CN113052844A - Method and device for processing images in intestinal endoscope observation video and storage medium - Google Patents
Method and device for processing images in intestinal endoscope observation video and storage medium Download PDFInfo
- Publication number
- CN113052844A CN113052844A CN202110605854.2A CN202110605854A CN113052844A CN 113052844 A CN113052844 A CN 113052844A CN 202110605854 A CN202110605854 A CN 202110605854A CN 113052844 A CN113052844 A CN 113052844A
- Authority
- CN
- China
- Prior art keywords
- image
- determining
- video
- intestinal
- detection
- 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.)
- Granted
Links
Images
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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/00002—Operational features of endoscopes
- A61B1/00004—Operational features of endoscopes characterised by electronic signal processing
- A61B1/00009—Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/31—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor for the rectum, e.g. proctoscopes, sigmoidoscopes, colonoscopes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
-
- 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
- G06T2207/30004—Biomedical image processing
- G06T2207/30028—Colon; Small intestine
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Optics & Photonics (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Geometry (AREA)
- Endoscopes (AREA)
- Image Processing (AREA)
Abstract
The application relates to a processing method, a device and a storage medium for images in an intestinal endoscope observation video, wherein the method comprises the following steps: intercepting an intestinal observation area image of each frame of video image from an endoscope observation video; zooming the intestinal observation area image of each frame of video image according to a preset pixel specification to obtain a plurality of detection images; determining the coordinates of the central point of the opening area of the intestinal canal far end of each detection image; mapping the coordinates of the central point of each detection image to a plurality of detection areas of a detection matrix with the same pixel specification; determining the average difference between the central point coordinate quantity of each detection area and the central point coordinate quantity of the plurality of detection images; determining the sum of the average difference absolute values of the plurality of detection areas according to the average difference; and determining the integrity of the intestinal canal observed through the endoscope according to the sum of the average difference absolute values. The method and the device can effectively control the quality of endoscope screening and improve the accuracy of endoscope screening.
Description
Technical Field
The application relates to the technical field of medical treatment, in particular to a processing method and device for images in an intestinal endoscope observation video and a storage medium.
Background
The endoscope is an important means for screening colorectal polyps, and the method for operating the endoscope by a doctor determines the quality of screening diagnosis, wherein the spiral retroscopy is an important method for completely observing the intestinal tract. However, some doctors may fail to observe the entire intestine due to unskilled manipulations, and thus may miss the examination due to the uneven doctor level.
Therefore, in order to control the quality of endoscope screening, facilitate doctors to know the screening operation condition and improve the accuracy of endoscope screening, a scheme for confirming the completeness of the endoscope for observing the intestinal tract needs to be developed.
Disclosure of Invention
In order to solve the above technical problem or at least partially solve the above technical problem, the present application provides a processing method, an apparatus, and a storage medium for images in an endoscopic observation video.
In a first aspect, the present application provides a method for processing an image in an endoscopic observation video, the method comprising:
intercepting an intestinal observation area image of each frame of video image from an endoscope observation video;
zooming the intestinal observation area image of each frame of video image according to a preset pixel specification to obtain a plurality of detection images;
determining the coordinates of the central point of the opening region of the far end of the intestinal tract displayed in each detection image;
mapping the coordinates of the central point of each detection image to a plurality of detection areas of a detection matrix with the same pixel specification;
determining the average difference between the central point coordinate quantity of each detection area and the central point coordinate quantity of the plurality of detection images;
determining the sum of the average difference absolute values of the plurality of detection areas according to the average difference;
and determining the integrity of the intestinal canal observed through the endoscope according to the sum of the average difference absolute values.
In the disclosure of the present invention, the intestinal tract may be any medium having intestinal tract morphology and/or structure, such as human intestinal tract, human intestinal tract simulation model, animal intestinal tract, etc., which are all considered to be included in the protection scope of the present invention.
Optionally, the cutting out the intestinal observation region image of each frame of video image from the endoscope observation video includes:
determining an effective boundary of the intestinal observation area in each frame of video image;
and cutting the intestinal observation area image of each frame of video image from each frame of video image according to the effective boundary of each frame of video image.
In the disclosure of the present invention, the capturing from the endoscopic observation video may be real-time capturing, or capturing from a stored video, and the like.
Optionally, the determining the effective boundary of the intestinal observation region in each frame of video image includes:
converting each frame of video image into a gray scale image;
in a gray scale image of each frame of video image, according to a predetermined effective gray scale value of an intestinal observation area, setting pixel points smaller than the effective gray scale value in the gray scale image as 0, and setting pixel points larger than the effective gray scale value as 255 to obtain a first binarized image;
and eliminating the noise point of the first binary image, and taking the boundary value of the pixel point larger than 0 in the first binary image with the noise point eliminated as the effective boundary.
Optionally, the determining the coordinates of the center point of the intestinal tract distal opening region displayed in each detection image includes:
determining a maximum connected domain in each detection image according to a preset dark space gray threshold of the far end of the intestinal tract, wherein the maximum connected domain corresponds to the opening area of the far end of the intestinal tract;
and determining the coordinates of the central point of the maximum connected domain in each detection image.
Optionally, the determining, according to a preset dark-area gray-scale threshold of the far end of the intestinal tract, a maximum connected domain in each detection image includes:
setting pixel points with gray values smaller than the gray threshold of the far-end dark space of the intestinal tract in each detection image as 0, and setting pixel points larger than the gray threshold of the far-end dark space of the intestinal tract as 255 to obtain a plurality of second binary images corresponding to each detection image;
and determining the maximum connected domain of the plurality of second binary images.
Optionally, the determining the coordinates of the center point of the maximum connected domain in each detection image includes:
reserving the maximum connected domain of the plurality of second binary images to obtain a plurality of third binary images;
determining the mean value of the first coordinates and the mean value of the second coordinates of the pixel points with the median value of 0 in each third binary image;
and determining the coordinate of the central point of the maximum connected domain according to the mean value of the first coordinate and the mean value of the second coordinate.
Optionally, setting the pixel point with the gray value smaller than the gray threshold of the far-end dark area of the intestinal tract in each detected image to be 0, and setting the pixel point with the gray threshold larger than the gray threshold of the far-end dark area of the intestinal tract to be 255 includes:
setting the pixel points with the gray values smaller than the preset out-of-view gray value in each detection image as 255;
the determining the maximum connected domain of each second binary image comprises the following steps:
and judging whether the area of the black area is not smaller than a preset image area threshold of the intestinal observation area, and determining the coordinate of the central point of the maximum connected domain in each detection image when the area of the black area is not smaller than the preset image area threshold of the intestinal observation area.
Optionally, determining the integrity of the intestine viewed through the endoscope from the sum of the mean absolute differences comprises:
determining the maximum integrity according to the number of the detection areas;
and determining the integrity of the intestinal canal observed by the endoscope according to the sum of the average difference absolute values, the maximum integrity and a preset weight coefficient.
In a second aspect, the present application provides a processing apparatus of an endoscopic observation video, including: a memory, a processor, and a computer program stored on the memory and executable on the processor;
the computer program, when executed by the processor, implements the steps of the method of processing images in endoscopic observation video as described in any one of the above.
Optionally, the memory is a cloud memory.
Optionally, the processing device is connected with a medical testing device and/or a medical imaging device for use;
further optionally, the medical imaging device is a magnetic resonance imaging device.
In a third aspect, the present application provides a computer-readable storage medium having stored thereon a program for processing an endoscopic observation video, the program for processing an image in an endoscopic observation video, when executed by a processor, implementing the steps of the method for processing an image in an endoscopic observation video as described in any one of the above.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the embodiment of the invention, the uniformity degree and the integral integrity of the movement of the endoscope are determined by detecting the position of the opening area of the far end of the intestinal tract, and the quality control of the endoscope screening can be effectively realized by the method in the embodiment of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of a processing method for processing images in an endoscopic observation video according to various embodiments of the present disclosure;
FIG. 2 is an endoscopic viewing video image provided by various embodiments of the present application;
FIG. 3 is a schematic view of the out-of-view area of various embodiments of the present application;
fig. 4 is a schematic view of the open distal region of the intestine according to various embodiments of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
Example one
An embodiment of the present invention provides a method for processing an image in an endoscopic video, as shown in fig. 1, the method for processing an image in an endoscopic video includes:
s101, intercepting an intestinal observation area image of each frame of video image from an endoscope observation video; as shown in fig. 2, each frame image of the endoscopic observation video includes an intestinal observation region image and an information region image;
s102, scaling the intestinal observation area image of each frame of video image according to a preset pixel specification to obtain a plurality of detection images; the pixel specification may be 534 x 480;
s103, determining the center point coordinates of the intestinal tract distal opening area of each detection image;
s104, mapping the central point coordinates of each detection image to a plurality of detection areas of a detection matrix with the same pixel specification;
s105, determining the ratio of the number of the center point coordinates of each detection area to the number of the center point coordinates of the plurality of detection images;
s106, determining the sum of the average difference absolute values of the plurality of detection areas according to the ratio;
and S107, determining the integrity of the intestinal canal observed through the endoscope according to the sum of the average difference absolute values.
The embodiment of the invention maps the central point coordinate of the intestinal tract far-end opening area in each detection image in the endoscope observation video into the detection matrix, determines the ratio of the central point coordinate quantity of each detection area of the detection matrix to all the central point coordinate quantities through calculation, determines the sum of the average difference absolute values through calculation, and determines the integrity of the intestinal tract observed through the endoscope according to the sum of the average difference absolute values, thereby determining the uniformity degree and the integral integrity of the movement of the endoscope through the position detection of the intestinal tract far-end opening area.
In some embodiments, the capturing of the intestinal observation region image of each frame of the video image from the endoscopic observation video may include:
determining an effective boundary of the intestinal observation area in each frame of video image;
and cutting the intestinal observation area image of each frame of video image from each frame of video image according to the effective boundary of each frame of video image.
In detail, the steps include:
converting each frame of video image into a gray scale image;
in a gray scale image of each frame of video image, according to a predetermined effective gray scale value of an intestinal observation area, setting pixel points smaller than the effective gray scale value in the gray scale image as 0, and setting pixel points larger than the effective gray scale value as 255 to obtain a first binarized image;
and eliminating noise of the first binarized image, and taking a boundary value larger than 0 in the noise-eliminated first binarized image as the effective boundary.
For example, the effective gray scale value of the intestinal observation region may be 20, specifically, first, the current frame image is converted into a gray scale image, and then the gray scale image is binarized, so that the pixel value with the gray scale value smaller than 20 is 0, and the pixel value with the gray scale value larger than 20 is 255, so as to obtain a binarized image 1 (i.e., a first binarized image).
Then, erosion and dilation operations are performed using OpenCV to clean noise.
And calculating upper, lower, left and right boundary values (namely effective boundary values) of the matrix larger than 0 by using numpy, and cutting the gray-scale image obtained by the binary image 1 according to the effective boundary values to obtain an intestinal observation area image of each frame of video image.
Finally, the cut effective region image is scaled to 534 × 480, resulting in the detection image H.
In some embodiments, the determining coordinates of the center point of the open area of the distal intestine end of each of the detection images comprises:
determining a maximum connected domain in each detection image according to a preset dark space gray threshold of the far end of the intestinal tract, wherein the maximum connected domain corresponds to the opening area of the far end of the intestinal tract;
and determining the coordinates of the central point of the maximum connected domain in each detection image.
Wherein, according to a preset dark space gray threshold of the far end of the intestinal tract, determining the maximum connected domain in each detection image optionally comprises:
setting pixel points with gray values smaller than the gray threshold of the far-end dark space of the intestinal tract in each detection image as 0, and setting pixel points larger than the gray threshold of the far-end dark space of the intestinal tract as 255 to obtain a plurality of second binary images corresponding to each detection image;
and determining the maximum connected domain of the black area of each second binary image.
Wherein, the determining the center point coordinate of the maximum connected domain in each detection image optionally includes:
reserving the maximum connected domain of the plurality of second binary images to obtain a plurality of third binary images;
determining the mean value of the first coordinates and the mean value of the second coordinates of the pixels with the median value of 0 in each third binary image;
and determining the coordinate of the central point of the maximum connected domain according to the mean value of the first coordinate and the mean value of the second coordinate.
In some embodiments, the setting of the pixel point with the gray value smaller than the far-end intestinal tract dark space gray threshold value in each detection image to be 0, and the setting of the pixel point with the gray value larger than the far-end intestinal tract dark space gray threshold value to be 255 may include:
setting the pixel points with the gray values smaller than the preset out-of-view gray value in each detection image as 255;
the determining the maximum connected domain of the black region of each second binary image comprises:
and judging whether the area of the black area is not smaller than a preset image area threshold of the intestinal observation area, and determining the coordinate of the central point of the maximum connected domain in each detection image when the area of the black area is not smaller than the preset image area threshold of the intestinal observation area.
In detail, the open area of the distal end of the intestine is determined by detecting darker areas.
First, as shown in fig. 3, the view field is an intestinal observation area image excluding the corner (four corners) black area, and the corner black area is an area outside the view field. The tone value of the corner black region in the present embodiment is set as the out-of-view tone value, and the out-of-view tone value in the present embodiment is set as the pixel value 16. The pixel point value of the gray value less than 16 in the filtering detection image H is set to 255, so that the interference of a pure black area outside the "view field" to the dark area detection is prevented.
Then, the image is subjected to gaussian smoothing to remove noise.
Binarizing the image, setting the pixel value with the gray value smaller than the 'intestinal far-end dark space gray threshold value' as 0, and setting the pixel value larger than the 'intestinal far-end dark space gray threshold value' as 255, and binarizing the image 2 (namely a second binarized image); meanwhile, whether the area of the black area of the binary image 2 is larger than 1 percent (the image area threshold value of the intestinal observation area) of the whole image is judged, if so, the current image is considered to have no intestinal far-end opening area, and subsequent calculation is not carried out.
And the maximum connected domain of the image is obtained by using an opencv function, namely the open region of the far end of the intestinal tract, as shown in fig. 4.
And (4) screening the binary image 2, and only keeping the maximum connected domain in the image to obtain an image 3 (namely a third binary image).
If the maximum connected domain exists, performing the subsequent steps; otherwise, the current image is regarded as having no intestinal tract distal opening, and subsequent calculation is not carried out.
And finally, calculating the coordinate of the central point of the distal opening of the intestinal tract, and counting the mean value of the x coordinate and the mean value of the y coordinate of the pixel with the value of 0 in the matrix in the image 3 as the coordinate of the central point.
In some embodiments, determining the integrity of the intestine viewed endoscopically from the sum of the mean absolute differences comprises:
determining the maximum integrity according to the number of the detection areas;
and determining the integrity of the intestinal canal observed by the endoscope according to the sum of the average difference absolute values, the maximum integrity and a preset weight coefficient.
In detail, the video detects and calculates the video overall result frame by frame, the obtained central point coordinate is stored in an array to obtain a set N, and the central point coordinate stored in the array is used for facilitating the unified calculation processing after the follow-up video is finished.
Since all the input images have dimensions 534 × 480, a detection matrix with dimensions 534 × 480 is created, and the matrix is divided into m × m (n total detection areas), each of which is an area block X.
Counting all central points in the set N, respectively corresponding the coordinates of each central point to the area blocks at corresponding positions, counting the number (marked as Xs) of the coordinates of the central point in each area block, and comparing the number of the central points in each area block with the total number of the central points, wherein the calculation formula is as follows: xs/sum (Xs).
The sum of the average absolute differences L of the n area blocks is calculated.
Finally, useFormula (L)max-L)/(Lmaxβ), the integrity of the global examination is calculated (1 for > 1).
The larger the average difference sum is, the larger the dispersion degree is, and the lower the integrity degree is; the higher the integrity, on the contrary. Since n region blocks are calculated, the optimum case is the sum LminThe ratio is 0, namely the proportion of each area block is 1/n, and the integrity is 100 percent at the moment; in the worst case, all points are collected in one grid, and the sum LmaxIs 2 x (n-1)/n, so the formula molecule uses Lmax-L; denominator is set as Lmax- β, β being a weighting factor.
In the embodiment, offset processing is performed by subtracting beta, videos are observed through a plurality of authoritative endoscopes, the videos are assumed to be gold standard operation under the actual condition, the completeness of the operations is calculated by analyzing the videos observed through the endoscopes, and the results are inversely substituted into a formula to obtain the beta.
In the embodiment, m is 8; n is 64; beta is 0.5.
The embodiment of the invention provides a processing method for images in an endoscope observation video, which is based on an opencv connected domain method to detect an intestinal far-end opening and deduce integrity by calculating average difference in blocks, and can effectively judge the integrity of endoscope screening so as to quantify indexes and further effectively control the quality of the endoscope screening.
Example two
An embodiment of the present invention provides a processing apparatus for an endoscopic observation video, including: a memory, a processor, and a computer program stored on the memory and executable on the processor;
the computer program, when executed by the processor, implements the steps of the method of processing images in endoscopic observation video according to any one of embodiments one.
Wherein the processing means for endoscopic viewing of the video may be an endoscopic examination device.
EXAMPLE III
An embodiment of the present invention provides a computer-readable storage medium, on which a processing program of an endoscopic observation video is stored, and when the processing program of an image in the endoscopic observation video is executed by a processor, the steps of the processing method of an image in the endoscopic observation video according to any one of embodiments are implemented.
The specific implementation of the second embodiment and the third embodiment can be referred to as the first embodiment, and has corresponding technical effects.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (13)
1. A method for processing images in an intestinal endoscope observation video, the method comprising:
intercepting an intestinal observation area image of each frame of video image from an endoscope observation video;
zooming the intestinal observation area image of each frame of video image according to a preset pixel specification to obtain a plurality of detection images;
determining the coordinates of the central point of the opening region of the far end of the intestinal tract displayed in each detection image;
mapping the coordinates of the central point of each detection image to a plurality of detection areas of a detection matrix with the same pixel specification;
determining the average difference between the central point coordinate quantity of each detection area and the central point coordinate quantity of the plurality of detection images;
determining the sum of the average difference absolute values of the plurality of detection areas according to the average difference;
and determining the integrity of the intestinal canal observed through the endoscope according to the sum of the average difference absolute values.
2. The method for processing images in endoscopic observation video according to claim 1, wherein said cutting out the intestinal observation region image of each frame of video image from the endoscopic observation video comprises:
determining an effective boundary of the intestinal observation area in each frame of video image;
and cutting the intestinal observation area image of each frame of video image from each frame of video image according to the effective boundary of each frame of video image.
3. The method of claim 2, wherein said determining the effective boundary of the intestinal observation region in each frame of video image comprises:
converting each frame of video image into a gray scale image;
in a gray scale image of each frame of video image, according to a predetermined effective gray scale value of an intestinal observation area, setting pixel points smaller than the effective gray scale value in the gray scale image as 0, and setting pixel points larger than the effective gray scale value as 255 to obtain a first binarized image;
and eliminating the noise point of the first binary image, and taking the boundary value of the pixel point larger than 0 in the first binary image with the noise point eliminated as the effective boundary.
4. The method for processing images in endoscopic observation video according to any of claims 1 to 3, wherein said determining coordinates of a center point of a region of a distal opening of the intestine shown in each of the detected images comprises:
determining a maximum connected domain in each detection image according to a preset dark space gray threshold of the far end of the intestinal tract, wherein the maximum connected domain corresponds to the opening area of the far end of the intestinal tract;
and determining the coordinates of the central point of the maximum connected domain in each detection image.
5. The method as claimed in claim 4, wherein said determining the maximum connected component in each detected image according to the preset threshold value of the dark area of the distal intestine end comprises:
setting pixel points with gray values smaller than the gray threshold of the far-end dark space of the intestinal tract in each detection image as 0, and setting pixel points larger than the gray threshold of the far-end dark space of the intestinal tract as 255 to obtain a plurality of second binary images corresponding to each detection image;
and determining the maximum connected domain of the plurality of second binary images.
6. The method of claim 5, wherein said determining coordinates of a center point of said largest connected component in each of said detected images comprises:
reserving the maximum connected domain of the plurality of second binary images to obtain a plurality of third binary images;
determining the mean value of the first coordinates and the mean value of the second coordinates of the pixel points with the median value of 0 in each third binary image;
and determining the coordinate of the central point of the maximum connected domain according to the mean value of the first coordinate and the mean value of the second coordinate.
7. The method of claim 5, wherein said step of setting pixels in each detected image having a gray scale value less than the gray scale threshold of the dark area distal to the intestine to 0 and pixels greater than the gray scale threshold of the dark area distal to the intestine to 255 comprises:
setting the pixel points with the gray values smaller than the preset out-of-view gray value in each detection image as 255;
the determining the maximum connected domain of each second binary image comprises the following steps:
and judging whether the area of the black area is not smaller than a preset image area threshold of the intestinal observation area, and determining the coordinate of the central point of the maximum connected domain in each detection image when the area of the black area is not smaller than the preset image area threshold of the intestinal observation area.
8. The method of processing images in endoscopic viewing video according to any of claims 1 to 3, wherein determining the integrity of the intestine viewed through the endoscope from said sum of the mean absolute differences comprises:
determining a maximum integrity degree value and a weight coefficient according to the number of the detection areas;
and determining the integrity of the intestinal canal observed through the endoscope according to the sum of the average difference absolute values, the maximum integrity and the weight coefficient.
9. An apparatus for processing an endoscopic observation video, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor;
the computer program, when executed by the processor, implements the steps of a method of processing images in endoscopic viewing video according to any of claims 1 to 8.
10. The processing apparatus according to claim 9, wherein the memory is a cloud memory.
11. A processing device according to claim 9, wherein the processing device is used in connection with a medical assay apparatus and/or a medical imaging apparatus.
12. The processing apparatus according to claim 11, wherein the medical imaging device is a magnetic resonance imaging device.
13. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a processing program of an endoscopic observation video, the processing method of an image in an endoscopic observation video program, when executed by a processor, realizing the steps of the processing method of an image in an endoscopic observation video according to any one of claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110605854.2A CN113052844B (en) | 2021-06-01 | 2021-06-01 | Method and device for processing images in intestinal endoscope observation video and storage medium |
| PCT/CN2022/095185 WO2022253093A1 (en) | 2021-06-01 | 2022-05-26 | Method and apparatus for processing image in intestinal endoscopic observation video, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110605854.2A CN113052844B (en) | 2021-06-01 | 2021-06-01 | Method and device for processing images in intestinal endoscope observation video and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113052844A true CN113052844A (en) | 2021-06-29 |
| CN113052844B CN113052844B (en) | 2021-08-10 |
Family
ID=76518597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110605854.2A Active CN113052844B (en) | 2021-06-01 | 2021-06-01 | Method and device for processing images in intestinal endoscope observation video and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113052844B (en) |
| WO (1) | WO2022253093A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419521A (en) * | 2022-03-28 | 2022-04-29 | 武汉楚精灵医疗科技有限公司 | Method and device for monitoring intestinal endoscopy |
| CN115035152A (en) * | 2022-08-12 | 2022-09-09 | 武汉楚精灵医疗科技有限公司 | Medical image processing method and device and related equipment |
| WO2022253093A1 (en) * | 2021-06-01 | 2022-12-08 | 天津御锦人工智能医疗科技有限公司 | Method and apparatus for processing image in intestinal endoscopic observation video, and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110128352A1 (en) * | 2005-05-23 | 2011-06-02 | The Penn State Research Foundation | Fast 3d-2d image registration method with application to continuously guided endoscopy |
| CN107967946A (en) * | 2017-12-21 | 2018-04-27 | 武汉大学 | Operating gastroscope real-time auxiliary system and method based on deep learning |
| CN110533609A (en) * | 2019-08-16 | 2019-12-03 | 域鑫科技（惠州）有限公司 | Image enchancing method, device and storage medium suitable for endoscope |
| CN111080585A (en) * | 2019-12-04 | 2020-04-28 | 绍兴文理学院 | Intelligent analysis method for detecting reflective region of colon endoscope |
| CN111325769A (en) * | 2018-12-13 | 2020-06-23 | 北京嘀嘀无限科技发展有限公司 | Target object detection method and device |
| CN111839429A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Detection method for judging completeness of colonoscopy based on image recognition |
| CN111863177A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Enteroscopy quality report management system based on big data |
| CN111839726A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Intestinal tract integrity detection system based on multi-sensor multi-data fusion 3D-SLAM modeling |
| CN111863209A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Colonoscopy quality assessment workstation based on image recognition |
| CN111861049A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Enteroscopy quality standard and scoring system based on image recognition |
| CN111932532A (en) * | 2020-09-21 | 2020-11-13 | 安翰科技(武汉)股份有限公司 | Method for evaluating capsule endoscope without reference image, electronic device, and medium |
| CN112785549A (en) * | 2020-12-29 | 2021-05-11 | 成都微识医疗设备有限公司 | Enteroscopy quality evaluation method and device based on image recognition and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100454340C (en) * | 2007-02-13 | 2009-01-21 | 上海交通大学 | Visual method for virtual incising tubular organ |
| JP5457764B2 (en) * | 2009-09-02 | 2014-04-02 | 株式会社東芝 | Medical image processing device |
| JP5715372B2 (en) * | 2010-10-15 | 2015-05-07 | オリンパス株式会社 | Image processing apparatus, method of operating image processing apparatus, and endoscope apparatus |
| US20130002842A1 (en) * | 2011-04-26 | 2013-01-03 | Ikona Medical Corporation | Systems and Methods for Motion and Distance Measurement in Gastrointestinal Endoscopy |
| CN108292366B (en) * | 2015-09-10 | 2022-03-18 | 美基蒂克艾尔有限公司 | System and method for detecting suspicious tissue regions during endoscopic surgery |
| CN113052844B (en) * | 2021-06-01 | 2021-08-10 | 天津御锦人工智能医疗科技有限公司 | Method and device for processing images in intestinal endoscope observation video and storage medium |
-
2021
- 2021-06-01 CN CN202110605854.2A patent/CN113052844B/en active Active
-
2022
- 2022-05-26 WO PCT/CN2022/095185 patent/WO2022253093A1/en active Application Filing
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110128352A1 (en) * | 2005-05-23 | 2011-06-02 | The Penn State Research Foundation | Fast 3d-2d image registration method with application to continuously guided endoscopy |
| CN107967946A (en) * | 2017-12-21 | 2018-04-27 | 武汉大学 | Operating gastroscope real-time auxiliary system and method based on deep learning |
| CN111325769A (en) * | 2018-12-13 | 2020-06-23 | 北京嘀嘀无限科技发展有限公司 | Target object detection method and device |
| CN111839429A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Detection method for judging completeness of colonoscopy based on image recognition |
| CN111863177A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Enteroscopy quality report management system based on big data |
| CN111839726A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Intestinal tract integrity detection system based on multi-sensor multi-data fusion 3D-SLAM modeling |
| CN111863209A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Colonoscopy quality assessment workstation based on image recognition |
| CN111861049A (en) * | 2019-04-25 | 2020-10-30 | 天津御锦人工智能医疗科技有限公司 | Enteroscopy quality standard and scoring system based on image recognition |
| CN110533609A (en) * | 2019-08-16 | 2019-12-03 | 域鑫科技（惠州）有限公司 | Image enchancing method, device and storage medium suitable for endoscope |
| CN111080585A (en) * | 2019-12-04 | 2020-04-28 | 绍兴文理学院 | Intelligent analysis method for detecting reflective region of colon endoscope |
| CN111932532A (en) * | 2020-09-21 | 2020-11-13 | 安翰科技(武汉)股份有限公司 | Method for evaluating capsule endoscope without reference image, electronic device, and medium |
| CN112785549A (en) * | 2020-12-29 | 2021-05-11 | 成都微识医疗设备有限公司 | Enteroscopy quality evaluation method and device based on image recognition and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022253093A1 (en) * | 2021-06-01 | 2022-12-08 | 天津御锦人工智能医疗科技有限公司 | Method and apparatus for processing image in intestinal endoscopic observation video, and storage medium |
| CN114419521A (en) * | 2022-03-28 | 2022-04-29 | 武汉楚精灵医疗科技有限公司 | Method and device for monitoring intestinal endoscopy |
| CN114419521B (en) * | 2022-03-28 | 2022-07-01 | 武汉楚精灵医疗科技有限公司 | Method and device for monitoring intestinal endoscopy |
| CN115035152A (en) * | 2022-08-12 | 2022-09-09 | 武汉楚精灵医疗科技有限公司 | Medical image processing method and device and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113052844B (en) | 2021-08-10 |
| WO2022253093A1 (en) | 2022-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113052844B (en) | Method and device for processing images in intestinal endoscope observation video and storage medium | |
| CN111862044B (en) | Ultrasonic image processing method, ultrasonic image processing device, computer equipment and storage medium | |
| US11164048B2 (en) | Focus-weighted, machine learning disease classifier error prediction for microscope slide images | |
| JP5113841B2 (en) | Computer-aided analysis using video from an endoscope | |
| CN110176010B (en) | Image detection method, device, equipment and storage medium | |
| CN109509186B (en) | Cerebral CT image-based ischemic stroke lesion detection method and device | |
| JP4717585B2 (en) | Medical image determination apparatus, medical image determination method and program thereof | |
| CN110619318B (en) | Image processing method, microscope, system and medium based on artificial intelligence | |
| CN111325739A (en) | Method and device for detecting lung focus and training method of image detection model | |
| JPH03206572A (en) | Automatizing system for gradation conversion | |
| US20110200238A1 (en) | Method and system for determining skinline in digital mammogram images | |
| CN110610498A (en) | Mammary gland molybdenum target image processing method, system, storage medium and equipment | |
| CN112950737B (en) | Fundus fluorescence contrast image generation method based on deep learning | |
| CN113034389A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN113989407A (en) | Training method and system for limb part recognition model in CT image | |
| CN115760858A (en) | Kidney pathological section cell identification method and system based on deep learning | |
| CN113689337B (en) | Ultrasonic image super-resolution reconstruction method and system based on generation countermeasure network | |
| CN112215878A (en) | X-ray image registration method based on SURF feature points | |
| JP2006280682A (en) | Method of supporting diagnostic image provided with noise detection function | |
| JP6935663B1 (en) | Oral mucosal disease diagnosis support system, method and program | |
| CN112704517B (en) | Method, system, equipment and storage medium for processing endometrium peristalsis ultrasonic image | |
| WO2021039454A1 (en) | Image processing device, radiography system, image processing method and program | |
| CN113962938A (en) | Image segmentation method and device, computer equipment and readable storage medium | |
| EP2074591B1 (en) | Methods, system and computer program product for detecting a protrusion | |
| CN116452488A (en) | Image processing method, device and computer readable storage medium |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40052845 Country of ref document: HK |