Digital image intelligent processing system suitable for urology

Abstract

The present invention belongs to the field of digital imaging and relates to data processing technology, and is specifically an intelligent digital image processing system suitable for urology, comprising an image acquisition module, an image segmentation module, a processing evaluation module and a processing optimization module, wherein the image acquisition module, the image segmentation module, the processing evaluation module and the processing optimization module are sequentially communicatively connected, and the image acquisition module is also communicatively connected with the processing optimization module; the present invention collects digital images of urology, classifies analysis images according to the image type and shooting purpose of the digital images, provides data support for the processing optimization analysis process, and performs segmentation processing on the digital images of urology through the image segmentation module, and divides the analysis images into a plurality of image sub-areas, so as to facilitate image analysis.

Description

Technical Field

[0001] The invention belongs to the field of digital imaging and relates to data processing technology, in particular to a digital imaging intelligent processing system suitable for urology. Background Art

[0002] Imaging examinations performed to understand the condition of the urinary system include abdominal plain film, urography, renal artery digital subtraction angiography (DSA), computed tomography (CT), magnetic resonance imaging (MRI), ultrasound and radionuclide imaging.

[0003] The invention patent with announcement number CN116580122A discloses a surgical intelligent digital image processing method and system, which calculates the actual minimum depth of the tumor and the depth of the tumor inside the human body, and determines the radiotherapy method and the radiotherapy time required for each radiotherapy method based on the actual minimum depth of the tumor and the depth of the tumor inside the human body, so as to achieve targeted radiotherapy; however, the above patent content cannot perform priority analysis on the segmentation method according to the medical purpose and image type of the digital image, resulting in the quality of the segmented digital image cannot be guaranteed.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent digital image processing system suitable for urology, which is used to solve the problem that the prior art cannot analyze the priority of segmentation methods according to the purpose of digital image diagnosis and image type;

[0006] The technical problem to be solved by the present invention is: how to provide a digital image intelligent processing system suitable for urology that can perform priority analysis on segmentation methods according to the medical purpose and image type of the digital image.

[0007] The object of the present invention can be achieved by the following technical solutions: a digital image intelligent processing system adapted for urology, comprising an image acquisition module, an image segmentation module, a processing evaluation module and a processing optimization module;

[0008] The image acquisition module is used to acquire digital images of urology: obtain the user's digital images of urology and mark them as analysis images, mark the image type and shooting purpose of the analysis images as basic parameters of the analysis images; send the analysis images to the image segmentation module, and send the basic parameters of the analysis images to the processing optimization module;

[0009] The image segmentation module is used to perform segmentation processing on the digital image of urology: randomly select a segmentation method to perform image segmentation on the analysis image to obtain a plurality of image sub-regions, the segmentation methods include OTSU threshold segmentation, region growth segmentation, edge detection segmentation and watershed algorithm segmentation; and send the image sub-regions obtained by segmentation to the processing and evaluation module;

[0010] The processing evaluation module is used to evaluate and analyze the segmentation processing effect of the urology digital image: obtain the spatial data KF, dense data MF and noise data ZS of the image sub-region and perform numerical calculation to obtain the processing coefficient CL of the image sub-region; sum and average the processing coefficients CL of all image sub-regions of the analyzed image to obtain the evaluation coefficient, perform variance calculation on the processing coefficients CL of all image sub-regions of the analyzed image to obtain the deviation coefficient, and judge whether the segmentation processing effect of the analyzed image meets the requirements through the evaluation coefficient and the deviation coefficient;

[0011] The processing optimization module is used to optimize the processing of urology digital images.

[0012] Furthermore, the image types of the analyzed images include B-ultrasound images, CT images and magnetic resonance images, and the shooting purposes of the analyzed images include physical examination, medical consultation and reexamination.

[0013] Furthermore, the spatial data KF is the maximum value of the spatial resolution of the image sub-region, the dense data MF is the maximum value of the density resolution of the image sub-region, and the noise data ZS is the image noise decibel value of the image sub-region.

[0014] Furthermore, the specific process of determining whether the segmentation processing effect of the analysis image meets the requirements includes: calling the evaluation threshold and the deviation threshold, and comparing the evaluation coefficient and the deviation coefficient of the analysis image with the evaluation threshold and the deviation threshold respectively: if the evaluation coefficient is greater than or equal to the evaluation threshold and the deviation coefficient is less than the deviation threshold, then it is determined that the segmentation processing effect of the analysis image meets the requirements, and the evaluation coefficient and the deviation coefficient of the analysis image are sent to the processing optimization module; otherwise, it is determined that the segmentation processing effect of the analysis image does not meet the requirements, and a re-segmentation signal is generated and the re-segmentation signal is sent to the image segmentation module.

[0015] Furthermore, after receiving the re-segmentation signal, the image segmentation module selects other segmentation methods and re-performs image segmentation processing, and sends the re-segmented image sub-region to the processing evaluation module again, and so on, until the segmentation processing effect of the analyzed image meets the requirements; after the image segmentation module uses all segmentation methods to perform image segmentation on the image sub-region, when the segmentation processing effect of the analyzed image does not meet the requirements, a re-acquisition signal is generated and sent to the image acquisition module; when the image acquisition module receives the re-acquisition signal, it re-acquires the patient's urology digital image.

[0016] Furthermore, the processing optimization module is used to optimize the urological digital images: generate an optimization cycle, freely combine the image type and the shooting purpose in the basic parameters of the analysis image received within the optimization cycle to obtain several parameter groups, mark the optimization method of the parameter group, and send the optimization method of the parameter group to the image segmentation module.

[0017] Furthermore, the specific process of marking the optimization method of the parameter group includes: numerically calculating the evaluation coefficient and the deviation coefficient of the analysis image to obtain the optimization coefficient YH of the analysis image; marking the analysis image whose basic parameters meet the parameter group as the matching image of the parameter group, summing and averaging the optimization coefficients YH of the matching images using the same segmentation method in the parameter group to obtain the optimization performance value of the segmentation method, and marking the segmentation method with the largest optimization performance value as the optimization method of the parameter group.

[0018] The present invention also proposes a digital image intelligent processing method suitable for urology, comprising the following steps:

[0019] Step 1: Collect digital images of urology surgery;

[0020] Step 2: Segmentation of urology digital images;

[0021] Step 3: Evaluate and analyze the segmentation effect of urology digital images;

[0022] Step 4: Optimize the processing of urology digital images.

[0023] The present invention has the following beneficial effects:

[0024] 1. The image acquisition module can be used to collect digital images of urology surgery, and the analysis images can be classified according to the image type and shooting purpose of the digital images to provide data support for the processing and optimization of the analysis process. The image segmentation module can be used to segment the digital images of urology surgery and divide the analysis images into several image sub-areas to facilitate image analysis;

[0025] 2. The processing and evaluation module can be used to evaluate and analyze the segmentation processing effect of urology digital images, collect and comprehensively calculate multiple quality parameters of the segmented image sub-regions to obtain evaluation coefficients and deviation coefficients, and evaluate the segmentation effect of the analysis image based on the evaluation coefficients and deviation coefficients. When the segmentation effect is abnormal, timely feedback and re-segmentation are performed to improve the image quality after the segmentation of the analysis image;

[0026] 3. The urology digital images can be optimized through the processing optimization module. The parameter groups are divided according to the basic parameters. Then, the segmentation method, evaluation coefficient and deviation coefficient used in the matching images in the parameter group are comprehensively analyzed to obtain the optimization method of the parameter group, thereby improving the matching degree between the segmentation method and the basic image parameters in subsequent image segmentation and improving the segmentation processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0029] Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Embodiment 1: Figure 1 As shown, a digital image intelligent processing system suitable for urology includes an image acquisition module, an image segmentation module, a processing evaluation module and a processing optimization module. The image acquisition module, the image segmentation module, the processing evaluation module and the processing optimization module are communicatively connected in sequence, and the image acquisition module is also communicatively connected with the processing optimization module.

[0032] The image acquisition module is used to acquire digital images of urology: obtain the user's digital images of urology and mark them as analysis images, mark the image type and shooting purpose of the analysis image as basic parameters of the analysis image, the image type of the analysis image includes B-ultrasound image, CT image and magnetic resonance image, the shooting purpose of the analysis image includes physical examination, medical treatment and reexamination, send the analysis image to the image segmentation module, and send the basic parameters of the analysis image to the processing optimization module;

[0033] When the image acquisition module receives the re-acquisition signal, it re-acquires the patient's urology digital image, classifies the analysis image according to the image type and shooting purpose of the digital image, and provides data support for processing and optimizing the analysis process. The image segmentation module can segment the urology digital image and divide the analysis image into several image sub-areas to facilitate image analysis.

[0034] The image segmentation module is used to segment the digital images of urology surgery: randomly select a segmentation method to segment the analysis image to obtain several image sub-regions. The segmentation methods include OTSU threshold segmentation, region growth segmentation, edge detection segmentation and watershed algorithm segmentation;

[0035] Threshold segmentation is one of the most basic and intuitive image segmentation methods. By setting one or more thresholds, points on the image plane are divided into different categories. The maximum inter-class variance method (OTSU algorithm) is a common method for automatically determining thresholds. It determines the optimal threshold by maximizing the inter-class variance and is suitable for situations where the image grayscale distribution has a bimodal characteristic.

[0036] Region growing segmentation starts with a set of seed points and combines pixels or sub-regions into larger regions according to pre-defined growth criteria. The selection of seed points has a great influence on the final segmentation result. Common criteria include grayscale difference and texture difference.

[0037] Edge detection segmentation is a technique for identifying the boundaries of objects in an image. Commonly used edge detection operators include the Sobel operator, Canny operator, Prewitt operator, and Roberts operator. The Canny edge detection algorithm is a widely used edge detection method that implements edge detection through multi-step processing.

[0038] The watershed algorithm is based on the gradient information of the image. It regards the image as a topographic map, the local minimum as a water basin, and the gradient value as a contour line. It simulates the rain filling process to separate the areas between the contour lines. The algorithm is sensitive to noise and usually requires a preprocessing step to improve the segmentation effect.

[0039] The image sub-region obtained by segmentation is sent to the processing and evaluation module; after receiving the re-segmentation signal, the image segmentation module selects other segmentation methods and re-performs image segmentation processing, and sends the re-segmented image sub-region to the processing and evaluation module again, and so on, until the segmentation processing effect of the analyzed image meets the requirements; after the image segmentation module uses all segmentation methods to perform image segmentation on the image sub-region, if the segmentation processing effect of the analyzed image does not meet the requirements, a re-capture signal is generated and sent to the image acquisition module.

[0040] The processing evaluation module is used to evaluate and analyze the segmentation processing effect of the urology digital image: obtain the spatial data KF, dense data MF and noise data ZS of the image sub-region, the spatial data KF is the maximum value of the spatial resolution of the image sub-region, the spatial resolution refers to the ability to display the smallest detail in the image, the dense data MF is the maximum value of the density resolution of the image sub-region, the density resolution refers to the ability to distinguish tissues of different densities, and the noise data ZS is the image noise decibel value of the image sub-region;

[0041] The processing coefficient CL of the image sub-region is obtained by the formula CL=k1×KF+k2×MF-k3×ZS, where k1, k2 and k3 are all proportional coefficients, and k1>k2>k3>1. The processing coefficient CL is a value that reflects the image quality of the image sub-region. The larger the value of the processing coefficient CL, the better the image quality of the image sub-region.

[0042] The processing coefficients CL of all image sub-regions of the analyzed image are summed and averaged to obtain the evaluation coefficient. The variance of the processing coefficients CL of all image sub-regions of the analyzed image is calculated to obtain the deviation coefficient. The evaluation threshold and the deviation threshold are retrieved, and the evaluation coefficient and the deviation coefficient of the analyzed image are compared with the evaluation threshold and the deviation threshold respectively:

[0043] If the evaluation coefficient is greater than or equal to the evaluation threshold and the deviation coefficient is less than the deviation threshold, it is determined that the segmentation processing effect of the analyzed image meets the requirements, and the evaluation coefficient and the deviation coefficient of the analyzed image are sent to the processing optimization module; otherwise, it is determined that the segmentation processing effect of the analyzed image does not meet the requirements, a re-segmentation signal is generated and the re-segmentation signal is sent to the image segmentation module;

[0044] Then, multiple quality parameters of the segmented image sub-regions are collected and comprehensively calculated to obtain evaluation coefficients and deviation coefficients. The segmentation effect of the analysis image is evaluated based on the evaluation coefficients and deviation coefficients. When the segmentation effect is abnormal, timely feedback and re-segmentation are performed to improve the image quality after segmentation for analysis of the image.

[0045] The processing optimization module is used to optimize the digital images of urology: generate an optimization cycle, freely combine the image type and shooting purpose in the basic parameters of the analysis image received within the optimization cycle to obtain several parameter groups, mark the evaluation coefficient and deviation coefficient of the analysis image as PG and PC respectively, and obtain the optimization coefficient YH of the analysis image through the formula YH=m1×PG-m2×PC, where m1 and m2 are both proportional coefficients, and m1>m2>1;

[0046] The analysis image whose basic parameters meet the parameter group is marked as the matching image of the parameter group, the optimization coefficients YH of the matching images using the same segmentation method in the parameter group are summed and averaged to obtain the optimized performance value of the segmentation method, the segmentation method with the largest optimized performance value is marked as the optimized method of the parameter group, and the optimized method of the parameter group is sent to the image segmentation module;

[0047] The parameter groups are divided according to the basic parameters, and then the segmentation method, evaluation coefficient and deviation coefficient used in the matching image within the parameter group are comprehensively analyzed to obtain the optimization method of the parameter group, thereby improving the matching degree between the segmentation method and the basic parameters of the image in subsequent image segmentation and improving the efficiency of the segmentation processing.

[0048] Embodiment 2: Figure 2 As shown, the present invention also proposes a digital image intelligent processing method suitable for urology, comprising the following steps:

[0049] Step 1: Collecting digital images of urology: obtaining digital images of urology of the user and marking them as analysis images, and marking the image type and shooting purpose of the analysis images as basic parameters of the analysis images;

[0050] Step 2: Segment the urology digital image: randomly select a segmentation method to segment the analysis image to obtain a number of image sub-regions, and send the segmented image sub-regions to the processing and evaluation module;

[0051] Step 3: Evaluate and analyze the segmentation effect of the urology digital image: obtain the spatial data KF, dense data MF and noise data ZS of all image sub-areas and perform numerical calculations to obtain the evaluation coefficient and deviation coefficient of the analyzed image;

[0052] Step 4: Optimize the processing of urology digital images: generate an optimization cycle, freely combine the image type and shooting purpose in the basic parameters of the analysis image received within the optimization cycle to obtain several parameter groups, perform numerical calculations on the evaluation coefficient and deviation coefficient of the analysis image to obtain the optimization coefficient YH, and mark the priority of the parameter group through the optimization coefficient YH.

[0053] When the present invention is working, it obtains the user's urology digital image and marks it as an analysis image, marks the image type and shooting purpose of the analysis image as basic parameters of the analysis image, randomly selects a segmentation method to perform image segmentation on the analysis image to obtain a plurality of image sub-regions, and sends the segmented image sub-regions to the processing and evaluation module;

[0054] The spatial data KF, dense data MF and noise data ZS of all image sub-areas are obtained and numerically calculated to obtain the evaluation coefficient and deviation coefficient of the analysis image, and an optimization cycle is generated. The image type and shooting purpose in the basic parameters of the analysis image received within the optimization cycle are freely combined to obtain several parameter groups. The evaluation coefficient and deviation coefficient of the analysis image are numerically calculated to obtain the optimization coefficient YH, and the priority mode of the parameter group is marked by the optimization coefficient YH.

[0055] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0056] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula CL=k1×KF+k2×MF-k3×ZS; technicians in this field collect multiple groups of sample data and set corresponding processing coefficients for each group of sample data; substitute the set processing coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of k1, k2 and k3 as 3.54, 2.82 and 2.31 respectively;

[0057] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the initial setting of the corresponding processing coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the processing coefficient is proportional to the value of the space-separated data.

[0058] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A digital image intelligent processing system suitable for urology, characterized in that: It includes image acquisition module, image segmentation module, processing evaluation module and processing optimization module; The image acquisition module is used to acquire digital images of urology: obtain the user's digital images of urology and mark them as analysis images, mark the image type and shooting purpose of the analysis images as basic parameters of the analysis images; send the analysis images to the image segmentation module, and send the basic parameters of the analysis images to the processing optimization module; The image segmentation module is used to perform segmentation processing on the digital image of urology: randomly select a segmentation method to perform image segmentation on the analysis image to obtain a plurality of image sub-regions, the segmentation methods include OTSU threshold segmentation, region growth segmentation, edge detection segmentation and watershed algorithm segmentation; and send the image sub-regions obtained by segmentation to the processing and evaluation module; The processing evaluation module is used to evaluate and analyze the segmentation processing effect of the urology digital image: obtain the spatial data KF, dense data MF and noise data ZS of the image sub-region and perform numerical calculation to obtain the processing coefficient CL of the image sub-region; sum and average the processing coefficients CL of all image sub-regions of the analyzed image to obtain the evaluation coefficient, perform variance calculation on the processing coefficients CL of all image sub-regions of the analyzed image to obtain the deviation coefficient, and judge whether the segmentation processing effect of the analyzed image meets the requirements through the evaluation coefficient and the deviation coefficient; The processing optimization module is used to optimize the urology digital image: generate an optimization cycle, freely combine the image type and the shooting purpose in the basic parameters of the analyzed image received within the optimization cycle to obtain a number of parameter groups, mark the optimization method of the parameter group, and send the optimization method of the parameter group to the image segmentation module; The specific process of marking the optimization method of the parameter group includes: numerically calculating the evaluation coefficient and the deviation coefficient of the analysis image to obtain the optimization coefficient YH of the analysis image; marking the analysis image whose basic parameters meet the parameter group as the matching image of the parameter group, summing and averaging the optimization coefficients YH of the matching images using the same segmentation method in the parameter group to obtain the optimization performance value of the segmentation method, and marking the segmentation method with the largest optimization performance value as the optimization method of the parameter group; The calculation process of the optimization coefficient YH of the analysis image includes: marking the evaluation coefficient and the deviation coefficient of the analysis image as PG and PC respectively, and obtaining the optimization coefficient YH of the analysis image through the formula YH=m1×PG-m2×PC, wherein m1 and m2 are both proportional coefficients, and m1>m2>1; The parameter groups are divided according to the basic parameters, and then the segmentation method, evaluation coefficient and deviation coefficient used in the matching image within the parameter group are comprehensively analyzed to obtain the optimization method of the parameter group, so as to improve the matching degree between the segmentation method and the basic parameters of the image in the subsequent image segmentation.

2. The digital image intelligent processing system suitable for urology according to claim 1, characterized in that: The image types for analysis include B-ultrasound images, CT images and magnetic resonance images, and the purposes of taking analysis images include physical examinations, medical consultations and follow-up examinations.

3. The digital image intelligent processing system suitable for urology according to claim 2 is characterized in that: The spatial data KF is the maximum value of the spatial resolution of the image sub-region, the dense data MF is the maximum value of the density resolution of the image sub-region, and the noise data ZS is the image noise decibel value of the image sub-region.

4. The digital image intelligent processing system suitable for urology according to claim 3 is characterized in that: The specific process of determining whether the segmentation processing effect of the analysis image meets the requirements includes: calling the evaluation threshold and the deviation threshold, and comparing the evaluation coefficient and the deviation coefficient of the analysis image with the evaluation threshold and the deviation threshold respectively: if the evaluation coefficient is greater than or equal to the evaluation threshold and the deviation coefficient is less than the deviation threshold, then it is determined that the segmentation processing effect of the analysis image meets the requirements, and the evaluation coefficient and the deviation coefficient of the analysis image are sent to the processing optimization module; otherwise, it is determined that the segmentation processing effect of the analysis image does not meet the requirements, and a re-segmentation signal is generated and sent to the image segmentation module.

5. The digital image intelligent processing system suitable for urology according to claim 4, characterized in that: After receiving the re-segmentation signal, the image segmentation module selects other segmentation methods and re-performs image segmentation processing, and sends the re-segmented image sub-region to the processing evaluation module again, and so on, until the segmentation processing effect of the analyzed image meets the requirements; after the image segmentation module uses all segmentation methods to perform image segmentation on the image sub-region, when the segmentation processing effect of the analyzed image does not meet the requirements, a re-acquisition signal is generated and sent to the image acquisition module; when the image acquisition module receives the re-acquisition signal, it re-acquires the patient's urology digital image.

6. A digital image intelligent processing method suitable for urology, using a digital image intelligent processing system suitable for urology as claimed in any one of claims 1 to 5, characterized in that: The following steps are involved: Step 1: Collect digital images of urology surgery; Step 2: Segmentation of urology digital images; Step 3: Evaluate and analyze the segmentation effect of urology digital images; Step 4: Optimize the processing of urology digital images.

Images