CN110335284A - A kind of method of the removal background of pathological image - Google Patents
A kind of method of the removal background of pathological image Download PDFInfo
- Publication number
- CN110335284A CN110335284A CN201910624429.0A CN201910624429A CN110335284A CN 110335284 A CN110335284 A CN 110335284A CN 201910624429 A CN201910624429 A CN 201910624429A CN 110335284 A CN110335284 A CN 110335284A
- Authority
- CN
- China
- Prior art keywords
- image
- tissue
- low range
- pathological
- background
- 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
- 230000001575 pathological effect Effects 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 39
- 239000012634 fragment Substances 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000009825 accumulation Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005549 size reduction Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 7
- 101100269850 Caenorhabditis elegans mask-1 gene Proteins 0.000 description 3
- 206010047571 Visual impairment Diseases 0.000 description 3
- 235000007926 Craterellus fallax Nutrition 0.000 description 2
- 240000007175 Datura inoxia Species 0.000 description 2
- 229920002334 Spandex Polymers 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000011017 operating method Methods 0.000 description 2
- 239000004759 spandex Substances 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 235000012149 noodles Nutrition 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 210000003296 saliva Anatomy 0.000 description 1
Classifications
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of methods of the removal background of pathological image, including, original image is obtained, and original image is scaled 4 times;The pathological image after the scaling is handled by medical treatment library Openslide;Binaryzation extraction is carried out to the tissue in the low range image;The tissue part that area in the fragment of tissue is greater than each tissue minimum pixel area is chosen, and is obtained on low range image per a piece of tissue contours;The tissue contours position on original image is found by the tissue contours in the low range figure, and obtains the tissue contours position;Image procossing is carried out to the original image by libvips, and obtains the image after removal background.By the image of the low range after zoomed image, after eliminating the noise on pathological image, by deleting the image of background parts, to save the memory space of image, and the displaying of image will not be had an impact.
Description
Technical field
The technical field of image procossing of the present invention, more particularly, it relates to a kind of side of the removal background of pathological image
Method.
Background technique
Because the image contacted at present belongs to SVS picture caused by Lycra, current maximum multiple be 20x~
100x has many noises on original image, and these noises all have a great impact to subsequent image procossing and algorithm realization,
Therefore it needs the background removal in original image, and the size for removing the image after background is also being reduced, these noises are serious
Influence user interaction and the dysopia that can generate.
And when general operation, the picture of SVS is larger, and the information content of storage is compared with horn of plenty, therefore general image procossing is calculated
Method is difficult to carry out processing operation to it.If by the SVS picture of original image size be stored as in a manner of normal storage JPG, PNG or
If tiff format, original image size is 343M, that is, is allowed to if being converted to normal format, but its size can become very big
(size becomes 1.83G after being such as converted to PNG format) causes very high even if configuring since information content is very big (there are many pixel number)
Computer open file can also waste time very much, it is even stuck.
Therefore, there are two defects for pathological image currently on the market:
(1) there are many noises on pathological image, and the serious vision that influences user's interaction and can generate of noise hinders
Hinder;
(2) size of the picture storage of pathological image is very big, is easy so that computer opening needs the long period, if computer is matched
Set lower, computer even can be stuck.
Summary of the invention
The purpose of this section is to summarize some aspects of the embodiment of the present invention and briefly introduce some preferable implementations
Example.It may do a little simplified or be omitted to avoid our department is made in this section and the description of the application and the title of the invention
Point, the purpose of abstract of description and denomination of invention it is fuzzy, and this simplification or omit and cannot be used for limiting the scope of the invention.
In view of above-mentioned and/or problems of the prior art, the present invention is proposed.
Therefore, the one of purpose of the present invention is to provide a kind of method of the removal background of pathological image.
In order to solve the above technical problems, the invention provides the following technical scheme: a kind of side of the removal background of pathological image
Method, including,
S1 obtains the original image of a pathological image, and original image is scaled 4 times;
S2, by medical treatment library Openslide to after the scaling pathological image handle, and obtain scaling 4 times after
Low range image;
S3 carries out binaryzation extraction to the tissue in the low range image;
S4, the image after being extracted binaryzation by morphology closed operation carry out internal filling and form a complete tissue
Fragment;
The fragment of tissue is opened operation removal noise spot by morphology by S5;
S6 chooses the tissue part that area in the fragment of tissue is greater than each tissue minimum pixel area, and in low power
It obtains on rate image per a piece of tissue contours;
S7 finds the tissue contours position on original image by the tissue contours in the low range figure, and obtains institute
State tissue contours position;
S8 carries out image procossing to the original image by libvips, and obtains the image after removal background.
A kind of preferred embodiment of the method for removal background as pathological image of the present invention, in which: the binaryzation
The step of extraction, is divided into three steps:
Low range image is transformed into HSV space, and extracts the channel information of saturation degree by S401;
S402 carries out mean filter to the low range image, and convolution kernel size is 100*100, removes small noise;
S403 uses Otsu threshold binaryzation to the low range image.
A kind of preferred embodiment of the method for removal background as pathological image of the present invention, in which: described extract is satisfied
With the formula of the channel information of degree are as follows:
Wherein, max indicates the maximum value in all pixels of present image, and min indicates the minimum value in pixel.
A kind of preferred embodiment of the method for removal background as pathological image of the present invention, in which: the mean value filter
The operating procedure of wave are as follows:
S4021 enables Sxy indicate center at picture point (x, y), and size is the rectangle subgraph window of m*n pixel;
S4022, the mean filter that counts calculate the average value of contaminated image g (x, y) in the region that Sxy is defined;
S4023, the restored image at point (x, y)Value, using Sxy define ground region in the calculated calculation of pixel
Number average value, that is,
A kind of preferred embodiment of the method for removal background as pathological image of the present invention, in which: the big saliva threshold
The step of being worth binaryzation:
S4031 calculates the normalization histogram of input low range image, uses pi, i=0,1,2 ..., L-1 indicates institute
State each component of histogram;
S4032 is usedFor ki, i=0,1,2 ..., L-1 calculate accumulation and P1(k);
S4033, formula is usedFor ki, i=0,1,2 ..., L-1 are calculated cumulative mean value m (k);
S4034, formula is usedCalculate global gray average mG;
S4035, formula is usedFor ki, i=0,1,2 ..., L-1 calculate inter-class variance
S4036, obtain so thatMaximum k value, that is, Otsu threshold k*If maximum value is not unique, with corresponding detection
The average value of each maximum value k arrived is k*;
S4037, in k=k*Place calculatesObtain separable measures η*, that is, divide threshold value;
S4038, binaryzation division is carried out to low range image according to the division threshold value that S4037 is obtained, obtains final knot
Fruit.
A kind of preferred embodiment of the method for removal background as pathological image of the present invention, in which: pass through
OpenSeadragon in the library JavaScript is by the picture presentation after removing background.
A kind of preferred embodiment of the method for removal background as pathological image of the present invention, in which: the displaying will
N times of actual picture size reduction, and n is more than or equal to 4.
Beneficial effects of the present invention: the background of the removal pathological image provided through the invention reaches two effects:
(1) by the image of the low range after zoomed image, after eliminating the noise on pathological image, then from original image
In find tissue contours, and obtain the outline position of original structure, and picture is stored according to edited format, finally
Image results are checked in page end;
(2) picture without message part in the image under each layer of resolution ratio is removed, that is, deletes the image of background parts, from
And the memory space of image is saved, and will not have an impact to the displaying of image.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill of field, without any creative labor, it can also be obtained according to these attached drawings other
Attached drawing.Wherein:
Fig. 1 is the entirety of the original image in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Structural schematic diagram;
Fig. 2 is the partial enlargement of Fig. 1 in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Schematic diagram;
Fig. 3 is the partial structurtes of Fig. 1 in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Schematic diagram;
Fig. 4 is the attribute of the original image in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Schematic diagram;
Fig. 5 is the signal of the binaryzation in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Figure;
Fig. 6 is showing for the removal noise spot in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
It is intended to;
Fig. 7 is described libvips pair in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
The step of original image, schemes;
Fig. 8 is described libvips pair in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
The step of result in Fig. 7 removes background is schemed;
After the removal background in a kind of embodiment that Fig. 9 provides for the method for the removal background of pathological image of the present invention
Image storage mode figure;
Figure 10 is the removal background in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Image display pattern figure afterwards;
Figure 11 is the removal background in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Schematic diagram afterwards;
Figure 12 is the removal background in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
Image result schematic diagram afterwards;
Figure 13 is the removal background in a kind of embodiment that the method for the removal background of pathological image of the present invention provides
The attribute schematic diagram of image afterwards.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, right with reference to the accompanying drawings of the specification
A specific embodiment of the invention is described in detail.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, but the present invention can be with
Implemented using other than the one described here other way, those skilled in the art can be without prejudice to intension of the present invention
In the case of do similar popularization, therefore the present invention is not limited by the specific embodiments disclosed below.
Secondly, " one embodiment " or " embodiment " referred to herein, which refers to, may be included at least one realization side of the invention
A particular feature, structure, or characteristic in formula." in one embodiment " that different places occur in the present specification not refers both to
The same embodiment, nor the individual or selective embodiment mutually exclusive with other embodiments.
Embodiment 1
The present invention provides a kind of methods of the removal background of pathological image, because the image contacted at present belongs to Lycra
Generated SVS picture, current maximum multiple is 20x~100x, shown referring to Figures 1 and 2.
Referring to Fig. 2, there are many noises on original image, and these noises have subsequent image procossing and algorithm realization
Very big influence, it is therefore desirable to which by the background removal in original image, and the size for removing the image after background is also being reduced.
It in rectangular box is all noise in figure, serious the influences user of these noises is interactive and can generate referring to Fig. 3
Dysopia.
And when general operation, the picture of SVS is larger, and the information content of storage is compared with horn of plenty, therefore general image procossing is calculated
Method is difficult to carry out processing operation to it.If by the SVS picture of original image size be stored as in a manner of normal storage JPG, PNG or
If tiff format, for the 8602.svs picture in figure 4 above, original image size is 343M, that is, allows to be converted to normal lattice
If formula, but its size can become very big (size becomes 1.83G after being such as converted to PNG format), due to information content it is very big (as
There are many prime number), cause to waste time very much configuring very high computer and opening file, it is even stuck.
In consideration of it, in one embodiment that the method for the removal background of pathological image of the present invention provides, the tool of this method
Body step includes following eight step:
S1 obtains the original image of a pathological image, because SVS image generally has 3 or more ranks,
The image under low range after selecting its 4 times of scaling (wide and high 4 times of scaling) when selection processing image.
S2 is handled the pathological image after the scaling by medical treatment library Openslide, this image procossing bottom storehouse layer
Write for C, can easily handle very much big file, picture without worry memory overflow the problem of, it is only necessary to picture into
The simple bicubic interpolation of row can obtain the low range image under four times of scalings, and obtain the low range figure after 4 times of scaling
Picture.
S3, because background is complex compared to tissue regions, and the color organized generally is easily determined (between purple
Between color and pink colour), therefore simple binaryzation extraction, reference are carried out to tissue with the color difference of RGB channel and colour gamut here
Fig. 5, tissue regions are white, remaining region is black, but it should be recognized that the tissue regions of the result extracted are
Openworks shape.
S4, referring to Fig. 5, periphery still has certain noise in figure, and the inside organized is Openworks shape, passes through form
It learns the image after binaryzation is extracted in closed operation and carries out one complete fragment of tissue of internal filling formation.
Wherein, the step of binaryzation is extracted is divided into three steps:
Low range image is transformed into HSV space by S401, under this space, coloury region (such as tissue regions),
Its saturation value is higher, and the region (such as background area) of color scarcity, and saturation degree numerical value is lower, because in operation
Extract the channel information of saturation degree;
S402 carries out mean filter to the low range image, and convolution kernel size is 100*100, tentatively removes small make an uproar
Point;
It should be noted that the operating procedure of the mean filter are as follows:
S4021 enables Sxy indicate center at picture point (x, y), and size is the rectangle subgraph window of m*n pixel;
S4022, the mean filter that counts calculate the average value of contaminated image g (x, y) in the region that Sxy is defined;
S4023, the restored image at point (x, y)Value, using Sxy define ground region in the calculated calculation of pixel
Number average value, that is,
Wherein, (s, t) is the subset of (x, y).
S403 uses Otsu threshold binaryzation to the low range image, obtains the result of Fig. 5.
Wherein, it should be noted that the formula of the channel information for extracting saturation degree are as follows:
Wherein, max indicates the maximum value in all pixels of present image, and min indicates the minimum value in pixel.
Wherein, the step of Otsu threshold binaryzation:
S4031 calculates the normalization histogram of input low range image, uses pi, i=0,1,2 ..., L-1 indicates institute
State each component of histogram;
S4032 is usedFor ki, i=0,1,2 ..., L-1 calculate accumulation and P1(k);
S4033, formula is usedFor ki, i=0,1,2 ..., L-1 are calculated cumulative mean value m (k);
S4034, formula is usedCalculate global gray average mG;
S4035, formula is usedFor ki, i=0,1,2 ..., L-1 calculate inter-class variance
S4036, obtain so thatMaximum k value, that is, Otsu threshold k*If maximum value is not unique, with corresponding detection
The average value of each maximum value k arrived is k*;
S4037, in k=k*Place calculatesObtain separable measures η*, that is, divide threshold value, wherein be divided into
For the gray variance of all pixels in local variance namely image;
S4038, binaryzation division is carried out to low range image according to the division threshold value that S4037 is obtained, obtains final knot
Fruit.
The fragment of tissue is opened operation removal noise spot by morphology referring to Fig. 6 by S5.
S6, by aforesaid operations, small noise spot can disappear, but for some biggish noises, can not reject, because
This chooses area in the fragment of tissue and is greater than each tissue minimum image according to the minimum pixel area of the barrier tissue of accumulation
The tissue part of vegetarian noodles product, and obtain on low range image per a piece of tissue contours.That is, the white area in left figure, has
White area can be very small, so we select the smallest white area area.
S7 finds the tissue contours position on original image (due to low point by the tissue contours in the low range figure
The picture of resolution zooms in and out in proportion, only needs equal proportion back to original image here), and obtain described group of driving wheel
Wide position;
S8 carries out image procossing to the original image by libvips, and obtains the image after removal background.It is described
Libvips to the original image carry out image procossing the step of include:
S801 reads in original image by libvips, and switchs to its processing format;
S802 carries out x [0,1]=[0, F] image [B, F] in processing S801 by formula;
S803 carries out image [0, F]+[240,0]=[240, F] in processing S802 by formula;
Wherein, the B indicates background, with organized region in F expression prospect.
For example, referring to Fig. 7 and Fig. 8, first, it needs to read in original image with libvips, switchs to its processing format.The
Two, original image is generated into two mask1, mask2s identical with original image size, the tissue contours in mask1 are filled
It is 1, remaining background is filled with 0, and the tissue contours in mask2 are filled with 0, remaining background is filled with more to be connect with original background
Close numerical value 240.Original image is multiplied by third referring to Fig. 7 according in S802 with mask1, other than tissue regions,
Remaining background pixel value all becomes 0.The result in S802 is added according in S803 with mask2 referring to Fig. 8, is organized
Region is constant, remaining Pekinese's value becomes 240, will then obtain the picture after background.
It should be noted that indicating tissue regions using ROI in figure.
S9, by the OpenSeadragon in the library JavaScript by the picture presentation after removing background, the displaying will
N times of actual picture size reduction, and n is more than or equal to 4.
Reference Fig. 9, the image after removing background, is stored and is shown by the way of number.Referring to Fig.1 0, it needs to make
Image is stored as deep zoom format, that is, the corresponding image of different resolution with libvips.
After image is stored with such format, and corresponding file is configured, it can checked in page end
The picture of oneself is taken over, if Figure 11 and Figure 12, Figure 11 are the 8602.svs picture after removing background.Noise in Figure 11 and Figure 12
It has been completely disappeared that, corresponding replacement has also been made in background colour, and the original resolution ratio of picture has also reached best preservation.
Preferably, the picture without message part in picture under each layer of resolution ratio can be deleted, that is, background portion
The picture divided is all deleted, and can achieve saving memory space in this way, and will not have an impact to the displaying of picture.
Referring to Fig. 4 and 13, the picture size after removing background is stored in a manner of deep zoom, and size becomes
67.2M, and the size of original image is 343M in Fig. 4.
It should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although referring to preferable
Embodiment describes the invention in detail, those skilled in the art should understand that, it can be to technology of the invention
Scheme is modified or replaced equivalently, and without departing from the spirit and scope of the technical solution of the present invention, should all be covered in this hair
In bright scope of the claims.
Claims (8)
1. a kind of method of the removal background of pathological image, it is characterised in that: including,
S1 obtains the original image of a pathological image, and original image is scaled 4 times;
S2 handles the pathological image after the scaling by medical treatment library Openslide, and obtains low after 4 times of scaling
Multiplying power image;
S3 carries out binaryzation extraction to the tissue in the low range image;
S4, the image progress inside filling formation one after being extracted binaryzation by morphology closed operation are completely organized broken
Piece;
The fragment of tissue is opened operation removal noise spot by morphology by S5;
S6 chooses the tissue part that area in the fragment of tissue is greater than each tissue minimum pixel area, and in low range figure
It obtains as upper per a piece of tissue contours;
S7 finds the tissue contours position on original image by the tissue contours in the low range figure, and obtains described group
Knit outline position;
S8 carries out image procossing to the original image by libvips, and obtains the image after removal background.
2. the method for the removal background of pathological image according to claim 1, it is characterised in that: what the binaryzation was extracted
Step is divided into three steps:
Low range image is transformed into HSV space, and extracts the channel information of saturation degree by S401;
S402 carries out mean filter to the low range image, and convolution kernel size is 100*100, removes small noise;
S403 uses Otsu threshold binaryzation to the low range image.
3. the method for the removal background of pathological image according to claim 1 or 2, it is characterised in that: the extraction saturation
The formula of the channel information of degree are as follows:
Wherein, max indicates the maximum value in all pixels of present image, and min indicates the minimum value in pixel.
4. the method for the removal background of pathological image according to claim 3, it is characterised in that: the behaviour of the mean filter
Make step are as follows:
S4021 enables Sxy indicate center at picture point (x, y), and size is the rectangle subgraph window of m*n pixel;
S4022, the mean filter that counts calculate the average value of contaminated image g (x, y) in the region that Sxy is defined;
S4023, the restored image at point (x, y)Value, using Sxy define ground region in pixel it is calculated count it is flat
Mean value, that is,
Wherein, (s, t) is the subset of (x, y).
5. the method for the removal background of pathological image according to claim 2 or 4, it is characterised in that: the Otsu threshold
The step of binaryzation:
S4031 calculates the normalization histogram of input low range image, uses pi, i=0,1,2 ..., L-1 indicates the histogram
Each component of figure;
S4032 is usedFor ki, i=0,1,2 ..., L-1 calculate accumulation and P1(k);
S4033, formula is usedFor ki, i=0,1,2 ..., L-1 are calculated cumulative mean value m (k);
S4034, formula is usedCalculate global gray average mG;
S4035, formula is usedFor ki, i=0,1,2 ..., L-1 calculate inter-class variance
S4036, obtain so thatMaximum k value, that is, Otsu threshold k*It is each with what is accordingly detected if maximum value is not unique
The average value of a maximum value k is k*;
S4037, in k=k*Place calculatesObtain separable measures η*, that is, divide threshold value, wherein institute in image
There is the gray variance of pixel;
S4038, binaryzation division is carried out to low range image according to the division threshold value that S4037 is obtained, obtains final result.
6. the method for the removal background of pathological image according to claim 1, it is characterised in that: the libvips is to institute
Stating the step of original image carries out image procossing includes:
S801 reads in original image by libvips, and switchs to its processing format;
S802 carries out x [0,1]=[0, F] image [B, F] in processing S801 by formula;
S803 carries out image [0, F]+[240,0]=[240, F] in processing S802 by formula;
Wherein, the B indicates background, with organized region in F expression prospect.
7. the according to claim 1, method of the removal background of any pathological image in 2,4 or 6, it is characterised in that: pass through
OpenSeadragon in the library JavaScript is by the picture presentation after removing background.
8. the method for the removal background of pathological image according to claim 7, it is characterised in that: described to show practical figure
N times of piece size reduction, and n is more than or equal to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910624429.0A CN110335284A (en) | 2019-07-11 | 2019-07-11 | A kind of method of the removal background of pathological image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910624429.0A CN110335284A (en) | 2019-07-11 | 2019-07-11 | A kind of method of the removal background of pathological image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110335284A true CN110335284A (en) | 2019-10-15 |
Family
ID=68146357
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910624429.0A Pending CN110335284A (en) | 2019-07-11 | 2019-07-11 | A kind of method of the removal background of pathological image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110335284A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112927230A (en) * | 2021-04-26 | 2021-06-08 | 常州市第一人民医院 | Image processing and analyzing system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1919144A (en) * | 2005-08-26 | 2007-02-28 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic image enhancement and spot inhibition method |
CN107256558A (en) * | 2017-05-18 | 2017-10-17 | 深思考人工智能机器人科技(北京)有限公司 | The cervical cell image automatic segmentation method and system of a kind of unsupervised formula |
US20180089849A1 (en) * | 2016-09-29 | 2018-03-29 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and non-transitory storage medium |
CN108564567A (en) * | 2018-03-15 | 2018-09-21 | 中山大学 | A kind of ultrahigh resolution pathological image cancerous region method for visualizing |
US20190005649A1 (en) * | 2017-06-29 | 2019-01-03 | HealthMyne, Inc. | Systems and methods for volumetric segmentation of structures in planar medical images |
US20190073752A1 (en) * | 2016-05-12 | 2019-03-07 | Shenzhen Institutes Of Advanced Technology Chinese Academy Of Sciences | Method and device for removing scanning bed from ct image |
US20190206544A1 (en) * | 2012-07-03 | 2019-07-04 | Sony Corporation | Input apparatus and information processing system |
CN109991215A (en) * | 2019-03-08 | 2019-07-09 | 深圳市象形字科技股份有限公司 | A kind of abnormal case method for early warning for urine detection instrument |
-
2019
- 2019-07-11 CN CN201910624429.0A patent/CN110335284A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1919144A (en) * | 2005-08-26 | 2007-02-28 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic image enhancement and spot inhibition method |
US20190206544A1 (en) * | 2012-07-03 | 2019-07-04 | Sony Corporation | Input apparatus and information processing system |
US20190073752A1 (en) * | 2016-05-12 | 2019-03-07 | Shenzhen Institutes Of Advanced Technology Chinese Academy Of Sciences | Method and device for removing scanning bed from ct image |
US20180089849A1 (en) * | 2016-09-29 | 2018-03-29 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and non-transitory storage medium |
CN107256558A (en) * | 2017-05-18 | 2017-10-17 | 深思考人工智能机器人科技(北京)有限公司 | The cervical cell image automatic segmentation method and system of a kind of unsupervised formula |
US20190005649A1 (en) * | 2017-06-29 | 2019-01-03 | HealthMyne, Inc. | Systems and methods for volumetric segmentation of structures in planar medical images |
CN108564567A (en) * | 2018-03-15 | 2018-09-21 | 中山大学 | A kind of ultrahigh resolution pathological image cancerous region method for visualizing |
CN109991215A (en) * | 2019-03-08 | 2019-07-09 | 深圳市象形字科技股份有限公司 | A kind of abnormal case method for early warning for urine detection instrument |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112927230A (en) * | 2021-04-26 | 2021-06-08 | 常州市第一人民医院 | Image processing and analyzing system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109919915B (en) | Retina fundus image abnormal region detection method and device based on deep learning | |
US8582881B2 (en) | Method and apparatus for modifying an image by using a saliency map based on color frequency | |
JP4363728B2 (en) | Digital image downsampling method and system | |
CN105488758A (en) | Image scaling method based on content awareness | |
Bloomberg | Multiresolution morphological approach to document image analysis | |
EP2431942B1 (en) | Defining a border for an image | |
CN110211058A (en) | A kind of data enhancement methods of medical image | |
WO2011091079A1 (en) | Selective diffusion of filtered edges in images | |
Fabrizio et al. | Text segmentation in natural scenes using toggle-mapping | |
WO2015161794A1 (en) | Method for acquiring thumbnail based on image saliency detection | |
CN105096330A (en) | Image processing method capable of automatically recognizing pure-color borders, system and a photographing terminal | |
WO2020232910A1 (en) | Target counting method and apparatus based on image processing, device, and storage medium | |
CN110047054A (en) | A kind of GAN medical image denoising method for extracting feature based on VGG-19 | |
CN109754423A (en) | A kind of extracting method and equipment of leaf spot lesion overlay area | |
CN110335284A (en) | A kind of method of the removal background of pathological image | |
Telea | Feature preserving smoothing of shapes using saliency skeletons | |
CN115965603A (en) | Image processing method, device, terminal and readable storage medium for endoscope image | |
CN114418987B (en) | Retina blood vessel segmentation method and system with multi-stage feature fusion | |
CN105046222A (en) | FPGA-based human face detection and tracking method | |
US20060257023A1 (en) | Method and system for image border color selection | |
CN113628129A (en) | Method for removing shadow of single image by edge attention based on semi-supervised learning | |
Choukikar et al. | Segmenting the optic disc in retinal images using thresholding | |
CN108520524A (en) | A kind of Image Iterative over-segmentation method based on edge cluster | |
Shaked et al. | Robust recursive envelope operators for fast Retinex | |
US8538163B2 (en) | Method and system for detecting edges within an image |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210524 Address after: No.275, Lane 700, Sichuan North Road, Hongkou District, Shanghai 200080 Applicant after: Shen Yi Address before: Room 120, 1st floor, Lane 16299, Puwei Road, Shanyang Town, Jinshan District, Shanghai Applicant before: Shanghai Changdao Medical Technology Co.,Ltd. |
|
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191015 |