CN108664937A - A kind of multizone scan method based on digital pathological section scanner - Google Patents
A kind of multizone scan method based on digital pathological section scanner Download PDFInfo
- Publication number
- CN108664937A CN108664937A CN201810458193.3A CN201810458193A CN108664937A CN 108664937 A CN108664937 A CN 108664937A CN 201810458193 A CN201810458193 A CN 201810458193A CN 108664937 A CN108664937 A CN 108664937A
- Authority
- CN
- China
- Prior art keywords
- pathological section
- digital pathological
- identification model
- scanning
- scanning area
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10008—Still image; Photographic image from scanner, fax or copier
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Abstract
The invention discloses the multizone scan methods based on digital pathological section scanner, according to pre-prepd training data, training forms an identification model in advance, the identification model on digital pathological section image for identifying that the scanning area for obtaining needing to scan, this method specifically include following steps：Scanning camera shoots pathological section and obtains corresponding digital pathological section image；The digital pathological section image is identified using the identification model, to identify the scanning area；The scanning area is scanned using pathological section scanner, it finally obtains pathological section scanning file and is automatically stored, compared with prior art, the beneficial effects of the invention are as follows, the multiple regions that digital pathological section image can be selected simultaneously are scanned, and are compressed, integrated to the scanning file of output, are improved work efficiency, output map sheet is reduced, the practicability of digital pathological section scanner is enhanced.
Description
Technical field
The present invention relates to image scan method more particularly to a kind of multizone scannings based on digital pathological section scanner
Method.
Background technology
Existing digital pathological section scanner first shoots the panoramic picture of one group of pathological section in scanned samples tissue,
Then technical staff needs according to inspection through the selected sample areas for needing depth scan of platform software, and digital pathological section is swept
Instrument is retouched then to focus to selection area and scan to obtain final scanning file.
Under normal conditions, as shown in Figure 1, sample to be detected on pathological section is a tissue, a region is concentrated on
It is interior, so digital pathological section scanners most of on the market only support single sector scanning at present, that is to say, that technical staff is only
The a certain single region that panoramic picture can be selected carries out depth scan.And in practical operation, it will appear on pathological section
The tissue of form dispersion, as shown in Fig. 2, if also according to common scan method, digital pathological section scanner can will divide
Scattered multiple tissues are scanned into the same region as a whole, as shown in Figure 3, it can be seen that, the same area is arrived in scanning
Multiple tissues between can leave many white spaces, and the scanning of these blank is meaningless for the detection of tissue samples, no
But sweep time is increased, and will increase output map sheet, wastes the memory space of computer.
Invention content
The multizone scan method based on digital pathological section scanner that the object of the present invention is to provide a kind of, with solution
The certainly above technical problem.
The present invention, which solves its technical problem, to be achieved through the following technical solutions.
The present invention provides a kind of multizone scan method based on digital pathological section scanner, according to pre-prepd instruction
Practice data training in advance and form an identification model, the identification model is needed for being identified on digital pathological section image
The scanning area of scanning, this method specifically include following steps：
Step 1：Scanning camera shoots pathological section and obtains corresponding digital pathological section image；
Step 2：The digital pathological section image is identified using the identification model, to identify the scanning
Region；
Step 3：The scanning area is scanned using pathological section scanner, finally obtains pathological section scanning text
Part is simultaneously automatically stored.
Further, the training data includes multiple pre-set described digital pathological section images, described in every
At least one scanning area is provided on digital pathological section image.
The identification model includes obtaining in the digital pathological section image including histiocytic group for identification
First identification model of tissue region, and for merging to form the scanning area according to the obtained tissue regions of identification
Second identification model；
The process that training forms the identification model specifically includes：
The digital pathological section image in the training data is input to first identification model by step A1
In；
Step A2, first identification model identifies in the digital pathological section image obtains all tissue regions simultaneously
Carry out, output by label the digital pathological section image, the tissue regions be include histiocytic region；
Step A3, to not identified by the identification model in the digital pathological section image by the way of manually marking
The tissue regions gone out are labeled, and by the digital pathological section image update after mark to the training data
In, it is then returned to the step A1, until in the digital pathological section image by label exported in the step A2
There is no it is unrecognized go out the tissue regions until；
Step A4 identifies to obtain the scanning area using second identification model according to all tissue regions,
Until second identification model training finishes；
Step A5, preservation include the identification model of first identification model and second identification model, then
It exits.
Further, the scanning area includes all tissue regions, and the white space in the scanning area
Area it is minimum；In in the scanning area, non-overlapping copies between each tissue regions.
Further, the method that first identification model marks the digital pathological section image is to define each
The specific coordinate position of the tissue regions is simultaneously numbered and stores to tissue regions described in each.
Further, one is provided in the digital pathological section scanner for the digital pathological section image
The operating platform being scanned, the operating platform may be displayed on display equipment on, user by input equipment such as keyboard,
Mouse etc. can carry out relevant operation on the operational platform.
Further, by the operating platform, user can simultaneously self-defined multiple scanning areas to the number disease
Reason sectioning image is scanned.The operating platform supports user to carry out single region for the digital pathological section image of input
The selected scanning simultaneously of selected or multizone.
Further, the scanned output of the scanning area obtains scanning file, i.e. a scanning area is scanned
A scanning file is obtained, multiple scanning files that the operating platform can obtain output are integrated, most end form
At a digital pathological section image scanning file and preserve.
The invention has the advantages that the present invention is by training identification model and uses advanced recognizer, to number
The function and performance of pathological section scanner have made further improvement and promotion, and technical staff can be very easily flat in operation
Platform realization, which selectes the multizone of biopsy tissues and is directed to each individual region, carries out depth scan, and the operating platform can also
Enough each scanning files obtained to scanning carry out integrating one digital pathological section image scanning file of final output, this is more
Sector scanning method can only not only save sweep time, improve work efficiency compared with single sector scanning in the past, Er Qieyou
Effect reduces output map sheet, avoids occupying excessive memory space.
Description of the drawings
Fig. 1 is pathological section list sector scanning figure in the prior art；
Fig. 2 is the pathological section schematic diagram there are multiple dispersion tissues；
Fig. 3 is in the prior art to there are the schematic diagrames that the pathological section of multiple dispersion tissues carries out single sector scanning；
Fig. 4 is the multizone identification scanning schematic diagram one of the embodiment of the present invention；
Fig. 5 is the multizone identification scanning schematic diagram two of the embodiment of the present invention；
Fig. 6 is the method flow diagram of the embodiment of the present invention；
Fig. 7 is the method flow diagram of the training identification model of the embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art obtained under the premise of not making creative work it is all its
His embodiment, shall fall within the protection scope of the present invention.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
The invention will be further described in the following with reference to the drawings and specific embodiments, but not as limiting to the invention.
Fig. 6 and Fig. 7 are please referred to, the present invention provides a kind of multizone scan method based on digital pathological section scanner,
This method forms an identification model according to the training in advance of pre-prepd training data, and the identification model is used in digital pathology
Identification obtains the scanning area for needing to scan on sectioning image, and this method specifically includes following steps：
Step 1：Scanning camera shoots pathological section 11 and obtains corresponding digital pathological section image；
Step 2：The digital pathological section image is identified using the identification model, to identify the scanning
Region 12；
Step 3：The scanning area 12 is scanned using pathological section scanner, finally obtains pathological section scanning
File is simultaneously automatically stored.
The multizone scan method based on digital pathological section scanner of the present invention, the training data includes that multiple are pre-
The digital pathological section image being first arranged is provided at least one scanning on every digital pathological section image
Region 12.
The multizone scan method based on digital pathological section scanner of the present invention, the identification model includes for knowing
Do not obtain include in the digital pathological section image histiocytic tissue regions 13 the first identification model, and be used for
The tissue regions 13 obtained according to identification merge the second identification model for forming the scanning area 12；
The process that training forms the identification model specifically includes：
The digital pathological section image in the training data is input to first identification model by step A1
In；
Step A2, first identification model identifies in the digital pathological section image obtains all tissue regions 13
And carry out, output by label the digital pathological section image, the tissue regions 13 be include histiocytic area
Domain；
Step A3, to not identified by the identification model in the digital pathological section image by the way of manually marking
The tissue regions 13 gone out are labeled, and by the digital pathological section image update after mark to the training data
In, it is then returned to the step A1, until in the digital pathological section image by label exported in the step A2
There is no it is unrecognized go out the tissue regions 13 until；
Step A4 obtains the scanning area using second identification model according to the identification of all tissue regions 13
Domain 12, until second identification model training finishes；
Step A5, preservation include the identification model of first identification model and second identification model, then
It exits.
The multizone scan method based on digital pathological section scanner of the present invention, please refers to Fig. 4 and Fig. 5, described to sweep
It includes all tissue regions 13 to retouch region 12, and the area of the white space in the scanning area 12 is minimum；In described
In scanning area 12, non-overlapping copies between each tissue regions 13.
The multizone scan method based on digital pathological section scanner of the present invention, first identification model mark institute
The method for stating digital pathological section image is to define the specific coordinate position of each tissue regions 13 and to each institute
Tissue regions 13 are stated to be numbered and store.
The multizone scan method based on digital pathological section scanner of the present invention, second identification model is according to institute
It is to preset each to state the method that the fusion of the tissue regions 13 that the first identification model identifies forms the scanning area 12
The scan area of a scanning area 12, and each described tissue regions 13 to numbering and storing carry out permutation and combination most
End form is at least one scanning area 12.
The multizone scan method based on digital pathological section scanner of the present invention, each preset described scanning area
The scan area in domain 12 can it is identical can not also be identical, as noted previously, as each described scanning area 12 is by least one
A 13 permutation and combination of the tissue regions and formed, but due to the size of tissue regions 13 described in each and differ,
So the tissue regions 13 of identical quantity combine the size of each scanning area 12 formed often and differ,
In order to which unified standard obtains the scanning file of identical map sheet in order to facilitate output simultaneously, each described scanning area can be preset
12 scan areas having the same.But the quantity of the tissue regions 13 due to including in scanning area 12 described in each is logical
It often and differs, and the area of each tissue regions 13 is also and different, if by each scanning area
12 force to be preset as identical scan area, will appear more white space in the scanning area 12, such as five identical
The tissue regions 13 of size, 13 permutation and combination of tissue regions described in two of which form a scanning area 12, separately
13 permutation and combination of outer three tissue regions forms another scanning area 12, if by scanning area described in above-mentioned two
Domain 12 is preset as identical scan area, then computer can be to the scanning area that is formed by two tissue regions 13
Other regions in 12 in addition to two tissue regions 13 are gone to plug a gap, and the scanning area 13 formed in this way will appear more
Blank, however, it is skimble-skamble to be scanned to these white spaces, and can waste a large amount of sweep time, so
In the embodiment of the present invention, the scan area of each scanning area 12 can be preset as differing, or can also lead to
Cross the tissue of the recognizer in the prior art to the scan area of scanning area described in each 12 according to permutation and combination
The quantity or size in region 12 carry out automatic identification calculating, to ensure the white space in each described scanning area 12
For minimum area.
The multizone scan method based on digital pathological section scanner of the present invention is scanned in the digital pathological section
An operating platform for being scanned to the digital pathological section image is provided in instrument, the operating platform can be shown
On the display device, user can carry out relevant operation on the operational platform by input equipment such as keyboard, mouse etc..Cross institute
State operating platform, user self-defined multiple scanning areas and can be scanned the digital pathological section image simultaneously.It should
Operating platform supports user to be carried out for the digital pathological section image of input, and single region is selected or multizone is selected simultaneously
After be scanned.The scanned output of scanning area obtains scanning file, i.e., a scanning area is scanned obtains one
A scanning file, multiple scanning files that the operating platform can obtain output are integrated, and ultimately form one
Digital pathological section image scanning file simultaneously preserves.
It is further to note that identification model described in the step 2 identifies the specific identification of the scanning area 12
Method is, using the Segmentation of Multi-target method based on three-valued image clustering, the multiple target based on three-valued image clustering
Dividing method includes the following steps：
One, the gradient of the panoramic picture A is calculated
(1) size that coloured image B, the coloured image B are obtained after being reduced to the panoramic picture A is w × h, and w is figure
Pixel number on image width degree, h are the pixel number in picture altitude；
(2) direction gradient on the RGB triple channel images of the coloured image B obtained in step (1) is calculated；
(3) coloured image B two is calculated according to the direction gradient on the RGB triple channel images of coloured image B in step (2)
Direction gradient in axial direction；
(4) the direction gradient intensity image M of coloured image B is described according to the direction gradient in step (3) in two axial directions；
(5) saturation degree for calculating coloured image B in step (1), obtains saturation degree image Z；
Two, in conjunction with the information of the saturation degree image Z in the direction gradient image M and step (5) in above-mentioned steps (4) to coloured silk
Color image B carries out threshold process, coloured image B individual elements is mapped as " foreground, profile, background " three values, by following
Formula obtains three-valued image C；
Wherein：100 indicate " profile ", and 255 indicate " foreground ", and 0 indicates " background "；MthresholdFor Grads threshold, gradient threshold
Value sums up the end value come for many experiments, and it is profile point to represent the pixel more than or equal to the threshold value, is less than the threshold value generation
The table pixel is not profile point；SthresholdFor saturation degree threshold value, saturation degree threshold value is equally that many experiments sum up the result come
Value indicates that pixel may be the target point with bright-colored more than the threshold value.
Three, the three-valued image C is carried out being based on morphologic cluster, obtains cluster result image E；
Four, target area reparation and Target Segmentation are carried out to the cluster result image E.
In addition, identification model described in the step 2 identifies that the recognizer of the scanning area 12 further includes based on straight
The Segmentation of Multi-target method of the image overall binaryzation of square figure, the recognizer realized using mode in the prior art, herein
It repeats no more.
The present invention is by training identification model and uses advanced recognizer, to the function of digital pathological section scanner
Further improvement and promotion are made with performance, technical staff can very easily realize in operating platform to the more of biopsy tissues
Region, which is selected and is directed to each individual region, carries out depth scan.In addition, the operating platform can also to scanning obtain it is every
One scanning file carry out integrate one digital pathological section image scanning file of final output, the multizone scan method with
Toward can only single sector scanning compare, not only save sweep time, improve work efficiency, and effectively reduce output figure
Width avoids occupying excessive memory space.
The foregoing is merely preferred embodiments of the present invention, are not intended to limit embodiments of the present invention and protection model
It encloses, to those skilled in the art, should can appreciate that all with made by description of the invention and diagramatic content
Equivalent replacement and obviously change obtained scheme, should all be included within the scope of the present invention.
Claims (8)
1. a kind of multizone scan method based on digital pathological section scanner, which is characterized in that according to pre-prepd instruction
Practice data training in advance and form an identification model, the identification model is needed for being identified on digital pathological section image
The scanning area of scanning, includes the following steps：
Step 1：Scanning camera shoots pathological section and obtains corresponding digital pathological section image；
Step 2：The digital pathological section image is identified using the identification model, to identify the scanning area
Domain；
Step 3：The scanning area is scanned using pathological section scanner, finally obtains pathological section scanning file simultaneously
It is automatically stored.
2. a kind of multizone scan method based on digital pathological section scanner as described in claim 1, which is characterized in that
The training data includes multiple pre-set described digital pathological section images, on every digital pathological section image
It is provided at least one scanning area；
The identification model includes obtaining in the digital pathological section image including histiocytic tissue area for identification
First identification model in domain, and for merging to form the second of the scanning area according to the obtained tissue regions of identification
Identification model；
The process that training forms the identification model specifically includes：
The digital pathological section image in the training data is input in first identification model by step A1；
Step A2, first identification model identify that obtaining all tissue regions goes forward side by side in the digital pathological section image
Row, output by label the digital pathological section image, the tissue regions be include histiocytic region；
Step A3, to not identified by the identification model in the digital pathological section image by the way of manually marking
The tissue regions are labeled, and by the digital pathological section image update to the training data after mark, with
After return to the step A1, until the step A2 in export by label the digital pathological section image in be not present
It is unrecognized go out the tissue regions until；
Step A4 identifies to obtain the scanning area using second identification model according to all tissue regions, until
The second identification model training finishes；
Step A5, preservation includes the identification model of first identification model and second identification model, with backed off after random.
3. a kind of multizone scan method based on digital pathological section scanner as claimed in claim 2, which is characterized in that
The scanning area includes all tissue regions, and the area of the white space in the scanning area is minimum；In described
In scanning area, non-overlapping copies between each tissue regions.
4. a kind of multizone scan method based on digital pathological section scanner as claimed in claim 3, which is characterized in that
The method that first identification model marks the digital pathological section image is define each tissue regions specific
Coordinate position is simultaneously numbered and stores to tissue regions described in each.
5. a kind of multizone scan method based on digital pathological section scanner as claimed in claim 4, which is characterized in that
Second identification model merges to form the scanning area according to the tissue regions that first identification model identifies
The method in domain is to preset the scan area of each scanning area, and each described tissue area to numbering and storing
Domain carries out permutation and combination and ultimately forms at least one scanning area.
6. a kind of multizone scan method based on digital pathological section scanner as claimed in claim 5, which is characterized in that
The scan area of each preset scanning area is identical.
7. a kind of multizone scan method based on digital pathological section scanner as claimed in claim 5, which is characterized in that
The scan area of each preset scanning area differs.
8. a kind of multizone scan method based on digital pathological section scanner as claimed in claims 6 or 7, feature exist
In being provided with one in the digital pathological section scanner for the operation that is scanned to the digital pathological section image
Platform；
By the operating platform, user self-defined multiple scanning areas can carry out the digital pathological section image simultaneously
Scanning；
The scanned output of scanning area obtains scanning file, multiple scanning texts that the operating platform obtains output
Part integrate and ultimately forms a digital pathological section image scanning file and preserve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810458193.3A CN108664937A (en) | 2018-05-14 | 2018-05-14 | A kind of multizone scan method based on digital pathological section scanner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810458193.3A CN108664937A (en) | 2018-05-14 | 2018-05-14 | A kind of multizone scan method based on digital pathological section scanner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108664937A true CN108664937A (en) | 2018-10-16 |
Family
ID=63778371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810458193.3A Pending CN108664937A (en) | 2018-05-14 | 2018-05-14 | A kind of multizone scan method based on digital pathological section scanner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108664937A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109975291A (en) * | 2019-03-08 | 2019-07-05 | 广州金域医学检验中心有限公司 | Generation method, device and the computer equipment of digital pathological section |
| CN110265142A (en) * | 2019-06-11 | 2019-09-20 | 透彻影像(北京)科技有限公司 | A kind of assistant diagnosis system and method for lesion region restored map |
| CN110909646A (en) * | 2019-11-15 | 2020-03-24 | 广州金域医学检验中心有限公司 | Digital pathological section image acquisition method and device, computer equipment and storage medium |
| CN112464802A (en) * | 2020-11-26 | 2021-03-09 | 湖南国科智瞳科技有限公司 | Automatic identification method and device for slide sample information and computer equipment |
| CN112508010A (en) * | 2020-11-30 | 2021-03-16 | 广州金域医学检验中心有限公司 | Method, system, device and medium for identifying digital pathological section target area |
| WO2022068883A1 (en) * | 2020-09-29 | 2022-04-07 | 先临三维科技股份有限公司 | Scanning result processing method and apparatus, and processor and scanning system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090109496A1 (en) * | 2007-10-29 | 2009-04-30 | Hiroyuki Baba | Image reading device and image forming device |
| CN103040429A (en) * | 2013-01-05 | 2013-04-17 | 无锡微奥科技有限公司 | Optical image detection device for oral cavity and imaging method |
| CN103473785A (en) * | 2013-09-29 | 2013-12-25 | 哈尔滨工业大学 | Rapid multiple target segmentation method based on three-valued image clustering |
| CN105374023A (en) * | 2015-08-25 | 2016-03-02 | 上海联影医疗科技有限公司 | Target area segmentation method, image reconstruction method and image reconstruction device |
| CN105550651A (en) * | 2015-12-14 | 2016-05-04 | 中国科学院深圳先进技术研究院 | Method and system for automatically analyzing panoramic image of digital pathological section |
| CN106485287A (en) * | 2016-10-25 | 2017-03-08 | 帝麦克斯(苏州)医疗科技有限公司 | The acquisition methods of scanning area, the acquisition methods of digital slices and device |
| CN106570505A (en) * | 2016-11-01 | 2017-04-19 | 北京昆仑医云科技有限公司 | Method for analyzing histopathologic image and system thereof |
| CN107209934A (en) * | 2014-12-03 | 2017-09-26 | 文塔纳医疗系统公司 | Mthods, systems and devices for quantitative analysis heterogeneous biological marker profile |
| CN107493403A (en) * | 2017-08-11 | 2017-12-19 | 宁波江丰生物信息技术有限公司 | A kind of digital pathological section scanning system |
-
2018
- 2018-05-14 CN CN201810458193.3A patent/CN108664937A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090109496A1 (en) * | 2007-10-29 | 2009-04-30 | Hiroyuki Baba | Image reading device and image forming device |
| CN103040429A (en) * | 2013-01-05 | 2013-04-17 | 无锡微奥科技有限公司 | Optical image detection device for oral cavity and imaging method |
| CN103473785A (en) * | 2013-09-29 | 2013-12-25 | 哈尔滨工业大学 | Rapid multiple target segmentation method based on three-valued image clustering |
| CN107209934A (en) * | 2014-12-03 | 2017-09-26 | 文塔纳医疗系统公司 | Mthods, systems and devices for quantitative analysis heterogeneous biological marker profile |
| CN105374023A (en) * | 2015-08-25 | 2016-03-02 | 上海联影医疗科技有限公司 | Target area segmentation method, image reconstruction method and image reconstruction device |
| CN105550651A (en) * | 2015-12-14 | 2016-05-04 | 中国科学院深圳先进技术研究院 | Method and system for automatically analyzing panoramic image of digital pathological section |
| CN106485287A (en) * | 2016-10-25 | 2017-03-08 | 帝麦克斯(苏州)医疗科技有限公司 | The acquisition methods of scanning area, the acquisition methods of digital slices and device |
| CN106570505A (en) * | 2016-11-01 | 2017-04-19 | 北京昆仑医云科技有限公司 | Method for analyzing histopathologic image and system thereof |
| CN107493403A (en) * | 2017-08-11 | 2017-12-19 | 宁波江丰生物信息技术有限公司 | A kind of digital pathological section scanning system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109975291A (en) * | 2019-03-08 | 2019-07-05 | 广州金域医学检验中心有限公司 | Generation method, device and the computer equipment of digital pathological section |
| CN110265142A (en) * | 2019-06-11 | 2019-09-20 | 透彻影像(北京)科技有限公司 | A kind of assistant diagnosis system and method for lesion region restored map |
| CN110265142B (en) * | 2019-06-11 | 2020-06-09 | 透彻影像(北京)科技有限公司 | Auxiliary diagnosis system for restoration image of lesion area |
| CN110909646A (en) * | 2019-11-15 | 2020-03-24 | 广州金域医学检验中心有限公司 | Digital pathological section image acquisition method and device, computer equipment and storage medium |
| CN110909646B (en) * | 2019-11-15 | 2023-10-20 | 广州金域医学检验中心有限公司 | Acquisition method and device of digital pathological section image, computer equipment and storage medium |
| WO2022068883A1 (en) * | 2020-09-29 | 2022-04-07 | 先临三维科技股份有限公司 | Scanning result processing method and apparatus, and processor and scanning system |
| CN112464802A (en) * | 2020-11-26 | 2021-03-09 | 湖南国科智瞳科技有限公司 | Automatic identification method and device for slide sample information and computer equipment |
| CN112464802B (en) * | 2020-11-26 | 2023-07-25 | 湖南国科智瞳科技有限公司 | Automatic identification method and device for slide sample information and computer equipment |
| CN112508010A (en) * | 2020-11-30 | 2021-03-16 | 广州金域医学检验中心有限公司 | Method, system, device and medium for identifying digital pathological section target area |
| WO2022110396A1 (en) * | 2020-11-30 | 2022-06-02 | 广州金域医学检验中心有限公司 | Method, system and device for identifying target area of digital pathology slide, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108664937A (en) | A kind of multizone scan method based on digital pathological section scanner | |
| JP4646797B2 (en) | Image processing apparatus, control method therefor, and program | |
| JP5274495B2 (en) | How to change the document image size | |
| CN102081496A (en) | Information processing apparatus, method, and computer-readable medium | |
| JP2007049388A (en) | Image processing apparatus and control method thereof, and program | |
| US9384519B1 (en) | Finding similar images based on extracting keys from images | |
| CN102473278B (en) | Image processing apparatus, image processing method, and storage medium | |
| US9064314B2 (en) | Robust automatic determination and location of MacBeth color checker charts | |
| CN113033558B (en) | Text detection method and device for natural scene and storage medium | |
| JP2006208339A (en) | Region-extracting device, microscope system and region-extracting program | |
| CN115812221A (en) | Image generation and coloring method and device | |
| CN108830874A (en) | A kind of number pathology full slice Image blank region automatic division method | |
| CN108965646B (en) | Image processing apparatus, image processing method, and program | |
| CN109543525B (en) | Table extraction method for general table image | |
| KR20230117752A (en) | Detection of annotated regions of interest in images | |
| CN108388898A (en) | Character identifying method based on connector and template | |
| CN109359652A (en) | A method of the fast automatic extraction rectangular scanning part from digital photograph | |
| WO2009104325A1 (en) | Line drawing processing device, program, and line drawing processing method | |
| WO2019181072A1 (en) | Image processing method, computer program, and recording medium | |
| JP6546385B2 (en) | IMAGE PROCESSING APPARATUS, CONTROL METHOD THEREOF, AND PROGRAM | |
| JP4208520B2 (en) | Image processing apparatus, image processing method, program, and storage medium | |
| JP4872610B2 (en) | Camera pointer device, labeling method and program | |
| CN109145618A (en) | A method of papery black and white printing sensitive data is hidden based on greyscale transformation | |
| US8295602B2 (en) | Image processing apparatus and image processing method | |
| US8649576B2 (en) | Arborization reconstruction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181016 |