CN113344859B - Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging - Google Patents

Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging Download PDF

Info

Publication number
CN113344859B
CN113344859B CN202110534698.5A CN202110534698A CN113344859B CN 113344859 B CN113344859 B CN 113344859B CN 202110534698 A CN202110534698 A CN 202110534698A CN 113344859 B CN113344859 B CN 113344859B
Authority
CN
China
Prior art keywords
microvascular
inertia
area
image
surrounding
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.)
Active
Application number
CN202110534698.5A
Other languages
Chinese (zh)
Other versions
CN113344859A (en
Inventor
于红刚
董泽华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University WHU
Original Assignee
Wuhan University WHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University WHU filed Critical Wuhan University WHU
Priority to CN202110534698.5A priority Critical patent/CN113344859B/en
Publication of CN113344859A publication Critical patent/CN113344859A/en
Application granted granted Critical
Publication of CN113344859B publication Critical patent/CN113344859B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • 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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30092—Stomach; Gastric
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30096—Tumor; Lesion

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Theoretical Computer Science (AREA)
  • Public Health (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Epidemiology (AREA)
  • Pathology (AREA)
  • Geometry (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Primary Health Care (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Endoscopes (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a method for quantifying the circumferential extent of a capillary for gastric mucosa staining amplification imaging, which comprises an image segmentation method, a single capillary extraction method and a section moment of inertia method. The image segmentation method is used for extracting a clear region and a microvascular integral image in the gastroscope image; the single capillary extraction method is used for extracting each single capillary from the whole capillary image; the section moment of inertia method is used for calculating the section moment of inertia of the single micro-blood vessel relative to the diagonal line of the minimum circumscribed rectangle. Finally, the surrounding degree coefficient of the microvessels is obtained by weighting the section moments of inertia of the microvessels relative to two diagonals of the minimum circumscribed rectangle of the microvessels, and then the surrounding degree grade of the microvessels is judged according to the surrounding degree coefficient.

Description

Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging
Technical Field
The application relates to the technical field of image recognition methods in the medical field, in particular to a microvascular circularity quantification method for gastric mucosa staining amplification imaging.
Background
Gastric cancer is the fifth most common cancer in the world, which accounts for the third leading cause of cancer death. The advent of pigment endoscopy has established an endoscopic diagnostic method for early-stage cancer. The magnifying gastroscope and the electronic staining endoscope are combined for application, so that a tiny blood vessel structure and a tiny mucous membrane surface structure which cannot be observed by a common gastroscope can be observed, and conditions are provided for diagnosing early gastric cancer under the endoscope. The abnormal blood vessel is an important condition for diagnosing early gastric cancer under a dyeing amplification endoscope.
AkiraYokoyama classifies Microvascular Structures (MVs) into fine mesh, helical, lobular endocyclic-1, and lobular endocyclic-2 in Novel narrow-band imaging endofibrous framework for early vascular cancer. Is an empirical, generalized summary and is not described quantitatively.
Disclosure of Invention
The invention aims to provide a method for quantifying the microvascular looping degree of gastric mucosa staining amplification imaging, which aims at overcoming the defects of the prior art, is suitable for quantifying the gastric microvascular looping degree in a large scale, is convenient for judging the gastric microvascular form, has high matching degree with the diagnosis result of an endoscopist, has high reliability, and can provide powerful data support for the endoscopist to perform early gastric cancer diagnosis from the aspect of the microvascular looping degree.
In order to achieve the above object, the present invention provides a method for quantifying the circumferential extent of a capillary in gastric mucosal staining and amplification imaging, which is characterized in that: the method for quantifying the circumferential extent of the capillary comprises the following steps:
s1: inputting an original image to be quantified for gastric mucosa staining and amplifying imaging, and extracting a clear area image from the original image of the endoscope by adopting an image segmentation model;
s2: adopting an image segmentation model to segment a whole microvascular image from a clear region image;
s3: on the basis of the connected domain, filtering out noise points in the whole microvascular map through the area and the perimeter of the connected domain, calculating an external rectangle of the retained microvascular and removing other noise vessels within the range of the external rectangle;
s4: traversing each microvessel, and respectively calculating the section inertia moment of all pixel points on the microvessel to two diagonal lines of the minimum circumscribed rectangle;
s5: weighting the section moment of inertia obtained in step S4 to obtain a microvascular surrounding degree coefficient, and then giving a microvascular surrounding degree level determination result according to the threshold interval.
Further, in step S1, a trained U-Net + + segmentation model is used to extract a clear region from the gastroscope image obtained by the image segmentation method.
Further, in step S2, a trained D-LinkNet model is used to extract a whole microvascular image from the clear region image obtained in step S1.
Further, in step S3, on the basis of the connected domain, noise points in the entire microvascular map are filtered out by the area and perimeter of the connected domain, the minimum circumscribed horizontal rectangle of the retained microvasculature is calculated, and other noise vessels within the range of the circumscribed horizontal rectangle are removed. The method for eliminating other noise blood vessels in the minimum external horizontal rectangular range of the current capillary comprises the following steps:
s3.1: calculating the minimum external horizontal rectangle of the current microvascular and calculating the areas of all connected domains in the external rectangle;
s3.2: finding out the connected domain with the largest area except the background in the step S3.1 as the target micro-vessel and recording the connected domain of the micro-vessel;
s3.3: and traversing all pixel points in the minimum external horizontal rectangle obtained in the step S3.1, and judging whether each pixel point is in the connected domain of the target blood vessel in the step S3.2 by adopting an area sum judgment method. Assuming that the vertex coordinate of the microvascular connected domain is A1(x1,y1)，A2(x2,y2)…An(xn,yn) The coordinate of a certain pixel point in the minimum external horizontal rectangle of the microvascular is P (x)i,yi) If the pixel point is in the target micro-vessel connected domain, the triangular area formed by the pixel point and all adjacent vertexes of the connected domain is equal to the polygonal area, and the following equation is satisfied
Figure BDA0003069345930000021
The pixel values for pixel points inside the microvascular minimum bounding horizontal rectangle that do not satisfy this equation are set as background pixels.
Further, in step S4, traversing each of the microvessels processed in step S3, calculating a minimum bounding rectangle thereof, and calculating coordinates of four vertices thereof as PA(xA,yA)，PB(xB,yB)，PC(xC,yC)，PD(xD,yD) At any point in the microvasculature Oi(xi,yi) Then the cross-sectional moment of inertia with respect to the diagonal AC is calculated as
Figure BDA0003069345930000022
Wherein λ isACFor penalty factors, defined here
Figure BDA0003069345930000031
LACIs a point Pi(xi,yi) The distance to the diagonal line AC is such that,
Figure BDA0003069345930000032
area-is the minimum circumscribed rectangle area, and area is LAB·LAD。
Similarly, the section inertia moment I relative to the diagonal BD can be calculatedBD。
Further, in step S5, the moment of area inertia obtained in step S4 is weighted to obtain a microvascular encircling degree coefficient, and a microvascular encircling degree level determination result is given based on the threshold interval.
S5.1: calculating a microvascular ringing coefficient
ξ＝ρAC·IAC+ρBD·IBD
Wherein the content of the first and second substances,
Figure BDA0003069345930000033
s5.2: judging surrounding degree grade, judging the surrounding degree grade of the microvessels according to the obtained surrounding degree coefficient xi, and when the surrounding degree coefficient xi is less than or equal to 0.72, the surrounding degree of the microvessels is normal; when the surrounding degree coefficient is 0.72 < xi < 1.04, the microvasculature is in general surrounding; when the surrounding degree coefficient xi is more than 1.04, the micro blood vessels are severely surrounded, i.e. the surrounding degree coefficient xi is more than 1.04
Figure BDA0003069345930000034
The invention has the following advantages and beneficial effects:
the method uses a cross-sectional moment of inertia method to quantify the surrounding degree of the microvessels, provides semi-automatic and automatic image analysis by developing a universal and repeatable program, quantifies the surrounding degree of the microvessels, and can assist an endoscopist to improve the reliability and accuracy of analysis and diagnosis of the early gastric cancer. According to the gastric microvascular morphological structure, each microvascular of an image is searched on the basis of a connected domain, the moment of inertia of the section of each microvascular is calculated, and finally a microvascular surrounding degree judgment interval with high diagnostic matching degree with an endoscopic physician is given. The method can realize full automation in the whole calculation process, greatly improves the rapidity of the quantization process and ensures high reliability.
Drawings
FIG. 1 is a schematic diagram of the method for quantifying the degree of gastric microvascular looping according to the present invention.
FIG. 2 is a schematic diagram of the method for establishing the gastric microvascular looping degree quantification of the present invention.
FIG. 3 is a schematic diagram illustrating whether a determination point is inside a polygon according to the present invention.
FIG. 4 is a schematic diagram of the calculation of the section moment of inertia.
Fig. 5 is a schematic diagram of the calculation of the moment of inertia of the cross section of the microvascular of the present invention.
Fig. 6 shows the calculation result of the sectional moment of inertia of the microvascular according to the present invention.
Detailed Description
The invention will be described in further detail with reference to the following figures and specific examples, without limiting the scope of the invention.
Referring to fig. 1, an implementation diagram of a method for quantifying a microvascular looping distance of a gastric mucosal staining amplification image is provided in the present invention. As shown in figure 1, the method for quantifying the circumferential extent of the microvasculature for the gastric mucosa staining and amplifying imaging comprises a cross-sectional moment of inertia method.
Referring to fig. 2, an embodiment of a method for quantifying a degree of a microvascular looping around a gastric mucosa for a stained and magnified imaging according to the present invention is taken as an example to illustrate the establishment of a process of the method for quantifying a degree of a gastric microvascular looping around a gastric mucosa according to the present invention, which includes the following steps S1-S5:
and step S1, extracting a clear region from the gastroscope image obtained by the image segmentation method by adopting the trained U-Net + + segmentation model.
And step S2, extracting a microvascular whole image from the clear region image obtained in step S1 by adopting a trained D-LinkNet model.
And step S3, on the basis of the connected domain, filtering out noise points in the whole microvascular map through the area and the perimeter of the connected domain, calculating the minimum external horizontal rectangle of the retained microvascular, and removing other noise vessels in the range of the external horizontal rectangle. The method for eliminating other noise blood vessels in the minimum external horizontal rectangular range of the current capillary comprises the following steps:
s3.1: calculating the minimum external horizontal rectangle of the current microvascular and calculating the areas of all connected domains in the external rectangle;
s3.2: finding out the connected domain with the largest area except the background in the step S3.1 as the target micro-vessel and recording the connected domain of the micro-vessel;
s3.3: and traversing all pixel points in the minimum external horizontal rectangle obtained in the step S3.1, and judging whether each pixel point is in the connected domain of the target blood vessel in the step S3.2 by adopting an area sum judgment method. As shown in FIG. 3, let A be the vertex coordinate of the connected capillary domain1(x1,y1)，A2(x2,y2)…An(xn,yn) The coordinate of a certain pixel point in the minimum external horizontal rectangle of the microvascular is P (x)i,yi) If the pixel point is in the target micro-vessel connected domain, the triangular area formed by the pixel point and all adjacent vertexes of the connected domain is equal to the polygonal area, and the following equation is satisfied
Figure BDA0003069345930000051
The pixel values for pixel points inside the microvascular minimum bounding horizontal rectangle that do not satisfy this equation are set as background pixels.
Step S4 is to traverse each microvascular processed in step S3, calculate the minimum bounding rectangle thereof, and calculate the coordinates of four vertexes thereof as PA(xA,yA)，PB(xB,yB)，PC(xC,yC)，PD(xD,yD) At any point in the microvasculature Oi(xi,yi). As shown in FIG. 4, the cross-sectional moment of inertia with respect to the diagonal line AC is calculated as
Figure BDA0003069345930000052
Wherein λ isACAs penalty factor, λ, as shown in FIG. 5ACIs calculated by the formula
Figure BDA0003069345930000053
LACIs a point Pi(xi,yi) The distance to the diagonal line AC is such that,
Figure BDA0003069345930000054
area-is the minimum circumscribed rectangle area, and area is LAB·LAD。
Similarly, the section inertia moment I relative to the diagonal BD can be calculatedBD。
Step S5 weights the moment of area inertia obtained in step S4 to obtain a microvascular encircling degree coefficient, and further gives a microvascular encircling degree level determination result according to the threshold interval, and the calculation result of the moment of area inertia is shown in fig. 6.
S5.1: calculating a microvascular ringing coefficient
ξ＝ρAC·IAC+ρBD·IBD
Wherein the content of the first and second substances,
Figure BDA0003069345930000055
s5.2: judging surrounding degree grade, judging the surrounding degree grade of the microvessels according to the obtained surrounding degree coefficient xi, and when the surrounding degree coefficient xi is less than or equal to 0.72, the surrounding degree of the microvessels is normal; when the surrounding degree coefficient is 0.72 < xi < 1.04, the microvasculature is in general surrounding; when the surrounding degree coefficient xi >1.04 the microvessels were severely encircled, i.e.
Figure BDA0003069345930000061
The results are shown in tables 1 and 2.
TABLE 1
Picture frame 1 2 3 4 5 6
Moment of inertia 1.38 1.18 0.56 0.62 0.88 1.1
TABLE 2
Figure BDA0003069345930000062

Claims (3)

1. A microvascular looping degree quantification method for gastric mucosa staining amplification imaging is characterized by comprising the following steps: the method for quantifying the circumferential extent of the capillary comprises a section moment of inertia method; the section moment of inertia method is used for quantifying the surrounding degree of the microvessels and giving a determination result of the surrounding degree grade of the microvessels, a clear area in a gastroscope image is obtained through an image segmentation method, all the microvessels in the clear area are extracted through the image segmentation method to form a microvessel whole image, a single microvessel is extracted from the microvessel whole image through a 8-communication mode, then the minimum circumscribed rectangle of each microvessel is solved, and the section moment of inertia is calculated;
comprises the following steps:
s1: inputting an original image to be quantified for gastric mucosa staining and amplifying imaging, and extracting a clear area image from the original image of the endoscope by adopting an image segmentation model;
s2: adopting an image segmentation model to segment a whole microvascular image from a clear region image;
s3: on the basis of the connected domain, filtering noise points in the whole microvascular graph through the area and the perimeter of the connected domain, calculating the minimum external horizontal rectangle of the retained microvascular and removing other noise vessels in the range of the external horizontal rectangle;
s4: quantifying the surrounding degree of the blood vessel by adopting a section moment of inertia method for the single micro blood vessel obtained in the step S3,
s5: judging the surrounding degree grade of the microvessels according to xi obtained in the step S4;
weighting the section moment of inertia obtained in the step S4 to obtain a microvascular surrounding degree coefficient, and further giving a microvascular surrounding degree grade determination result according to the threshold interval, wherein the method comprises the following steps:
s5.1: calculating a microvascular ringing coefficient
ξ＝ρAC·IAC+ρBD·IBD
Wherein the content of the first and second substances,
Figure FDA0003544347170000011
s5.2: judging the surrounding degree grade, and according to the obtained surrounding degree coefficient xi, carrying out blood microcirculation treatmentJudging the degree grade of the tube encircling degree, wherein when the encircling degree coefficient xi is less than or equal to 0.72, the encircling degree of the microvessels is normal; when the surrounding degree coefficient is 0.72 < xi < 1.04, the microvasculature is in general surrounding; when the surrounding degree coefficient xi is more than 1.04, the micro blood vessels are severely surrounded, i.e. the surrounding degree coefficient xi is more than 1.04
Figure FDA0003544347170000012
2. The method for quantifying the circumferential extent of the microvasculature through gastric mucosal staining and magnification imaging according to claim 1, wherein: in step S3, the method eliminates other noisy blood vessels within the minimum external horizontal rectangle of the current microvessel, and proceeds as follows:
s3.1: calculating the minimum external horizontal rectangle of the current microvascular and calculating the areas of all connected domains in the external rectangle;
s3.2: finding out the connected domain with the largest area except the background in the step S3.1 as the target micro-vessel and recording the connected domain of the micro-vessel;
s3.3: traversing all pixel points in the minimum external horizontal rectangle obtained in the step S3.1, and judging whether each pixel point is in the connected domain of the target blood vessel in the step S3.2 by adopting an area sum judgment method; assuming that the vertex coordinate of the microvascular connected domain is A1(x1,y1)，A2(x2,y2)…An(xn,yn) The coordinate of a certain pixel point in the minimum external horizontal rectangle of the microvascular is P (x)i,yi) If the pixel point is in the target micro-vessel connected domain, the triangular area formed by the pixel point and all adjacent vertexes of the connected domain is the polygonal area, and the following equation is satisfied:
Figure FDA0003544347170000021
setting the pixel value of the pixel point which does not satisfy the equation in the minimal external horizontal rectangle of the microvessel as a background pixel;
step of traversingCalculating the minimum circumscribed rectangle of each microvessel after the processing of S3, and calculating the coordinates of four vertexes as PA(xA,yA)，PB(xB,yB)，PC(xC,yC)，PD(xD,yD) At any point in the microvasculature Oi(xi,yi) Then, the cross-sectional moment of inertia with respect to the diagonal line AC is calculated as:
Figure FDA0003544347170000022
wherein λ isACFor penalty factors, defined here
Figure FDA0003544347170000023
LACIs a point Pi(xi,yi) The distance to the diagonal line AC is such that,
Figure FDA0003544347170000024
area-is the minimum circumscribed rectangle area, and area is LAB·LAD；
Similarly, the section inertia moment I relative to the diagonal BD can be calculatedBD。
3. The method for quantifying the circumferential extent of the microvasculature through gastric mucosal staining and amplified imaging according to claim 2, wherein: traversing each microvessel processed in the step S3, calculating the minimum bounding rectangle, and calculating the coordinates of four vertexes as PA(xA,yA)，PB(xB,yB)，PC(xC,yC)，PD(xD,yD) At any point in the microvasculature Oi(xi,yi) Relative to diagonal ACThe formula for calculating the section moment of inertia is as follows:
Figure FDA0003544347170000031
wherein λ isACFor penalty factors, defined here
Figure FDA0003544347170000032
LACIs a point Pi(xi,yi) The distance to the diagonal line AC is such that,
Figure FDA0003544347170000033
area-is the minimum circumscribed rectangle area, and area is LAB·LAD；
Similarly, the section inertia moment I relative to the diagonal BD can be calculatedBD。
CN202110534698.5A 2021-05-17 2021-05-17 Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging Active CN113344859B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110534698.5A CN113344859B (en) 2021-05-17 2021-05-17 Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110534698.5A CN113344859B (en) 2021-05-17 2021-05-17 Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging

Publications (2)

Publication Number Publication Date
CN113344859A CN113344859A (en) 2021-09-03
CN113344859B true CN113344859B (en) 2022-04-26

Family

ID=77468914

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110534698.5A Active CN113344859B (en) 2021-05-17 2021-05-17 Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging

Country Status (1)

Country Link
CN (1) CN113344859B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706533B (en) * 2021-10-28 2022-02-08 武汉大学 Image processing method, image processing device, computer equipment and storage medium
CN113887677B (en) * 2021-12-07 2022-03-01 武汉大学 Method, device, equipment and medium for classifying capillary vessel images in epithelial papilla
CN114359280B (en) * 2022-03-18 2022-06-03 武汉楚精灵医疗科技有限公司 Gastric mucosa image boundary quantification method, device, terminal and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108986220A (en) * 2018-07-16 2018-12-11 浙江大学 A method of accelerating finite element solving object lattice model flexible deformation
CN110147802A (en) * 2019-05-13 2019-08-20 安徽工业大学 The inertinite classification method and system of trend fluction analysis are gone based on multi-fractal
CN111870230A (en) * 2020-07-16 2020-11-03 武汉大学 Multi-parameter tumor blood vessel normalization detection system and detection method
CN112435246A (en) * 2020-11-30 2021-03-02 武汉楚精灵医疗科技有限公司 Artificial intelligent diagnosis method for gastric cancer under narrow-band imaging amplification gastroscope

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108986220A (en) * 2018-07-16 2018-12-11 浙江大学 A method of accelerating finite element solving object lattice model flexible deformation
CN110147802A (en) * 2019-05-13 2019-08-20 安徽工业大学 The inertinite classification method and system of trend fluction analysis are gone based on multi-fractal
CN111870230A (en) * 2020-07-16 2020-11-03 武汉大学 Multi-parameter tumor blood vessel normalization detection system and detection method
CN112435246A (en) * 2020-11-30 2021-03-02 武汉楚精灵医疗科技有限公司 Artificial intelligent diagnosis method for gastric cancer under narrow-band imaging amplification gastroscope

Also Published As

Publication number Publication date
CN113344859A (en) 2021-09-03

Similar Documents

Publication Publication Date Title
CN113344859B (en) Method for quantifying capillary surrounding degree of gastric mucosa staining amplification imaging
CN113205492B (en) Microvessel distortion degree quantification method for gastric mucosa staining amplification imaging
WO2021169128A1 (en) Method and apparatus for recognizing and quantifying fundus retina vessel, and device and storage medium
CN112435246A (en) Artificial intelligent diagnosis method for gastric cancer under narrow-band imaging amplification gastroscope
CN107478657A (en) Stainless steel surfaces defect inspection method based on machine vision
CN110751605B (en) Image processing method and device, electronic equipment and readable storage medium
AU2018282455A1 (en) Diagnosis assisting device, and image processing method in diagnosis assisting device
WO2008044466A1 (en) Image processing device, image processing method, and image processing program
CN110189303B (en) NBI image processing method based on deep learning and image enhancement and application thereof
JPH03206572A (en) Automatizing system for gradation conversion
JP2002257679A (en) Method of obtaining luminance information, image quality evaluating method, device of obtaining luminance information of display apparatus and image quality evaluating method of the display apparatus
CN113344860B (en) Abnormal degree quantification method for microstructure of gastric mucosa staining and amplifying image
CN113052844B (en) Method and device for processing images in intestinal endoscope observation video and storage medium
CN117012344B (en) Image analysis method for 4CMOS camera acquisition
CN110660048B (en) Leather surface defect detection method based on shape characteristics
CN112396565A (en) Method and system for enhancing and segmenting blood vessels of images and videos of venipuncture robot
CN115546232A (en) Liver ultrasonic image working area extraction method and system and electronic equipment
CN109658394B (en) Fundus image preprocessing method and system and microangioma detection method and system
CN112446889A (en) Medical video reading method based on ultrasound
CN112700409A (en) Automatic retinal microaneurysm detection method and imaging method
Afonso et al. Hair detection in dermoscopic images using percolation
CN110705615A (en) Thyroid nodule detection and classification method based on TV model and GoogLeNet model
CN115994999A (en) Goblet cell semantic segmentation method and system based on boundary gradient attention network
CN113393425B (en) Microvessel distribution symmetry quantification method for gastric mucosa staining amplification imaging
CN111292285A (en) Automatic screening method for diabetes mellitus based on naive Bayes and support vector machine

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
GR01 Patent grant
GR01 Patent grant