CN110533612A - Imaging method, device, equipment and the medium of endoscopic images - Google Patents
Imaging method, device, equipment and the medium of endoscopic images Download PDFInfo
- Publication number
- CN110533612A CN110533612A CN201910797335.3A CN201910797335A CN110533612A CN 110533612 A CN110533612 A CN 110533612A CN 201910797335 A CN201910797335 A CN 201910797335A CN 110533612 A CN110533612 A CN 110533612A
- Authority
- CN
- China
- Prior art keywords
- channel
- image
- feature
- enhancing
- endoscopic images
- 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
- 238000003384 imaging method Methods 0.000 title claims abstract description 23
- 230000002708 enhancing effect Effects 0.000 claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 49
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 13
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 7
- 230000002792 vascular Effects 0.000 claims description 71
- 230000006870 function Effects 0.000 claims description 66
- 238000012545 processing Methods 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 32
- 238000001125 extrusion Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 3
- 210000004400 mucous membrane Anatomy 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000005291 magnetic effect Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 239000008280 blood Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 210000005081 epithelial layer Anatomy 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 210000002784 stomach Anatomy 0.000 description 2
- 210000004876 tela submucosa Anatomy 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 210000003238 esophagus Anatomy 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 244000144985 peep Species 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 210000000813 small intestine Anatomy 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 210000003708 urethra Anatomy 0.000 description 1
- 208000008918 voyeurism Diseases 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- 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
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Image Processing (AREA)
Abstract
This application provides a kind of imaging method of endoscopic images, device, equipment and media, the method is related to R in endoscopic images, G, and the channel image of channel B component is adjusted, comprising: obtains endoscopic images data, and the endoscopic images data are carried out RGB channel decomposition, and generate channel image, the channel image includes R channel image, G channel image and channel B image；The channel image is separately input into preset Tuning function model；The channel enhancing image of the Tuning function model output is obtained, the channel enhancing image includes the channel R enhancing image, and the channel G, which enhances image and channel B, enhances image；Enhance image according to the channel R, the channel the G enhancing image and channel B enhancing image generate endoscopic images.This method is independently adjusted by R, G, the channel B component to image, so that the tone of background tissue and blood vessel generates apparent contrast effect.
Description
Technical field
This application involves the imaging method of medical science, especially endoscopic images, device, equipment and media.
Background technique
Endoscope is that one kind can pass through human body with the optical device of detecting object internal image information, medical endoscope
Natural hole or the small notch of operation enter in human body, the inside of human body knot that doctor can be helped to see that X-ray cannot be shown
Structure becomes a kind of essential instrument in checking the inside of human body diseases such as stomach, esophagus, small intestine.It is obtained by endoscope clear
Clear image helps doctor to establish patient information, can effectively improve the accuracy of diagnosis and treatment process.
But the shooting of endoscopic images is influenced by alimentary canal bubble, illumination and shooting angle, causes picture quality irregular not
Together, simultaneously as endoscope automatic light source irradiation condition --- the limitation and inside of human body of illumination and shooting angle influence
The complexity of environmental structure --- the influence of alimentary canal bubble etc., the image that endoscope reflects is unsatisfactory, due to exposure
Image large area caused by deficiency is gloomy, affects greatly to the assessment of observation patient disease's situation during operation.
There are many such as histogram equalization enhancing, Laplace operator enhancing, gamma transformation for traditional image enchancing method
Enhancing and multi-scale image enhancing algorithm etc., due to the special screne of intravascular sight glass, illumination, angle etc. are different, and tradition is calculated
Method is unable to complete the enhancing of image, is not suitable for the scene.
Summary of the invention
In view of described problem, the application is proposed in order to provide overcoming described problem or at least being partially solved described ask
Imaging method, device, equipment and the medium of the endoscopic images of topic, comprising:
A kind of imaging method of endoscopic images, the method are related to R in endoscopic images, G and channel B component
Channel image be adjusted, comprising:
Endoscopic images data are obtained, and the endoscopic images data are subjected to RGB channel decomposition, and generate channel figure
Picture, the channel image include R channel image, G channel image and channel B image；
The channel image is separately input into preset Tuning function model；
The channel enhancing image of the Tuning function model output is obtained, the channel enhancing image includes the enhancing of the channel R
Image, the channel G, which enhances image and channel B, enhances image；
Enhance image according to the channel R, is peeped in the channel the G enhancing image and channel B enhancing image generation
Mirror image.
Further, the step of channel for obtaining the Tuning function model output enhances image, comprising:
Feature extraction is carried out to the channel image by the feature extraction function of the Tuning function model, obtains blood vessel
Minutia, the vascular detail feature include the channel R vascular detail feature, the channel G vascular detail feature and channel B blood
Pipe minutia；
Feature enhancing is carried out to the vascular detail feature by the feature enhancing function of the Tuning function model, is obtained
Vascular detail Enhanced feature；
Generating the channel according to the vascular detail Enhanced feature enhances image.
Further, the feature extraction function by the Tuning function model carries out feature to the channel image
The step of extracting, obtaining vascular detail feature, comprising:
The brightness of image layer in the channel image, institute are obtained by the Steerable filter function in the feature extraction function
Stating brightness of image layer includes R channel image brightness layer, G channel image brightness layer and channel B brightness of image layer；
The vascular detail feature is generated according to the channel image and described image brightness layer.
Further, the feature enhancing function by the Tuning function model carries out the vascular detail feature
The step of feature enhances, and obtains vascular detail Enhanced feature, comprising:
The vascular detail feature is enhanced by specified gain coefficient α, obtains the vascular detail Enhanced feature,
The specified gain coefficient α includes R channel gain factor alphaR, G channel gain factor alphaGAnd channel B gain coefficient αB。
Further, described the step of generating the channel enhancing image according to the vascular detail Enhanced feature, comprising:
Stretch processing is carried out to described image brightness layer by specified drawing coefficient β, obtains stretch processing layer, it is described specified
Drawing coefficient β includes R channel extrusion factor betaR, G channel extrusion factor betaGAnd channel B drawing coefficient βB；The stretch processing
Layer includes R channel extrusion process layer, G channel extrusion process layer and channel B stretch processing layer；
Generating the channel according to the vascular detail Enhanced feature and the stretch processing layer enhances image.
Further, the specified gain coefficient α is obtained through the following steps, comprising:
The signal-to-noise ratio of the channel image is obtained, the signal-to-noise ratio includes R channel image signal-to-noise ratio, G channel image noise
Than and channel B signal noise ratio (snr) of image；
The specified gain coefficient α is generated according to the signal-to-noise ratio.
Further, training obtains the specified drawing coefficient β through the following steps, comprising:
It obtains training image collection and stretches initial coefficients, the training image collection includes the channel R training image collection, the channel G
Training image collection and channel B training image collection；The stretching initial coefficients include R channel extrusion initial coefficients, and the channel G is drawn
It stretches initial coefficients and channel B stretches initial coefficients；
The specified drawing coefficient β is trained according to the training image collection and stretching initial coefficients.
A kind of imaging device of endoscopic images is related to the channel figure to R in endoscopic images, G and channel B component
As being adjusted, comprising:
Module is obtained, carries out RGB channel point for obtaining endoscopic images data, and by the endoscopic images data
Solution, and channel image is generated, the channel image includes R channel image, G channel image and channel B image；
Input module, for the channel image to be separately input into preset Tuning function model；
Enhance module, the channel for obtaining the Tuning function model output enhances image, and the channel enhances image
Enhance image including the channel R, the channel G, which enhances image and channel B, enhances image；
Generation module, for enhancing image according to the channel R, the channel the G enhancing image and the channel B increase
Strong image generates endoscopic images.
A kind of equipment, including processor, memory and be stored on the memory and can transport on the processor
Capable computer program, the computer program realize the imaging of endoscopic images as described above when being executed by the processor
The step of method.
A kind of computer readable storage medium stores computer program, the meter on the computer readable storage medium
The step of calculation machine program realizes the imaging method of endoscopic images as described above when being executed by processor.
The application has the following advantages:
In embodiments herein, carried out by obtaining endoscopic images data, and by the endoscopic images data
RGB channel decomposes, and generates channel image, and the channel image includes R channel image, G channel image and channel B image；
The channel image is separately input into preset Tuning function model；Obtain the channel enhancing of the Tuning function model output
Image, the channel enhancing image include the channel R enhancing image, and the channel G, which enhances image and channel B, enhances image；According to institute
The channel R enhancing image is stated, the channel the G enhancing image and channel B enhancing image generate endoscopic images, this method
It is independently adjusted by R, G, the channel B component to image, particularly enhances the G of image, B component and reduces R component, to making
The tone for obtaining background tissue and blood vessel generates apparent contrast effect, and makes the brightness layer in each channel by Steerable filter
It is separated with levels of detail, and the levels of detail comprising blood vessel feature is enhanced, and make overall G, B by stretching brightness layer
Component increases, and R component reduces, and further enhances the contrast of image.
Detailed description of the invention
It, below will be to attached needed in the description of the present application in order to illustrate more clearly of the technical solution of the application
Figure is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for this field
For those of ordinary skill, without any creative labor, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of step flow chart of the imaging method for endoscopic images that one embodiment of the application provides；
Fig. 2 is a kind of implementation procedure flow chart of the imaging method for endoscopic images that one embodiment of the application provides；
Fig. 3 is a kind of structural block diagram of the imaging device for endoscopic images that one embodiment of the application provides；
Fig. 4 is a kind of structural schematic diagram of computer equipment of one embodiment of the invention.
Specific embodiment
It is with reference to the accompanying drawing and specific real to keep the objects, features and advantages of the application more obvious and easy to understand
Applying mode, the present application will be further described in detail.Obviously, described embodiment is some embodiments of the present application, without
It is whole embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall in the protection scope of this application.
It should be noted that the imaging method is applied to in endoscopic images in any embodiment of the present invention
Background tissue and blood vessel feature distinguish, and improve the accuracy rate of doctor's interpretation.
It should be noted that since the organ surfaces such as the oral cavity of human body, oesophagus, stomach, intestines, urethra are made of mucous membrane tissue,
Mucous membrane tissue is mainly made of epithelial layer and mucous layer.Blood vessel is mainly distributed on mucous layer and submucosa.When light irradiation is various
When organ, blue wave band penetrates epithelial layer, reaches mucous membrane shallow-layer and is reflected, and the blood vessel in shallow-layer absorbs blue wave band, therefore
Channel B picture content in endoscopic images contains the abundant information of mucous membrane shallow-layer medium vessels；And green light can reach mucous membrane
Middle layer, by middle layer fine vascular all absorb, it is known that the G channel image component in image contains the blood in mucous membrane deep layer
Pipe information；And red spectral band penetrates epithelial layer and mucous layer, is absorbed by the blood vessel in submucosa, so that the R for obtaining image is logical
Road picture content does not include the vessel information of mucous layer.
Referring to Fig.1-2, a kind of imaging method of endoscopic images of one embodiment of the application offer, the method are provided
It is related to R in endoscopic images, the channel image of G and channel B component is adjusted, comprising:
S110, endoscopic images data are obtained, and the endoscopic images data is subjected to RGB channel decomposition, and generate
Channel image, the channel image include R channel image, G channel image and channel B image；
S120, the channel image is separately input into preset Tuning function model；
S130, the channel for obtaining the Tuning function model output enhance image, and the channel enhancing image includes the channel R
Enhance image, the channel G, which enhances image and channel B, enhances image；
S140, enhance image according to the channel R, the channel the G enhancing image and channel B enhancing image are raw
At endoscopic images.
In embodiments herein, carried out by obtaining endoscopic images data, and by the endoscopic images data
RGB channel decomposes, and generates channel image, and the channel image includes R channel image, G channel image and channel B image；
The channel image is separately input into preset Tuning function model；Obtain the channel enhancing of the Tuning function model output
Image, the channel enhancing image include the channel R enhancing image, and the channel G, which enhances image and channel B, enhances image；According to institute
The channel R enhancing image is stated, the channel the G enhancing image and channel B enhancing image generate endoscopic images, this method
It is independently adjusted by R, G, the channel B component to image, particularly enhances the G, B component and reduction R component of image, so that
The tone of background tissue and blood vessel generates apparent contrast effect, and by Steerable filter make the brightness layer in each channel with
Levels of detail separation, and the levels of detail comprising blood vessel feature is enhanced, and make overall G, B points by stretching brightness layer
Amount increases, and R component reduces, and further enhances the contrast of image.
In the following, by being further described to the imaging method of endoscopic images in the present exemplary embodiment.
As described in above-mentioned steps S110, endoscopic images data are obtained, and endoscopic images data progress RGB is led to
Road decomposes, and generates channel image, and the channel image includes R channel image, G channel image and channel B image；
It should be noted that due to can see that clearer blood vessel, G and channel B image contain glutinous in R channel image
The fine vascular of film layer.Compared to G, channel B image, R channel image includes that the information of shallow-layer is less, and noise information is more.Cause
The endoscopic images data are decomposed into the channel image corresponding to R, G and channel B component by this, be suitable for pair
The enhancing of channel image is answered to adjust.
As described in above-mentioned steps S120, the channel image is separately input into preset Tuning function model；
Such as: enhanced or reduced by the channel image of different channel components using Tuning function model, makes interior peep
The display of mirror image target area (angiosomes) after imaging can get a promotion.
As an example, by adjusting the picture characteristics of the computation performance of function model and endoscopic images to G, B
The channel image of channel components carries out enhancing processing；Reduction processing is carried out to the channel image of R channel components.
As described in above-mentioned steps S130, the channel enhancing image of the Tuning function model output is obtained, the channel increases
Strong image includes the channel R enhancing image, and the channel G, which enhances image and channel B, enhances image；
In one embodiment, it can be further illustrated in step S130 in conjunction with following description and " obtain the Tuning function mould
The channel of type output enhances image, and the channel enhancing image includes the channel R enhancing image, and the channel G enhances image and B is logical
The detailed process of road enhancing image ".
As described in the following steps: being carried out by the feature extraction function of the Tuning function model to the channel image special
Sign is extracted, and vascular detail feature is obtained, and the vascular detail feature includes the channel R vascular detail feature, and the channel G vascular detail is special
Sign and channel B vascular detail feature；
For example, carrying out Steerable filter to R, G and the corresponding channel image of channel B using preset Steerable filter function
Processing, then designated treatment is carried out by former channel image and filtered channel image and obtains the vascular detail feature.
In an advanced embodiment, " spy of the Tuning function model can be passed through in conjunction with following description further explanation
Sign extract function to the channel image carry out feature extraction, obtain vascular detail feature " detailed process.
As described in the following steps: being obtained in the channel image by the Steerable filter function in the feature extraction function
Brightness of image layer, described image brightness layer includes R channel image brightness layer, G channel image brightness layer and channel B image
Brightness layer；
One in the specific implementation, by each channel image Ic(x, y) carries out scheming to carry out Steerable filter as guiding with this, obtains
Brightness of image layer Lc(x, y), wherein each channel image obtains described image brightness layer L by following equationc(x, y):
Lc(x, y)=fguildfilter(Ic(x, y))
In formula: c indicates R, G, channel B；fguildfilterIndicate Steerable filter function.
As described in the following steps: generating the vascular detail feature according to the channel image and described image brightness layer.
It should be noted that the vascular detail feature is one according to the channel image and the generation of described image brightness layer
Image, specially one with vascular detail figure layer, specifically, by the channel image Ic(x, y) subtracts corresponding described
Brightness of image layer Lc(x, y) obtains the details tomographic image Dc(x, y), specific formula indicate as follows:
Dc(x, y)=Ic(x, y)-Lc(x, y)
In formula: c indicates R, G, channel B.
As described in the following steps: by the feature enhancing function of the Tuning function model to the vascular detail feature into
The enhancing of row feature, obtains vascular detail Enhanced feature；
For example, it is special that the enhancing that the vascular detail feature carries out preset gain coefficient is waited until that the vascular detail enhances
Sign, wherein the vascular detail feature in different channel components (R, G and B) is carried out by corresponding to the gain coefficient in the channel
Enhancing.
In an advanced embodiment, " spy of the Tuning function model can be passed through in conjunction with following description further explanation
Levy enhancing function to the vascular detail feature carry out feature enhancing, obtain vascular detail Enhanced feature " detailed process.
The vascular detail feature is enhanced by specified gain coefficient α, obtains the vascular detail Enhanced feature,
The specified gain coefficient α includes R channel gain factor alphaR, G channel gain factor alphaGAnd channel B gain coefficient αB。
One in the specific implementation, enhancing the vascular detail feature by following formula, increased with obtaining the vascular detail
Strong feature,
Vascular detail Enhanced featurec=αc×Dc(x, y)
In formula: c indicates R, G, channel B.
In one embodiment, the specified gain coefficient α is obtained through the following steps, comprising:
The signal-to-noise ratio of the channel image is obtained, the signal-to-noise ratio includes R channel image signal-to-noise ratio, G channel image noise
Than and channel B signal noise ratio (snr) of image；
The specified gain coefficient α is generated according to the signal-to-noise ratio.
One in the specific implementation, obtaining the specified gain coefficient α by following formula,
αc=10 × SNR (Ic(x, y))
In formula: c indicates R, G, channel B；SNR(Ic(x, y)) indicate channel image signal-to-noise ratio.
As described in the following steps: generating the channel according to the vascular detail Enhanced feature enhances image.
In an advanced embodiment, it can further illustrate in conjunction with following description " according to the vascular detail Enhanced feature
Generate channel enhancing image " detailed process.
Stretch processing is carried out to described image brightness layer by specified drawing coefficient β, obtains stretch processing layer, it is described specified
Drawing coefficient β includes R channel extrusion factor betaR, G channel extrusion factor betaGAnd channel B drawing coefficient βB；The stretch processing
Layer includes R channel extrusion process layer, G channel extrusion process layer and channel B stretch processing layer；
One in the specific implementation, stretch processing is carried out to described image brightness layer by following formula, to obtain the drawing
Process layer is stretched,
Stretch processing layerc=βc×Lc(x, y)
In formula: c indicates R, G, channel B.
In one embodiment, training obtains the specified drawing coefficient β through the following steps, comprising:
It obtains training image collection and stretches initial coefficients, the training image collection includes the channel R training image collection, the channel G
Training image collection and channel B training image collection；The stretching initial coefficients include R channel extrusion initial coefficients, and the channel G is drawn
It stretches initial coefficients and channel B stretches initial coefficients；
The specified drawing coefficient β is trained according to the training image collection and stretching initial coefficients.
Such as: it can use the characteristic of drawing coefficient, by a large amount of different volunteer (including but not limited to following one
Kind or it is a variety of: the age, if having the state of an illness, gender, patient's condition etc.) endoscope original image carry out prescribed coefficient codomain stretching at
Reason, using the original image of volunteer as training image, and using drawing coefficient codomain as the input data of operational model, to drawing
The value for stretching coefficient is adjusted, by adjusting the value of drawing coefficient, image and original image after obtaining stretch processing
Maximum hue distance obtains the final value of drawing coefficient by maximum hue distance conversion.
One in the specific implementation, obtaining the specified drawing coefficient β through the following steps,
For the specified drawing coefficient β (β in each channelR, βG, βB) determination, be defined as follows maximum hue distance:
Wherein: Dist indicates maximum hue distance, BenIndicate the channel enhancing image EcBackground area in (x, y)；
VenIndicate the channel enhancing image EcAngiosomes in (x, y)；||Ben, Ven| | indicate the channel enhancing image Ec(x,
Y) the distance between background area and angiosomes in；BoriIndicate the channel image IcBackground area in (x, y)；VoriTable
Show the channel image IcAngiosomes in (x, y)；||Bori, Vori| | indicate the channel image IcBackground area in (x, y)
The distance between angiosomes.
Specifically, it is determined that the process of the specified drawing coefficient β is as follows:
It chooses m width training image and forms the training image collection and n group stretching initial coefficients (wherein, βR∈ [0.6,
0.85], βG∈ [1.05,1.3], βB∈ [1.05,1.3], 0.05) step-length, which takes, to be determined, specific step is as follows for calculation method:
Step 1: the i-th width image of input, image size is 128 × 128, if i is greater than m, terminates to calculate and jumps to Step 8)；
Otherwise Step 2 is executed).
Step 2) input jth group parameter, Step 7 is jumped to if j is greater than n)；Otherwise Step 3 is executed).
Step 3) input picture is handled using contrast enhancement algorithms.
Step 4) choose original image and enhanced image angiosomes and background area.
Step 5) image is transformed into CIE color space from rgb space, conversion formula is as follows:
X=2.7690R+1.7518G+1.1300B
Y=1.0000R+4.5907G+0.0601B
Z=0.0000R+0.0565G+5.5943B
Step 6) calculate separately the distance between original image and the background area and the angiosomes that handle image | | Ben,
Ven| | with | | Bori, Vori| |, value Dist is then stored in array VdisIn, and jump back to Step 2), in which:
In formula: (Vori(x), Vori(y)) mass center in original image medium vessels region is indicated；(Ven(x), Ven(y)) at expression
Manage the mass center in image medium vessels region；(Bori(x), Bori(y)) mass center of background area in processing image is indicated；(Ben(x), Ben
(y)) mass center of image background regions in processing image is indicated.
Step 7) according to hue distance maximization target, one group of optimized parameter β of available i-th width imageR, βG, βB。
Parameter is stored in V respectivelyecR, VecG, VecB, and jump back to Step 1).
Step 8) to VecR, VecG, VecBMean value is carried out respectively, obtains one group of optimized parameter βRbest, βGbest, βBbest, as
The specified drawing coefficient β.
Generating the channel according to the vascular detail Enhanced feature and the stretch processing layer enhances image.
One in the specific implementation, the vascular detail Enhanced feature and the stretch processing are laminated by following formula
Add, to obtain the channel enhancing image,
Ec(x, y)=βc×Lc(x, y)+αc×Dc(x, y)
In formula: c indicates R, G, channel B.
As described in above-mentioned steps S140, enhance image, the channel the G enhancing image and the B according to the channel R
Channel enhances image and generates endoscopic images.
It should be noted that the channel R after acquisition image enhancement processing is enhanced image, the channel the G enhancing figure
Picture and channel B enhancing image carry out the inverse resolution process of RGB channel, obtain the endoscopic images.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Referring to Fig. 3, a kind of imaging device of endoscopic images of one embodiment of the application offer is provided, is related to internally peeping
The channel image of R in mirror image, G and channel B component is adjusted, comprising:
Module 310 is obtained, carries out RGB channel for obtaining endoscopic images data, and by the endoscopic images data
It decomposes, and generates channel image, the channel image includes R channel image, G channel image and channel B image；
Input module 320, for the channel image to be separately input into preset Tuning function model；
Enhance module 330, the channel for obtaining the Tuning function model output enhances image, the channel enhancing figure
As including that the channel R enhances image, the channel G, which enhances image and channel B, enhances image；
Generation module 340, for enhancing image, the channel the G enhancing image and the channel B according to the channel R
Enhance image and generates endoscopic images.
In one embodiment, the enhancing module 330, comprising:
Vascular detail feature acquisition submodule, for the feature extraction function by the Tuning function model to described logical
Road image carries out feature extraction, obtains vascular detail feature, and the vascular detail feature includes the channel R vascular detail feature, and G is logical
Road vascular detail feature and channel B vascular detail feature；
Vascular detail feature enhances submodule, for the feature enhancing function by the Tuning function model to the blood
Pipe minutia carries out feature enhancing, obtains vascular detail Enhanced feature；
Channel enhances image and generates submodule, for generating the channel enhancing figure according to the vascular detail Enhanced feature
Picture.
In one embodiment, the vascular detail feature acquisition submodule, comprising:
Brightness of image layer acquisition submodule, described in being obtained by the Steerable filter function in the feature extraction function
Brightness of image layer in channel image, described image brightness layer include R channel image brightness layer, G channel image brightness layer, and
Channel B brightness of image layer；
Vascular detail feature generates submodule, for generating the blood according to the channel image and described image brightness layer
Pipe minutia.
In one embodiment, the vascular detail feature enhances submodule, comprising:
Coefficient enhances submodule, for enhancing by specified gain coefficient α the vascular detail feature, obtains institute
Vascular detail Enhanced feature is stated, the specified gain coefficient α includes R channel gain factor alphaR, G channel gain factor alphaGAnd B
Channel gain factor alphaB。
In one embodiment, the channel enhancing image generates submodule, comprising:
Stretch processing layer generates submodule, for being carried out at stretching by specified drawing coefficient β to described image brightness layer
Reason, obtains stretch processing layer, the specified drawing coefficient β includes R channel extrusion factor betaR, G channel extrusion factor betaGAnd B is logical
Road drawing coefficient βB；The stretch processing layer includes R channel extrusion process layer, and G channel extrusion process layer and channel B stretch
Process layer；
Channel enhances image and synthesizes submodule, for raw according to the vascular detail Enhanced feature and the stretch processing layer
Enhance image at the channel.
In one embodiment, the specified gain coefficient α is obtained by following devices, comprising:
Signal-to-noise ratio obtains module, and for obtaining the signal-to-noise ratio of the channel image, the signal-to-noise ratio includes R channel image letter
It makes an uproar and compares, G channel image signal-to-noise ratio and channel B signal noise ratio (snr) of image；
Specified gain coefficient α generation module, for generating the specified gain coefficient α according to the signal-to-noise ratio.
In one embodiment, the specified drawing coefficient β is obtained by following devices training, comprising:
Training image collection and stretching initial coefficients obtain module, for obtaining training image collection and stretching initial coefficients, institute
Stating training image collection includes the channel R training image collection, the channel G training image collection and channel B training image collection；The stretching
Initial coefficients include R channel extrusion initial coefficients, and G channel extrusion initial coefficients and channel B stretch initial coefficients；
Specified drawing coefficient β generation module, it is described for being trained according to the training image collection and stretching initial coefficients
Specified drawing coefficient β.
Referring to Fig. 4, a kind of computer equipment of the imaging method of endoscopic images of the invention is shown, specifically can wrap
It includes as follows:
Above-mentioned computer equipment 12 is showed in the form of universal computing device, the component of computer equipment 12 may include but
Be not limited to: one or more processor or processing unit 16, system storage 28, connecting different system components (including is
Unite memory 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few 18 structures of class bus or a variety of, including memory bus 18 or memory control
Device, peripheral bus 18, graphics acceleration port, processor or the office using 18 structure of any bus in a variety of 18 structures of bus
Domain bus 18.For example, these architectures include but is not limited to industry standard architecture (ISA) bus 18, microchannel
Architecture (MAC) bus 18, enhanced isa bus 18, audio-video frequency electronic standard association (VESA) local bus 18 and outer
Enclose component interconnection (PCI) bus 18.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Computer equipment 12 may further include other movement/it is not removable
Dynamic, volatile/non-volatile computer decorum storage medium.Only as an example, storage system 34 can be used for read and write can not
Mobile, non-volatile magnetic media (commonly referred to as " hard disk drive ").Although not shown in fig 4, it can provide for can
The disc driver of mobile non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable anonvolatile optical disk (such as CD-
ROM, DVD-ROM or other optical mediums) read-write CD drive.In these cases, each driver can pass through one
A or multiple data mediums interface is connected with bus 18.Memory may include at least one program product, the program product
With one group of (for example, at least one) program module 42, these program modules 42 are configured to perform the function of various embodiments of the present invention
Energy.
Program/utility 40 with one group of (at least one) program module 42, can store in memory, for example,
Such program module 42 includes --- but being not limited to --- operating system, one or more application program, other program moulds
It may include the realization of network environment in block 42 and program data, each of these examples or certain combination.Program mould
Block 42 usually executes function and/or method in embodiment described in the invention.
Computer equipment 12 can also with one or more external equipments 14 (such as keyboard, sensing equipment, display 24,
Camera etc.) communication, the equipment interacted with the computer equipment 12 can be also enabled a user to one or more to be communicated, and/
Or with enable the computer equipment 12 and one or more other calculate any equipment that equipment are communicated (such as network interface card,
Modem etc.) communication.This communication can be carried out by interface input/output (I/O) 22.Also, computer equipment
12 can also by network adapter 20 and one or more network (such as local area network (LAN)), wide area network (WAN) and/or
Public network (such as internet) communication.As shown, network adapter 20 passes through other of bus 18 and computer equipment 12
Module communication.It should be understood that although not shown in fig 4, other hardware and/or software mould can be used in conjunction with computer equipment 12
Block, including but not limited to: microcode, device driver, redundant processing unit 16, external disk drive array, RAID system, magnetic
Tape drive and data backup storage system 34 etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the imaging method of endoscopic images provided by the embodiment of the present invention.
That is, above-mentioned processing unit 16 is realized when executing above procedure: obtaining endoscopic images data, and interior peeped described
Mirror image data carries out RGB channel decomposition, and generates channel image, and the channel image includes R channel image, G channel image,
And channel B image；The channel image is separately input into preset Tuning function model；Obtain the Tuning function model
The channel of output enhances image, and the channel enhancing image includes the channel R enhancing image, and the channel G enhances image and channel B
Enhance image；Enhance image according to the channel R, the channel the G enhancing image and the channel B enhance in image generation
Sight glass image.
In embodiments of the present invention, the present invention also provides a kind of computer readable storage medium, it is stored thereon with computer
Program realizes the imaging method of the endoscopic images provided such as all embodiments of the application when the program is executed by processor:
That is, realization when being executed by processor to program: obtaining endoscopic images data, and by the endoscopic images number
According to progress RGB channel decomposition, and channel image is generated, the channel image includes R channel image, and G channel image and B are logical
Road image；The channel image is separately input into preset Tuning function model；Obtain the Tuning function model output
Channel enhances image, and the channel enhancing image includes the channel R enhancing image, and the channel G enhances image and channel B enhancing figure
Picture；Enhance image according to the channel R, the channel the G enhancing image and channel B enhancing image generate endoscope figure
Picture.
It can be using any combination of one or more computer-readable media.Computer-readable medium can be calculating
Machine gram signal media or computer readable storage medium.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.Computer
The more specific example (non exhaustive list) of readable storage medium storing program for executing includes: electrical connection with one or more conducting wires, portable
Formula computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory
(EPOM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
Above-mentioned any appropriate combination.In this document, computer readable storage medium can be it is any include or storage program
Tangible medium, the program can be commanded execution system, device or device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, above procedure design language include object oriented program language --- such as Java, Smalltalk, C+
+, further include conventional procedural programming language --- such as " C " language or similar programming language.Program code
It can fully execute on the user computer, partly execute, held as an independent software package on the user computer
Part executes on the remote computer or holds on a remote computer or server completely on the user computer for row, part
Row.In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network
(LAN) or wide area network (WAN) --- it is connected to subscriber computer, or, it may be connected to outer computer (such as using because of spy
Service provider is netted to connect by internet).All the embodiments in this specification are described in a progressive manner, each
What embodiment stressed is the difference from other embodiments, the mutual coherent in same and similar part between each embodiment
See.
Although preferred embodiments of the embodiments of the present application have been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and all change and modification within the scope of the embodiments of the present application.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, limited by sentence " including one ... "
Element, it is not excluded that including identical being wanted in the process, method of the element, article or terminal device there is also other
Element.
Above to the imaging method of endoscopic images provided herein, device, equipment and medium, detailed Jie has been carried out
It continues, specific examples are used herein to illustrate the principle and implementation manner of the present application, and the explanation of above embodiments is only
It is to be used to help understand the method for this application and its core ideas；At the same time, for those skilled in the art, according to this Shen
Thought please, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not manage
Solution is the limitation to the application.
Claims (10)
1. a kind of imaging method of endoscopic images, the method is related to R in endoscopic images, G and channel B component
Channel image is adjusted characterized by comprising
Endoscopic images data are obtained, and the endoscopic images data are subjected to RGB channel decomposition, and generate channel image,
The channel image includes R channel image, G channel image and channel B image；
The channel image is separately input into preset Tuning function model；
The channel enhancing image of the Tuning function model output is obtained, the channel enhancing image includes the channel R enhancing image,
The channel G, which enhances image and channel B, enhances image；
Enhance image according to the channel R, the channel the G enhancing image and channel B enhancing image generate endoscope figure
Picture.
2. the method according to claim 1, wherein the channel for obtaining the Tuning function model output increases
The step of strong image, comprising:
Feature extraction is carried out to the channel image by the feature extraction function of the Tuning function model, obtains vascular detail
Feature, the vascular detail feature include the channel R vascular detail feature, and the channel G vascular detail feature and channel B blood vessel are thin
Save feature；
Feature enhancing is carried out to the vascular detail feature by the feature enhancing function of the Tuning function model, obtains blood vessel
Details Enhanced feature；
Generating the channel according to the vascular detail Enhanced feature enhances image.
3. according to the method described in claim 2, it is characterized in that, the feature extraction letter by the Tuning function model
It is several that feature extraction, the step of obtaining vascular detail feature are carried out to the channel image, comprising:
The brightness of image layer in the channel image, the figure are obtained by the Steerable filter function in the feature extraction function
Image brightness layer includes R channel image brightness layer, G channel image brightness layer and channel B brightness of image layer；
The vascular detail feature is generated according to the channel image and described image brightness layer.
4. according to the method described in claim 3, it is characterized in that, the feature by the Tuning function model enhances letter
It is several that feature enhancing, the step of obtaining vascular detail Enhanced feature are carried out to the vascular detail feature, comprising:
The vascular detail feature is enhanced by specified gain coefficient α, obtains the vascular detail Enhanced feature, it is described
Specified gain coefficient α includes R channel gain factor alphaR, G channel gain factor alphaGAnd channel B gain coefficient αB。
5. according to the method described in claim 4, it is characterized in that, described according to described in vascular detail Enhanced feature generation
Channel enhances the step of image, comprising:
Stretch processing is carried out to described image brightness layer by specified drawing coefficient β, obtains stretch processing layer, the specified stretching
Factor beta includes R channel extrusion factor betaR, G channel extrusion factor betaGAnd channel B drawing coefficient βB；The stretch processing layer packet
Include R channel extrusion process layer, G channel extrusion process layer and channel B stretch processing layer；
Generating the channel according to the vascular detail Enhanced feature and the stretch processing layer enhances image.
6. according to the method described in claim 4, it is characterized in that, the specified gain coefficient α is obtained through the following steps, packet
It includes:
Obtaining the signal-to-noise ratio of the channel image, the signal-to-noise ratio includes R channel image signal-to-noise ratio, G channel image signal-to-noise ratio, with
And channel B signal noise ratio (snr) of image；
The specified gain coefficient α is generated according to the signal-to-noise ratio.
7. according to the method described in claim 5, it is characterized in that, the specified drawing coefficient β through the following steps training obtain
, comprising:
It obtains training image collection and stretches initial coefficients, the training image collection includes the channel R training image collection, the training of the channel G
Image set and channel B training image collection；The stretching initial coefficients include R channel extrusion initial coefficients, at the beginning of G channel extrusion
Beginning coefficient and channel B stretch initial coefficients；
The specified drawing coefficient β is trained according to the training image collection and stretching initial coefficients.
8. a kind of imaging device of endoscopic images, is related to the channel image to R in endoscopic images, G and channel B component
It is adjusted characterized by comprising
Module is obtained, carries out RGB channel decomposition for obtaining endoscopic images data, and by the endoscopic images data, and
Channel image is generated, the channel image includes R channel image, G channel image and channel B image；
Input module, for the channel image to be separately input into preset Tuning function model；
Enhance module, the channel for obtaining the Tuning function model output enhances image, and the channel enhancing image includes R
Channel enhances image, and the channel G, which enhances image and channel B, enhances image；
Generation module, for enhancing image, the channel the G enhancing image and channel B enhancing figure according to the channel R
As generating endoscopic images.
9. a kind of equipment, which is characterized in that including processor, memory and be stored on the memory and can be at the place
The computer program run on reason device is realized when the computer program is executed by the processor as appointed in claim 1 to 7
Method described in one.
10. a kind of computer readable storage medium, which is characterized in that store computer journey on the computer readable storage medium
Sequence realizes the method as described in any one of claims 1 to 7 when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910797335.3A CN110533612A (en) | 2019-08-27 | 2019-08-27 | Imaging method, device, equipment and the medium of endoscopic images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910797335.3A CN110533612A (en) | 2019-08-27 | 2019-08-27 | Imaging method, device, equipment and the medium of endoscopic images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110533612A true CN110533612A (en) | 2019-12-03 |
Family
ID=68664670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910797335.3A Pending CN110533612A (en) | 2019-08-27 | 2019-08-27 | Imaging method, device, equipment and the medium of endoscopic images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533612A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080547A (en) * | 2019-12-11 | 2020-04-28 | 苏州新光维医疗科技有限公司 | Endoscope image enhancement method |
| CN111462125A (en) * | 2020-04-03 | 2020-07-28 | 杭州恒生数字设备科技有限公司 | Enhanced in vivo detection image processing system |
| CN111626962A (en) * | 2020-05-27 | 2020-09-04 | 重庆邮电大学 | CMOS endoscope image enhancement method |
| CN111968051A (en) * | 2020-08-10 | 2020-11-20 | 珠海普生医疗科技有限公司 | Endoscope blood vessel enhancement method based on curvature analysis |
| CN113068015A (en) * | 2021-03-24 | 2021-07-02 | 南京锐普创科科技有限公司 | Endoscope image distortion correction system based on optical fiber probe |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140369601A1 (en) * | 2012-01-03 | 2014-12-18 | Chung-Ang University Industry-Academy Cooperation Foundation | Apparatus and method for enhancing image using color channel |
| CN107451963A (en) * | 2017-07-05 | 2017-12-08 | 广东欧谱曼迪科技有限公司 | Multispectral nasal cavity endoscope Real-time image enhancement method and endoscopic imaging system |
| US20190087940A1 (en) * | 2017-09-15 | 2019-03-21 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium |
-
2019
- 2019-08-27 CN CN201910797335.3A patent/CN110533612A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140369601A1 (en) * | 2012-01-03 | 2014-12-18 | Chung-Ang University Industry-Academy Cooperation Foundation | Apparatus and method for enhancing image using color channel |
| CN107451963A (en) * | 2017-07-05 | 2017-12-08 | 广东欧谱曼迪科技有限公司 | Multispectral nasal cavity endoscope Real-time image enhancement method and endoscopic imaging system |
| US20190087940A1 (en) * | 2017-09-15 | 2019-03-21 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 姜鸿鹏等: "一种血管内窥镜图像增强算法", 《光电工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080547A (en) * | 2019-12-11 | 2020-04-28 | 苏州新光维医疗科技有限公司 | Endoscope image enhancement method |
| CN111462125A (en) * | 2020-04-03 | 2020-07-28 | 杭州恒生数字设备科技有限公司 | Enhanced in vivo detection image processing system |
| CN111462125B (en) * | 2020-04-03 | 2021-08-20 | 杭州恒生数字设备科技有限公司 | Enhanced in vivo detection image processing system |
| CN111626962A (en) * | 2020-05-27 | 2020-09-04 | 重庆邮电大学 | CMOS endoscope image enhancement method |
| CN111968051A (en) * | 2020-08-10 | 2020-11-20 | 珠海普生医疗科技有限公司 | Endoscope blood vessel enhancement method based on curvature analysis |
| CN113068015A (en) * | 2021-03-24 | 2021-07-02 | 南京锐普创科科技有限公司 | Endoscope image distortion correction system based on optical fiber probe |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110533612A (en) | Imaging method, device, equipment and the medium of endoscopic images | |
| US11915415B2 (en) | Image processing method and apparatus, computer-readable medium, and electronic device | |
| Gono | Narrow band imaging: technology basis and research and development history | |
| CN113496489B (en) | Training method of endoscope image classification model, image classification method and device | |
| WO2012015285A2 (en) | Method and apparatus for processing image and medical image system employing the apparatus | |
| US20230080098A1 (en) | Object recognition using spatial and timing information of object images at diferent times | |
| WO2021159811A1 (en) | Auxiliary diagnostic apparatus and method for glaucoma, and storage medium | |
| CN113470029B (en) | Training method and device, image processing method, electronic device and storage medium | |
| CN111488912B (en) | Laryngeal disease diagnosis system based on deep learning neural network | |
| CN110276408A (en) | Classification method, device, equipment and the storage medium of 3D rendering | |
| CN115049666B (en) | Endoscope virtual biopsy device based on color wavelet covariance depth map model | |
| TWI779284B (en) | Device for marking image data | |
| CN112560785A (en) | Control method for adjusting multi-screen brightness through face tracking based on artificial intelligence | |
| CN114897756A (en) | Model training method, medical image fusion method, device, equipment and medium | |
| CN113781489A (en) | Polyp image semantic segmentation method and device | |
| Wang et al. | Endoscopic image luminance enhancement based on the inverse square law for illuminance and retinex | |
| Lin et al. | A desmoking algorithm for endoscopic images based on improved U‐Net model | |
| TW202044271A (en) | Method and system for analyzing skin texture and skin lesion using artificial intelligence cloud based platform | |
| Shen et al. | Automatic polyp image segmentation and cancer prediction based on deep learning | |
| Tan et al. | An endoscope image enhancement algorithm based on image decomposition | |
| Mehta et al. | CPulse: heart rate estimation from RGB videos under realistic conditions | |
| CN110414593A (en) | Image processing method and device, processor, electronic equipment and storage medium | |
| US11961225B2 (en) | Systems and methods for detecting potential malignancies | |
| Odagawa et al. | Feasibility Study for Computer-Aided Diagnosis System with Navigation Function of Clear Region for Real-Time Endoscopic Video Image on Customizable Embedded DSP Cores | |
| Feng et al. | Research and application of tongue and face diagnosis based on deep learning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191203 |
|
| WD01 | Invention patent application deemed withdrawn after publication |