CN113487553A - Intestinal tract endoscope withdrawal speed smoothing method - Google Patents
Intestinal tract endoscope withdrawal speed smoothing method Download PDFInfo
- Publication number
- CN113487553A CN113487553A CN202110737719.3A CN202110737719A CN113487553A CN 113487553 A CN113487553 A CN 113487553A CN 202110737719 A CN202110737719 A CN 202110737719A CN 113487553 A CN113487553 A CN 113487553A
- Authority
- CN
- China
- Prior art keywords
- speed
- value
- smoothing
- picture
- intestinal tract
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000009499 grossing Methods 0.000 title claims abstract description 38
- 210000001035 gastrointestinal tract Anatomy 0.000 title claims abstract description 27
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 238000013507 mapping Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000005315 distribution function Methods 0.000 claims description 3
- 230000010355 oscillation Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000000968 intestinal effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 208000003200 Adenoma Diseases 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 206010001233 Adenoma benign Diseases 0.000 description 2
- 208000037062 Polyps Diseases 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000011010 flushing procedure Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 206010009944 Colon cancer Diseases 0.000 description 1
- 208000001333 Colorectal Neoplasms Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 238000002052 colonoscopy Methods 0.000 description 1
- 201000002758 colorectal adenoma Diseases 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 231100000517 death Toxicity 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000001839 endoscopy Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 210000004877 mucosa Anatomy 0.000 description 1
- 210000000664 rectum Anatomy 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4023—Decimation- or insertion-based scaling, e.g. pixel or line decimation
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
Abstract
The invention relates to the technical field of medical technology assistance, in particular to a method for smoothing the speed of withdrawing a speculum from an intestinal tract, which is used for carrying out frame acquisition on a real-time speculum withdrawing video of the intestinal tract to obtain a speculum picture; calculating the Hash fingerprint of the enteroscope picture; calculating the Hamming distance between the current frame and the previous n frames of enteroscopy pictures according to the Hash fingerprints of the current frame and the previous n frames of enteroscopy pictures; carrying out weighted average on the Hamming distance vector; mapping the weighted average Hamming distance into a speed value as the speed value of the current enteroscope picture; taking the speed value of the latest X enteroscopy pictures as a sequence, and smoothing the sequence by Savitzky-Golay filtering to obtain a smoothed speed value sequence; and taking out the last value of the smoothed speed sequence and carrying out truncation processing to obtain the mirror backing speed value of the smoothed current image. The invention eliminates the oscillation by a smoothing method, improves the robustness of the endoscope withdrawing speed and the operation experience of doctors, and ensures the quality of the enteroscopy.
Description
Technical Field
The invention relates to the technical field of medical technology assistance, in particular to a method for smoothing the speed of intestinal tract endoscope withdrawal.
Background
Colorectal cancer incidence and mortality is second in all cancers, resulting in approximately 88 million deaths per year. The enteroscope can effectively prevent the occurrence of rectum by detecting and excising precancerous lesions such as colorectal adenoma. However, the quality of the enteroscopy varies among endoscopists, resulting in about 22% missed diagnosis of adenomas. The insufficient observation of the mucosa caused by the excessively high endoscope withdrawal speed of the enteroscope is one of the main reasons for the missed diagnosis of adenomas. Studies have shown that the polyp detection rate, adenoma detection rate, and the average number of polyp findings per subject increase significantly in enteroscopy patients with increasing time to withdrawal.
The real-time monitoring of the enteroscopy speed is realized through a perceptual hash algorithm in the earlier stage, and a real-time monitoring method and a real-time monitoring system of the enteroscopy speed based on computer vision, which are disclosed by the patent number CN109598716B, are applied. The technology can assist an endoscopist to withdraw the endoscope stably at a constant speed, and the detection rate of adenoma is improved by about one time in clinic. However, due to the complexity and changeability of the intestinal environment, the method in the patent is easy to vibrate when encountering the complex environment, so that doctors cannot accurately judge the current endoscope withdrawal speed and generate nervous emotion. After comprehensively comparing several data flow smoothing methods, combining a special scene of the intestinal endoscope, and smoothing the intestinal endoscope withdrawal speed in real time by using Savitzky-Golay filtering on the premise of not changing the effectiveness of the withdrawal speed. Therefore, a method for smoothing the speed of endoscope withdrawal of the intestinal tract is provided.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: in the implementation process of the enteroscopy, when the influence of interference factors such as flushing, wall adhesion and the like is met, the enteroscopy withdrawal speed can generate violent shock, the stability guidance can not be accurately given to a doctor, and the doctor can generate tension. The invention eliminates the oscillation by a smoothing method, improves the robustness of the endoscope withdrawing speed and the operation experience of doctors, and ensures the quality of the enteroscopy.
The invention provides the following technical scheme: a method for smoothing the speed of intestinal tract endoscope withdrawal comprises the following steps:
s1, acquiring frames of the real-time intestinal tract endoscope withdrawing video to obtain an enteroscope picture;
s2, calculating the hash fingerprint of the enteroscope picture;
s3, calculating the Hamming distance between the current frame and the previous n frames of enteroscopy pictures according to the Hash fingerprints of the current frame and the previous n frames of enteroscopy pictures;
s4, carrying out weighted average on the Hamming distance vector obtained in the S3;
s5, mapping the weighted average Hamming distance obtained in the S4 into a speed value as the speed value of the current enteroscope picture;
s6, taking the speed value of the latest X enteroscopy pictures as a sequence, and smoothing the sequence by Savitzky-Golay filtering to obtain a smoothed speed value sequence;
and S7, taking out the last value of the smoothed speed sequence and performing truncation processing, namely the speed value of the mirror backing after the current image is smoothed.
Preferably, in the step S1, after the enteroscopy picture is obtained, the picture is cut, converted into a gray scale image, and reduced.
The calculation formula for converting the picture into the gray-scale image is as follows:
Gray＝R×0.299+G×0.587+B×0.114；
r, G, B represents the gray value of each pixel point of the picture in three channels of red light, green light and blue light, and when the picture is reduced, the interpolation is carried out by using a region interpolation method.
Preferably, after the picture is changed into a 9 × 8 grayscale image in step S2, when the hash fingerprint is calculated by dHash, the size of the previous pixel and the size of the next pixel in each row of pixels are compared, where the previous pixel is greater than the next pixel, and the previous pixel is 1, and otherwise, the previous pixel is 0; a total of 8 comparison results can be generated by 9 pixels in each row, and finally a hash value of 64 bits is generated by 8 × 8, which is calculated as follows:
preferably, the weighted average hamming distance of the current frame in step S4 is:
wherein d isiIs the Hamming distance, w, between the current frame and the ith frame in the nearest n framesiThe weighted value of the ith frame;
is the weighted hamming distance; wherein, the weight distribution accords with the random variable distribution, and the distribution function is as follows:
and obviously it satisfies
In the present algorithm, n takes the value 10.
Preferably, in step S5, the hamming distance is obtained according to the difference between the statistical corresponding positions of the two 64-bit numbers, the range of the value is [0,64], and the hamming distance is mapped to the [0,100] interval, that is, the current frame backing speed value V, and the formula is as follows:
preferably, the calculation formula of the Savitzky-Golay filtering in step S6 is as follows:
wherein ViThe speed of the smooth mirror-back after Savitzky-Golay filtering is adopted, M is the window length of the Savitzky-Golay filtering and must be an odd number; k is the order of the polynomial of the fitted sample, Convj(M, K) is the jth coefficient of the Savitzky-Golay filtering convolution kernel, and the convolution kernel is as long as the window; v. ofjThe j-th lens-backing speed value in the lens-backing speed sequence is not smoothed, and n is the length of the lens-backing speed sequence.
Preferably, in step S6, M is 5, K is 3, n is 10, and the extended signal mode selects nearest.
Preferably, in step S7, the smooth step-out velocity value of the latest 10 frames of images is obtained, the smooth step-out velocity value corresponding to the current frame, that is, the last velocity value of the smoothing sequence, is taken out, the reasonable value range of the velocity value is [0,100], and if the value exceeds the range after smoothing, the value needs to be truncated, and the truncation method is as follows:
the cut-off processing is the final speed value of the back mirror of the current image after smoothing.
The invention provides a method for smoothing the endoscope withdrawing speed of an intestinal tract, which is used for smoothing the endoscope withdrawing speed of the intestinal tract in real time, reducing the oscillation of the endoscope withdrawing speed while ensuring that the endoscope withdrawing speed can reflect the operation stability of a doctor in real time, improving the operation experience of the doctor, enabling the doctor to accurately judge the endoscope withdrawing state and improving the inspection quality of the intestinal tract.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic diagram of a pixel area relationship according to the present invention;
FIG. 3 is a schematic diagram of a pixel being included in a pixel region when the pixel is not divisible according to the present invention;
FIG. 4 is an exemplary segment of an intestinal colonoscopy withdrawal sequence of the present invention;
FIG. 5 is a schematic diagram of Savitzky-Golay filter window sliding according to the present invention;
FIG. 6 is a comparison of before and after Savitzky-Golay filtering according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present invention provides a technical solution: a method for smoothing the speed of intestinal tract endoscope withdrawal comprises the following steps:
s1, acquiring a real-time video of the enteroscope through the endoscopy equipment, starting to monitor the speed of the enteroscope withdrawing after the enteroscope reaches the ileocecal part at the tail end of the intestinal tract, and decoding the video into pictures (8 frames per second).
And S2, after obtaining the enteroscope picture, cutting the picture, converting the picture into a gray-scale picture and reducing the picture.
The calculation formula for converting the picture into the gray-scale image is as follows:
Gray＝R×0.299+G×0.587+B×0.114；
r, G, B represents the gray value of each pixel point of the picture in three channels of red light, green light and blue light, and when the picture is reduced, the interpolation is carried out by using a region interpolation method. In this case, the picture has 480 × 480 and 23 ten thousand pixels, and contains a very large amount of picture detail information. While in general dnash is calculated, this much picture detail is not required. In order to reduce the amount of calculation, it is necessary to downsize the picture to a size of 9 × 8 pixels.
The reduced picture adopts a regional interpolation method, and compared with other picture scaling methods, the method does not generate corresponding ripples, and the quality of the reduced picture is high. The region interpolation method is a method for performing interpolation according to the corresponding relationship of pixel regions before and after picture scaling. Such asAs shown in fig. 2, when the picture is reduced, the pixel point (x ', y ') of the reduced picture corresponds to (x ' x scale) at the upper left corner of the original picturex，y′×scaley) Lower right corner ((x' +1) × scale)x-1，(y′+1)×scaley-1) a pixel Area in which scalex，scaleyThe width and height of the original image are divided by the width and height after reduction, and when the original image cannot be divided completely, the multiple is a decimal number. The pixel value of the pixel point (x ', y') is the average value of all the points included in the pixel area in the original image. When the scaling factor is not an integer, as shown in fig. 3, only a part of the edge pixels may be included in the pixel region, where the weight of the fully included pixels is 1, and the part of the included pixels is weighted according to the included proportion. Thus, the formula for region interpolation is expressed as follows:
wherein, SCale _ x and SCale _ y are the multiple of the width and height of the original image divided by the width and height after reduction, Weight (x, y) is the proportion of the pixel (x, y) on the original image to be contained in the pixel Area, and Area is the Area of the pixel Area.
After the picture is changed into a gray image with the size of 9 multiplied by 8, when the hash fingerprint is calculated by the dHash, the size of the previous pixel and the size of the next pixel in each row of pixels are compared, if the size is larger, the front pixel is 1, and if the size is not larger, the back pixel is 0; a total of 8 comparison results can be generated by 9 pixels in each row, and finally a hash value of 64 bits is generated by 8 × 8, which is calculated as follows:
s3, calculating the Hamming distance between the current frame and the previous n frames of enteroscopy pictures according to the Hash fingerprints of the current frame and the previous n frames of enteroscopy pictures;
specifically, the hamming distance between the hash fingerprint of the current frame and the hash fingerprint of the previous 10 frames is calculated. And calculating the total number of different numbers of corresponding positions of the hash fingerprints of the two pictures by the Hamming distance. The calculation formula is as follows:
in the intestinal endoscope video, the sampling frequency is 8 frames per second, that is, the time interval between every two frames is 1/8 seconds, in this period, the farther the lens moves, the greater the difference of the captured intestinal tract pictures, and the closer the lens moves, the smaller the picture difference. Therefore, the hamming distance can reflect the moving speed of the lens in the intestinal tract by calculating the difference degree of the two pictures. If only two frames of pictures are used for calculating the enteroscope speed, the statistical deviation is larger, and the enteroscope speed is calculated by increasing the sampling number more typically. The hamming distance between the current frame and the previous 10 frames is calculated.
S4, carrying out weighted average on the Hamming distance vector obtained in the S3;
the hamming distance between the current frame and the previous 10 frames is normally smaller for two frames closer in time, and vice versa. To reduce this inherent difference, two frame hamming distances far apart should be given less weight and vice versa. The current frame weighted average hamming distance is:
wherein d isiIs the Hamming distance, w, between the current frame and the ith frame in the nearest n framesiThe weighted value of the ith frame;
is the weighted hamming distance; wherein, the weight distribution accords with the random variable distribution, and the distribution function is as follows:
and obviously it satisfies
In the present algorithm, n takes the value 10.
S5, mapping the weighted average Hamming distance obtained in the S4 into a speed value as the speed value of the current enteroscope picture;
the Hamming distance is obtained according to the position difference corresponding to the number statistics of two 64-bit numbers, the numerical range is [0,64], and the Hamming distance is mapped to the [0,100] interval, namely the current frame backing mirror velocity value V, and the formula is as follows:
s6, taking the speed value of the latest X enteroscopy pictures as a sequence, and smoothing the sequence by Savitzky-Golay filtering to obtain a smoothed speed value sequence;
repeating the steps, the intestinal tract retroscopic velocity value of the latest 10 frames can be obtained. The obtained speed of endoscope withdrawal is based on the assumption that the larger the picture difference is, the faster the speed of endoscope withdrawal is, which is normally true, but in the actual operation process of the intestinal endoscope, interference factors such as flushing, adherence and the like in fig. 4 often exist, and when the interference factors are encountered, the speed of endoscope withdrawal will be greatly oscillated due to the instantly larger picture difference. Therefore, the interference influence needs to be eliminated by using a smoothing method, and Savitzky-Golay filtering is selected for smoothing.
Savitzky-Golay filtering is widely applied to smooth noise reduction of data streams, and is a filtering method based on local polynomial least square fitting in a time domain. The filter has the greatest characteristic that the shape and the width of a signal can be ensured to be unchanged while noise is filtered, and the accuracy of data is improved under the condition that the trend of the signal is not influenced. In addition, compared with other methods of firstly processing a frequency domain filter and then converting the frequency domain filter into a time domain, the filter directly processes data from the time domain, the system overhead is low, and the application scene of real-time endoscope withdrawal speed of the intestinal tract is met.
The formula for the Savitzky-Golay filter is as follows:
wherein Vi is the smooth mirror-withdrawing speed after Savitzky-Golay filtering, M is the window length of Savitzky-Golay filtering and must be an odd number; k is the order of the polynomial of the fitted sample, Convj(M, K) is the jth coefficient of the Savitzky-Golay filtering convolution kernel, and the convolution kernel is as long as the window; vj is the jth mirror-backing speed value in the mirror-backing speed sequence which is not smoothed, and n is the length of the mirror-backing speed sequence. M is 5, K is 3, n is 10, and the extended signal mode selects nearest. The working schematic diagram is shown in figure 5.
And S7, taking out the last value of the smoothed speed sequence and performing truncation processing, namely the speed value of the mirror backing after the current image is smoothed.
Obtaining the smooth mirror-off speed value of the latest 10 frames of images, taking out the smooth mirror-off speed value corresponding to the current frame, namely the last speed value of the smooth sequence, wherein the reasonable value range of the speed value is [0,100], and if the smooth mirror-off speed value exceeds the range after smoothing, the numerical value needs to be cut off, and the cutting method comprises the following steps:
the cut-off processing is the final speed value of the back mirror of the current image after smoothing. Fig. 5 intuitively shows the difference between the mirror-down speed before and after smoothing, and it can be seen that after smoothing, the violent oscillation of the mirror-down speed is obviously eliminated, and the smoothed mirror-down speed still maintains the original trend and range.
According to the invention, the speed of withdrawing the endoscope of the enteroscope is smoothed in real time, the oscillation of the speed of withdrawing the endoscope is reduced while the speed of withdrawing the endoscope is ensured to reflect the operation stability of a doctor in real time, the operation experience of the doctor is improved, the doctor can accurately judge the state of withdrawing the endoscope, and the quality of enteroscope examination is improved.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (9)
1. A method for smoothing the speed of intestinal tract endoscope withdrawal is characterized by comprising the following steps: the method comprises the following steps:
s1, acquiring frames of the real-time intestinal tract endoscope withdrawing video to obtain an enteroscope picture;
s2, calculating the hash fingerprint of the enteroscope picture;
s3, calculating the Hamming distance between the current frame and the previous n frames of enteroscopy pictures according to the Hash fingerprints of the current frame and the previous n frames of enteroscopy pictures;
s4, carrying out weighted average on the Hamming distance vector obtained in the S3;
s5, mapping the weighted average Hamming distance obtained in the S4 into a speed value as the speed value of the current enteroscope picture;
s6, taking the speed value of the latest X enteroscopy pictures as a sequence, and smoothing the sequence by Savitzky-Golay filtering to obtain a smoothed speed value sequence;
and S7, taking out the last value of the smoothed speed sequence and performing truncation processing, namely the speed value of the mirror backing after the current image is smoothed.
2. The method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 1, wherein: in the step S1, after obtaining the enteroscope picture, the picture is cut, converted into a gray scale image, and reduced.
3. The method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 2, wherein: the calculation formula for converting the picture into the gray-scale image is as follows:
Gray＝R×0.299+G×0.587+B×0.114；
r, G, B represents the gray value of each pixel point of the picture in three channels of red light, green light and blue light, and when the picture is reduced, the interpolation is carried out by using a region interpolation method.
4. The method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 2, wherein: after the picture is changed into a 9 × 8 gray-scale image in step S2, when the hash fingerprint is calculated by dHash, the size of the previous pixel and the size of the next pixel in each row of pixels are compared, where the larger the previous pixel and the next pixel is 1, and the larger the previous pixel and the next pixel is 0 otherwise; a total of 8 comparison results can be generated by 9 pixels in each row, and finally a hash value of 64 bits is generated by 8 × 8, which is calculated as follows:
5. the method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 1, wherein: in step S4, the weighted average hamming distance of the current frame is:
wherein d isiIs the Hamming distance, w, between the current frame and the ith frame in the nearest n framesiThe weighted value of the ith frame;
is the weighted hamming distance; wherein, the weight distribution accords with the random variable distribution, and the distribution function is as follows:
and obviously it satisfies
In the present algorithm, n takes the value 10.
6. The method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 1, wherein: in step S5, the hamming distance is obtained according to the position difference corresponding to the number statistics of two 64-bit numbers, the numerical range is [0,64], and the hamming distance is mapped to the [0,100] interval, which is the current frame mirror-backing speed value V, and the formula is as follows:
7. the method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 1, wherein: the calculation formula of the Savitzky-Golay filtering in step S6 is as follows:
wherein ViThe speed of the smooth mirror-back after Savitzky-Golay filtering is adopted, M is the window length of the Savitzky-Golay filtering and must be an odd number; k is the order of the polynomial of the fitted sample, Convj(M, K) is the jth coefficient of the Savitzky-Golay filtering convolution kernel, and the convolution kernel is as long as the window; v. ofjThe j-th lens-backing speed value in the lens-backing speed sequence is not smoothed, and n is the length of the lens-backing speed sequence.
8. The method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 7, wherein: in step S6, M is 5, K is 3, n is 10, and the extended signal mode selects nearest.
9. The method for smoothing the speed of intestinal tract endoscope withdrawal according to claim 1, wherein: the step S7 obtains a smooth receding mirror velocity value of the latest 10 frames of images, and takes out the smooth receding mirror velocity value corresponding to the current frame, that is, the last velocity value of the smoothing sequence, where the reasonable value range of the velocity value is [0,100], and if the value exceeds the range after smoothing, the value needs to be truncated, and the truncation method is as follows:
the cut-off processing is the final speed value of the back mirror of the current image after smoothing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110737719.3A CN113487553A (en) | 2021-06-30 | 2021-06-30 | Intestinal tract endoscope withdrawal speed smoothing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110737719.3A CN113487553A (en) | 2021-06-30 | 2021-06-30 | Intestinal tract endoscope withdrawal speed smoothing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113487553A true CN113487553A (en) | 2021-10-08 |
Family
ID=77937026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110737719.3A Pending CN113487553A (en) | 2021-06-30 | 2021-06-30 | Intestinal tract endoscope withdrawal speed smoothing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113487553A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113706536A (en) * | 2021-10-28 | 2021-11-26 | 武汉大学 | Sliding mirror risk early warning method and device and computer readable storage medium |
| CN113823400A (en) * | 2021-11-22 | 2021-12-21 | 武汉楚精灵医疗科技有限公司 | Method and device for monitoring speed of endoscope withdrawal of intestinal tract and computer readable storage medium |
| 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 |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000375A (en) * | 2006-01-13 | 2007-07-18 | 中国科学院声学研究所 | Steady spactracing method for synthetic aperture sonar signal real-time processing |
| CN101262559A (en) * | 2008-03-28 | 2008-09-10 | 北京中星微电子有限公司 | A method and device for eliminating sequential image noise |
| CN103902100A (en) * | 2014-04-01 | 2014-07-02 | 西北工业大学 | Speed characteristics based stroke partitioning method for intelligent freehand sketching |
| CN105825201A (en) * | 2016-03-31 | 2016-08-03 | 武汉理工大学 | Moving object tracking method in video monitoring |
| CN109598716A (en) * | 2018-12-05 | 2019-04-09 | 上海珍灵医疗科技有限公司 | Colonoscopy based on computer vision moves back mirror speed method of real-time and system |
| CN109615624A (en) * | 2018-12-05 | 2019-04-12 | 北京工业大学 | A kind of flow velocity waveforms automatic identification method based on ultrasound image |
| US20200065957A1 (en) * | 2018-05-31 | 2020-02-27 | Rdi Technologies, Inc. | Monitoring of objects based on frequency spectrum of motion and frequency filtering |
| CN111402201A (en) * | 2020-02-23 | 2020-07-10 | 中国科学院西安光学精密机械研究所 | Non-contact respiration signal measuring method capable of resisting motion interference |
-
2021
- 2021-06-30 CN CN202110737719.3A patent/CN113487553A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000375A (en) * | 2006-01-13 | 2007-07-18 | 中国科学院声学研究所 | Steady spactracing method for synthetic aperture sonar signal real-time processing |
| CN101262559A (en) * | 2008-03-28 | 2008-09-10 | 北京中星微电子有限公司 | A method and device for eliminating sequential image noise |
| CN103902100A (en) * | 2014-04-01 | 2014-07-02 | 西北工业大学 | Speed characteristics based stroke partitioning method for intelligent freehand sketching |
| CN105825201A (en) * | 2016-03-31 | 2016-08-03 | 武汉理工大学 | Moving object tracking method in video monitoring |
| US20200065957A1 (en) * | 2018-05-31 | 2020-02-27 | Rdi Technologies, Inc. | Monitoring of objects based on frequency spectrum of motion and frequency filtering |
| CN109598716A (en) * | 2018-12-05 | 2019-04-09 | 上海珍灵医疗科技有限公司 | Colonoscopy based on computer vision moves back mirror speed method of real-time and system |
| CN109615624A (en) * | 2018-12-05 | 2019-04-12 | 北京工业大学 | A kind of flow velocity waveforms automatic identification method based on ultrasound image |
| CN111402201A (en) * | 2020-02-23 | 2020-07-10 | 中国科学院西安光学精密机械研究所 | Non-contact respiration signal measuring method capable of resisting motion interference |
Non-Patent Citations (5)
| Title |
|---|
| TAKUJI KAWAMURA 等: "Clinical evaluation of a newly developed single-balloon enteroscope", 《GASTROINTESTINAL ENDOSCOPY》 * |
| YING-KIT LEUNG 等: "Double balloon endoscopy in pediatric patients", 《GASTROINTESTINAL ENDOSCOPY》 * |
| 刘凯伦 等: "基于图像感知哈希的运动目标跟踪", 《电脑知识与技术》 * |
| 李秋敬: "i-Scan高清电子染色技术在筛查右半结肠息肉样病变中的应用价值", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
| 雷林平: "基于 Savitzky-Golay 算法的曲线平滑去噪", 《电脑与信息技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113706536A (en) * | 2021-10-28 | 2021-11-26 | 武汉大学 | Sliding mirror risk early warning method and device and computer readable storage medium |
| CN113706536B (en) * | 2021-10-28 | 2022-01-18 | 武汉大学 | Sliding mirror risk early warning method and device and computer readable storage medium |
| CN113823400A (en) * | 2021-11-22 | 2021-12-21 | 武汉楚精灵医疗科技有限公司 | Method and device for monitoring speed of endoscope withdrawal of intestinal tract and computer readable storage medium |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11800969B2 (en) | Method and device for monitoring colonoscope withdrawal speed | |
| CN113487553A (en) | Intestinal tract endoscope withdrawal speed smoothing method | |
| JP5113841B2 (en) | Computer-aided analysis using video from an endoscope | |
| CN111383214B (en) | Real-time endoscope enteroscope polyp detection system | |
| JP6150583B2 (en) | Image processing apparatus, endoscope apparatus, program, and operation method of image processing apparatus | |
| US8290280B2 (en) | Image processing device, image processing method, and computer readable storage medium storing image processing program | |
| EP2008571B1 (en) | Endoscope insertion direction detecting device and endoscope insertion direction detecting method | |
| US9154745B2 (en) | Endscope apparatus and program | |
| EP2339534A1 (en) | Specular reflection compensation | |
| EP3933672A1 (en) | Method of automatic image freezing of digestive endoscopy | |
| Suman et al. | Image enhancement using geometric mean filter and gamma correction for WCE images | |
| CN113888518A (en) | Laryngopharynx endoscope tumor detection and benign and malignant classification method based on deep learning segmentation and classification multitask | |
| Sasmal et al. | Active contour segmentation of polyps in capsule endoscopic images | |
| US20220369920A1 (en) | Phase identification of endoscopy procedures | |
| CN111784686A (en) | Dynamic intelligent detection method, system and readable storage medium for endoscope bleeding area | |
| JPH08313823A (en) | Endoscopic image processing device | |
| CN113781489B (en) | Polyp image semantic segmentation method and device | |
| CN111754503B (en) | Enteroscope mirror-withdrawing overspeed duty ratio monitoring method based on two-channel convolutional neural network | |
| CN109389085B (en) | Lip language recognition model training method and device based on parameterized curve | |
| CN113744266B (en) | Method and device for displaying focus detection frame, electronic equipment and storage medium | |
| CN115965603A (en) | Image processing method, device, terminal and readable storage medium for endoscope image | |
| CN113115054B (en) | Video stream encoding method, device, system, electronic device and storage medium | |
| CN114419074B (en) | 4K medical image processing method | |
| CN116977411B (en) | Endoscope moving speed estimation method and device, electronic equipment and storage medium | |
| CN111932507B (en) | Method for identifying lesion in real time based on digestive endoscopy |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211008 |
|
| RJ01 | Rejection of invention patent application after publication |