CN109961448A - Sketch the contours method and system in lesion tissue region - Google Patents
Sketch the contours method and system in lesion tissue region Download PDFInfo
- Publication number
- CN109961448A CN109961448A CN201910286313.0A CN201910286313A CN109961448A CN 109961448 A CN109961448 A CN 109961448A CN 201910286313 A CN201910286313 A CN 201910286313A CN 109961448 A CN109961448 A CN 109961448A
- Authority
- CN
- China
- Prior art keywords
- tissue
- image
- contours
- organization chart
- chart picture
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
Abstract
The present invention relates to medical domains, sketch the contours method and system in particular to lesion tissue region.Sketch the contours method in lesion tissue region, comprising the following steps: obtain organization chart picture；Image recognition, while converting organization chart picture to the image of tissue actual size；Cutting sampling generates cutting sampling drawing；To tissue production slice；Scanning obtains sectioning image；Pathological image is checked, and lesion region is marked on cutting sampling drawing, generates labeled data；Labeled data carries out coordinate conversion, is mapped in the organization chart picture, and figure is sketched the contours in formation.The present invention realizes that lesion region automation is sketched the contours, and replaces conventional method to determine method by manual measurement and realizes that lesion region is sketched the contours, not only saves human cost, improve efficiency, and improve the precision that region is sketched the contours.
Description
Technical field
The present invention relates to medical domains, sketch the contours method and system in particular to lesion tissue region.
Background technique
The tissue specimen to get off is cut off in endoscopic excision operation, lesion region is carried out and substantially sketches the contours, be the hair of pathological analysis
Exhibition trend, Japanese medical institutions have been carried out this technology tradition for many years, and implementation step is as follows:
1. pair tissue specimen carries out the production of subregion wax stone；
2. pair wax stone carries out microsection manufacture, be made as 1~N block slice, every piece of slice comprising 1~N number of fine strip shape tissue；
3. observing under mirror slice, lesion tissue area length of field is measured using graduated scale, and records lesion region and rises
Begin, end position；
4. carrying out lesion tissue region according to the position of excision using mapping software by hand and sketching the contours；
It since the 3rd, 4 step of this technology needs manually measure under the microscope, and manually records on drawing paper, not only exists
Time-consuming, process is cumbersome for implementation, and measurement error is big, is difficult to popularize so as to cause the business.Only Beijing University, China at present
Only a fews hospital this business such as hospital.
In view of this, the present invention is specifically proposed.
Summary of the invention
The first object of the present invention is to provide a kind of lesion tissue region and sketches the contours method, fixed by computer automatic analysis
Position method realizes that lesion region is sketched the contours, and replaces in conventional method and determines method by manual measurement, not only saves human cost, improves effect
Rate, and improve the precision that region is sketched the contours.
The second object of the present invention is that providing lesion tissue region sketches the contours system, provides technology branch for above-mentioned method
It holds.
In order to realize above-mentioned purpose of the invention, the following technical scheme is adopted:
Sketch the contours method in lesion tissue region, comprising the following steps:
Obtain organization chart picture；
Image recognition is carried out to the organization chart picture, while converting the organization chart picture in the figure of tissue actual size
Picture；
Cutting sampling is carried out on the image of the tissue actual size, generates cutting sampling drawing；
According to cutting sampling drawing to tissue production slice；
The slice scanning obtains sectioning image；
Obtain the pathological image as a result, and lesion region is marked on cutting sampling drawing, generate
Labeled data；
The cutting sampling drawing subscript note data carry out coordinate conversion, are mapped in the organization chart picture, formation is sketched the contours
Figure.
The present invention first obtains organization chart picture, then by the identification and conversion to organization chart picture, obtains tissue actual size
Image, carry out cutting sampling on this basis, generate cutting sampling drawing, accordingly to tissue production wax stone and slice, according to
The observation of the slice of specific position is labeled on corresponding position on cutting sampling drawing, generates labeled data, be mapped to
In organization chart picture, figure is sketched the contours in formation.
Present invention combination imaging system, image processing system, image analysis labeling system and digital pathological section scanning system
System, realization automatically generate wax stone production drawing, automatic measurement lesion region length, and automatically record lesion region starting, terminate
Position, it is automatic to carry out sketching the contours for lesion tissue region, human cost is not only saved, is improved efficiency, and improves what region was sketched the contours
Precision.The difficulty that method realization lesion region is sketched the contours is determined by manual measurement relative to conventional method, this business can be effectively reduced
Carry out difficulty, save and implement the time, measurement accuracy is improved, to push the development of this business.
Further, with the label for marking the tissue actual size in the organization chart picture.
Preferably, the tissue has known scale and does not block the masking-out of information of interest in the tissue, shoots institute
It states tissue and masking-out obtains the organization chart picture.
Preferably, the masking-out is surface plate with a scale.
That is, tissue is put into surface plate with a scale and obtains the organization chart picture.
Further, the scale plate is dot scale plate, the central area for organizing to be put into the dot scale plate.
Further, the scale identification uses Hough circle detection algorithm.
In the present invention, scale identification can also be using other means, such as DeepLab-v3 algorithm.
Further, it is converted by the actual size of surface plate with a scale to the tissue, by the organization chart
Image as being converted into tissue actual size.
DeepLab-v3 algorithm identifies that differentiation degree is high, and identification content is comprehensively reliable, and recognition effect is stablized.
Further, described image identification is identified using DeepLab-v3 algorithm.
Efficiency and accuracy are had both, generally, the size of wax stone is no more than 5cm*4cm, and sampling bar number is no more than 6.
The present invention also provides a kind of computer storage medium, it is stored thereon with the executable generation for realizing above-mentioned method
Code.
The present invention also provides a kind of image processing equipments, comprising:
Memory: it is stored with the executable code for realizing above-mentioned method；
Processor: connecting with the memory, executes the executable code being stored on the memory.
The present invention also provides lesion tissue regions to sketch the contours system, comprising:
Imaging system: organization chart picture is obtained；
Image processing system: being converted into the image of tissue actual size to the organization chart picture, in the practical ruler of tissue
Cutting sampling is carried out on very little image, generates cutting sampling drawing；
Scanning system: histotomy is scanned and obtains sectioning image；
Labeling system: lesion tissue region is carried out on cutting sampling drawing according to the pathological examination of the sectioning image
Label generates labeled data, and is mapped in the organization chart picture of the imaging system, sketches the contours of lesion tissue region.
Further, the imaging system is made of surface plate and photographic equipment with a scale.
Further, described image processing system is mainly made of picture recognition module and cutting module；
Described image recognition template identifies scale and tissue regions in the organization chart picture, and is scaled the practical ruler of tissue
Very little image；
The cutting module cuts the image of tissue actual size according to maximum Cutting Length, the sampling bar number of setting,
Generate cutting sampling drawing.
Further, the scanning system is by digital pathology scanning to the high-resolution slice map of slice scanning acquisition
Picture.
Compared with prior art, the invention has the benefit that
(1) present invention combines digital pathological section scanner, image analysis marking software, image mosaic integration technology to be formed
System realization automatically generates wax stone production drawing, automatic measurement lesion region length, and automatically records lesion region starting, terminates
Sketching the contours automatically for lesion tissue region is realized in position.
(2) human cost is not only saved, is improved efficiency, and improves the precision that region is sketched the contours.
(3) difficult problem being drawn using artificial for the prior art, the present invention can be effectively reduced this business and carry out difficulty,
It saves and implements the time, measurement accuracy is improved, to push the development of this business.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described.
Fig. 1 is the flow diagram that method is sketched the contours in the lesion tissue region that the embodiment of the present invention 1 provides；
Fig. 2 is the operation schematic diagram for the image processing system that the embodiment of the present invention 1 provides；
Fig. 3 is the schematic diagram for the imaging system that the embodiment of the present invention 2 provides；
Fig. 4 is that the high photographing instrument camera imaging that the embodiment of the present invention 2 provides obtains organization chart picture figure；
Fig. 5 is tissue regions identification and scale recognition effect figure in the image processing system that the embodiment of the present invention 2 provides；
Fig. 6 is the generation wax stone cutting sampling drawing that the embodiment of the present invention 2 provides；
Fig. 7 is the pathological image that the embodiment of the present invention 2 provides；
Fig. 8 is that the histopathology that the embodiment of the present invention 2 provides sketches the contours figure.
Specific embodiment
In a first aspect, the present invention provides lesion tissue regions to sketch the contours method, comprising the following steps:
Obtain organization chart picture；
Image recognition is carried out to the organization chart picture, while converting the organization chart picture in the figure of tissue actual size
Picture；
Cutting sampling is carried out on the image of the tissue actual size, generates cutting sampling drawing；
According to cutting sampling drawing to tissue production slice；
The slice scanning obtains sectioning image；
The pathological examination of the sectioning image is obtained, and lesion region is marked on cutting sampling drawing,
Generate labeled data；
The cutting sampling drawing subscript note data carry out coordinate conversion, are mapped in the organization chart picture, formation is sketched the contours
Figure.
It obtains in organization chart picture step, for the ease of the subsequent image for converting organization chart picture to tissue actual size,
When obtaining organization chart picture, object of reference is placed around tissue, such as surface plate with a scale.Therefore, in some embodiments, group
It knits to be put into surface plate with a scale and obtains the organization chart picture.
Further, with the label for marking the tissue actual size in the organization chart picture.
Preferably, the tissue has known scale and does not block the masking-out of information of interest in the tissue, shoots institute
It states tissue and masking-out obtains the organization chart picture.
Preferably, the masking-out is surface plate with a scale.
In some embodiments, the scale plate is dot scale plate, and the tissue is put into the dot scale plate
Heart district domain.
Such as, it obtains organization chart picture to complete using imaging system, imaging system such as high photographing instrument, shooting effect is stablized.
Dot scale plate is placed horizontally on high photographing instrument platform when use, it is each while each with the platform of high photographing instrument as far as possible
In parallel.Then tissue is put into as far as possible to the center of dot scale plate, finally obtain organization chart picture by high photographing instrument camera imaging.
It such as, is dot scale plate, the identification of scale uses Hough circle detection algorithm.
In some embodiments, described image identification is identified using DeepLab-v3 algorithm.
In some embodiments, it is converted by the actual size of surface plate with a scale to the tissue, it will be described
Organization chart picture is converted into the image of tissue actual size.
After image recognition, according to the scale plate of image peripheral, pixel is converted into image, according to pixel conversion, by tissue
Image is converted into the image of tissue actual size.
Cutting sampling is carried out on the image of obtained tissue actual size, cutting sampling drawing is generated, according to this to tissue
Make wax stone and slice.
In the present invention, each tissue according to circumstances makes multiple wax stones.
In the present invention, multiple sampling bar numbers are according to circumstances arranged in each wax stone, taking into account based on efficiency and accuracy, such as wax
The size of block is no more than 5cm*4cm, and sampling bar number is no more than 6.
Each wax stone is sampled according to the sampling cutting line in cutting sampling drawing, be put into slide and is sent into scanning system
System is scanned, and generates pathological image, and pathologist is labeled lesion tissue region in labeling system, and labeling system will
Mark coordinate maps to the coordinate after original structure image.Repeat mark is sketched the contours until all lesion regions all draw generation
Figure.
Second aspect is stored thereon with the present invention also provides a kind of computer storage medium and realizes above-mentioned method
Executable code.
The third aspect, the present invention provides a kind of image processing equipments, comprising:
Memory: it is stored with the executable code for realizing above-mentioned method；
Processor: connecting with the memory, executes the executable code being stored on the memory.
Fourth aspect, the present invention provides lesion tissue regions to sketch the contours system, comprising:
Imaging system: organization chart picture is obtained；
Image processing system: being converted into the image of tissue actual size to the organization chart picture, in the practical ruler of tissue
Cutting sampling is carried out on very little image, generates cutting sampling drawing；
Scanning system: histotomy is scanned and obtains sectioning image；
Labeling system: lesion tissue region is carried out on cutting sampling drawing according to the pathological examination of the sectioning image
Label generates labeled data, and is mapped in the organization chart picture of the imaging system, sketches the contours of lesion tissue region.
In the present invention, imaging system uses existing imaging device, such as high photographing instrument and other equipment for having camera
Deng.
In some embodiments, the imaging system is made of surface plate and photographic equipment with a scale.
In use, surface plate with a scale is placed horizontally on high photographing instrument platform, each side as far as possible with the platform of high photographing instrument
Each side is parallel；Then tissue is put into as far as possible to the central area of surface plate plate, finally pass through high photographing instrument camera imaging acquisition group
Knit image.
Image processing system is mainly made of picture recognition module and cutting module.
Wherein, image recognition template identifies scale and tissue regions in the organization chart picture, and is scaled tissue reality
The image of size.
Since the color of scale can be manually set before surface plate production, can be obtained by color segmentation when identifying scale,
The reality of each pixel is calculated after identification scale according to the length in pixels in the picture of scale in image and scale physical length
Border length.Tissue regions identification can extract the region of tissue in the picture by background subtraction or semantic segmentation scheduling algorithm, and count
The size for calculating the region minimum circumscribed rectangle calculates the actual size of tissue in conjunction with the physical length of each pixel.
Cutting module cuts the image of tissue actual size according to maximum Cutting Length, the sampling bar number of setting, generates
Cutting sampling drawing.
Wherein, in cutting sampling drawing, cutting line and dimension information are labeled with.
In the present invention, scanning system passes through digital pathology scanning and obtains high-resolution sectioning image to slice scanning.
After final pathologist is labeled lesion tissue region in labeling system, labeling system is reflected coordinate is marked
Coordinate after being incident upon original image, until all lesion regions, which all draw generation, sketches the contours figure.
Embodiment of the present invention is described in detail below in conjunction with embodiment, but those skilled in the art will
Understand, the following example is merely to illustrate the present invention, and is not construed as limiting the scope of the invention.It is not specified in embodiment specific
Condition person carries out according to conventional conditions or manufacturer's recommended conditions.Reagents or instruments used without specified manufacturer is
The conventional products that can be obtained by commercially available purchase.
Embodiment 1
System is substantially sketched the contours in lesion tissue region, mainly by tissue imaging systems, image processing system, scanning system and mark
The big system of injection system 4 composition.
As shown in Figure 1, tissue first to be generated to the organization chart picture of tissue by imaging system.
Specifically, imaging system is made of surface plate and camera with a scale, and wherein surface plate is horizontal positioned, camera suspension
Surface plate plate the top, and camera lens face level board.Camera is carried out before use, first scaling board level is put among surface plate
Calibration obtains camera parameter.In use, tissue is put into the centre of surface plate, by camera to tissue and surface plate scale at
Picture obtains organization chart picture.
Then image processing system samples drawing according to the cutting that organization chart picture generates tissue.
As shown in Fig. 2, image processing system is mainly made of picture recognition module and cutting module.
Image recognition template mainly identifies scale and tissue regions in image.Since the color of scale makes in surface plate
Before can be manually set, can be obtained, be identified after scale according to scale in image in the picture by color segmentation when identifying scale
Length in pixels and scale physical length calculate the physical length of each pixel.Tissue regions identification can by background subtraction or
Semantic segmentation scheduling algorithm extracts the region of tissue in the picture, and calculates the size of the region minimum circumscribed rectangle, in conjunction with each
The physical length of a pixel calculates the actual size of tissue.
Cutting module is cut according to the maximum Cutting Length being manually arranged, the actual size of sampling bar number and tissue, generation
Tapping master drawing paper.
The production of region wax stone and microsection manufacture manually are carried out to tissue according to cutting sampling drawing.
Slice generates high-resolution digital pathological image by scanning system.
Digital pathological image is marked by labeling system on cutting sampling drawing manually, and labeled data is sat
Mark maps to organization chart picture generation and sketches the contours image.
Scanning system passes through digital pathology scanning and obtains high-resolution sectioning image to slice scanning.
Pathologist checks pathological image by labeling system, and lesion region is marked, and generates mark
Data.Labeling system carries out coordinate conversion to labeled data, is mapped to organization chart picture, and figure is sketched the contours in formation.
Embodiment 2
As shown in figure 3, the imaging system of the embodiment of the present invention is carved by the good farmland high photographing instrument (Fig. 3 a) and dot for having camera
It spends plate (Fig. 3 b), wherein lateral center of circle maximum spacing is Wreal-scale=20cm, longitudinal center of circle maximum spacing are Hreal-scale=
12cm。
Dot scale plate is placed horizontally on high photographing instrument platform when use, it is each while each with the platform of high photographing instrument as far as possible
In parallel, then tissue is put into as far as possible to the center of dot scale plate, finally obtain organization chart picture such as by high photographing instrument camera imaging
Fig. 4.
Tissue regions identification in the image processing system of the embodiment of the present invention identifies tissue using DeepLab-v3 algorithm
Region obtains the mask such as Fig. 5 (a), and seeks the Pixel Dimensions of mask minimum rectangle, the Pixel Dimensions organized in figure in this example:
Wide Wpixel-width=676, high Hpixel-height=487.The identification of this example orbicular spot scale obtains figure using Hough circle detection algorithm
Black circles shown in 5 (b), and finding out lateral center of circle maximum distance is Wpixel-scale=1122, longitudinal maximum distance is
Hpixel-scale=674.Then:
Horizontal each pel spacing is Wscale=Wreal-scale/Wpixel-scale
Wscale=0.01783cm.
Vertical each pel spacing is Hscale=Hreal-scale/Hpixel-scale
Hscale=0.01780cm.
The actual size then organized are as follows:
W=Wscale*Wpixel-scale
W=12.05cm.
H=Hscale*Hpixel-scale
H=8.67cm.
The full-size of wax stone is 5cm*4cm in this example, and maximum sampling bar number is 6, generates wax stone cutting sampling drawing
Such as Fig. 6.Manually according to drawing 6, tissue is cut and generates 9 wax stones, each wax stone is sampled according to sampling cutting line, is put
Enter slide and be sent into scanning system to be scanned, generates pathological image such as Fig. 7 (a).
After pathologist is labeled lesion tissue region in labeling system, labeling system is mapped to coordinate is marked
Coordinate such as Fig. 7 (b) after original image.Repeat mark sketches the contours figure (such as Fig. 8) until all lesion regions all draw generation.
Although illustrate and describing the present invention with specific embodiment, it will be appreciated that without departing substantially from of the invention
Many other change and modification can be made in the case where spirit and scope.It is, therefore, intended that in the following claims
Including belonging to all such changes and modifications in the scope of the invention.
Claims (10)
1. method is sketched the contours in lesion tissue region, which comprises the following steps:
Obtain organization chart picture；
Image recognition is carried out to the organization chart picture, while converting the organization chart picture to the image of tissue actual size；
Cutting sampling is carried out on the image of the tissue actual size, generates cutting sampling drawing；
According to cutting sampling drawing to tissue production slice；
The slice scanning obtains sectioning image；
The pathological examination of the sectioning image is obtained, and lesion region is marked on cutting sampling drawing, is generated
Labeled data；
The cutting sampling drawing subscript note data carry out coordinate conversion, are mapped in the organization chart picture, figure is sketched the contours in formation.
2. method is sketched the contours in lesion tissue region according to claim 1, which is characterized in that with use in the organization chart picture
In the label for marking the tissue actual size；
Preferably, the tissue has known scale and does not block the masking-out of information of interest in the tissue, shoots described group
It knits and masking-out obtains the organization chart picture；
Preferably, the masking-out is surface plate with a scale.
3. method is sketched the contours in lesion tissue region according to claim 2, which is characterized in that the scale plate is dot scale
Plate, the central area for organizing to be put into the dot scale plate.
4. method is sketched the contours in lesion tissue region according to claim 3, which is characterized in that the identification of the scale is using suddenly
Husband's circle detection algorithm；
Further, described image identification is identified using DeepLab-v3 algorithm.
5. sketching the contours method according to the described in any item lesion tissue regions claim 2-4, which is characterized in that by with a scale
Surface plate converts to the actual size of the tissue, converts the organization chart picture to the image of tissue actual size.
6. a kind of computer storage medium, which is characterized in that be stored thereon with and realize the described in any item methods of claim 1-5
Executable code.
7. a kind of image processing equipment characterized by comprising
Memory: it is stored with the executable code for realizing the described in any item methods of claim 1-5；
Processor: connecting with the memory, executes the executable code being stored on the memory.
8. system is sketched the contours in lesion tissue region characterized by comprising
Imaging system: organization chart picture is obtained；
Image processing system: being converted into the image of tissue actual size to the organization chart picture, in the tissue actual size
Cutting sampling is carried out on image, generates cutting sampling drawing；
Scanning system: histotomy is scanned and obtains sectioning image；
Labeling system: lesion tissue region is marked on cutting sampling drawing according to the pathological examination of the sectioning image
Note generates labeled data, and is mapped in the organization chart picture of the imaging system, sketches the contours of lesion tissue region.
9. system is sketched the contours in lesion tissue region according to claim 8, which is characterized in that the imaging system is by with a scale
Surface plate and photographic equipment composition.
10. system is sketched the contours in lesion tissue region according to claim 9, which is characterized in that described image processing system master
It to be made of picture recognition module and cutting module；
Described image recognition template identifies scale and tissue regions in the organization chart picture, and is scaled tissue actual size
Image；
The cutting module cuts the image of tissue actual size according to maximum Cutting Length, the sampling bar number of setting, generates
Cutting sampling drawing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910286313.0A CN109961448A (en) | 2019-04-10 | 2019-04-10 | Sketch the contours method and system in lesion tissue region |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910286313.0A CN109961448A (en) | 2019-04-10 | 2019-04-10 | Sketch the contours method and system in lesion tissue region |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109961448A true CN109961448A (en) | 2019-07-02 |
Family
ID=67025939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910286313.0A Pending CN109961448A (en) | 2019-04-10 | 2019-04-10 | Sketch the contours method and system in lesion tissue region |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961448A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110432924A (en) * | 2019-08-06 | 2019-11-12 | 杭州智团信息技术有限公司 | Borborygmus sound detection device, method and electronic equipment |
| CN110477851A (en) * | 2019-07-15 | 2019-11-22 | 广东工业大学 | A kind of method of accurate measurement pupil and iris absolute diameter |
| CN111179264A (en) * | 2020-01-10 | 2020-05-19 | 中国人民解放军总医院 | Method and device for producing restored image of specimen, specimen processing system, and electronic device |
| CN111260648A (en) * | 2020-05-06 | 2020-06-09 | 杭州迪英加科技有限公司 | Method and device for measuring lesion area of gastric mucosa ESD excision specimen image |
| CN111281443A (en) * | 2020-03-12 | 2020-06-16 | 西安瑞丰仪器设备有限责任公司 | ESD sample automatic processing equipment and method |
| CN111358573A (en) * | 2020-02-26 | 2020-07-03 | 西安交通大学医学院第二附属医院 | Hyperspectral imaging surgical area rapid detection and marking device and detection method |
| CN111795879A (en) * | 2020-07-14 | 2020-10-20 | 青岛大学附属医院 | Application of pathological specimen manufactured by dehydration set in digital evaluation system |
| US11436724B2 (en) | 2020-10-30 | 2022-09-06 | International Business Machines Corporation | Lesion detection artificial intelligence pipeline computing system |
| WO2022184154A1 (en) * | 2021-03-05 | 2022-09-09 | 深圳英美达医疗技术有限公司 | Method and system for recognizing extension length of miniature endoscopic ultrasonography probe, and storage medium |
| US11587236B2 (en) | 2020-10-30 | 2023-02-21 | International Business Machines Corporation | Refining lesion contours with combined active contour and inpainting |
| US11688517B2 (en) | 2020-10-30 | 2023-06-27 | Guerbet | Multiple operating point false positive removal for lesion identification |
| US11688063B2 (en) | 2020-10-30 | 2023-06-27 | Guerbet | Ensemble machine learning model architecture for lesion detection |
| US11694329B2 (en) | 2020-10-30 | 2023-07-04 | International Business Machines Corporation | Logistic model to determine 3D z-wise lesion connectivity |
| US11749401B2 (en) | 2020-10-30 | 2023-09-05 | Guerbet | Seed relabeling for seed-based segmentation of a medical image |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251402A (en) * | 2008-04-08 | 2008-08-27 | 中冶京诚工程技术有限公司 | System and method for processing gas-holder location data |
| US20100278311A1 (en) * | 2008-10-28 | 2010-11-04 | Kevin Hammerstrom | Device and method for scaling medical images |
| KR101400829B1 (en) * | 2013-05-24 | 2014-05-30 | 서울대학교병원 (분사무소) | Apparatus and method for histopathological mapping examination |
| US20150088293A1 (en) * | 2011-06-06 | 2015-03-26 | Biomet Manufacturing, Llc | Pre-Operative Planning And Manufacturing Method For Orthopedic Procedure |
| CN104502245A (en) * | 2015-01-08 | 2015-04-08 | 青岛理工大学 | Method for determining fineness modulus of sand by utilizing image analysis technology |
| CN105813579A (en) * | 2013-08-08 | 2016-07-27 | 全球生物疗法有限公司 | Clamp device for minimally invasive procedures and uses thereof |
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| CN106153635A (en) * | 2016-09-27 | 2016-11-23 | 山东省科学院新材料研究所 | The quantitative detecting method of defect in a kind of magnesium and magnesium alloy |
| CN106535734A (en) * | 2014-09-25 | 2017-03-22 | 奥林巴斯株式会社 | Endoscope system |
| CN106875393A (en) * | 2017-03-28 | 2017-06-20 | 四川大学 | A kind of DNA of tumor cell detection method of content based on graphical analysis |
| 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 |
| CN108508016A (en) * | 2018-04-09 | 2018-09-07 | 扬州大学附属医院 | A kind of prostate cancer three-dimensional pathology configuration method |
| CN108629777A (en) * | 2018-04-19 | 2018-10-09 | 麦克奥迪（厦门）医疗诊断系统有限公司 | A kind of number pathology full slice image lesion region automatic division method |
| CN109389610A (en) * | 2018-11-21 | 2019-02-26 | 上海衡道医学病理诊断中心有限公司 | A kind of skin lesion area computation method based on artificial intelligence identification |
-
2019
- 2019-04-10 CN CN201910286313.0A patent/CN109961448A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251402A (en) * | 2008-04-08 | 2008-08-27 | 中冶京诚工程技术有限公司 | System and method for processing gas-holder location data |
| US20100278311A1 (en) * | 2008-10-28 | 2010-11-04 | Kevin Hammerstrom | Device and method for scaling medical images |
| US20150088293A1 (en) * | 2011-06-06 | 2015-03-26 | Biomet Manufacturing, Llc | Pre-Operative Planning And Manufacturing Method For Orthopedic Procedure |
| KR101400829B1 (en) * | 2013-05-24 | 2014-05-30 | 서울대학교병원 (분사무소) | Apparatus and method for histopathological mapping examination |
| CN105813579A (en) * | 2013-08-08 | 2016-07-27 | 全球生物疗法有限公司 | Clamp device for minimally invasive procedures and uses thereof |
| CN106535734A (en) * | 2014-09-25 | 2017-03-22 | 奥林巴斯株式会社 | Endoscope system |
| 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 |
| CN104502245A (en) * | 2015-01-08 | 2015-04-08 | 青岛理工大学 | Method for determining fineness modulus of sand by utilizing image analysis technology |
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| CN106153635A (en) * | 2016-09-27 | 2016-11-23 | 山东省科学院新材料研究所 | The quantitative detecting method of defect in a kind of magnesium and magnesium alloy |
| CN106875393A (en) * | 2017-03-28 | 2017-06-20 | 四川大学 | A kind of DNA of tumor cell detection method of content based on graphical analysis |
| CN108508016A (en) * | 2018-04-09 | 2018-09-07 | 扬州大学附属医院 | A kind of prostate cancer three-dimensional pathology configuration method |
| CN108629777A (en) * | 2018-04-19 | 2018-10-09 | 麦克奥迪（厦门）医疗诊断系统有限公司 | A kind of number pathology full slice image lesion region automatic division method |
| CN109389610A (en) * | 2018-11-21 | 2019-02-26 | 上海衡道医学病理诊断中心有限公司 | A kind of skin lesion area computation method based on artificial intelligence identification |
Non-Patent Citations (1)
| Title |
|---|
| 柏树令 等: "《中国医学百科全书 人体解剖学》", 31 October 2015 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110477851A (en) * | 2019-07-15 | 2019-11-22 | 广东工业大学 | A kind of method of accurate measurement pupil and iris absolute diameter |
| CN110432924B (en) * | 2019-08-06 | 2021-10-22 | 杭州智团信息技术有限公司 | Bowel sound detection device and method and electronic equipment |
| CN110432924A (en) * | 2019-08-06 | 2019-11-12 | 杭州智团信息技术有限公司 | Borborygmus sound detection device, method and electronic equipment |
| CN111179264A (en) * | 2020-01-10 | 2020-05-19 | 中国人民解放军总医院 | Method and device for producing restored image of specimen, specimen processing system, and electronic device |
| CN111179264B (en) * | 2020-01-10 | 2023-10-03 | 中国人民解放军总医院 | Method and device for manufacturing restoration graph of specimen, specimen processing system and electronic equipment |
| CN111358573A (en) * | 2020-02-26 | 2020-07-03 | 西安交通大学医学院第二附属医院 | Hyperspectral imaging surgical area rapid detection and marking device and detection method |
| CN111358573B (en) * | 2020-02-26 | 2023-06-20 | 西安交通大学医学院第二附属医院 | Device and method for rapidly detecting and marking hyperspectral imaging operation area |
| CN111281443A (en) * | 2020-03-12 | 2020-06-16 | 西安瑞丰仪器设备有限责任公司 | ESD sample automatic processing equipment and method |
| CN111281443B (en) * | 2020-03-12 | 2022-07-05 | 西安瑞丰仪器设备有限责任公司 | ESD sample automatic processing equipment and method |
| CN111260648A (en) * | 2020-05-06 | 2020-06-09 | 杭州迪英加科技有限公司 | Method and device for measuring lesion area of gastric mucosa ESD excision specimen image |
| CN111795879A (en) * | 2020-07-14 | 2020-10-20 | 青岛大学附属医院 | Application of pathological specimen manufactured by dehydration set in digital evaluation system |
| US11436724B2 (en) | 2020-10-30 | 2022-09-06 | International Business Machines Corporation | Lesion detection artificial intelligence pipeline computing system |
| US11587236B2 (en) | 2020-10-30 | 2023-02-21 | International Business Machines Corporation | Refining lesion contours with combined active contour and inpainting |
| US11688065B2 (en) | 2020-10-30 | 2023-06-27 | Guerbet | Lesion detection artificial intelligence pipeline computing system |
| US11688517B2 (en) | 2020-10-30 | 2023-06-27 | Guerbet | Multiple operating point false positive removal for lesion identification |
| US11688063B2 (en) | 2020-10-30 | 2023-06-27 | Guerbet | Ensemble machine learning model architecture for lesion detection |
| US11694329B2 (en) | 2020-10-30 | 2023-07-04 | International Business Machines Corporation | Logistic model to determine 3D z-wise lesion connectivity |
| US11749401B2 (en) | 2020-10-30 | 2023-09-05 | Guerbet | Seed relabeling for seed-based segmentation of a medical image |
| WO2022184154A1 (en) * | 2021-03-05 | 2022-09-09 | 深圳英美达医疗技术有限公司 | Method and system for recognizing extension length of miniature endoscopic ultrasonography probe, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961448A (en) | Sketch the contours method and system in lesion tissue region | |
| US9014443B2 (en) | Image diagnostic method, image diagnostic apparatus, and image diagnostic program | |
| CN111275016B (en) | Slide scanning image acquisition and analysis method and device | |
| CN111062955A (en) | Lung CT image data segmentation method and system | |
| CN108830149B (en) | Target bacterium detection method and terminal equipment | |
| CN110974306B (en) | System for discernment and location pancreas neuroendocrine tumour under ultrasonic endoscope | |
| KR102580984B1 (en) | Image processing method, program and recording medium | |
| CN113689374B (en) | Method and system for determining surface roughness of plant leaf | |
| CN101947103B (en) | Optical bioluminescence tomography method | |
| CN110265142A (en) | A kind of assistant diagnosis system and method for lesion region restored map | |
| CN109461183A (en) | A kind of method of space coordinate point and point cloud location point Three Dimensional Contrast | |
| CN109410139A (en) | Inside a kind of historical relic and surface disease digital assay appraisal procedure | |
| Failmezger et al. | Semi-automated 3D leaf reconstruction and analysis of trichome patterning from light microscopic images | |
| CN115546605A (en) | Training method and device based on image labeling and segmentation model | |
| RU2716746C2 (en) | Information transformation in digital pathology | |
| JP4985480B2 (en) | Method for classifying cancer cells, apparatus for classifying cancer cells, and program for classifying cancer cells | |
| CN112464802B (en) | Automatic identification method and device for slide sample information and computer equipment | |
| CN113989343A (en) | Attention mechanism-based sensor fusion depth reconstruction data driving method | |
| CN112509122A (en) | Method and device for detecting concentration and activity of high-concentration microparticles based on multi-height lensless digital holography | |
| CN115082529B (en) | System and method for collecting and analyzing multi-dimensional information of gross tissue | |
| CN112330660B (en) | Sperm tail detection method and system based on neural network | |
| CN102999904A (en) | Plane-based micro-nano object image tilt correction method | |
| CN115880295B (en) | Computer-aided tumor ablation navigation system with accurate positioning function | |
| MacLeod | Imaging and analysis of skeletal morphology: New tools and techniques | |
| CN117455898B (en) | Deep learning-based organism internal structure generation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190702 |
|
| RJ01 | Rejection of invention patent application after publication |