Blood vessel enhancement method, device and equipment for medical endoscope image and storage medium
By denoising and gamma adjustment of medical endoscopic images, the problem of insignificance of image clarity and vascular characteristics is solved, and image enhancement of high definition and obvious vascular characteristics is achieved, improving the doctor's diagnostic accuracy.
Patent Information
- Application Number
- CN202411285017.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-11-12
AI Technical Summary
During the acquisition and transmission of medical endoscopic images, noise problems caused by hardware equipment limitations and environmental factors lead to insufficient clarity of blood vessel structure and insignificant characteristics, which affects the doctor's diagnostic accuracy.
By denoising the initial detail layer image and gamma adjustment and vascular enhancement treatment of the initial color layer image, the target image with obvious vascular characteristics and high definition was obtained after the merge.
It improves doctors' ability to observe and judge details, ensures the accuracy of the diagnosis of the disease, and meets the needs of clinical diagnosis.
Smart Images

Figure CN118941479A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, equipment and storage medium for blood vessel enhancement of medical endoscope images. Background Art
[0002] With the continuous advancement of science and technology and the increasing maturity of electronic medicine, the endoscope has become one of the most widely used medical diagnostic equipment today. The endoscope is essentially a camera with a light source that can penetrate deep into the human body to observe the internal tissues. It plays a very important role in auxiliary diagnosis and treatment as well as minimally invasive surgery.
[0003] At present, in the process of acquiring and transmitting medical endoscopic images, there is often a lot of noise due to the limitations of the hardware equipment conditions of the endoscopic camera system and the influence of various factors such as the external environment and the internal environment of the human body. As a result, the vascular structure on the collected medical endoscopic images is not clear enough, the vascular features are not obvious, and the color is lighter, which makes it difficult for doctors to accurately judge the condition, limits doctors' observation and judgment of details, and causes certain interference to subsequent clinical medical diagnosis.
[0004] At present, the methods for blood vessel enhancement of medical endoscope images include single-scale Retinex (SSR) algorithm and multi-scale Retinex (MSR) algorithm, etc., which divide the image into a detail layer image and a color layer image, and enhance the contrast of the detail layer image and the brightness of the color layer image respectively before performing image fusion to obtain the target image. However, since the use of filtering operation when layering the image will bring a lot of noise to the detail layer image, and the use of filtering method for blood vessel enhancement in the color layer image, the blood vessels in the fused target image are not clear enough and the colors are distorted, making it difficult to display a blood vessel enhanced image that meets the clinical diagnosis needs of doctors. Summary of the invention
[0005] (1) Technical issues to be solved
[0006] The present invention provides a method, device, equipment and storage medium for blood vessel enhancement of medical endoscope images. After denoising the initial detail layer image and enhancing the blood vessel part in the initial color layer image, the fused image not only has obvious blood vessel features but also has high clarity, which can improve the doctor's observation and judgment of details and enable the doctor to accurately judge the condition.
[0007] (2) Technical solution
[0008] In the first aspect, an embodiment of the present invention proposes a method for enhancing blood vessels of medical endoscopic images, which is used to enhance the display of blood vessel information of medical endoscopic images, including obtaining a medical endoscopic image to be processed; performing image processing on the medical endoscopic image according to an image enhancement algorithm to obtain an initial detail layer image and an initial color layer image; performing denoising processing on the initial detail layer image according to an image denoising algorithm to obtain a first detail layer image; processing the initial color layer image according to a gamma algorithm to obtain a first color layer image; performing enhancement processing on the first color layer image according to a blood vessel enhancement algorithm to obtain a second color layer image; and merging the first detail layer image with the second color layer image to obtain a target image.
[0009] Furthermore, the medical endoscope image is processed according to the image enhancement algorithm to obtain an initial detail layer image and an initial color layer image, including filtering the medical endoscope image according to the filtering algorithm to obtain the initial color layer image; processing the initial color layer image and the medical endoscope image according to a single-scale Retinex algorithm or a multi-scale Retinex algorithm to obtain the initial detail layer image.
[0010] Furthermore, the denoising process is performed on the initial detail layer image according to an image denoising algorithm to obtain a first detail layer image, including copying the initial detail layer image to obtain a first copied detail layer image; subtracting a first pixel threshold from the pixel values of all pixels on the first copied detail layer image to obtain a second copied detail layer image; denoising the second copied detail layer image according to a binarization algorithm to obtain a third copied detail layer image; performing morphological operations on the third copied detail layer image to obtain a fourth copied detail layer image; and calculating the pixel values of all pixels of the fourth copied detail layer image, the pixel values of all pixels of the initial detail layer image, and the second pixel threshold according to a first function to obtain the first detail layer image.
[0011] Furthermore, the processing of the initial color layer image according to the gamma algorithm to obtain the first color layer image includes obtaining gamma parameters; normalizing the initial color layer image to obtain a processed initial color layer image; and denormalizing the processed initial color layer image to obtain the first color layer image.
[0012] Furthermore, the enhancing process of the first color layer image according to the blood vessel enhancement algorithm to obtain the second color layer image includes extracting the color channels of the first color layer image, the color channels including a red channel, a blue channel and a green channel; performing gain processing on the pixel values of the red channel, the pixel values of the blue channel and the pixel values of the green channel to obtain the second color layer image.
[0013] Furthermore, the method further includes adjusting the color difference of the target image according to a color difference adjustment algorithm.
[0014] Furthermore, the color difference adjustment of the target image according to the color difference adjustment algorithm includes converting the RGB color format of the target image into a CIE-lab color format; performing a linear transformation on the converted CIE-lab color format using a parameter matrix; and converting the CIE-lab color format after the linear transformation into an RGB color format.
[0015] In the second aspect, an embodiment of the present invention further proposes a vascular enhancement device for medical endoscopic images, comprising an image acquisition module for acquiring medical endoscopic images; an image segmentation module for segmenting the medical endoscopic images to obtain detail layer images and color layer images; an image processing module for denoising the detail layer images and for vascular enhancement of the color layer images; an image fusion module for merging the denoised detail layer image and the vascular enhanced color layer image to obtain a target image; and a chromatic aberration adjustment module for adjusting the chromatic aberration of the target image, so as to implement the vascular enhancement method for medical endoscopic images as described in the first aspect.
[0016] In a third aspect, an embodiment of the present invention further proposes an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for blood vessel enhancement of medical endoscopic images as described in the first aspect is implemented.
[0017] In a fourth aspect, an embodiment of the present invention further proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for blood vessel enhancement of a medical endoscope image as described in the first aspect.
[0018] (3) Beneficial effects
[0019] In summary, the initial detail layer image is denoised to obtain a first detail layer image with higher clarity, the blood vessel part in the initial color layer image is gamma adjusted to obtain a first color layer image with higher brightness, and the blood vessel part in the first color layer image is color enhanced to obtain a first detail layer image with darker color, so that the target image obtained by fusion of the first detail layer image and the first detail layer image not only has obvious blood vessel features but also has higher clarity.
[0020] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0022] Figure 1 The present invention is a flowchart of a method for enhancing blood vessels in a medical endoscope image according to an embodiment of the present invention.
[0023] Figure 2 Another flow chart of a method for blood vessel enhancement in a medical endoscope image according to an embodiment of the present invention.
[0024] Figure 3 The present invention is a flowchart of obtaining an initial detail layer image and an initial color layer image according to an embodiment of the present invention.
[0025] Figure 4 This is a flow chart of obtaining a first detail layer image according to an embodiment of the present invention.
[0026] Figure 5 This is a flow chart of obtaining a first color layer image according to an embodiment of the present invention.
[0027] Figure 6 The flowchart of obtaining the second color layer image according to an embodiment of the present invention.
[0028] Figure 7 The figure is a schematic structural diagram of a blood vessel enhancement device for medical endoscope images according to an embodiment of the present invention.
[0029] Figure 8 The figure is a structural principle diagram of an electronic device according to an embodiment of the present invention.
[0030] Fig. 9 Schematic diagram of a medical endoscope image to be processed according to an embodiment of the present invention.
[0031] Fig.10 is a schematic diagram of a second color layer image according to an embodiment of the present invention.
[0032] Fig.11 is a schematic diagram of a first detail layer image according to an embodiment of the present invention.
[0033] Fig.12 is a schematic diagram of a target image according to an embodiment of the present invention.
[0034] Fig.13 The figure is a schematic diagram of the coordinates of a certain pixel point on a medical endoscope image to be processed according to an embodiment of the present invention.
[0035] In the figure:
[0036] 10-image acquisition module; 20-image segmentation module; 30-image processing module; 40-image fusion module; 50-color difference adjustment module; 60-memory; 70-processor. DETAILED DESCRIPTION
[0037] The following is a further detailed description of the embodiments of the present invention in conjunction with the accompanying drawings and examples. The detailed description of the following embodiments and the accompanying drawings are used to exemplarily illustrate the principles of the present invention, but cannot be used to limit the scope of the present invention, that is, the present invention is not limited to the described embodiments, and covers any modification, replacement and improvement of parts, components and connection modes without departing from the spirit of the present invention.
[0038] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0039] First, as Figure 1 The present invention relates to a method for enhancing blood vessels of medical endoscope images, which is used to enhance the blood vessel information of medical endoscope images, and comprises the following steps: obtaining a medical endoscope image to be processed (such as Fig. 9 ); performing image processing on the medical endoscope image according to an image enhancement algorithm to obtain an initial detail layer image and an initial color layer image; performing denoising on the initial detail layer image according to an image denoising algorithm to obtain a first detail layer image (as shown in Fig.11 ); processing the initial color layer image according to the gamma algorithm to obtain a first color layer image; enhancing the first color layer image according to the blood vessel enhancement algorithm to obtain a second color layer image (as shown in Fig.10 ); merging the first detail layer image and the second color layer image to obtain a target image (as shown in Fig.12 As shown), the target image is a medical endoscope image with obvious vascular features and high definition.
[0040] The present invention performs denoising on the initial detail layer image to obtain a first detail layer image with higher definition, performs gamma adjustment on the blood vessel part in the initial color layer image to obtain a first color layer image with higher brightness, and performs color enhancement processing on the blood vessel part in the first color layer image to obtain a first detail layer image with darker color, so that the target image obtained by fusion of the first detail layer image and the first detail layer image not only has obvious blood vessel features but also has higher definition, which can improve the doctor's observation and judgment of details, so that the doctor can accurately judge the condition.
[0041] As a preferred embodiment, Figure 3As shown, the medical endoscope image is processed according to the image enhancement algorithm to obtain an initial detail layer image and an initial color layer image, including:
[0042] Performing filtering processing on the medical endoscope image according to a filtering algorithm to obtain an initial color layer image;
[0043] The initial color layer image and the medical endoscope image are processed according to a single-scale Retinex algorithm or a multi-scale Retinex algorithm to obtain an initial detail layer image.
[0044] Since the reflection component (i.e., detail layer information) and the illumination component (color layer information) of the image cannot be directly obtained, it is necessary to use a filtering algorithm to filter the medical endoscope image to be processed. The filtering algorithm includes but is not limited to Gaussian filtering, average filtering, bilateral filtering, guided filtering, Laplace pyramid filtering and other image filtering algorithms. The present invention adopts the Gaussian filtering algorithm. According to the formula The Gaussian convolution kernel is calculated. In the above formula, G(x, y) is the Gaussian convolution kernel, x, y are the coordinates of each point in the convolution kernel, that is, the coordinates of all pixel points of the medical endoscope image to be processed (such as Fig.13 shown), σ 2 is the parameter controlling the two-dimensional Gaussian distribution, σ 2 It can be calculated after multiple experiments. When the value range is 0.01 to 20, the color effect of the initial color layer image meets clinical needs. The Gaussian convolution kernel is shown in the following table:
[0045]
[0046] After determining the Gaussian convolution kernel, use the convolution kernel to convolve with the original image, that is, use the formula The illumination component is calculated to obtain the initial color layer image. Where G is the Gaussian convolution kernel, I is the medical endoscope image to be processed, and L is the initial color layer image.
[0047] After obtaining the initial color layer image, a single-scale Retinex algorithm or a multi-scale Retinex algorithm is used to obtain the initial detail layer image based on the initial color layer image and the medical endoscope image to be processed. If the single-scale Retinex algorithm is used, the formula log[R(x1, y1)]=log[I(x1, y1)]-log[L(x1, y1)] is used for calculation. If the multi-scale Retinex algorithm is used, the formula Calculation is performed, where R is the initial detail layer image, x1, y1 are the coordinates of the pixels to be processed on each corresponding image, where x1 is the number of rows of the pixels to be processed on each corresponding image, y1 is the number of columns of the pixels to be processed on each corresponding image, I is the medical endoscope image to be processed, L is the initial color layer image, and each corresponding image includes the medical endoscope image to be processed, the initial detail layer image, and the initial color layer image.
[0048] As another preferred embodiment, Figure 4 As shown, the initial detail layer image is denoised according to an image denoising algorithm to obtain a first detail layer image, including copying the initial detail layer image to obtain a first copied detail layer image; subtracting a first pixel threshold from the pixel values of all pixels on the first copied detail layer image to obtain a second copied detail layer image; denoising the second copied detail layer image according to a binarization algorithm to obtain a third copied detail layer image; performing morphological operations on the third copied detail layer image to obtain a fourth copied detail layer image; and calculating the pixel values of all pixels of the fourth copied detail layer image, the pixel values of all pixels of the second copied detail layer image, and the second pixel threshold according to a first function to obtain the first detail layer image.
[0049] Since the use of a filtering algorithm to perform a filtering operation on the medical endoscope image to be processed will incorporate noise into the corresponding initial detail layer image, in order to obtain a target image with higher clarity, the noise added to the initial detail layer image needs to be eliminated. In order to ensure that the detail information in the initial detail layer image is not affected during the noise elimination process, the initial detail layer image is copied to obtain a first copied detail layer image. To ensure that the noise in the initial detail layer image is eliminated, all pixel values of the noise part and the detail information part of the first copied detail layer image are first digitized, that is, the absolute value of the difference between the pixel values of all pixels on the first copied detail layer image and the first pixel threshold is obtained to obtain the first copied detail layer image. The pixel values of all pixels on the node layer image are converted into non-negative real numbers to obtain a second copied detail layer image, the value range of the first pixel threshold is an integer greater than 0 and less than 255, and then in order to eliminate a part of the noise with lower pixel values, a binarization algorithm is used to perform denoising on the second copied detail layer image, by comparing the pixel values of all pixels on the second copied detail layer image with the third pixel threshold, marking the pixels on the second copied detail layer image that are less than or equal to the third pixel threshold as 0, indicating that the pixel is noise, and marking the pixels on the second copied detail layer image that are greater than the third pixel threshold as 1, indicating that the pixel is detail information, to obtain a third copied detail layer image marked with noise and detail information, the The third pixel threshold is selected as the maximum pixel value that can judge the noise, which can be obtained through multiple experiments. The specific acquisition method is the existing technology, so it will not be repeated here. Then, in order to eliminate the morphologically isolated or small noise in the initial detail layer image, the third copied detail layer image is subjected to morphological operation, and all the pixels on the third copied detail layer image are subjected to corrosion operation with the preset template matrix parameters, and then the processing result after the corrosion operation is subjected to expansion operation with the preset template matrix parameters to obtain the fourth copied detail layer image. The template matrix parameters are nine matrix parameters randomly combined by two numbers 0 or 1 in a nine-square matrix template. Finally, in order to eliminate the noise on the initial detail layer image, it is necessary to The fourth copied detail layer image is fused with the initial detail layer image, and the pixel values of all pixels of the fourth copied detail layer image, the pixel values of all pixels of the initial detail layer image, and the second pixel threshold are calculated according to the first function to obtain the first detail layer image, and the first function is M=(N*(R-K1)+K1)*a*b, wherein M is the first detail layer image, N is the pixel value of all pixels on the fourth copied detail layer image, R is the pixel value of all pixels on the initial detail layer image, K1 is the second pixel threshold, and its value is 1, a is the gain of the blood vessel in the initial detail layer image, and its value range is 0-1, and b is the gain of the overall enhancement of the initial detail layer image, and its value range is 0-10.
[0050] As another optional implementation.
[0051] Preferably, if Figure 5 As shown, in order to improve the color depth or brightness of the blood vessel part in the target image, it is necessary to improve the color depth or brightness of the blood vessel part in the initial color layer image, so as to achieve fusion with the first detail layer image to obtain a target image that meets clinical needs. The color enhancement of the initial color layer image includes but is not limited to gamma adjustment, brightness adjustment and saturation adjustment, but gamma adjustment can be quickly and stably implemented on the FPGA of the image processing module using a tabulation method to improve the efficiency of image processing. Therefore, the present invention adopts a gamma algorithm for color enhancement processing. In order to meet the calculation requirements of the gamma algorithm, it is necessary to first obtain a large amount of data through experiments. The gamma parameter has a value range of 0-20. Then the initial color layer image is normalized, i.e., the pixel values of all pixels on the initial color layer image are divided by the normalization constant, and the reciprocal of the gamma parameter is used as the exponent of the value of the pixel value divided by the normalization constant to obtain the processed initial color layer image. Finally, the processed initial color layer image is denormalized, i.e., the result of the operation using the reciprocal of the gamma parameter as the exponent of the value of the pixel value divided by the normalization constant is multiplied by the normalization constant to obtain the first color layer image. The overall formula of the normalization and denormalization is L′=(L / N) 1 / gamma *N, where L' is the enhanced color layer image, L is the color layer image before enhancement, and N is a normalization constant. For example, N is 255 for an 8-bit image and 1023 for a 10-bit image.
[0052] Preferably, if Figure 6 As shown, in order to obtain blood vessel information with obvious features and darker colors, a blood vessel enhancement algorithm is used to perform blood vessel enhancement processing on the first color layer image after color enhancement processing to obtain a second color layer image, including extracting the color channels of the first color layer image, the color channels including a red channel, a blue channel and a green channel; performing gain processing on the pixel values of the red channel, the pixel values of the blue channel and the pixel values of the green channel, that is, using the formula R′ L =beta R *R L , G′ L =beta G *GL and B′ L =beta B *B L The pixel values of the red channel, the green channel, and the blue channel are multiplied by their corresponding gain coefficients to obtain the pixel values of the red channel, the green channel, and the blue channel after gain processing, and the second color layer image is obtained, where R L , GL , B L The three are the red channel, green channel and blue channel components of the second color layer image, beta R , beta G , beta B are the three gain coefficients corresponding to the red channel, green channel and blue channel, and beta R The value is usually smaller than beta G , beta B , and the value range of the three is 0.5-2.
[0053] Preferably, if Figure 2 As shown, since color difference is easily generated in the obtained image during the process of denoising the initial detail layer image to obtain the first detail layer image, and during the process of color enhancement and blood vessel enhancement on the initial color layer image, in order to ensure that the fusion of the first detail layer image and the second color layer image to obtain the target image meets clinical needs, the blood vessel enhancement method of the medical endoscope image also includes adjusting the color difference of the target image according to the color difference adjustment algorithm, including converting the RGB color format of the target image into the CIE-lab color format, and linearly transforming the converted CIE-lab color format using a parameter matrix, and then converting the CIE-lab color format after the linear transformation back into the RGB color format, which meets the color difference requirements of the target image. Since the color difference adjustment method is a prior art, it will not be repeated here.
[0054] Second, as Figure 7 As shown, the present invention also provides a blood vessel enhancement device for medical endoscopic images, including an image acquisition module 10, for acquiring the medical endoscopic image to be processed; and an image segmentation module 20, which is electrically connected to the image acquisition module 10, for receiving and segmenting the medical endoscopic image to be processed to obtain an initial detail layer image and an initial color layer image; and an image processing module 30, which is electrically connected to the image segmentation module 20, for denoising the initial detail layer image and for performing blood vessel enhancement processing on the initial color layer image; and an image fusion module 40, which is electrically connected to the image processing module 30, for merging the denoised initial detail layer image and the blood vessel enhanced initial color layer image to obtain a target image; and a chromatic aberration adjustment module 50, which is electrically connected to the image fusion module 40, for receiving and adjusting the chromatic aberration of the target image.
[0055] The image segmentation module 20 is used to receive the medical endoscope image to be processed, filter the medical endoscope image using a Gaussian filtering algorithm to obtain the initial color layer image, and calculate and obtain the initial detail layer image based on the initial color layer image and the medical endoscope image to be processed using a single-scale Retinex algorithm or a multi-scale Retinex algorithm.
[0056] The image processing module 30 is used to obtain a first copied detail layer image after copying the initial detail layer image, and to obtain the absolute value of the difference between the pixel values of all pixels on the first copied detail layer image and the first pixel threshold, to convert the pixel values of all pixels on the first copied detail layer image into non-negative real numbers to meet the needs of binarization processing, to compare the obtained non-negative real number pixel values with the noise threshold according to the binarization algorithm, to obtain a third copied detail layer image with a noise part and a detail information part marked, to first perform an erosion operation and then a dilation operation on the pixel values of all pixels on the third copied detail layer image according to the image morphological operation model, to obtain a fourth copied detail layer image from which morphologically isolated or small-area noise has been eliminated, to perform calculations based on the first function based on the pixel values of all pixels of the fourth copied detail layer image, the pixel values of all pixels of the initial detail layer image and the second pixel threshold, to obtain the first detail layer image from which all noise has been eliminated.
[0057] The image processing module 30 is also used to perform color enhancement processing on the initial color layer image using a gamma algorithm to obtain a first color layer image after color enhancement, and to perform vascular enhancement processing on the first color layer image according to a vascular enhancement algorithm to obtain a second color layer image with obvious vascular feature information.
[0058] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0059] Thirdly, Figure 8 As shown, the present invention also provides an electronic device, including a memory 60 and a processor 70, wherein the memory 60 stores a computer program, and the processor 70 is configured to run the computer program to execute the blood vessel enhancement method for medical endoscope images according to the first aspect. The electronic device may be a terminal, a computer or a similar computing device, and the terminal may include one or more ( Figure 8Only one is shown in the figure) processor 70 and memory 60 for storing data, wherein the processor 70 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA, the above-mentioned terminal may also include a transmission device and an input and output device for communication functions, and the memory 60 may be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the blood vessel enhancement method of medical endoscope images in this embodiment, and the processor 70 executes various functional applications and data processing by running the computer program stored in the memory 60, that is, the blood vessel enhancement method of medical endoscope images described in the first aspect is realized. The memory 60 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 60 may further include a memory remotely arranged relative to the processor 70, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.
[0060] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor 70, implements the method for enhancing blood vessels in a medical endoscope image according to the first aspect, comprising the following steps:
[0061] S1: Acquire a medical endoscope image to be processed;
[0062] S2: Perform image processing on the medical endoscope image according to the image enhancement algorithm to obtain the initial detail layer image and the initial color layer image
[0063] S3: performing denoising processing on the initial detail layer image according to an image denoising algorithm to obtain a first detail layer image;
[0064] S4: Processing the initial color layer image according to a gamma algorithm to obtain a first color layer image;
[0065] S5: performing enhancement processing on the first color layer image according to a blood vessel enhancement algorithm to obtain a second color layer image;
[0066] S6: Merge the first detail layer image and the second color layer image to obtain a target image.
[0067] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.
[0068] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0069] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0070] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.
[0071] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0072] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0073] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0074] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.
[0075] It should be clear that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. The present invention is not limited to the specific steps and structures described above and shown in the figures. In addition, for the sake of brevity, a detailed description of known methods and technologies is omitted here.
[0076] The above description is only an embodiment of the present application and is not limited to the present application. For those skilled in the art, the present application may have various modifications and changes without departing from the scope of the present invention. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.
[0077] It should be clear that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. The present invention is not limited to the specific steps and structures described above and shown in the figures. In addition, for the sake of brevity, a detailed description of known methods and technologies is omitted here.
[0078] The above is only an embodiment of the present application and is not limited to the present application. For those skilled in the art, the present application may have various changes and variations without departing from the scope of the present invention. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for enhancing blood vessels in medical endoscope images, for enhancing and displaying blood vessel information in medical endoscope images, characterized in that: include Acquiring a medical endoscope image to be processed; Performing image processing on the medical endoscope image according to an image enhancement algorithm to obtain an initial detail layer image and an initial color layer image; Performing denoising processing on the initial detail layer image according to an image denoising algorithm to obtain a first detail layer image; Processing the initial color layer image according to a gamma algorithm to obtain a first color layer image; Performing enhancement processing on the first color layer image according to a blood vessel enhancement algorithm to obtain a second color layer image; The first detail layer image and the second color layer image are combined to obtain a target image.
2. The blood vessel enhancement method of medical endoscope image according to claim 1, characterized in that: The step of performing image processing on the medical endoscope image according to the image enhancement algorithm to obtain an initial detail layer image and an initial color layer image includes: Performing filtering processing on the medical endoscope image according to a filtering algorithm to obtain the initial color layer image; The initial color layer image and the medical endoscope image are processed according to a single-scale Retinex algorithm or a multi-scale Retinex algorithm to obtain the initial detail layer image.
3. The blood vessel enhancement method of medical endoscope image according to claim 1, characterized in that: The step of performing denoising processing on the initial detail layer image according to an image denoising algorithm to obtain a first detail layer image includes: Copying the initial detail layer image to obtain a first copied detail layer image; Subtract a first pixel threshold from the pixel values of all pixels on the first copied detail layer image to obtain a second copied detail layer image; Performing denoising processing on the second replicated detail layer image according to a binarization algorithm to obtain a third replicated detail layer image; Performing a morphological operation on the third replicated detail layer image to obtain a fourth replicated detail layer image; The pixel values of all pixels of the fourth replicated detail layer image, the pixel values of all pixels of the initial detail layer image, and the second pixel threshold are calculated according to the first function to obtain the first detail layer image.
4. The blood vessel enhancement method of medical endoscope image according to claim 1, characterized in that: The step of processing the initial color layer image according to the gamma algorithm to obtain the first color layer image includes: Get gamma parameters; Normalizing the initial color layer image to obtain a processed initial color layer image; The processed initial color layer image is subjected to denormalization processing to obtain the first color layer image.
5. The method for blood vessel enhancement of medical endoscope images according to claim 1, characterized in that: The step of performing enhancement processing on the first color layer image according to the blood vessel enhancement algorithm to obtain the second color layer image includes: Extracting color channels of the first color layer image, the color channels including a red channel, a blue channel, and a green channel; Gain processing is performed on the pixel values of the red channel, the pixel values of the blue channel, and the pixel values of the green channel to obtain a second color layer image.
6. The method for blood vessel enhancement of medical endoscope images according to claim 1, characterized in that: The method also includes adjusting the color difference of the target image according to a color difference adjustment algorithm.
7. The blood vessel enhancement method of medical endoscope image according to claim 6, characterized in that: The step of adjusting the color difference of the target image according to the color difference adjustment algorithm includes: Convert the RGB color format of the target image to the CIE-lab color format; The converted CIE-lab color format is linearly transformed using the parameter matrix; Convert the CIE-lab color format after linear transformation to RGB color format.
8. A blood vessel enhancement device for medical endoscope images, characterized in that: include An image acquisition module (10) is used to acquire a medical endoscope image to be processed; An image segmentation module (20), used for segmenting the medical endoscope image to be processed to obtain an initial detail layer image and an initial color layer image; An image processing module (30) for denoising the initial detail layer image and for blood vessel enhancement of the initial color layer image; An image fusion module (40) is used to merge the denoised initial detail layer image and the blood vessel enhanced initial color layer image to obtain a target image; The color difference adjustment module (50) is used to adjust the color difference of the target image.
9. An electronic device, characterized in that: It comprises a memory (60) and a processor (70), wherein the memory (60) stores a computer program, and when the processor (70) executes the computer program, the blood vessel enhancement method for medical endoscope images as claimed in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor (70), the blood vessel enhancement method for a medical endoscope image according to any one of claims 1 to 7 is implemented.
