CN116563299B - Medical image screening method, device, electronic device and storage medium - Google Patents
Medical image screening method, device, electronic device and storage medium Download PDFInfo
- Publication number
- CN116563299B CN116563299B CN202310852571.7A CN202310852571A CN116563299B CN 116563299 B CN116563299 B CN 116563299B CN 202310852571 A CN202310852571 A CN 202310852571A CN 116563299 B CN116563299 B CN 116563299B
- Authority
- CN
- China
- Prior art keywords
- image
- images
- medical
- brightness
- clear
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012216 screening Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000011156 evaluation Methods 0.000 claims description 49
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 description 30
- 230000008569 process Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 6
- 230000008014 freezing Effects 0.000 description 6
- 238000007710 freezing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013500 data storage Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20216—Image averaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a medical image screening method, a device, an electronic device and a storage medium, wherein the medical image screening method comprises the following steps: acquiring a plurality of medical images; determining an image quality parameter of each medical image based on a pixel value of a preset position in each medical image; determining an area parameter of a target object in each medical image; the target medical image is selected from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images. The application solves the problem of low definition of medical images and improves the definition of medical images.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a medical image screening method, a medical image screening device, an electronic device, and a storage medium.
Background
With the rapid development of the endoscope technology and related medical equipment industry, the functions of the endoscope are also increasing. Most of the existing endoscopes have an image freezing function, and image freezing refers to making a device continuously display a frozen frame on a display interface, and the frozen frame is called a frozen image.
At present, when a user freezes an image through an endoscope, the obtained frozen image is in global or local blurring due to slight movement of an endoscope handle and an endoscope head end inevitably, and further, subsequent diagnosis is carried out through the blurred frozen medical image, and the subsequent diagnosis result is greatly negatively influenced, so that risks of focus missing detection and false detection are high.
Aiming at the problem of low definition of medical images in the related art, no effective solution is proposed at present.
Disclosure of Invention
In this embodiment, a medical image screening method, apparatus, electronic apparatus, and storage medium are provided to solve the problem of low medical image definition in the related art.
In a first aspect, in this embodiment, there is provided a medical image screening method, including:
acquiring a plurality of medical images;
determining an image quality parameter of each medical image based on a pixel value of a preset position in each medical image;
determining an area parameter of a target object in each of the medical images;
and screening the target medical image from the medical images based on the image quality parameters of the medical images and the area parameters of the target object in the medical images.
In some of these embodiments, the determining the image quality parameter of each of the medical images based on the pixel value of the preset position in each of the medical images includes:
dividing a medical image to be processed into a plurality of sub-images, wherein the medical image to be processed is any image in the plurality of medical images;
determining a definition evaluation value of a sub-image to be processed based on pixel values of a vertex and a center point in the sub-image to be processed, wherein the sub-image to be processed is any sub-image of the medical image to be processed;
and determining an image quality parameter of the medical image to be processed based on the definition evaluation values of all the sub-images of the medical image to be processed.
In some embodiments, the determining the sharpness evaluation value of the sub-image to be processed based on the pixel values of the vertex and the center point in the sub-image to be processed includes:
determining the average value of pixels of the vertexes of the sub-images to be processed on R, G, B three channels as a vertex pixel value;
determining the average value of pixels of the center point of the sub-image to be processed on three R, G, B channels as a center point pixel value;
and determining a definition evaluation value of the sub-image to be processed based on the vertex pixel values of all vertexes of the sub-image to be processed and the center point pixel value.
In some embodiments, the number of the plurality of medical images is m, where m is a positive integer greater than or equal to 1, and the selecting the target medical image from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images includes:
screening n object salient images from a plurality of medical images based on a preset area range and area parameters of target objects in each medical image, wherein the area parameters of the target objects in the object salient images are in the preset area range, and n is a positive integer which is greater than or equal to 1 and less than or equal to m;
screening s clear images from the n object salient images based on the image quality parameters of the n object salient images, wherein s is a positive integer greater than or equal to 1 and less than or equal to n;
and determining the target medical image based on the brightness values of the s clear images.
In some of these embodiments, the determining the target medical image based on the luminance values of the s distinct images includes:
dividing a clear image to be processed into a plurality of clear sub-images, wherein the clear image to be processed is any image in s clear images;
Determining the brightness value of each clear sub-image and the brightness value of the clear image to be processed based on the pixel values of all pixel points in each clear sub-image on R, G, B three channels and the brightness evaluation weights of the clear image to be processed on R, G, B three channels respectively;
determining a brightness distribution value of the clear image to be processed based on the brightness value of each clear sub-image and the brightness value of the clear image to be processed;
and determining the target medical image from the s clear images based on the brightness distribution values of the s clear images.
In some of these embodiments, after the screening of the target medical image from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images, the method further comprises:
determining a highlight pixel point in the target medical image based on brightness values and brightness threshold values of all pixel points in the target medical image;
determining the replacement pixel value of the highlight pixel point based on the pixel values of all the pixel points in a preset distance range around the highlight pixel point;
and replacing the pixel value of the highlight pixel point with the replaced pixel value to obtain the target medical image without the bright spots.
In some embodiments, the determining the replacement pixel value of the highlight pixel point based on the pixel values of all the pixel points within the preset distance range around the highlight pixel point includes:
determining the brightness average value of all pixel points in a preset distance range around the highlight pixel point;
if the brightness average value is larger than or equal to the brightness threshold value, the preset distance range is adjusted to obtain an adjusted preset distance range, and the brightness average value of all the pixel points in the adjusted preset distance range is calculated again until the brightness average value of all the pixel points in the adjusted preset distance range is smaller than the brightness threshold value;
and determining the average value of the pixels of all the pixel points in the adjusted preset distance range as the replacement pixel value of the highlight pixel point.
In a second aspect, in this embodiment, there is provided a medical image screening apparatus including:
an acquisition module for acquiring a plurality of medical images, the medical images comprising a target object;
the first determining module is used for determining an image quality parameter of each medical image based on a pixel value of a preset position in each medical image;
a second determining module for determining an area parameter of the target object in each of the medical images;
And the image screening module is used for screening target medical images from the medical images based on the image quality parameters of the medical images and the area parameters of the medical images.
In a third aspect, in this embodiment, there is provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the medical image screening method according to any one of the embodiments of the first aspect when the processor executes the computer program.
In a fourth aspect, in this embodiment, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the medical image screening method according to any one of the embodiments of the first aspect described above.
Compared with the related art, the medical image screening method, the device, the electronic device and the storage medium provided in the embodiment determine the image quality parameter of each medical image through the pixel value of the preset position in each medical image in the plurality of medical images, further determine the area parameter of the target object in each medical image, and further screen the plurality of medical images according to the image quality parameters of the plurality of medical images and the area parameter of the target object in the plurality of medical images to obtain the target medical image. When medical image screening is carried out, the image quality parameters and the area parameters of the target objects are used as reference factors for medical image screening, so that the screened target medical images can meet the quality requirements of the medical images, and the target objects can be intuitively determined from the medical images, thereby improving the definition of the medical images.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
fig. 1 is a schematic view of an application scenario of a medical image screening method according to an embodiment of the present application;
FIG. 2 is a flowchart of a medical image screening method according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for setting a fixed value of exposure time and a fixed value of gain parameter of an endoscope camera according to an embodiment of the present application;
FIG. 4 is a flowchart of an embodiment of a medical image screening method according to an embodiment of the present application;
fig. 5 is a block diagram of a medical image screening apparatus according to an embodiment of the present application;
fig. 6 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application.
Detailed Description
The present application will be described and illustrated with reference to the accompanying drawings and examples for a clearer understanding of the objects, technical solutions and advantages of the present application.
Unless defined otherwise, technical or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," "these" and similar terms in this application are not intended to be limiting in number, but may be singular or plural. The terms "comprising," "including," "having," and any variations thereof, as used herein, are intended to encompass non-exclusive inclusion; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (units) is not limited to the list of steps or modules (units), but may include other steps or modules (units) not listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in this disclosure are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. Typically, the character "/" indicates that the associated object is an "or" relationship. The terms "first," "second," "third," and the like, as referred to in this disclosure, merely distinguish similar objects and do not represent a particular ordering for objects.
The medical image screening method provided by the embodiment of the application can be applied to an application scene shown in fig. 1, and fig. 1 is a schematic diagram of the application scene of the medical image screening method provided by the embodiment of the application. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. In particular, the terminal 102 may be an endoscope and the data storage system may be used to store medical images obtained by the endoscope. It should be noted that, in the embodiment of the present application, the terminal 102 is only an endoscope as an example, and in practical application, the terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
With the rapid development of the endoscope technology and related medical equipment industry, the functions of the endoscope are also increasing. Most of the existing endoscopes have an image freezing function, and image freezing refers to making a device continuously display a frozen frame on a display interface, and the frozen frame is called a frozen image.
At present, when a user freezes an image through an endoscope, the obtained frozen image is in global or local blurring due to slight movement of an endoscope handle and an endoscope head end inevitably, and further, subsequent diagnosis is carried out through the blurred frozen medical image, and the subsequent diagnosis and treatment result is greatly negatively influenced, so that risks of focus missing detection and false detection are high.
Therefore, how to improve the sharpness of medical images is a problem to be solved.
In this embodiment, a medical image screening method is provided, and fig. 2 is a flowchart of a medical image screening method provided in this embodiment of the present application, and an execution subject of the method may be an electronic device, optionally, the electronic device may be a server or a terminal device, but the present application is not limited thereto. Specifically, as shown in fig. 2, the process includes the following steps:
Step S201, a plurality of medical images are acquired.
The medical image screening method provided by the application can be applied to a use scene of an endoscope, specifically, a plurality of medical images of specified body parts can be obtained through the endoscope, and when the medical images are obtained through the endoscope, the medical images can include target objects, and the medical images can also not include the target objects or only include partial target objects due to shake of hands of a user, and the target objects can refer to tumor cells, normal cells and other tissues of the body parts, so that the medical image screening method is not limited.
Step S202, determining an image quality parameter of each medical image based on pixel values of preset positions in each medical image.
Further, an image quality parameter of the corresponding medical image is determined according to the pixel value of the preset position in each medical image.
Specifically, the image quality parameter may refer to the sharpness of the medical image, or may refer to the brightness of the medical image, or may refer to the gray scale of the medical image, or may refer to the combination of the sharpness, brightness, and gray scale of the medical image, which is not limited herein. The preset position may refer to one or more positions of a center pixel, a vertex pixel, and any other pixel in the medical image, which is not limited herein.
In step S203, an area parameter of the target object in each medical image is determined.
Further, determining an area parameter of the target object according to the area of the minimum circumscribing polygon comprising the target object in the medical image.
If a plurality of target objects are included in one medical image, the area parameter of the target object may be an average value of areas of the smallest circumscribing polygons of the plurality of target objects.
It should be noted that the shape of the minimum circumscribed polygon may be rectangular, pentagonal, hexagonal, or other shapes, which is not limited in this regard.
Step S204, screening the target medical image from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images.
Further, the plurality of medical images are screened according to the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images, so that the target medical images with higher image quality parameters and larger area parameters of the target object are screened.
In the implementation process, the image quality parameter of the medical image is determined according to the pixel value of the preset position in the medical image, so that the accuracy of determining the medical image quality parameter can be improved, further, the area parameter of the target object in the medical image is determined, the medical image is screened according to the image quality parameter of the medical image and the area parameter of the target object in the medical image, and the target medical image is obtained, so that the screened target medical image can meet the quality requirement of the medical image, and the target object can be intuitively determined from the medical image, so that the definition of the medical image is improved.
In some of these embodiments, determining the image quality parameter for each medical image based on the pixel value of the preset location in each medical image may comprise the steps of:
step 1: dividing the medical image to be processed into a plurality of sub-images, wherein the medical image to be processed is any image in the plurality of medical images.
Step 2: and determining a definition evaluation value of the sub-image to be processed based on pixel values of the top point and the center point in the sub-image to be processed, wherein the sub-image to be processed is any sub-image of the medical image to be processed.
Step 3: an image quality parameter of the medical image to be processed is determined based on the sharpness evaluation values of all sub-images of the medical image to be processed.
Illustratively, taking the image quality parameter as the definition of the image as an example, the medical image to be processed is divided into a plurality of sub-images of equal size, and the medical image to be processed is any one of the plurality of medical images.
As one example, the medical image to be processed may be divided into a plurality of sub-images of equal size, each of which may be of the sizeMay be +.>May also be +.>Other sizes are also possible, and the number of sub-images may be determined according to the size of the medical image to be processed, for example, the medical image to be processed may be divided into 160 sub-images of equal size, and the size of each sub-image is ∈ >。
Further, according to the pixel values of the four vertex pixels of the sub-image to be processed and the pixel values of the center point pixels of the sub-image to be processed, determining a definition evaluation value of the sub-image to be processed, wherein the sub-image to be processed is any sub-image of the medical image to be processed.
Further, according to the definition evaluation values of all the sub-images in the medical image to be processed, the image quality parameters of the image to be processed are determined. Specifically, the sum of the definition evaluation values of all the sub-images in the medical image to be processed is determined as the image quality parameter of the medical image to be processed. As another example, the image quality parameters of the medical image to be processed may also be obtained by weighted summation of sharpness evaluation values of all sub-images in the medical image to be processed.
In the implementation process, the medical image to be processed is divided into a plurality of sub-images, the definition evaluation value of the sub-images is determined according to the vertex pixel value and the center point pixel value of each sub-image, and the definition of each sub-image can be accurately evaluated according to the pixel value distribution of the center point pixel and each vertex pixel in each sub-image, and further, the image quality parameters of the medical image to be processed are determined according to the definition evaluation values of all the sub-images, so that the accuracy of determining the image quality parameters of the medical image to be processed is improved.
In some embodiments, determining the sharpness evaluation value of the sub-image to be processed based on the pixel values of the vertices and the center points in the sub-image to be processed may include the steps of:
step 1: and determining the average value of pixels of the vertexes of the sub-images to be processed on the R, G, B three channels as a vertex pixel value.
Step 2: and determining the average value of pixels of the center point of the sub-image to be processed on the R, G, B three channels as a center point pixel value.
Step 3: and determining a definition evaluation value of the sub-image to be processed based on the vertex pixel values of all the vertices and the center point pixel values of the sub-image to be processed.
Illustratively, the average value of pixels of the vertex pixels of the sub-image to be processed on three channels R, G, B is determined as the vertex pixel value, so that the vertex pixel values of four vertices in the sub-image to be processed can be determined.
Further, determining the average value of pixels of the center point pixel of the sub-image to be processed on the R, G, B three channels to obtain the pixel value of the center point.
Further, the sum of squares of the differences between the pixel values of each vertex and the pixel value of the center point is determined as a sharpness evaluation value of the sub-image to be processed.
In the implementation process, according to the pixel average value of the pixel points in the sub-image on the R, G, B three channels, the pixel average value is used as the pixel value of the pixel points, so that the accuracy of determining the pixel value is improved, furthermore, the square sum of the difference between the pixel values of each vertex and the center point in the sub-image is determined, so that the distribution value of the definition in the sub-image is accurately determined, and further, the distribution value of the definition in the sub-image is determined as the definition evaluation value of the sub-image, and the accuracy of the definition evaluation of the sub-image is improved.
In some embodiments, the number of the plurality of medical images is m, m is a positive integer greater than or equal to 1, and the selecting the target medical image from the plurality of medical images based on the image quality parameter of the plurality of medical images and the area parameter of the target object in the plurality of medical images may include:
step 1: and screening n object salient images from the medical images based on a preset area range and the area parameters of the target object in each medical image, wherein the area parameters of the target object in the object salient images are in the preset area range, and n is a positive integer which is greater than or equal to 1 and less than or equal to m.
For example, if the number of medical images acquired by the endoscope is m, where m is a positive integer greater than or equal to 1, in order to acquire medical images with significant target objects from the m medical images, n significant target images may be selected from the plurality of medical images according to an area parameter of the target objects in each medical image and a preset area range.
Specifically, a preset area range can be determined, and images of m medical images, of which target objects exceed the preset area range, are removed, so that object salient images are obtained, that is, the area parameters of the target objects in the object salient images are in the preset area range, the number of the object salient images is n, n is a positive integer which is greater than or equal to 1 and less than or equal to m, and therefore the target objects in the m medical images are removed too small or too large, and screening of the salient target object images is achieved.
As an embodiment, the preset area range may be set in advance, or may be determined according to area parameters of all target objects in the m medical images.
Specifically, if the average value of the area parameters of all the target objects in the m medical images is P, the preset area range may be set to [ P-Y%, p+y% ], where 30.ltoreq.y.ltoreq.50, Y may be equal to 20, or may be equal to 30, or may be equal to 35, or may be another number, which is not limited herein.
Step 2: and screening s clear images from the n object salient images based on the image quality parameters of the n object salient images, wherein s is a positive integer which is greater than or equal to 1 and less than or equal to n.
Further, the image quality parameters of the n screened object salient images are sequenced from large to small to obtain n sequenced object salient images, and the first Q percent of the n sequenced object salient images are determined to be clear images, namelyQ is 5.ltoreq.Q.ltoreq.10, Q is 5 or 7 or 8, or other numbers, and s is a positive integer of 1 or more and n or less.
Step 3: and determining the target medical image based on the brightness values of the s clear images.
Further, the brightness value of each of the s clear images is determined, the brightness distribution value of each clear image is determined, and the clear image with the minimum brightness distribution value is determined as the target medical image.
In the implementation process, according to the preset area range and the area parameter of the target object in each medical image, determining the medical image with obvious target object, further, determining the image with higher definition in the medical image with obvious target object, so that the determined clear image has higher definition, the target object in the medical image can be clearly and intuitively observed, and the clear image with the minimum brightness distribution value is determined as the target medical image, so that the target medical image with uniform brightness distribution is obtained.
In some of these embodiments, after the target medical image is selected from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images, the method may further include: and performing image freezing on the target medical image to obtain a frozen image.
In the implementation process, the screened target medical image is subjected to image freezing, so that the obtained frozen image can clearly reflect a target object, and the subsequent diagnosis is carried out according to the frozen image, thereby effectively improving the accuracy of a diagnosis result and further reducing the risks of focus missing detection and false detection.
In some of these embodiments, determining the target medical image based on the luminance values of the s sharp images may include the steps of:
step 1: dividing the clear image to be processed into a plurality of clear sub-images, wherein the clear image to be processed is any one image of the s clear images.
Illustratively, the clear image to be processed is divided into a plurality of clear sub-images with equal size, and the pixel values of all pixel points in each clear sub-image on R, G, B three channels are determined, and the brightness evaluation weights of the clear image to be processed on R, G, B three channels respectively.
Step 2: and determining the brightness value of each clear sub-image and the brightness value of the clear image to be processed based on the pixel values of all pixel points in each clear sub-image on R, G, B three channels and the brightness evaluation weights of the clear image to be processed on R, G, B three channels respectively.
For example, if the luminance evaluation weights of the to-be-processed clear images on the three channels R, G, B are 0.3,0.6,0.1, the luminance value of any pixel point in each clear sub-image is:thereby determining the brightness value of all pixel points in each clear sub-image.
Further, an average value of the luminance values of all the pixel points in one clear sub-image is determined as the luminance value of the clear sub-image.
Further, an average value of brightness values of all the clear sub-images in the clear image to be processed is determined as the brightness value of the clear image to be processed.
Step 3: and determining the brightness distribution value of the clear image to be processed based on the brightness value of each clear sub-image and the brightness value of the clear image to be processed.
Illustratively, the luminance variance value of the to-be-processed clear image is determined according to the luminance value of each clear sub-image and the luminance value of the to-be-processed clear image, and further, the luminance variance value is determined as the luminance distribution value of the to-be-processed clear image.
Specifically, if the brightness value of the clear image to be processed isThe brightness value of the clear sub-image is X i Where i is 1,2,3, …, k, k is the total number of clear sub-images in the clear image to be processed, and the brightness distribution value of the clear image to be processed is:
wherein S is 2 Is the brightness distribution value of the clear image to be processed.
Step 4: and determining the target medical image from the s clear images based on the brightness distribution values of the s clear images.
Further, the brightness distribution values of the s clear images are determined, and the clear image with the minimum brightness distribution value in the s clear images is determined as the target medical image.
As another embodiment, a clear image having a luminance distribution value smaller than a preset luminance distribution threshold value among the s clear images is determined as a luminance uniformity image, and further, any one of the luminance uniformity images is determined as a target medical image.
In the implementation process, since the endoscope is generally applied to each body tissue, and the surface convex-concave degree of the body tissue is different, particularly, liquid is inevitably remained in the alimentary canal, so that the brightness distribution of the acquired image is uneven.
Because the light source at the head end of the endoscope body inevitably generates bright spots in the image when being directly irradiated, the imaging quality of the image is affected, and therefore, the bright spots in the image need to be eliminated.
In some of these embodiments, after screening the target medical image from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images, further comprising: and eliminating the bright spots on the target medical image to obtain the target medical image without the bright spots.
Specifically, the method for eliminating the bright spots on the target medical image to obtain the target medical image without the bright spots can comprise the following steps:
step 1: and determining the highlight pixel points in the target medical image based on the brightness values and the brightness threshold values of all the pixel points in the target medical image.
For example, the brightness values of all pixels in the target medical image may be determined, and the pixels with brightness values greater than the brightness threshold in the target medical image may be determined as the highlight pixels, where the brightness threshold may be M, where the range of M is 250+.m+.255.
Step 2: and determining the replacement pixel value of the highlight pixel based on the pixel values of all the pixel points within a preset distance range around the highlight pixel.
Step 3: and replacing the pixel value of the highlight pixel point with the replaced pixel value to obtain the target medical image without the bright spots.
Further, an average value of pixel values of all pixels within a preset distance range around the highlight pixel is determined as a replacement pixel value of the highlight pixel.
Further, the pixel value of the highlight pixel point is replaced by the replacement pixel value, so that the target medical image without the bright spots is obtained.
In the implementation process, according to the pixel values of all the pixel points in the target medical image and the brightness threshold value, the high brightness pixel points in the target medical image are determined, and the pixel values of the high brightness pixel points are replaced by the pixel values of the pixel points around the high brightness pixel points, so that the elimination of the bright spots in the target medical image is realized, and the pixel values of the high brightness pixel points are replaced by the pixel values around the high brightness pixel points, so that the uniformity of brightness in the target medical image can be effectively improved.
In some embodiments, determining the replacement pixel value of the highlight pixel based on the pixel values of all the pixels within the preset distance range around the highlight pixel may include the steps of:
step 1: and determining the brightness average value of all the pixel points in the preset distance range around the highlight pixel point.
Step 2: if the average brightness value is greater than or equal to the brightness threshold value, the preset distance range is adjusted to obtain the adjusted preset distance range, and the average brightness value of all the pixel points in the adjusted preset distance range is calculated again until the average brightness value of all the pixel points in the adjusted preset distance range is smaller than the brightness threshold value.
Step 3: and determining the average value of the pixels of all the pixel points in the adjusted preset distance range as the replacement pixel value of the highlight pixel point.
For example, if the preset distance is r, the preset distance range may be a square with a side length r centered on the highlighted pixel, further, an average value of brightness values of all pixels in the square with a side length r centered on the highlighted pixel is determined, and the average value of brightness values is determined as a brightness average value of the square.
Further, the average brightness value of the square and the brightness threshold value are determined.
If the average brightness value of the square is smaller than the brightness threshold value, determining the average pixel value of all the pixel points in the square range in R, G, B three channels as the replacement pixel value of the highlighted pixel point.
If the average brightness value of the square is greater than or equal to the brightness threshold value, the preset distance range is increased, as an example, the preset distance may be increased, the step size of the increase may be r, the adjusted preset distance is r1=r+r, and correspondingly, the adjusted preset distance range is a square with the highlighted pixel point as the center and the side length of r1, the average value of the brightness values of all the pixel points in the square with the side length of r1 is determined again, and the average value of the brightness values is determined as the average brightness value of the square with the side length of r 1.
If the average brightness value of the square is smaller than the brightness threshold value, determining the average pixel value of all the pixel points in the square range in R, G, B three channels as the replacement pixel value of the highlighted pixel point, if the average brightness value of the square is larger than or equal to the brightness threshold value, increasing the preset distance again, wherein the increasing step length can be r, the preset distance after adjustment is r2=r+r+r, corresponding, the adjusted preset distance range is a square with a side length of r2 by taking the highlight pixel point as the center, and then determining the average value of the brightness values of all the pixel points in the square with the side length of r2, and determining the average value of the brightness values as the average value of the brightness of the square with the side length of r 2.
Repeating the steps until the average value of the brightness values of all the pixel points in the square with the side length being the adjusted preset distance is smaller than the brightness threshold value by taking the highlighted pixel point as the center, and determining the average value of the pixels in the square with the adjusted preset distance in R, G, B three channels as the replacement pixel value of the highlighted pixel point.
It should be noted that, in the embodiment of the present application, only the increasing step is taken as an example for describing, and the value range of r may be: in practical application, the step length added each time can be the same or different, the step length can be 2r or 3r, and the method is not limited.
In the implementation process, if the average value of the brightness of all the pixel points in the preset distance range is greater than or equal to the brightness threshold value, the preset distance range is adjusted until the average value of the brightness of all the pixel points in the adjusted preset distance range is smaller than the brightness threshold value, and the average value of the pixels in the adjusted preset distance range is determined to be the replacement pixel value of the highlight pixel point, so that the pixel value of the highlight pixel point after replacement is smaller than the brightness threshold value.
In some of these embodiments, prior to acquiring the plurality of medical images, further comprising: and adjusting the exposure time and the gain parameter of the endoscope camera so that the brightness value of the endoscope image obtained by the endoscope under the adjusted exposure time and gain parameter is in the normal brightness value range corresponding to the current working level of the endoscope light source, thereby obtaining the fixed value of the exposure time and the fixed value of the gain parameter under the current working level of the endoscope.
Fig. 3 is a flowchart of a method for setting a fixed exposure time value and a fixed gain parameter value of an endoscope camera according to an embodiment of the present application, as shown in fig. 3, where the flowchart includes:
step S301: at the current operating level, the endoscope camera is set to the highest exposure time and lowest gain parameters.
Specifically, the working levels of the endoscope light source may include a low brightness level, a normal brightness level, and a high brightness level, and each working level has a corresponding normal brightness value range. The endoscope light source sets the endoscope camera to the highest exposure time and lowest gain parameters at the normal brightness level.
It should be noted that, setting the gain parameter to be the lowest can ensure that the least noise is introduced, setting the exposure time of the endoscope camera to be the highest, and selecting the highest exposure time parameter is for selecting the real-time image of the endoscope camera under the condition of the lowest gain parameter not to be too dark easily.
Step S302: and acquiring a test image under the current exposure time and the current gain parameter.
Further, a test image is acquired by the endoscope camera under the current exposure time and the current gain parameters.
If the current exposure time of the endoscope camera is the highest exposure time and the current gain parameter is the lowest gain parameter, acquiring a test image through the endoscope camera under the highest exposure time and the lowest gain parameter, and if the current exposure time of the endoscope camera is the adjusted exposure time and the current gain parameter is the adjusted gain parameter, acquiring the test image through the endoscope camera under the adjusted exposure time and the adjusted gain parameter.
Specifically, the test image may be an image obtained by photographing the flat blank paper by the endoscope camera, and the photographing distance may be adjusted according to the difference of actual working conditions.
Step S303: it is determined whether the brightness evaluation value of the test image is within a normal brightness value range at the current operation level.
Further, if the operation level of the endoscope light source is the normal brightness level, it is judged whether the brightness evaluation value of the test image is within the normal brightness range of the normal brightness level.
Specifically, the test image is divided into a plurality of area images with equal size, the number of the area images can be determined according to the size of the test image, and the test image can be divided into 16 blocksThe area images of the same size are exemplified.
Further, the pixel values of all the pixel points in each area image on the R, G, B three channels are determined, and the brightness evaluation weights of the test images on the R, G, B three channels respectively under the current working grade are determined. When the current working level of the endoscope light source is the normal brightness level, the brightness evaluation weights of the test image on the R, G, B three channels are respectively 0.3, 0.6 and 0.1, and further, in the area image, the brightness value of each pixel point is = 。
And determining the average value of the brightness values of all the pixel points in the area image as the brightness value of the area image.
Further, a position saliency parameter of the target object in the region image is determined. Since there is no target object in the area image, the position saliency parameter of the no area image may be 1.
The product of the luminance value of each area image and the corresponding position saliency parameter is determined as a luminance evaluation value of each area image.
Further, the minimum value among the luminance evaluation values of all the area images is determined as the luminance evaluation value of the test image.
Step S304: and if the brightness evaluation value of the test image is not in the normal brightness value range under the current working level, adjusting the exposure time and/or gain parameters of the endoscope camera until the brightness evaluation value of the test image is in the normal brightness value range under the current working level.
Specifically, the exposure time parameter of the endoscope camera can be classified into F grades, the exposure time parameter of the endoscope camera can be sequentially increased from 1 to F, the step length is 1, and the brightness of the picture acquired by the camera is sequentially improved under the condition that the brightness of the endoscope light source is unchanged; the gain parameters of the endoscope camera can be graded into Z, the gain parameters of the endoscope camera can be sequentially increased from 1 to Z, the step length is 1, and the brightness of the pictures collected by the camera is sequentially improved under the condition that the brightness of the endoscope light source is unchanged, so that the brightness adjustable grades of the endoscope camera are shared And each. In a specific implementation, the exposure time parameter and the gain parameter are set to 1 each time the step size is adjusted.
Specifically, the current working level of the endoscope light source is a normal brightness level, the normal brightness value range of the normal brightness level is [60, 120], if the brightness evaluation value of the test image is higher than 120, the image brightness is excessively high, and if the brightness evaluation value of the test image is lower than 60, the brightness is excessively low.
If the brightness value of the test image is within the normal brightness value range, the exposure time parameter of the endoscope camera is reduced by 1 level, the step S302 is returned until the brightness value of the test image is lower than the normal brightness range, and the exposure time of the camera before the last reduction is selected as the exposure time fixed parameter of the endoscope camera.
In the implementation process, under the initial conditions of the highest exposure time parameter and the lowest gain parameter, if the brightness of the test image is within the normal brightness range, the imaging quality can be improved by reducing the exposure time parameter of the camera.
If the brightness value of the test image is lower than the normal brightness range and the brightness of the test image before the last adjustment is in the normal brightness range, setting the exposure time parameter of the camera before the last adjustment as a fixed value of the exposure time parameter of the camera, and setting the gain parameter before the last adjustment as a fixed value of the gain parameter; if the brightness value of the test image is lower than the normal brightness range and the brightness of the test image before the last adjustment is not in the normal brightness range, the gain parameter is adjusted up, and the step S302 is returned until the brightness value of the test image is in the normal brightness range, and the gain parameter after the last adjustment is taken as the gain parameter fixed value.
If the brightness value of the test image is higher than the normal brightness range and the brightness value of the test image before the last adjustment is in the normal brightness range, the camera exposure time parameter before the adjustment is a camera exposure time parameter fixed value, and the gain parameter before the adjustment is a gain parameter fixed value; if the brightness value of the test image is higher than the normal brightness range and the test image is not in the normal brightness range before the last adjustment, the camera exposure time parameter is reduced, and the step S302 is returned until the brightness value of the test image is in the normal brightness range, and the camera exposure time parameter after the last reduction is taken as the camera exposure time parameter fixed value.
In the implementation process, before the primary adjustment of the brightness of the endoscope light source, the exposure time and the gain parameter of the camera of the endoscope are set to fixed values respectively, and in the adjustment process of the brightness of the endoscope light source, the exposure time and the gain parameter are kept unchanged, so that the influence of the exposure time and the gain parameter on the image brightness value can be effectively avoided, and the accuracy of the adjustment of the brightness of the endoscope light source is ensured.
Fig. 4 is a flowchart of an embodiment of a medical image screening method according to an embodiment of the present application, as shown in fig. 4, where the flowchart includes the following steps:
Step S401: the exposure time and gain parameters of the camera of the endoscope are set to fixed values.
Specifically, if the endoscope light source is at the common brightness level, setting the exposure time and gain parameters of the camera of the endoscope to fixed values at the common brightness level; if the endoscope light source is at a low brightness level, setting the exposure time and gain parameters of a camera of the endoscope to fixed values at the low brightness level; if the endoscope light source is at a high brightness level, the exposure time and gain parameters of the camera of the endoscope are set to fixed values at the high brightness level.
Step S402: under the current setting, a plurality of medical images are acquired by an endoscopic camera over a fixed time interval.
Specifically, the fixed time interval can be set according to practical situations, and is generally the real-time frame rate T, and T is more than or equal to 500ms and less than or equal to 1000ms.
Step S403: and screening s medical images from the plurality of medical images according to the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images.
Specifically, each medical image is divided into a plurality of sub-images with equal size, and each sub-image may be square or rectangular, and in the embodiment of the present application, the shape of the sub-image is taken as a square as an example.
And determining the average value of pixels of three channel types at R, G, B of any pixel point in each sub-image as the gradient evaluation value of the pixel point.
Further, the sum of squares of the differences between the gradient evaluation values of the four vertex pixels and the gradient evaluation value of the center pixel in any square sub-image is used as the definition evaluation value of the square sub-image.
Further, the sharpness evaluation values of all the sub-images in one medical image are summed up and determined as the image quality parameter of the medical image.
For example, a Canny edge detection function may be used to determine a minimum bounding rectangle of the target objects in the medical image, and if a minimum bounding rectangle of a plurality of target objects is detected in a certain medical image, an area average value of the minimum bounding rectangle of the plurality of target objects is determined as an area parameter of the target objects in the medical image.
Further, according to the determined image quality parameters of the plurality of medical images and the area parameters of the target objects in the plurality of medical images, clear medical images with obvious target objects are screened for the first time.
Further, an average value of the area parameter of the target object in the plurality of medical images is determined.
And removing the medical image corresponding to the outlier of the minimum circumscribed rectangular area from the m medical images, wherein the outlier is defined as Y% which is larger than or smaller than the average value of the area parameters of the target objects in the medical images, wherein Y is larger than or equal to 30 and smaller than or equal to 50, so that n obvious images of the objects are obtained.
Further, in the n significant images of the object, the first Q percent is reserved according to the image quality parameters from large to small, wherein Q is more than or equal to 5 and less than or equal to 10, so that s clear images are obtained.
Step S404: and determining the target medical image with uniform brightness according to the brightness values of the s clear images.
Specifically, any clear image is divided into a plurality of clear sub-images, and the brightness values of all the clear sub-images and the brightness values of the clear images are determined.
Specifically, the pixel values of all the pixels in each clear sub-image under R, G, B three channels are determined, and further, the pixel values of each pixel in each clear sub-image under R, G, B three channels are weighted and summed to obtain the brightness value of each pixel, i.e., the brightness value of each pixel in each clear sub-image =Wherein a1, a2 and a3 are R, G respectivelyAs an example, a1, a2, a3 are respectively 0.3,0.6,0.1, and r, G, B are respectively pixel values under the corresponding channels.
It should be noted that, in the embodiment of the present application, only 0.3,0.6,0.1 is taken as an example of the luminance evaluation weight under R, G, B three channels, and in practical application, the luminance evaluation weight under R, G, B three channels may be 0.4,0.4,0.2, or may be other ratios, which is not limited herein.
Determining the average value of the brightness values of all pixel points in any clear sub-image as the brightness value of the clear sub-image; in any clear image, the average value of the brightness values of all the pixel points is determined as the brightness value of the clear image.
In any clear image, the brightness variance of the clear image is determined according to the brightness values of all the clear sub-images and the brightness values of the clear image, so as to obtain the brightness variance of all the clear images.
Further, a clear image with the smallest brightness variance among the s clear images is determined as a target medical image with uniform brightness, so that secondary screening is completed.
Step S405: and determining a high-brightness pixel point in the target medical image, and replacing the pixel value of the high-brightness pixel point with the pixel value of the pixel points around the high-brightness pixel point to obtain the medical image without the bright spots.
Specifically, the brightness values of all the pixel points in the target medical image are determined, and the pixel point with the brightness value larger than M is determined as a highlight pixel point, namely a bright spot.
Further, determining the average brightness value of all the pixels in a square range with the side length r taking the bright spot as the center, and if the average brightness value of all the pixels in the square range is smaller than M, calculating the average brightness value of all the pixels in the square range on R, G, B three channels to be used as a new R, G, B channel value of the bright pixel.
If the average brightness value of all the pixel points in the square range is greater than or equal to M, expanding the side length of the square intoIf the average brightness value of all the pixel points in the enlarged square range is still more than or equal to M, repeating the steps until the average brightness value of all the pixel points in the enlarged square range is less than M.
Further, the pixel average value of all pixels in the square range on the R, G, B three channels is used as a new R, G, B channel value of the highlight pixel.
Although the steps in the flowcharts according to the embodiments described above are shown in order as indicated by the arrows, these steps are not necessarily executed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
In this embodiment, a medical image screening apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and will not be described in detail. The terms "module," "unit," "sub-unit," and the like as used below may refer to a combination of software and/or hardware that performs a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.
Fig. 5 is a block diagram of a medical image screening apparatus according to an embodiment of the present application, as shown in fig. 5, including:
an acquisition module 501 for acquiring a plurality of medical images, the medical images including a target object;
a first determining module 502, configured to determine an image quality parameter of each medical image based on a pixel value of a preset position in each medical image;
a second determining module 503 for determining an area parameter of the target object in each medical image;
an image screening module 504 is configured to screen a target medical image from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the plurality of medical images.
In some of these embodiments, the first determining module 502 is specifically configured to:
dividing a medical image to be processed into a plurality of sub-images, wherein the medical image to be processed is any image in the plurality of medical images;
determining a definition evaluation value of the sub-image to be processed based on pixel values of the top point and the center point in the sub-image to be processed, wherein the sub-image to be processed is any sub-image of the medical image to be processed;
an image quality parameter of the medical image to be processed is determined based on the sharpness evaluation values of all sub-images of the medical image to be processed.
In some of these embodiments, the first determining module 502 is specifically configured to:
determining the average value of pixels of the vertexes of the sub-images to be processed on R, G, B three channels as a vertex pixel value;
determining the average value of pixels of the center point of the sub-image to be processed on R, G, B three channels as a center point pixel value;
and determining a definition evaluation value of the sub-image to be processed based on the vertex pixel values of all the vertices and the center point pixel values of the sub-image to be processed.
In some embodiments, the number of the plurality of medical images is m, where m is a positive integer greater than or equal to 1, and the image filtering module 504 is specifically configured to:
Based on a preset area range and area parameters of target objects in each medical image, screening n object salient images from a plurality of medical images, wherein the area parameters of the target objects in the object salient images are in the preset area range, and n is a positive integer which is greater than or equal to 1 and less than or equal to m;
based on the image quality parameters of the n object salient images, screening s clear images from the n object salient images, wherein s is a positive integer which is greater than or equal to 1 and less than or equal to n;
and determining the target medical image based on the brightness values of the s clear images.
In some of these embodiments, the image screening module 504 is specifically configured to:
dividing a clear image to be processed into a plurality of clear sub-images, wherein the clear image to be processed is any image in the s clear images;
determining the brightness value of each clear sub-image and the brightness value of the clear image to be processed based on the pixel values of all pixel points in each clear sub-image on R, G, B three channels and the brightness evaluation weights of the clear image to be processed on R, G, B three channels respectively;
determining a brightness distribution value of the clear image to be processed based on the brightness value of each clear sub-image and the brightness value of the clear image to be processed;
And determining the target medical image from the s clear images based on the brightness distribution values of the s clear images.
In some of these embodiments, the image screening module 504 is further configured to:
determining a highlight pixel point in the target medical image based on brightness values and brightness threshold values of all pixel points in the target medical image;
determining replacement pixel values of the highlight pixel points based on pixel values of all the pixel points within a preset distance range around the highlight pixel points;
and replacing the pixel value of the highlight pixel point with the replaced pixel value to obtain the target medical image without the bright spots.
In some of these embodiments, the image screening module 504 is specifically configured to:
determining the brightness average value of all pixel points in a preset distance range around the highlight pixel point;
if the brightness average value is greater than or equal to the brightness threshold value, adjusting the preset distance range to obtain an adjusted preset distance range, and calculating the brightness average value of all the pixel points in the adjusted preset distance range again until the brightness average value of all the pixel points in the adjusted preset distance range is smaller than the brightness threshold value;
and determining the average value of the pixels of all the pixel points in the adjusted preset distance range as the replacement pixel value of the highlight pixel point.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
In one embodiment, a computer device is provided, where the computer device may be a server, and an internal structure diagram of the computer device may be shown in fig. 6, and fig. 6 is a schematic diagram of an internal structure diagram of the computer device according to an embodiment of the present application. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing medical image data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a medical image screening method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, there is also provided an electronic device including a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method embodiments described above when executing the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
The user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random AccessMemory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (StaticRandom Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the patent claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (8)
1. A medical image screening method, comprising:
acquiring a plurality of medical images;
determining an image quality parameter of each medical image based on a pixel value of a preset position in each medical image;
determining an area parameter of a target object in each of the medical images;
screening a target medical image from a plurality of medical images based on image quality parameters of the medical images and area parameters of a target object in the medical images;
The number of the medical images is m, m is a positive integer greater than or equal to 1, and the screening the target medical image from the medical images based on the image quality parameters of the medical images and the area parameters of the target object in the medical images comprises the following steps:
screening n object salient images from a plurality of medical images based on a preset area range and area parameters of target objects in each medical image, wherein the area parameters of the target objects in the object salient images are in the preset area range, and n is a positive integer which is greater than or equal to 1 and less than or equal to m;
screening s clear images from the n object salient images based on the image quality parameters of the n object salient images, wherein s is a positive integer greater than or equal to 1 and less than or equal to n;
determining the target medical image based on the brightness values of the s clear images;
the determining the target medical image based on the brightness values of the s clear images comprises:
dividing a clear image to be processed into a plurality of clear sub-images, wherein the clear image to be processed is any image in s clear images;
Determining the brightness value of each clear sub-image and the brightness value of the clear image to be processed based on the pixel values of all pixel points in each clear sub-image on R, G, B three channels and the brightness evaluation weights of the clear image to be processed on R, G, B three channels respectively;
determining a brightness distribution value of the clear image to be processed based on the brightness value of each clear sub-image and the brightness value of the clear image to be processed;
and determining the target medical image from the s clear images based on the brightness distribution values of the s clear images.
2. The medical image screening method according to claim 1, wherein the determining an image quality parameter of each of the medical images based on pixel values of preset positions in each of the medical images includes:
dividing a medical image to be processed into a plurality of sub-images, wherein the medical image to be processed is any image in the plurality of medical images;
determining a definition evaluation value of a sub-image to be processed based on pixel values of a vertex and a center point in the sub-image to be processed, wherein the sub-image to be processed is any sub-image of the medical image to be processed;
And determining an image quality parameter of the medical image to be processed based on the definition evaluation values of all the sub-images of the medical image to be processed.
3. The medical image screening method according to claim 2, wherein the determining the sharpness evaluation value of the sub-image to be processed based on the pixel values of the vertices and the center points in the sub-image to be processed includes:
determining the average value of pixels of the vertexes of the sub-images to be processed on R, G, B three channels as a vertex pixel value;
determining the average value of pixels of the center point of the sub-image to be processed on three R, G, B channels as a center point pixel value;
and determining a definition evaluation value of the sub-image to be processed based on the vertex pixel values of all vertexes of the sub-image to be processed and the center point pixel value.
4. The medical image screening method according to claim 1, further comprising, after the screening of the target medical image from the plurality of medical images based on the image quality parameters of the plurality of medical images and the area parameters of the target object in the plurality of medical images:
determining a highlight pixel point in the target medical image based on brightness values and brightness threshold values of all pixel points in the target medical image;
Determining the replacement pixel value of the highlight pixel point based on the pixel values of all the pixel points in a preset distance range around the highlight pixel point;
and replacing the pixel value of the highlight pixel point with the replaced pixel value to obtain the target medical image without the bright spots.
5. The medical image screening method according to claim 4, wherein the determining the replacement pixel value of the highlight pixel based on the pixel values of all the pixels within the preset distance range around the highlight pixel includes:
determining the brightness average value of all pixel points in a preset distance range around the highlight pixel point;
if the brightness average value is larger than or equal to the brightness threshold value, the preset distance range is adjusted to obtain an adjusted preset distance range, and the brightness average value of all the pixel points in the adjusted preset distance range is calculated again until the brightness average value of all the pixel points in the adjusted preset distance range is smaller than the brightness threshold value;
and determining the average value of the pixels of all the pixel points in the adjusted preset distance range as the replacement pixel value of the highlight pixel point.
6. A medical image screening apparatus, comprising:
An acquisition module for acquiring a plurality of medical images, the medical images comprising a target object;
the first determining module is used for determining an image quality parameter of each medical image based on a pixel value of a preset position in each medical image;
a second determining module for determining an area parameter of the target object in each of the medical images;
an image screening module, configured to screen a target medical image from a plurality of medical images based on image quality parameters of the plurality of medical images and area parameters of the plurality of medical images;
the number of the medical images is m, m is a positive integer greater than or equal to 1, and the image screening module is specifically configured to:
screening n object salient images from a plurality of medical images based on a preset area range and area parameters of target objects in each medical image, wherein the area parameters of the target objects in the object salient images are in the preset area range, and n is a positive integer which is greater than or equal to 1 and less than or equal to m;
screening s clear images from the n object salient images based on the image quality parameters of the n object salient images, wherein s is a positive integer greater than or equal to 1 and less than or equal to n;
Determining the target medical image based on the brightness values of the s clear images;
the image screening module is used for determining the target medical image based on the brightness values of the s clear images, and is particularly used for:
dividing a clear image to be processed into a plurality of clear sub-images, wherein the clear image to be processed is any image in s clear images;
determining the brightness value of each clear sub-image and the brightness value of the clear image to be processed based on the pixel values of all pixel points in each clear sub-image on R, G, B three channels and the brightness evaluation weights of the clear image to be processed on R, G, B three channels respectively;
determining a brightness distribution value of the clear image to be processed based on the brightness value of each clear sub-image and the brightness value of the clear image to be processed;
and determining the target medical image from the s clear images based on the brightness distribution values of the s clear images.
7. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the medical image screening method of any one of claims 1 to 5.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the medical image screening method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310852571.7A CN116563299B (en) | 2023-07-12 | 2023-07-12 | Medical image screening method, device, electronic device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310852571.7A CN116563299B (en) | 2023-07-12 | 2023-07-12 | Medical image screening method, device, electronic device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116563299A CN116563299A (en) | 2023-08-08 |
CN116563299B true CN116563299B (en) | 2023-09-26 |
Family
ID=87498705
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310852571.7A Active CN116563299B (en) | 2023-07-12 | 2023-07-12 | Medical image screening method, device, electronic device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116563299B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104680503A (en) * | 2013-11-26 | 2015-06-03 | 上海西门子医疗器械有限公司 | Medical image processing method, medical image processing device, and medical X-ray imaging equipment |
CN108063920A (en) * | 2017-12-26 | 2018-05-22 | 深圳开立生物医疗科技股份有限公司 | A kind of freeze frame method, apparatus, equipment and computer readable storage medium |
CN109509183A (en) * | 2018-10-31 | 2019-03-22 | 上海联影医疗科技有限公司 | Screening technique, device, medical supply, Medical Imaging System and the storage medium of medical image |
CN110378875A (en) * | 2019-06-18 | 2019-10-25 | 中国科学院苏州生物医学工程技术研究所 | Internal lithangiuria ingredient discrimination method based on machine learning algorithm |
CN111861991A (en) * | 2020-06-11 | 2020-10-30 | 北京百度网讯科技有限公司 | Method and device for calculating image definition |
CN113240630A (en) * | 2021-04-16 | 2021-08-10 | 深圳市安思疆科技有限公司 | Speckle image quality evaluation method and device, terminal equipment and readable storage medium |
CN113554628A (en) * | 2021-07-27 | 2021-10-26 | 苏州微景医学科技有限公司 | Image processing method, image processing apparatus, and computer-readable storage medium |
CN114677676A (en) * | 2022-03-24 | 2022-06-28 | 上海微觅医疗器械有限公司 | Target phenomenon monitoring method and device, computer equipment and storage medium |
CN114764775A (en) * | 2021-01-12 | 2022-07-19 | 深圳市普渡科技有限公司 | Infrared image quality evaluation method, device and storage medium |
CN115700759A (en) * | 2022-11-14 | 2023-02-07 | 上海微创医疗机器人(集团)股份有限公司 | Medical image display method, medical image processing method, and image display system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10984894B2 (en) * | 2018-12-27 | 2021-04-20 | Ge Healthcare Limited | Automated image quality control apparatus and methods |
-
2023
- 2023-07-12 CN CN202310852571.7A patent/CN116563299B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104680503A (en) * | 2013-11-26 | 2015-06-03 | 上海西门子医疗器械有限公司 | Medical image processing method, medical image processing device, and medical X-ray imaging equipment |
CN108063920A (en) * | 2017-12-26 | 2018-05-22 | 深圳开立生物医疗科技股份有限公司 | A kind of freeze frame method, apparatus, equipment and computer readable storage medium |
CN109509183A (en) * | 2018-10-31 | 2019-03-22 | 上海联影医疗科技有限公司 | Screening technique, device, medical supply, Medical Imaging System and the storage medium of medical image |
CN110378875A (en) * | 2019-06-18 | 2019-10-25 | 中国科学院苏州生物医学工程技术研究所 | Internal lithangiuria ingredient discrimination method based on machine learning algorithm |
CN111861991A (en) * | 2020-06-11 | 2020-10-30 | 北京百度网讯科技有限公司 | Method and device for calculating image definition |
CN114764775A (en) * | 2021-01-12 | 2022-07-19 | 深圳市普渡科技有限公司 | Infrared image quality evaluation method, device and storage medium |
CN113240630A (en) * | 2021-04-16 | 2021-08-10 | 深圳市安思疆科技有限公司 | Speckle image quality evaluation method and device, terminal equipment and readable storage medium |
CN113554628A (en) * | 2021-07-27 | 2021-10-26 | 苏州微景医学科技有限公司 | Image processing method, image processing apparatus, and computer-readable storage medium |
CN114677676A (en) * | 2022-03-24 | 2022-06-28 | 上海微觅医疗器械有限公司 | Target phenomenon monitoring method and device, computer equipment and storage medium |
CN115700759A (en) * | 2022-11-14 | 2023-02-07 | 上海微创医疗机器人(集团)股份有限公司 | Medical image display method, medical image processing method, and image display system |
Non-Patent Citations (3)
Title |
---|
CVIQD: SUBJECTIVE QUALITY EVALUATION OF COMPRESSED VIRTUAL REALITY IMAGES;Wei Sun 等;《ICIP 2017》;3450-3454 * |
融合二级评价指标的人脸图像质量评价方法;邹国锋 等;《山东大学学报(工学版)》;第46卷(第2期);6-13 * |
面向纤维显微成像的图像清晰度评价算法;瞿瑞德 等;《毛纺科技》;第50卷(第12期);85-94 * |
Also Published As
Publication number | Publication date |
---|---|
CN116563299A (en) | 2023-08-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108898567B (en) | Image noise reduction method, device and system | |
CN108961303B (en) | Image processing method and device, electronic equipment and computer readable medium | |
WO2018136373A1 (en) | Image fusion and hdr imaging | |
CN108234858B (en) | Image blurring processing method and device, storage medium and electronic equipment | |
CN110619318B (en) | Image processing method, microscope, system and medium based on artificial intelligence | |
CN108961206B (en) | Non-reference objective evaluation method for defogging effect | |
CN114697623B (en) | Projection plane selection and projection image correction method, device, projector and medium | |
JP2018195084A (en) | Image processing apparatus, image processing method, program, and storage medium | |
US8983188B1 (en) | Edge-aware smoothing in images | |
CN111028170A (en) | Image processing method, image processing apparatus, electronic device, and readable storage medium | |
US20190370949A1 (en) | Blending images | |
JP7265316B2 (en) | Image processing device and image processing method | |
CN111183630B (en) | Photo processing method and processing device of intelligent terminal | |
CN116580028A (en) | Object surface defect detection method, device, equipment and storage medium | |
CN116563299B (en) | Medical image screening method, device, electronic device and storage medium | |
KR101437898B1 (en) | Apparatus and method for generating a High Dynamic Range image using single image | |
CN116309435A (en) | Medical image specular reflection restoration method and system | |
CN115578291A (en) | Image brightness correction method, storage medium and electronic device | |
CN111080543B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
CN114066794A (en) | Image processing method, device and equipment and storage medium | |
CN109727193B (en) | Image blurring method and device and electronic equipment | |
CN116528056A (en) | Endoscope light source brightness adjusting method, device, electronic device and storage medium | |
CN111835968B (en) | Image definition restoration method and device and image shooting method and device | |
CN116664449B (en) | Satellite image processing method | |
Das et al. | Image Enhancement Techniques to Modify an Image with Machine Learning Application |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |