Method and apparatus for processing medical images

Abstract

The present application provides a method and apparatus for processing medical images, which are applied in a medical image viewing system and include: obtaining a medical image; determining a first region of interest of the medical image according to a user's selection and determining a smoothing level; and performing smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest that has been smoothed. The method and apparatus for processing medical images of the present application perform smoothing processing on the region of interest according to the region of interest and the smoothing level selected by the user, can reduce the jaggedness and holes of the region of interest, simplify the operation steps of the viewer, and improve the viewing efficiency of the viewer.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and more specifically, to a method and apparatus for processing medical images, a computer-readable storage medium, and an electronic device. Background Art

[0002] DICOM (Digital Imaging and Communications in Medicine) is an international standard (ISO 12052) for medical images and related information. It defines a medical image format that can be used for data exchange and whose quality meets clinical requirements.

[0003] In the process of processing medical images, it is usually necessary to select a region of interest (ROI) on the medical image, but the existing methods for processing medical images have a poor effect on the selection of the region of interest. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method and apparatus for processing medical images, a computer-readable storage medium, and an electronic device, which can improve the effect of selecting the region of interest.

[0005] In a first aspect, an embodiment of this application provides a method for processing medical images, which is applied to a medical image viewing system. The processing method includes: obtaining a medical image; determining a first region of interest of the medical image according to a user's selection, and determining a smoothing level; performing smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest that has been smoothed.

[0006] In some embodiments of this application, the processing method further includes: calculating medical parameters of the second region of interest, where the medical parameters include one or more of the major axis, minor axis, area, maximum brightness, and minimum brightness of the second region of interest.

[0007] In some embodiments of this application, performing smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest that has been smoothed includes: performing dilation processing on the first region of interest according to a preset dilation coefficient to obtain a first region of interest that has been dilated; performing blurring processing on the first region of interest that has been dilated according to the smoothing level and a Gaussian smoothing algorithm to obtain a first region of interest that has been blurred; automatically drawing the contour of the first region of interest that has been blurred to generate a second region of interest.

[0008] In some embodiments of the present application, determining the smoothing level includes: calculating the major axis of the first region of interest using the Hough transform algorithm, and calculating the area of the first region of interest using the vector cross product method; determining the smoothing level based on the major axis of the first region of interest and the area of the first region of interest.

[0009] In some embodiments of the present application, determining the smoothing level based on the major axis of the first region of interest and the area of the first region of interest includes: weighting the major axis of the first region of interest and the area of the first region of interest to determine the smoothing level, where the smoothing level is determined by the following formula:

[0010] Level = max(10L, 100) × w L × 0.1 + max(S, 100) × w S × 0.1

[0011] In the formula, Level is the smoothing level, L is the value of the major axis of the first region of interest, w L is the weight of the major axis of the first region of interest, S is the value of the area of the first region of interest, w S is the weight of the area of the first region of interest.

[0012] In some embodiments of the present application, determining the first region of interest of the medical image includes: determining the first region of interest according to the selection parameters, where the selection parameters include the brush width and / or the tolerance value and / or the region value, the brush width is used to adjust the brush size, the color selection range of the first region of interest does not exceed the range of the tolerance value, and the coordinate selection range of the first region of interest does not exceed the range of the region value.

[0013] In some embodiments of the present application, determining the first region of interest according to the selection parameters includes: determining the first region of interest using the flood fill algorithm according to the selection parameters.

[0014] In a second aspect, an embodiment of the present application provides a processing device for medical images, which is applied in a medical image viewing system. The processing device includes: an acquisition module for acquiring medical images; a determination module for determining the first region of interest of the medical image and determining the smoothing level according to the user's selection; a smoothing module for smoothing the first region of interest according to the smoothing level to generate a second region of interest that has been smoothed.

[0015] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program for executing the medical image processing method according to any one of the first aspect.

[0016] Fourthly, an embodiment of the present application provides an electronic device, including: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute the medical image processing method according to any one of the first aspect.

[0017] According to the region of interest selected by the user and the smoothing level, the medical image processing method of the present application performs smoothing processing on the region of interest, which can reduce the jaggedness and holes in the region of interest, simplify the operation steps of the viewer, and improve the viewing efficiency of the viewer. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of an implementation environment of a medical image processing method provided by an embodiment of the present application.

[0019] Figure 2 It is a schematic flowchart of a medical image processing method provided by an embodiment of the present application.

[0020] Figure 3 It is a schematic flowchart of a smoothing processing method provided by another embodiment of the present application.

[0021] Figure 4 It is a schematic flowchart of a method for determining the smoothing level provided by another embodiment of the present application.

[0022] Figure 5a The figure shows a schematic diagram of selecting parameters provided by an exemplary embodiment of the present application.

[0023] Figure 5b The figure shows a schematic diagram of the effect of the first region of interest provided by an exemplary embodiment of the present application.

[0024] Figure 5c The figure shows a schematic diagram of the effect of the second region of interest provided by an exemplary embodiment of the present application.

[0025] Figure 6 The figure shows a schematic structural diagram of a medical image processing device provided by an embodiment of the present application.

[0026] Figure 7 The figure shows a block diagram of an electronic device for executing the medical image processing method provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not used to limit the protection scope of the present application.

[0028] The term "including" and its variants used in the present application are open-ended, that is, "including but not limited to". The term "according to" means "at least partially according to". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment". The relevant definitions of other terms will be given in the following description.

[0029] Embodiments of the present application can be used in a medical image reading system. In terms of image management, the medical image reading system supports multi-center image upload, image query, and performs review and quality control management on the uploaded images. In terms of reading management, it supports the design of the reading process, the allocation, tracking, and query of multi-level reading, and also supports multiple readings. In the entire business process, intelligent statistical management is carried out on the upload review and reading of images, and the image status and reading progress are followed up in real time.

[0030] Medical images, which can also be referred to as medical pictures, can be medical images such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Computed Radiography (CR), or Digital radiography (DR). The embodiments of the present application do not make specific limitations in this regard.

[0031] The DICOM image file structure mainly consists of two parts: a file header and a data set. The file header is used to indicate whether the file is a DICOM image file. The data set includes data related to the imaging instance such as the name of the subject (e.g., patient), imaging modality, and image size, as well as the image pixel data of the imaging instance. The embodiments of the present application do not limit the specific form of medical images, which can be original medical images, pre-processed medical images, or a part of the original medical images.

[0032] In the process of researching a medical image reading system, the applicant found that the current medical image reading system has poor selection effects for regions of interest. For example, it is unable to intelligently and quickly select regions of interest with irregular shapes, or there are a large number of holes and serrations in the selected regions of interest, and there is a phenomenon of inward contraction at the edge of the selected area, resulting in the need for the reader to re-mark the regions of interest and manually measure medical parameters such as the major and minor diameters, which reduces the reading efficiency of the reader.

[0033] To solve the above problems, the present application provides a method for processing medical images.

[0034] Figure 1 It is a schematic diagram of an implementation environment provided by an embodiment of the present application. The implementation environment includes a CT scanner 110 and a computer device 120.

[0035] The computer device 110 can obtain medical images from the CT scanner 110. For example, the computer device 120 can communicate with the CT scanner 110 through a wired network or a wireless network.

[0036] The CT scanner 110 is used to perform X-ray scanning on human tissues to obtain CT medical images of human tissues. In one embodiment, by scanning the chest of a human body with the CT scanner 110, a chest CT medical image can be obtained.

[0037] The computer device 120 can be a general-purpose computer or a computer device composed of dedicated integrated circuits, etc., and the embodiments of the present application do not limit this. For example, the computer device 120 can be a mobile terminal device such as a tablet computer, or it can also be a personal computer (PC), such as a laptop computer and a desktop computer, etc.

[0038] Those skilled in the art can know that the number of the above computer devices 120 can be one or more, and their types can be the same or different. For example, the above computer device 120 can be one, or the above computer device 120 can be dozens or hundreds, or more. The embodiments of the present application do not limit the number and device type of the computer device 120.

[0039] In some alternative embodiments, the computer device 120 obtains medical images from the CT scanner 110, determines a first region of interest and a smoothing level of the medical images, and performs smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest that has been smoothed.

[0040] Figure 2 Schematically shows a flowchart of a method for processing medical images provided by an embodiment of the present invention. Figure 2The described method is executed by a computing device (e.g., a server), but the embodiments of the present application are not limited thereto. The server can be a single server, or composed of several servers, or a virtualization platform, or a cloud computing service center, and the embodiments of the present application do not limit this. As Figure 2 shown, the method includes the following content.

[0041] S210: Obtain a medical image.

[0042] Specifically, after a medical imaging device scans a subject, a medical image can be obtained from the medical imaging device. For example, the medical image can be a DICOM image file. The medical imaging device can be a computed tomography device, a magnetic resonance imaging device, a positron emission tomography device, etc.

[0043] S220: Determine a first region of interest of the medical image according to the user's selection, and determine a smoothing level.

[0044] Specifically, the user can set the brush width and control the mouse to select the first region of interest. For example, the flood fill algorithm can be used to select the first region of interest in one key. The brush width is also called the stroke size and is used to draw and select the first region of interest. The user can be a radiologist, and the radiologist uses a medical image viewing system to review the medical image, such as the selection and marking of the region of interest.

[0045] The medical image viewing system of this embodiment is provided with multiple smoothing levels, and the smoothing effects of different smoothing levels are different. The smoothing level can be determined according to the user's setting, and the smoothing level is used for the smoothing process in subsequent steps. The user can choose to automatically obtain the smoothing level of the first region of interest, or manually set or adjust the smoothing level. The step of determining the smoothing level can be before the step of determining the first region of interest. For example, the user first manually sets the smoothing level and then selects the first region of interest. The step of determining the smoothing level can also be after the step of determining the first region of interest. For example, the user first selects the option to automatically obtain the smoothing level, and then determines the first region of interest. At this time, the viewing system determines the smoothing level of the first region of interest according to the first region of interest selected by the user. The present application does not limit the sequence of the step of determining the smoothing level and the step of determining the first region of interest. The relevant description of automatically obtaining the smoothing level can be seen in the description of the following embodiments.

[0046] S230: Smooth the first region of interest according to the smoothing level to generate a second region of interest that has been smoothed.

[0047] Specifically, the Gaussian smoothing algorithm can be used to smooth the first region of interest to generate a second region of interest that has been smoothed. Different smoothing levels correspond to different degrees of smoothing. For example, the lower the smoothing level, the lower the degree of smoothing, and vice versa, the higher the smoothing level, the higher the degree of smoothing. The user can adjust the degree of smoothing of the first region of interest by adjusting the smoothing level to reduce or eliminate the jagged edges and holes in the first region of interest.

[0048] Figure 5b The following is a schematic diagram of the effect of the first region of interest provided by an exemplary embodiment of the present application. As Figure 5b shown, there are a large number of jagged edges and holes in the first region of interest without smoothing, which has a great impact on image reading and the calculation of medical parameters. Figure 5c The following is a schematic diagram of the effect of the second region of interest provided by an exemplary embodiment of the present application. As Figure 5c shown, when the smoothing level is increased, the holes and jagged edges in the second region of interest that has been smoothed are significantly reduced.

[0049] The method for processing medical images of the present application smoothes the region of interest according to the region of interest and the smoothing level selected by the user, can reduce the jagged edges and holes in the region of interest, improve the selection effect of the region of interest, improve the usability and functionality of the medical image reading system, simplify the operation steps of the image reader, and improve the image reading efficiency of the image reader.

[0050] In one embodiment, the processing method further includes: calculating medical parameters of the second region of interest, where the medical parameters include one or more of the major axis, minor axis, area, maximum brightness, and minimum brightness of the second region of interest.

[0051] Specifically, after generating the smoothed second region of interest, medical parameters of the second region of interest can be calculated. The long diameter and short diameter of the second region of interest can be calculated using the Hough transform algorithm. The Hough transform is a feature detection method (Feature Extraction) that is widely used in image analysis (Image Analysis), computer vision (Computer Vision), and digital image processing (Digital Image Processing). The Hough transform is used to identify features in an object, such as lines. The general process is as follows: Given the type of shape of an object to be identified, the algorithm performs voting in the parameter space (Parameter Space) to determine the shape of the object, and the local maximum (Local Maximum) in the accumulator space (Accumulator Space) determines it. The shape of an object can be detected using the Hough transform algorithm, that is, the generalized Hough transform is applied to detect a graphic with an arbitrary shape boundary. First, an arbitrary point (a, b) in the shape is selected as the reference point, and then from each point on the edge of the arbitrary shape graphic, its tangent direction φ, the offset vector r to the position of the reference point (a, b), and the angle α between r and the x-axis are calculated. The position of the reference point (a, b) can be calculated by the following formula:

[0052] a = x + r(φ)cos(α(φ))

[0053] b = x + r(φ)sin(α(φ)).

[0054] In this embodiment, by calculating the medical parameters of the second region of interest, it is avoided that the film reader manually measures medical parameters such as the long and short diameters, improving the film reading efficiency of the film reader, the usability and functionality of the medical image film reading system.

[0055] In one embodiment, as Figure 3 shown, the first region of interest is smoothed according to the smoothing level to generate a smoothed second region of interest (step 230), including the following content.

[0056] S231: According to a preset dilation coefficient, the first region of interest is dilated to obtain a dilated first region of interest.

[0057] Specifically, since the Gaussian smoothing algorithm will blur the entire image during smoothing, as the smoothing level increases, the edges of the entire selected area will continuously shrink. Therefore, in this embodiment, the dilation algorithm in image morphology is used to dilate the selected area to a certain extent according to the preset dilation coefficient to solve the edge shrinkage phenomenon caused by smoothing, so that the smoothing process will not affect the change of the selected area. For example, the preset dilation coefficient can be set to 1%.

[0058] S232: Blur the first region of interest after dilation processing according to the smoothing level and the Gaussian smoothing algorithm to obtain the blurred first region of interest.

[0059] Specifically, the Gaussian distribution function can be expressed as a one-dimensional function:

[0060]

[0061] Or the Gaussian distribution function can also be expressed as a two-dimensional function:

[0062]

[0063] In the above functions, x and y represent the offset values (pixel offsets) relative to the pixel of the original center tap, that is, the number of pixels from the center. σ in the function is also called "sigma" and is often used to represent "standard deviation" in statistics. Gaussian smoothing is also called Gaussian blur. The standard deviation of Gaussian blur represents the extension distance of the blur. Its default value is generally set to 1, and a stronger effect can be obtained by increasing the default value. e in the function is Euler's Number, and its value is generally taken as 2.7. The result of the above function, that is, the weighted value (weight) centered on x (in one direction) or (x, y) (in two directions), or the degree to which this point affects the blurred pixel. The higher the smoothing level, the greater the degree of blur processing.

[0064] S233: Automatically draw the contour of the blurred first region of interest to generate the second region of interest.

[0065] Specifically, after obtaining the blurred first region of interest, the medical image reading system automatically draws the contour of the blurred first region of interest, and this contour is the second region of interest.

[0066] The smoothing method of this embodiment dilates the first region of interest first and then blurs it, eliminating the edge shrinkage phenomenon caused by the smoothing process, so that the area of the first region of interest does not change significantly after the smoothing process.

[0067] In one embodiment, as Figure 4 shown, determining the smoothing level includes the following content.

[0068] S221: Calculate the major axis of the first region of interest using the Hough transform algorithm, and calculate the area of the first region of interest using the vector cross product method.

[0069] S222: Determine the smoothing level according to the major axis of the first region of interest and the area of the first region of interest.

[0070] Specifically, when the user selects to automatically obtain the smoothing level, the medical image reading system can first calculate the major axis length and area of the first region of interest, and then automatically calculate the appropriate smoothing level for the first region of interest based on the major axis length and area, and perform smoothing processing for subsequent steps according to this smoothing level.

[0071] In this embodiment, by calculating the major axis length and area of the first region of interest, the appropriate smoothing level for the first region of interest can be automatically obtained, avoiding the loss of some edge details caused by too high a smoothing level or a large number of holes and sawteeth caused by too low a smoothing level.

[0072] In one embodiment, determining the smoothing level (step 222) according to the major axis length of the first region of interest and the area of the first region of interest includes: weighting the major axis length of the first region of interest and the area of the first region of interest to determine the smoothing level, where the smoothing level is determined by the following formula:

[0073] Level = max(10L, 100) × w L × 0.1 + max(S, 100) × w S × 0.1

[0074] In the formula, Level is the smoothing level, L is the value of the major axis length of the first region of interest, w L is the weight of the major axis length of the first region of interest, S is the value of the area of the first region of interest, w S is the weight of the area of the first region of interest.

[0075] Specifically, since the user does not know the specific medical parameters (such as the major and minor axis lengths) of the first region of interest before selecting the first region of interest, situations where the smoothing degree is too high or too low may occur. For example, if the smoothing level is too low, a large number of holes and sawteeth will be left at the edge and inside of the first region of interest (i.e., Gaussian smoothing is undersaturated), and if the smoothing level is too high, some edge details of the first region of interest will be lost (i.e., Gaussian smoothing is oversaturated), which will cause certain obstacles to image reading. Based on the above problems, the applicant developed a weighted average matching rule to match the major axis length and area of the first region of interest, that is:

[0076] Level = max(10L, 100) × w L × 0.1 + max(S, 100) × w S × 0.1

[0077] In the formula, Level is the smoothing level, L is the value of the major axis length of the first region of interest, and the unit can be mm, w LThe weight of the major axis of the first region of interest, S is the value of the area of the first region of interest, and the unit can be mm 2 , w S is the weight of the area of the first region of interest, and the smoothing level is calculated according to the above formula.

[0078] In this embodiment, the weights of the major axis and the area of the first region of interest are assigned, and the smoothing level of the first region of interest can be calculated to automatically obtain the appropriate smoothing degree of the first region of interest.

[0079] In one embodiment, determining the first region of interest of a medical image includes: determining the first region of interest according to the selection parameters, where the selection parameters include the brush width and / or the tolerance value and / or the region value. The brush width is used to adjust the brush size, the color selection range of the first region of interest does not exceed the range of the tolerance value, and the coordinate selection range of the first region of interest does not exceed the range of the region value.

[0080] Figure 5a The following is a schematic diagram of the selection parameters provided by an exemplary embodiment of the present application. As Figure 5a shown, the selection parameters include the brush width (i.e., the brush size), the tolerance value, the region value, and the smoothing level. The radiologist can set the brush width, the tolerance value, the region value, and the smoothing level simultaneously to select the first region of interest, or only set some of the selection parameters to select the first region of interest. For example, only set the brush width and the tolerance value, and select to automatically obtain the smoothing level. The brush width is used to adjust the brush size, the tolerance value is used to limit the color selection range of the first region of interest, and the region value is used to limit the coordinate selection range of the first region of interest.

[0081] In this embodiment, the first region of interest is selected through four dimensions: the brush width, the tolerance value, the region value, and the smoothing level, which can realize the fast one-key selection of irregular regions of interest based on human-computer interaction and improve the radiologist's reading efficiency.

[0082] In one embodiment, determining the first region of interest according to the selection parameters includes: using the flood fill algorithm to determine the first region of interest according to the selection parameters.

[0083] Specifically, the flood fill algorithm can be used to quickly and one-key select the first region of interest. The flood fill algorithm (Flood Fill) starts from a starting pixel point, extracts or fills the nearby connected pixel points with different colors until all the pixel points in the closed area have been processed. It is a classic algorithm for extracting several connected points from a region to distinguish it from other adjacent regions. It can be implemented by using the recursive method of depth-first search or the iteration of breadth-first search.

[0084] This embodiment uses a flood filling algorithm, which can select the first region of interest (ROI) with one click, improving the functionality and usability of a medical image reading system, saving the operation steps of the reader, and enhancing the reading efficiency of the reader.

[0085] Figure 6 The following is a schematic structural diagram of a processing device for medical images provided by an embodiment of the present application, including:

[0086] An acquisition module 610, configured to acquire medical images;

[0087] A determination module 620, configured to determine the first region of interest of the medical image according to the user's selection, and determine the smoothing level;

[0088] A smoothing module 630, configured to perform smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest after smoothing processing.

[0089] The processing device for medical images of the present application performs smoothing processing on the region of interest according to the region of interest and the smoothing level selected by the user, which can reduce the jaggedness and holes in the region of interest, improve the selection effect of the region of interest, enhance the usability and functionality of the medical image reading system, simplify the operation steps of the reader, and improve the reading efficiency of the reader.

[0090] According to an embodiment of the present application, the processing device further includes: calculating medical parameters of the second region of interest, where the medical parameters include one or more of the major axis, minor axis, area, maximum brightness, and minimum brightness of the second region of interest.

[0091] According to an embodiment of the present application, the smoothing module 630 performs dilation processing on the first region of interest according to a preset dilation coefficient to obtain a first region of interest after dilation processing; performs blurring processing on the first region of interest after dilation processing according to the smoothing level and the Gaussian smoothing algorithm to obtain a first region of interest after blurring processing; automatically draws the contour of the first region of interest after blurring processing to generate a second region of interest.

[0092] According to an embodiment of the present application, the determination module 620 uses the Hough transform algorithm to calculate the major axis of the first region of interest and uses the vector cross product method to calculate the area of the first region of interest; determines the smoothing level according to the major axis of the first region of interest and the area of the first region of interest.

[0093] According to an embodiment of the present application, the determination module 620 weights the major axis of the first region of interest and the area of the first region of interest to determine the smoothing level, where the smoothing level is determined by the following formula:

[0094] Level = max(10L, 100) × w L×0.1 + max(S, 100) × w S ×0.1

[0095] Wherein, Level is the smoothing level, L is the value of the major axis of the first region of interest, w L is the weight of the major axis of the first region of interest, S is the value of the area of the first region of interest, w S is the weight of the area of the first region of interest.

[0096] According to an embodiment of the present application, the determination module 620 determines the first region of interest according to the selected parameters, where the selected parameters include the brush width and / or the tolerance value and / or the region value. The brush width is used to adjust the brush size, the color selection range of the first region of interest does not exceed the tolerance value range, and the coordinate selection range of the first region of interest does not exceed the region value range.

[0097] According to an embodiment of the present application, the determination module 620 determines the first region of interest according to the selected parameters by using the flood fill algorithm.

[0098] For the specific limitations of the medical image processing device, reference can be made to the limitations of the medical image processing method in the above text, which will not be elaborated here.

[0099] Figure 7 The block diagram of the electronic device 700 for executing the medical image processing method provided by an exemplary embodiment of the present application is shown, including a processor 710 and a memory 720.

[0100] The memory 720 is used to store the executable instructions of the processor. The processor 710 is used to run the executable instructions to execute the medical image processing method described in any one of the above embodiments.

[0101] The present application also provides a computer-readable storage medium, and the storage medium stores a computer program, and the computer program is used to execute the medical image processing method described in any one of the above embodiments.

[0102] The medical image processing method and device of the present application perform smoothing processing on the region of interest according to the region of interest and the smoothing level selected by the user, can reduce the jaggedness and holes of the region of interest, improve the selection effect of the region of interest, improve the usability and functionality of the medical image reading system, simplify the operation steps of the reader, and improve the reading efficiency of the reader.

[0103] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, fiber optic, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a digital video disc (DVD)), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0104] Those of ordinary skill in the art will realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in an electrical, mechanical, or other form.

[0106] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, each functional unit in various embodiments of the present application may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit.

[0108] As described above, only the specific implementation manners of the present application are provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for processing medical images, characterized in that, Applied in a medical image reading system, the processing method includes: Obtain medical images; According to the user's selection, determine a first region of interest of the medical image and determine a smoothing level, wherein the first region of interest is an irregular-shaped region; Perform smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest after smoothing processing, Wherein, determining the first region of interest of the medical image includes: Determine the first region of interest according to selection parameters, wherein the selection parameters include a brush width, a tolerance value, a region value, and a smoothing level. The brush width is used to adjust the brush size, the color selection range of the first region of interest does not exceed the range of the tolerance value, and the coordinate selection range of the first region of interest does not exceed the range of the region value. The performing smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest after smoothing processing includes: Perform dilation processing on the first region of interest according to a preset dilation coefficient to obtain a first region of interest after dilation processing; Perform blurring processing on the first region of interest after dilation processing according to the smoothing level and a Gaussian smoothing algorithm to obtain a first region of interest after blurring processing; Automatically draw the contour of the first region of interest after blurring processing to generate the second region of interest.

2. The processing method according to claim 1, wherein It further includes: Calculate medical parameters of the second region of interest, where the medical parameters include one or more of the major axis, minor axis, area, maximum brightness, and minimum brightness of the second region of interest.

3. The processing method according to claim 1, characterized in that, The determining the smoothing level includes: using the Hough transform algorithm to calculate the major axis of the first region of interest and using the vector cross product method to calculate the area of the first region of interest; Determine the smoothing level according to the major axis of the first region of interest and the area of the first region of interest.

4. The processing method according to claim 3, wherein The determining the smoothing level according to the major axis of the first region of interest and the area of the first region of interest includes: Perform weighting on the major axis of the first region of interest and the area of the first region of interest to determine the smoothing level, wherein the smoothing level is determined by the following formula: Level = max(10L, 100) × w L × 0.1 + max(S, 100) × w S × 0.1 Wherein, Level is the smoothing level, L is the value of the major axis of the first region of interest, w L is the weight of the major axis of the first region of interest, S is the value of the area of the first region of interest, w S is the weight of the area of the first region of interest.

5. The processing method according to claim 1, characterized in that The determining the first region of interest according to the selection parameters includes: Determine the first region of interest using the flood fill algorithm according to the selection parameters.

6. A processing device for medical images, characterized in that, Applied in a medical image reading system, the processing device includes: An acquisition module for acquiring medical images; A determination module for determining a first region of interest of the medical image and determining a smoothing level according to the user's selection, wherein the first region of interest is an irregular-shaped region; A smoothing module for performing smoothing processing on the first region of interest according to the smoothing level to generate a second region of interest after smoothing processing, Wherein, the determining module is further configured to determine the first region of interest according to the selection parameters, where the selection parameters include a brush width, a tolerance value, a region value, and a smoothing level. The brush width is used to adjust the brush size. The color selection range of the first region of interest does not exceed the range of the tolerance value, and the coordinate selection range of the first region of interest does not exceed the range of the region value. The determining module is further configured to perform dilation processing on the first region of interest according to a preset dilation coefficient to obtain a dilated first region of interest; perform blurring processing on the dilated first region of interest according to the smoothing level and a Gaussian smoothing algorithm to obtain a blurred first region of interest; automatically draw the contour of the blurred first region of interest to generate the second region of interest.

7. A computer-readable storage medium storing a computer program for executing the method for processing medical images according to any one of claims 1 to 5 above.

8. An electronic device, comprising: a processor; a memory for storing executable instructions of the processor, wherein the processor is configured to execute the method for processing medical images according to any one of claims 1 to 5 above.

Images