an image processing method according to one embodiment of the present invention is shown;

[0048] Figure 3 A flowchart illustrating the steps included in each iteration of the image processing method according to an embodiment of the present invention is shown.

[0049] Figure 4A flowchart of an image processing method according to another embodiment of the present invention is shown;

[0050] Figure 5 A schematic block diagram of an endoscope system according to one embodiment of the present invention is shown. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0052] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.

[0053] It should be understood that the invention can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0054] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0055] To fully understand this invention, detailed image processing methods and apparatus will be presented in the following description to illustrate the technical solutions proposed by this invention. Optional embodiments of the invention are described in detail below; however, in addition to these detailed descriptions, the invention may have other embodiments.

[0056] Specifically, the image processing method and apparatus of this application will be described in detail below with reference to the accompanying drawings. Unless otherwise specified, the features of the following embodiments and implementations can be combined with each other.

[0057] Below, please refer to the appendix. Figure 1 An image processing apparatus according to one embodiment of the present invention will be described.

[0058] like Figure 1 As shown, the image processing apparatus 100 includes one or more processors 101, a memory 102, a display 103, and a communication interface (not shown). These components are interconnected via a bus system and / or other forms of connection mechanisms (not shown). It should be noted that... Figure 1 The components and structures of the image processing apparatus 100 shown are merely exemplary and not limiting; the image processing apparatus 100 may also have other components and structures as needed.

[0059] Memory 102 is used to store various data and executable programs generated during image processing, such as system programs for image processing devices, various application programs, or algorithms that implement various specific functions. It may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0060] Processor 101 may be a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other processing units with data processing and / or instruction execution capabilities, and may control other components in the monitoring system to perform desired functions. For example, the processor may include one or more embedded processors, processor cores, microprocessors, logic circuits, hardware finite state machines (FSMs), digital signal processors (DSPs), graphics processing units (GPUs), or combinations thereof.

[0061] The processor 101 can be used to execute program instructions stored in memory, causing the processor to perform the image processing method described below.

[0062] In one example, the image processing apparatus 100 also includes a communication interface (not shown) for communication between the various components of the image processing apparatus 100 and between the various components of the image processing apparatus 100 and other devices outside the system (e.g., remote devices).

[0063] The communication interface can be an interface based on any known communication protocol, such as a wired or wireless interface. The communication interface may include one or more serial ports, USB interfaces, Ethernet ports, WiFi, wired networks, DVI interfaces, device integrated interconnect modules, or other suitable ports, interfaces, or connections. The image processing device 100 can also access wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G, 5G, or combinations thereof. In one exemplary embodiment, the communication interface receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication interface also includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0064] In one example, the image processing device 100 also includes an input device (not shown), which may be a device used by a user to input instructions, and may include one or more of a keyboard, trackball, mouse, microphone and touch screen, or other input devices consisting of control buttons.

[0065] The image processing apparatus 100 of this embodiment of the invention also includes an output device, which can output various information (such as images or sounds) to the outside (e.g., a user), and may include one or more of a display, a speaker, etc.

[0066] In one example, the image processing device 100 also includes one or more displays 103, which are used to display at least any visual information, such as the image to be processed, a processed, textured medical image, an image parameter adjustment interface, etc.

[0067] The image processing device 100 may also include a user interface through which a user can control the operation of the image processing device 100. The user interface may include a display 103, which may include a touchscreen allowing the user to input operation commands to the image processing device 100 from the display 103, and / or include one or more control panels, through which the user can control the operation of the monitoring system.

[0068] It should be noted that the image processing device 100 described above can serve as the execution subject of the image processing method described below. The image processing device 100 can be part of a medical device, which includes, but is not limited to, any device capable of acquiring medical images of a target object, such as an endoscope system, or the image processing device 100 can also be all or part of a computer device that is communicatively connected to the medical device.

[0069] With the widespread use of various digital instruments and products, images have become the most commonly used information carrier in human activities. However, during the acquisition, transmission, and storage of images, various noises often interfere with and affect the image quality, leading to degradation. Furthermore, the quality of image preprocessing algorithms directly impacts the effectiveness of subsequent image processing, such as image segmentation, target recognition, and edge extraction. Therefore, to obtain high-quality digital images, image denoising is essential. The challenge of image denoising lies in reducing noise while preserving image details, a hot topic in image processing and computer vision research. On the other hand, it's also necessary to enhance image details to make them more easily perceived by the human eye. However, most common image processing algorithms currently separate image denoising and image enhancement, generally requiring significant computational resources to achieve good results. The rise of edge computing in recent years has highlighted the advantages of low-power, high-speed parallel computing, particularly in mobile and portable devices. However, FPGA computing resources are very limited, resulting in less than ideal performance of common image processing algorithms on FPGAs. Therefore, achieving high-quality image denoising and image enhancement on FPGAs has become an urgent need in today's technology market.

[0070] In view of the above problems, this application proposes an image processing method, comprising: first, acquiring an image to be processed, wherein the image to be processed is a medical image; then, performing at least two iterations on the image to be processed based on a preset processing model, so as to obtain an initial detail texture image and a denoised image in each iteration, wherein each iteration includes the following steps: acquiring image parameters of the image to be processed input to the processing model; extracting detail texture information in the corresponding image to be processed according to the image parameters to obtain an initial detail texture image, wherein the detail texture information includes at least one of the following: vascular information, nerve information, tissue texture information, lesion texture information; performing denoising processing on the image to be processed based on the processing model and image parameters to obtain a denoised image after denoising; finally, fusing the denoised image and the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture.

[0071] Below, for reference Figures 2 to 4 The image processing method of this application is described, wherein, Figure 2 A flowchart of an image processing method according to one embodiment of the present invention is shown; Figure 3 A flowchart illustrating the steps included in each iteration of the image processing method according to an embodiment of the present invention is shown. Figure 4 A flowchart of an image processing method according to another embodiment of the present invention is shown.

[0072] In one embodiment, firstly, as Figure 2 As shown, in step S210, the image to be processed is acquired.

[0073] The image to be processed can be the original image, which has not yet undergone any subsequent iterations. This original image can be an image of the target object's tissue region acquired by an image acquisition device, or it can be an image of the target object's tissue region obtained by other imaging devices. For example, the original image to be processed can be obtained by capturing images using the camera system of an endoscope. The tissue region of the target object can be a portion of the tissue to be examined (also called the site to be observed), such as the intestines, stomach, etc.

[0074] The original image to be processed can be an RGB color space image containing real noise, or an image in another color space.

[0075] Then, continue as follows Figure 2 As shown, in step S220, the image to be processed is subjected to at least two iterations based on a preset processing model, so as to obtain an initial detail texture image and a denoised image in each iteration.

[0076] In one example, the image processing method of this application further includes the step of extracting the pixel matrix of the luminance component and the pixel matrix of the chrominance component of the image to be processed. Optionally, when the image to be processed is an image in the RGB color space, the method of this application further includes: converting the image to be processed (e.g., the original image to be processed mentioned above) from the RGB color space to a first color space to obtain a converted image in the first color space; extracting image information of the converted image, wherein the image information of the converted image includes the pixel matrix of the luminance component and the pixel matrix of the chrominance component, optionally, the pixel matrix of the chrominance component further includes the pixel matrix of the Cb component and the pixel matrix of the Cr component, optionally, the first color space includes the YCbCr color space, or other color spaces that can separate the luminance component and the chrominance component. The steps of color space and extraction of luminance and chrominance components can be performed during the iteration process or before the iteration, for example, before the first iteration.

[0077] The color space of the image to be processed can be converted from the RGB color space to the YCbCr color space using any suitable method well known to those skilled in the art. For example, the conversion can be performed using the following formula:

[0078] Y=0.257*R+0.564*G+0.098*B+16

[0079] Cb=-0.148*R-0.291*G+0.439*B+128

[0080] Cr=0.439*R-0.368*G-0.071*B+128

[0081] It is worth mentioning that the pixel matrix of the luminance component in this application refers to the matrix composed of the luminance component values ​​of all pixel units in the entire image.

[0082] In one example, the image to be processed is subjected to at least two iterations based on a preset processing model to obtain an initial detailed texture image and a denoised image in each iteration, including: performing at least two iterations on the pixel matrix of the luminance component based on the preset processing model to obtain an initial detailed texture image and a denoised image in each iteration.

[0083] Optionally, the preset processing model can be any processing model that can be used for denoising, such as partial differential equations. Based on this preset processing model, image parameters of the image to be processed can be obtained while filtering noise from the input image.

[0084] Optionally, such as Figure 3 As shown, each iteration process includes the following steps S221 to S223: In step S221, the image parameters of the image to be processed input to the processing model are obtained; in step S222, the detailed texture information in the corresponding image to be processed is extracted according to the image parameters to obtain the initial detailed texture image; in step S223, the image to be processed is denoised based on the image parameters to obtain the denoised image after denoising.

[0085] It is worth mentioning that the order of steps S221 to S223 can be interchanged or performed simultaneously without conflict. For example, step S223 can be performed after step S221. Alternatively, steps S221 and S223 can be performed simultaneously. That is, while obtaining the image parameters of the image to be processed input to the processing model, the image to be processed is denoised based on the image parameters to obtain a denoised image. Or, steps S221 and S223 can both be performed based on the processing model. For example, the image to be processed is denoised based on the processing model to obtain a denoised image, and the image parameters of the image to be processed input to the processing model are obtained simultaneously based on the processing model.

[0086] Optionally, the preset processing model can be any processing model that can be used for denoising, such as partial differential equations.

[0087] For example, the image parameters corresponding to the image to be processed in each iteration include the total gradient of the image to be processed. and the gradient of the image to be processed in the normal direction That is, in each iteration, the image parameters are input to the input image in the processing model, such as a partial differential equation.

[0088] In one example, the image to be processed is subjected to at least two iterations based on a preset processing model, including: inputting the transformed image as the image to be processed into the processing model for the first iteration to obtain the initial iterative image; and inputting the initial iterative image as the updated image to be processed into the processing model for the second iteration to obtain the secondary iterative image. That is, the image to be processed in the first iteration is the transformed image, and the denoised image after the previous iteration is used as the image to be processed in the processing model for the next iteration. The image to be processed in the first iteration is the transformed image. For example, the original image to be processed can be an image in the RGB color space containing real noise. The color space of the image to be processed (e.g., the original image to be processed) is converted from the RGB color space to the first color space to obtain the transformed image in the first color space.

[0089] For example, image parameters can be obtained while denoising the image to be processed, based on the following denoising and sharpening partial differential equation (Equation (1)):

[0090]

[0091] Among them, I out I represents the output image, and 'I' represents the input image. This indicates the intensity term controlling the noise reduction.

[0092] This represents the sharpening term, where, γ represents the texture detector, and γ·(I-υ) represents the sharpening complement.

[0093] It is worth mentioning that the input image can correspond to a pixel matrix that includes the luminance component of the input image, and the output image can correspond to a pixel matrix that includes the luminance component of the output image.

[0094] Based on the denoising and sharpening partial differential equation, after one iteration, the total gradient of the image to be processed generated in the current iteration can be obtained. and the gradient of the image to be processed in the normal direction These parameters can be used not only for noise filtering, but also for extracting detailed textures to obtain detailed texture images.

[0095] Optionally, texture is used to characterize the surface properties of an image or the target corresponding to an image region. In this application, detailed texture information includes at least one of the following: vascular information, neural information, tissue texture information, lesion texture information, or may also include other texture information.

[0096] In step S222, the detailed texture information in the image to be processed can be extracted based on the image parameters using any suitable method to obtain an initial detailed texture image. For example, it can be based on statistical methods, geometric methods, model methods, signal processing methods, etc. Among them, statistical methods can include texture feature analysis methods of gray-level co-occurrence matrix, image autocorrelation function, semivariogram, etc.

[0097] In one example, this application can extract image textures based on the following image texture extraction equation and the obtained image parameters. The formula for the image texture extraction equation is as follows:

[0098]

[0099] I represents the input image. This represents the total gradient of the input image (i.e., the image to be processed input in each iteration). Let represent the gradient of the input image along the normal direction, where Since the image is obtained during the denoising process, compared to methods that perform denoising and detail texture enhancement separately, this application utilizes the image parameters obtained during the denoising process to extract the detail texture information in the corresponding image to be processed, thereby obtaining an initial detail texture image. This method extracts image parameters through a preset processing model and applies these image parameters to denoising and detail texture extraction, thereby integrating the image denoising process and the image detail texture enhancement process simultaneously, reducing the amount of computation, and achieving good denoising and detail texture enhancement effects. Since the denoising process and detail texture enhancement process of this application are integrated and performed simultaneously, compared to methods that separate the denoising process and detail texture enhancement, the method of this application can be implemented without consuming too many computing resources and can be deployed on some processing chips with limited computing resources, such as on a single FPGA chip.

[0100] In step S223, the image to be processed can also be denoised based on the image parameters and the anisotropic denoising method to obtain the denoised image after filtering. The anisotropic denoising method can be any suitable method known to those skilled in the art. For example, the anisotropic denoising method is a denoising method based on partial differential equations. The partial differential equation is, for example, the partial differential equation shown in formula (1) above, or it can be other types of partial differential equations that require the use of image parameters.

[0101] It is worth mentioning that after obtaining the pixel matrix of the luminance component of the image to be processed, each iteration of the image to be processed can be an iteration of the pixel matrix of the luminance component of the image to be processed. The initial detail texture image and the denoised image obtained in each iteration can both be represented by the pixel matrix of the luminance component.

[0102] The processing model includes multiple iterative parameters, wherein the iterative parameters are adjustable during each iteration. The iterative parameters include at least one of a first parameter, a second parameter, and a third parameter. The first parameter is used to control the contribution of the denoising intensity term to the denoised image, the second parameter is used to control the contribution of the denoising sharpening term to the denoised image, and the third parameter is used to control the contribution of the sharpening supplement term to the denoised image.

[0103] For example, the processing model includes the denoising and sharpening partial differential equation shown in formula (1). Then, the multiple iteration parameters are α, β, k, b, and γ. For example, the first parameter includes α, the second parameter includes one or more of the following parameters: β, k, and b, and the third parameter includes γ. During the iteration process, the user's input instructions for each iteration parameter can be obtained, and the corresponding iteration parameter can be adjusted to the value corresponding to the value indicated by the input instruction.

[0104] Users can also adjust the iteration parameters according to the desired image effect in the actual scenario. Image effect refers to the denoising effect and detail / texture enhancement effect achievable after image processing. In practical applications, users usually want the image to have as little noise as possible, while the image details and textures should be as clear and sharp as possible. However, in current image processing algorithms, the parameters controlling denoising and detail / texture enhancement are not completely independent, but rather mutually influential. If the denoising effect is stronger, the detail enhancement will be weaker, and vice versa. Therefore, in practical applications, we will strike a balance between these two effects based on the specific usage environment. For example, the method of this application may also include: adjusting the iteration parameters according to the application scenario of the medical equipment (e.g., an endoscope system) used to acquire the image to be processed. Different departments may correspond to different iteration parameters, or some iteration parameters may be the same while others are different.

[0105] The number of iterations can be at least two, for example, two, three, four, five, etc. Each iteration produces one denoised image and one initial detail texture image. If four iterations are performed, four denoised images and four initial detail texture images will be produced. Since each subsequent iteration usually uses the denoised image from the previous iteration as input, the denoising effect of the denoised image after each subsequent iteration is usually better than that of the previous iteration.

[0106] Finally, continue as follows Figure 2 As shown, the denoised image and the initial detail texture image obtained in each iteration are fused to obtain a processed medical image with clear texture.

[0107] Since at least two initial detail texture images and at least two denoised images have been obtained through the aforementioned steps, in one example, the denoised images and the initial detail texture images obtained in each iteration are fused to obtain a processed medical image with clear texture. This includes: obtaining each initial detail texture image obtained in each iteration; fusing the initial detail texture images to obtain a target detail image with clear texture; and fusing the target detail image and the denoised images to obtain a processed medical image with clear texture. Optionally, the denoised image used for fusion can be a denoised image obtained in any iteration process, wherein preferably, the denoised image used for fusion is the denoised image obtained in the last iteration process.

[0108] Optionally, the image information of the target detail image includes a first pixel matrix containing a luminance component, and the image information of the denoised image includes a second pixel matrix containing a luminance component. The denoised image and the initial detail texture image obtained in each iteration are fused to obtain a processed medical image with clear texture. This includes fusing the first pixel matrix and the second pixel matrix to obtain a fused pixel matrix containing the luminance component. When the input image includes a pixel matrix containing the luminance component in each iteration, the initial detail texture image and the denoised image also contain pixel matrices containing the luminance component. That is, the initial detail texture image and the denoised image are represented by the pixel matrix containing the luminance component. Therefore, the fusion of the initial detail texture image and the denoised image is also the fusion of their luminance component pixel matrices. Thus, the obtained image can be a fused pixel matrix containing the luminance component (i.e., a fused pixel matrix containing the luminance component). Subsequently, the pixel matrix of the fused luminance component and the pixel matrix of the chrominance component of the transformed image (i.e., the transformed image mentioned above) are combined into a composite image matrix in a first color space, such as an image matrix in the YCbCr color space. This image matrix includes the chrominance index and luminance value of each pixel unit of the image. The synthesis process is also the process of matching the luminance component value and chrominance component value of the corresponding pixel unit. After that, the composite image matrix is ​​converted from the first color space to the RGB color space to obtain a processed medical image with clear texture, so as to obtain a better display effect. The medical image is both denoised and its details and textures are enhanced at the same time.

[0109] Subsequently, the method of this application may also include the step of displaying a processed, textured medical image. By displaying a medical image that has been denoised and enhanced in detail and texture to the user, the user can obtain more information about the target object to be observed from the medical image, thereby providing doctors with better surgical observation assistance, etc.

[0110] In another embodiment of this application, provided the effect allows, only one iteration process may be performed. For example... Figure 4The diagram shows the flow of the image processing method of this application when only one iteration is performed, as follows: Figure 4 As shown, the image processing method of this application includes the following steps S410 to S450: In step S410, an image to be processed is acquired, which includes a medical image. The image to be processed is the original image to be processed. Detailed descriptions of the image to be processed can be found above and will not be repeated here. In step S420, image parameters of the image to be processed are acquired based on a preset processing model. In step S430, detailed texture information of the image to be processed is extracted based on the image parameters to obtain a detailed texture image. The detailed texture information includes at least one of the following: vascular information, nerve information, and tissue texture information. In step S440, the image to be processed is denoised based on the image parameters to obtain a denoised image. In step S450, the detailed texture image and the denoised image are fused to obtain a processed medical image with clear texture.

[0111] Compared with the previous embodiments, the method in this embodiment only performs one iteration process. Specifically, the detailed description of each step in this embodiment can be found in the description of the related steps above, and will not be repeated here.

[0112] In summary, the image processing method of this application has the following advantages:

[0113] 1. This method extracts image parameters through a preset processing model and applies these image parameters to denoising and detail texture extraction, thereby integrating the image denoising process and the image detail texture enhancement process simultaneously, reducing the amount of computation, and still achieving good denoising and detail texture enhancement effects.

[0114] 2. Since the noise reduction process and the detail texture enhancement process of this application are integrated and performed simultaneously, compared with the method of performing the noise reduction process and the detail texture enhancement process separately, the method of this application can be implemented without consuming too many computing resources, and can be deployed on some processing chips with limited computing resources, such as on a single FPGA chip.

[0115] Continue to refer to Figure 1 As an example, this application also provides an image processing apparatus 100, including: a memory 102 for storing executable program instructions; and a processor 101 for executing the program instructions stored in the memory 102, causing the processor to execute the image processing method described above. Detailed descriptions of the various steps of the image processing method can be found above.

[0116] In one example, processor 101 is further configured to execute program instructions stored in memory 102, causing the processor to perform the following steps: acquiring an image to be processed, wherein the image to be processed is a medical image; performing at least two iterations on the image to be processed based on a preset processing model to obtain an initial detail texture image and a denoised image in each iteration, wherein each iteration includes the following steps: acquiring image parameters of the image to be processed input to the processing model; extracting detail texture information from the corresponding image to be processed based on the image parameters to obtain an initial detail texture image, wherein the detail texture information includes at least one of the following: vascular information, nerve information, tissue texture information, lesion texture information; performing denoising processing on the image to be processed based on the image parameters to obtain a denoised image after filtering; and fusing the denoised image and the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture.

[0117] In one example, the processor 101 is further configured to execute program instructions stored in the memory 102, causing the processor to perform the following steps: acquiring an image to be processed, the image to be processed including a medical image; acquiring image parameters of the image to be processed based on a preset processing model; extracting detailed texture information of the image to be processed based on the image parameters to obtain a detailed texture image, wherein the detailed texture information includes at least one of the following: vascular information, nerve information, tissue texture information; performing denoising processing on the image to be processed based on the image parameters to obtain a denoised image; and fusing the detailed texture image and the denoised image to obtain a processed medical image with clear texture.

[0118] The image processing apparatus of this application also includes a display for displaying a target image. By displaying a target image that has been denoised and enhanced in detail and texture to a user, the user can obtain more information about the part of the target object to be observed from the target image, thereby providing better surgical observation assistance to doctors.

[0119] In one embodiment, such as Figure 5 As shown, this application also provides a medical device 500, which includes an image acquisition device 510 and the image processing device described above.

[0120] The image acquisition device 510 is used to acquire images of the parts of the target object to be observed in order to obtain the original image to be processed. The image acquisition device 510 is communicatively connected to the image processing device 100, so that the image processing device can acquire the image acquired by the image acquisition device 510 and process it according to the image processing method described above.

[0121] The medical device includes, but is not limited to, any device capable of acquiring medical images of the target object, such as an endoscope system. When the medical device is an endoscope system, the site to be observed in the target object can be the intestines, stomach, etc.

[0122] The structure of an endoscopic system can be one well-known to those skilled in the art. For example, an endoscopic system may include: a light source, a beam guide, a rigid endoscope, an optical bayonet, a camera, a main unit, a display, and a bus. The light source, beam guide, rigid endoscope, optical bayonet, camera, main unit, and display can be coupled via a bus. Those skilled in the art should understand that an endoscopic camera system may also have more or fewer components, or combine certain components, or different components. For example, an endoscopic camera system may also include a speculum, a smoke control device, input / output devices, network access devices, etc.

[0123] In addition, embodiments of the present invention also provide a computer storage medium on which a computer program is stored. One or more computer program instructions may be stored on the computer-readable storage medium, and a processor may execute the program instructions stored in the storage device to implement the functions (implemented by the processor) in the embodiments of the present invention and / or other desired functions, such as performing corresponding steps of the image processing method according to embodiments of the present invention. Various applications and various data may also be stored in the computer-readable storage medium, such as various data used and / or generated by the applications.

[0124] For example, computer storage media may include a memory card for a smartphone, a storage component for a tablet computer, a hard disk for a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media.

[0125] In summary, the image processing apparatus, medical device, and computer storage medium according to this application all have the same advantages as the aforementioned image processing method since they are all capable of performing the aforementioned image processing method.

[0126] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0127] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0129] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0130] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0131] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or elements of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature serving the same, equivalent, or similar purpose.

[0132] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0133] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules according to embodiments of the present invention. The present invention can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing some or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0134] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. An image processing method, characterized in that, The method includes: Acquire an image to be processed, wherein the image to be processed is a medical image; The image to be processed is subjected to at least two iterations based on a preset processing model, in order to obtain an initial detailed texture image and a denoised image in each iteration. Each iteration includes the following steps: Image parameters of the image to be processed input into the processing model are obtained, wherein the image parameters include the total gradient of the image to be processed and the gradient of the image to be processed in the normal direction. The image to be processed in the first iteration is a transformed image, which is obtained by converting the color space of the original image to be processed from the RGB color space to the first color space. After the first iteration, the denoised image after the previous iteration is used as the image to be processed input into the processing model in the next iteration. Based on the image parameters, extract the detailed texture information from the corresponding image to be processed to obtain an initial detailed texture image, wherein the detailed texture information includes at least one of the following: blood vessel information, nerve information, tissue texture information, and lesion texture information; The image to be processed is denoised based on the image parameters to obtain a denoised image after filtering. The image parameters are applied to the denoising process and the extraction of detail texture information, so that the denoising process and the extraction of detail texture information are integrated and performed simultaneously. The denoised image is fused with the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture.

2. The method as described in claim 1, characterized in that, The processing model processes the image to be processed through iterative parameters, which include at least one of a first parameter, a second parameter, and a third parameter. The first parameter controls the contribution of the denoising intensity term to the denoised image, the second parameter controls the contribution of the denoising sharpening term to the denoised image, and the third parameter controls the contribution of the sharpening supplement term to the denoised image.

3. The method as described in claim 1, characterized in that, When the image to be processed is an RGB color space image, the method further includes: The image to be processed is converted from the RGB color space to the first color space to obtain a converted image in the first color space; Extract the image information of the transformed image, wherein the image information of the transformed image includes the pixel matrix of the luminance component and the pixel matrix of the chrominance component.

4. The method as described in claim 3, characterized in that, The process of performing at least two iterations on the image to be processed based on the preset processing model includes: The transformed image is input into the processing model as the image to be processed for the first iteration to obtain the initial iterative image; The initial iterative image is used as the updated image to be processed and input into the processing model for a second iteration to obtain the secondary iterative image.

5. The method as described in claim 3, characterized in that, The process of fusing the denoised image with the initial detailed texture image obtained in each iteration to obtain a processed medical image with clear texture includes: Obtain the initial detail texture images corresponding to each iteration, and fuse the initial detail texture images to obtain a target detail image with clear texture; The target detail image and the denoised image are fused together to obtain a processed medical image with clear texture.

6. The method as described in claim 5, characterized in that, The image information of the target detail image includes a first pixel matrix containing a luminance component, and the image information of the denoised image includes a second pixel matrix containing a luminance component. The step of fusing the denoised image and the initial detail texture image obtained in each iteration to obtain a processed medical image with clear texture includes: The first pixel matrix and the second pixel matrix are fused to obtain a fused pixel matrix of luminance components; The fused pixel matrix and the pixel matrix of the chromaticity component of the transformed image are combined into a composite image matrix in the first color space; The synthesized image matrix is ​​converted from the first color space to the RGB color space to obtain a processed medical image with clear texture.

7. An image processing apparatus, characterized in that, include: Memory is used to store executable program instructions; The processor is further configured to execute the program instructions stored in the memory, causing the processor to perform the image processing method as described in any one of claims 1 to 6.

8. The image processing apparatus as claimed in claim 7, characterized in that, The image processing apparatus further includes a display for displaying the medical image.

9. A medical device, characterized in that, The medical device includes: An image acquisition device is used to acquire images of the parts of a target object to be observed, in order to obtain the original image to be processed; and The image processing apparatus according to any one of claims 7 or 8.

Images