CN116091451A - Retinal pigment epithelial cell image segmentation method and system - Google Patents
Retinal pigment epithelial cell image segmentation method and system Download PDFInfo
- Publication number
- CN116091451A CN116091451A CN202310028792.2A CN202310028792A CN116091451A CN 116091451 A CN116091451 A CN 116091451A CN 202310028792 A CN202310028792 A CN 202310028792A CN 116091451 A CN116091451 A CN 116091451A
- Authority
- CN
- China
- Prior art keywords
- pigment epithelial
- retinal pigment
- epithelial cell
- image
- segmentation
- 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
- 210000000844 retinal pigment epithelial cell Anatomy 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003709 image segmentation Methods 0.000 title claims abstract description 30
- 230000011218 segmentation Effects 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 15
- 230000003044 adaptive effect Effects 0.000 claims abstract description 10
- 238000003672 processing method Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 210000002919 epithelial cell Anatomy 0.000 abstract description 3
- 239000000049 pigment Substances 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 210000001525 retina Anatomy 0.000 abstract 2
- 206010064930 age-related macular degeneration Diseases 0.000 description 6
- 208000002780 macular degeneration Diseases 0.000 description 6
- 241000699666 Mus <mouse, genus> Species 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 241000699670 Mus sp. Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001218 confocal laser scanning microscopy Methods 0.000 description 1
- 238000004624 confocal microscopy Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000009509 drug development Methods 0.000 description 1
- 230000008378 epithelial damage Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000002207 retinal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000004393 visual impairment Effects 0.000 description 1
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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- 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
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/30041—Eye; Retina; Ophthalmic
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a retina pigment epithelial cell image segmentation method and a retina pigment epithelial cell image segmentation system, wherein the method comprises the following steps: s1, extending a retinal pigment epithelial cell image; s2, segmenting by adopting an adaptive threshold image segmentation algorithm, and taking the segmented dark area as a potential retinal pigment epithelial cell area; s3, filtering out areas with areas smaller than a threshold value; s4, optimizing by adopting an image morphology processing method; s5, removing the extension part to obtain a segmentation result. The invention builds a simple accurate segmentation algorithm of the retinal pigment epithelial cell image under the fluorescence confocal microscope by using the self-adaptive threshold image segmentation and image morphology processing technology, and can solve the problems that the existing automatic retinal pigment epithelial cell image segmentation algorithm under the fluorescence confocal microscope has complex flow and is difficult to realize or needs to consume a large amount of resources to train an algorithm model.
Description
Technical Field
The invention relates to the field of medical image processing, in particular to a retinal pigment epithelial cell image segmentation method and system under a fluorescence confocal microscope.
Background
Fluorescence confocal microscopy is a commonly used imaging technique in ophthalmology research that can be applied to imaging of mouse retinal pigment epithelial cells ex vivo. In the study of age-related macular degeneration, researchers can use a fluorescence confocal microscope to image mouse retinal pigment epithelial cells, so as to observe the influence of age-related macular degeneration on the mouse retinal pigment epithelial cells, and further infer the protective effect of test drugs on the retinal pigment epithelial cells of mice suffering from age-related macular degeneration. To quantitatively calculate the effect of age-related macular degeneration on mouse retinal pigment epithelial cells, it is necessary to segment the retinal pigment epithelial cell image under a fluorescence confocal microscope. At present, the segmentation of the retinal pigment epithelial cell image under a fluorescence confocal microscope is mostly realized by adopting an artificial mode in the research. The manual segmentation method is time-consuming and labor-consuming and has strong subjectivity. Therefore, development of an automated fluorescence confocal microscope retinal pigment epithelial cell image segmentation algorithm is particularly important. Existing mainly automated fluorescent confocal microscopy retinal pigment epithelial cell image segmentation algorithms fall into two main categories, namely non-machine learning-based algorithms and machine learning-based algorithms. The flow of the non-machine learning method is complex and difficult to realize, and the machine learning method needs to consume a large amount of resources to train the model of the algorithm.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a system for segmenting retinal pigment epithelial cell images under a fluorescence confocal microscope aiming at the defects in the prior art.
In order to solve the technical problems, the invention adopts the following technical scheme: a method for segmenting retinal pigment epithelial cell images under a fluorescence confocal microscope comprises the following steps:
s1, extending a retinal pigment epithelial cell image;
s2, segmenting the extended image obtained in the step S1 by adopting an adaptive threshold image segmentation algorithm, and taking the segmented dark area as a potential retinal pigment epithelial cell area;
s3, filtering out areas with areas smaller than a threshold value in the potential retinal pigment epithelial cell areas obtained in the step S2;
s4, optimizing the potential retinal pigment epithelial cell area obtained in the step S3 by adopting an image morphology processing method;
s5, removing the extension part in the optimized image obtained in the step S4, and obtaining a segmentation result of the lower retinal pigment epithelial cell image.
Preferably, the step S1 specifically includes: symmetrically filling the image edges as axes, and stretching the retinal pigment epithelial cell image to ensure that each side length of the stretched image is alpha times as long as the original image, and alpha is more than 1.
Preferably, wherein α=1.2.
Preferably, the threshold T in the step S3 is η of the area average value of each potential retinal pigment epithelial cell, and the calculation formula is:
wherein A is i Representing the area of the ith potential retinal pigment epithelial cell region, i=1, 2, 3..n, N is the potential visual network in the imageTotal number of membrane pigment epithelial cell areas.
Preferably, wherein η < 30.
Preferably, wherein η=10.
Preferably, in the step S4, the edge of the potential retinal pigment epithelial cell region is shrunk to a single line by using an image morphological erosion operation, so as to obtain an optimized image.
The invention also provides a retinal pigment epithelial cell image segmentation system, which adopts the method to segment retinal pigment epithelial cell images under a fluorescence confocal microscope, and comprises the following steps:
an extension module for extending the retinal pigment epithelial cell image;
the segmentation module is used for segmenting the image obtained by the extension module by adopting an adaptive threshold image segmentation algorithm, and taking the segmented dark area as a potential retinal pigment epithelial cell area;
a filtering module for filtering out the area smaller than the threshold value in the potential retinal pigment epithelial cell area obtained by the segmentation module;
an optimizing module for optimizing the potential retinal pigment epithelial cell region obtained by the filtering module by adopting an image morphology processing method;
and an extension area removing module for removing extension parts in the optimized image obtained by the optimizing module to obtain a segmentation result of the lower retinal pigment epithelial cell image.
The present invention also provides a storage medium having stored thereon a computer program which when executed is adapted to carry out the method as described above.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method as described above when executing the computer program.
The beneficial effects of the invention are as follows:
the invention builds a simple accurate segmentation algorithm of the retinal pigment epithelial cell image under the fluorescence confocal microscope by using the self-adaptive threshold image segmentation and image morphology processing technology, can solve the problems that the existing automatic retinal pigment epithelial cell image segmentation algorithm under the fluorescence confocal microscope is complex in flow and difficult to realize or needs to consume a large amount of resources to train an algorithm model, and has potential medical value for drug development of age-related macular degeneration.
Drawings
FIG. 1 is a process flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of an image edge extension operation of the method of the present invention;
FIG. 3 is a schematic view of adaptive thresholding image segmentation in accordance with the method of the present invention;
FIG. 4 is a schematic representation of a region of too small a filtration area of the method of the present invention;
FIG. 5 is a schematic representation of the contraction of the border region of potential retinal pigment epithelial cells in the method of the present invention;
FIG. 6 is a schematic illustration of the removal extension of the method of the present invention;
FIG. 7 is a graph showing the image segmentation effect of retinal pigment epithelial cells in the disclosed dataset by the method of the present invention.
Detailed Description
The present invention is described in further detail below with reference to examples to enable those skilled in the art to practice the same by referring to the description.
It will be understood that terms, such as "having," "including," and "comprising," as used herein, do not preclude the presence or addition of one or more other elements or groups thereof.
Example 1
Referring to fig. 1, the present embodiment provides a retinal pigment epithelial cell image segmentation method, including the steps of:
s1, extending a retinal pigment epithelial cell image: and (3) symmetrically filling the image edges as axes, and stretching the retinal pigment epithelial cell image to ensure that each side length of the stretched image is 1.2 times of the original length.
In the collected image of retinal pigment epithelial cells under the fluorescence confocal microscope, as shown in a red dotted frame of fig. 2, retinal pigment epithelial cells at the edge of the image are not completely displayed; these retinal pigment epithelial cells that show incomplete are sometimes prone to image segmentation errors. Therefore, in this embodiment, the image of the retinal pigment epithelial cells is extended, and the extended portion is the portion outside the red dashed line frame in fig. 2, and the extended portion is symmetrically filled with the image edge as an axis, and the length after the extended portion is 1.2 times of the original edge length; in this way, retinal pigment epithelial cells at the edges of the pre-expansion image are formed into a complete region, as shown in FIG. 2, which facilitates proper segmentation of the cells. Although the edge portion of the large image after extension is not segmented well, it belongs to the redundant image and is removed after segmentation is completed.
S2, segmenting the extended image obtained in the step S1 by adopting an adaptive threshold image segmentation algorithm, and taking the segmented dark area as a potential retinal pigment epithelial cell area;
as shown in the left diagrams of fig. 2 and 3, due to the uneven brightness of the edges of the retinal pigment epithelial cells in the images, the image after extension obtained in the step 1 is segmented by adopting an adaptive threshold image segmentation algorithm, and as shown in fig. 3, the segmented black areas are potential retinal pigment epithelial cell areas.
S3, filtering out areas with areas smaller than a threshold value in the potential retinal pigment epithelial cell areas obtained in the step S2;
as shown in the right and left graphs of fig. 3 and 4, after the adaptive threshold image segmentation, a part of the impurities may be erroneously segmented into retinal pigment epithelial cell edge regions. Since these areas are small, they are filtered by setting an area threshold in this example, the threshold T is 10% of the area mean of each potential retinal pigment epithelial cell, and the calculation formula is:
wherein A is i The area of the ith potential retinal pigment epithelial cell region is represented, i=1, 2, 3..n, N being the total number of potential retinal pigment epithelial cell regions in the image.
S4, optimizing the potential retinal pigment epithelial cell area obtained in the step S3 by adopting an image morphology processing method;
as shown in the right and left panels of fig. 4 and 5, segmentation of retinal pigment epithelial cell images after filtering potential cell areas of too small an area requires optimization, although at initial success. The image morphological erosion procedure is used in this example to shrink the border region of the potential retinal pigment epithelial cells (i.e., the white region in the left panel of fig. 5) until it shrinks to a single line, as shown in the right panel of fig. 5.
S5, removing the extension part in the optimized image obtained in the step S4 to obtain a segmentation result of the lower retinal pigment epithelial cell image, as shown in FIG. 6.
FIG. 7 is a graph showing the effect of the method of the present invention on segmentation of retinal pigment epithelial cell images in the public data set [1], which demonstrates the high accuracy of the proposed method in segmentation of retinal pigment epithelial cell images under a fluorescence confocal microscope.
[1]Ding,J.D.,Johnson,L.V.,Herrmann,R.,Farsiu,S.,Smith,S.G.,Groelle,M.,&Rickman,C.B.(2011).Anti-amyloid therapy protects against retinal pigmented epithelium damage and vision loss in a model of age-related macular degeneration.Proceedings of the National Academy of Sciences,108(28),E279-E287.
Example 2
A retinal pigment epithelial cell image segmentation system, characterized in that it performs segmentation of retinal pigment epithelial cell images by the method of example 1, comprising:
an extension module for extending the retinal pigment epithelial cell image;
the segmentation module is used for segmenting the image obtained by the extension module by adopting an adaptive threshold image segmentation algorithm, and taking the segmented dark area as a potential retinal pigment epithelial cell area;
a filtering module for filtering out the area smaller than the threshold value in the potential retinal pigment epithelial cell area obtained by the segmentation module;
an optimizing module for optimizing the potential retinal pigment epithelial cell region obtained by the filtering module by adopting an image morphology processing method;
and an extension area removing module for removing extension parts in the optimized image obtained by the optimizing module to obtain a segmentation result of the lower retinal pigment epithelial cell image.
The present embodiment also provides a storage medium having stored thereon a computer program which when executed is adapted to carry out the method of embodiment 1.
The present embodiment also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of embodiment 1 when executing the computer program.
Although embodiments of the present invention have been disclosed above, it is not limited to the use of the description and embodiments, it is well suited to various fields of use for the invention, and further modifications may be readily apparent to those skilled in the art, and accordingly, the invention is not limited to the particular details without departing from the general concepts defined in the claims and the equivalents thereof.
Claims (10)
1. A retinal pigment epithelial cell image segmentation method, comprising the steps of:
s1, extending a retinal pigment epithelial cell image;
s2, segmenting the extended image obtained in the step S1 by adopting an adaptive threshold image segmentation algorithm, and taking the segmented dark area as a potential retinal pigment epithelial cell area;
s3, filtering out areas with areas smaller than a threshold value in the potential retinal pigment epithelial cell areas obtained in the step S2;
s4, optimizing the potential retinal pigment epithelial cell area obtained in the step S3 by adopting an image morphology processing method;
s5, removing the extension part in the optimized image obtained in the step S4, and obtaining a segmentation result of the lower retinal pigment epithelial cell image.
2. The method for segmenting retinal pigment epithelial cell image according to claim 1, wherein the step S1 is specifically: symmetrically filling the image edges as axes, and stretching the retinal pigment epithelial cell image to ensure that each side length of the stretched image is alpha times as long as the original image, and alpha is more than 1.
3. The method of image segmentation of retinal pigment epithelial cells according to claim 2, wherein α=1.2.
4. The method according to claim 2, wherein the threshold T in the step S3 is η% of the area mean value of each potential retinal pigment epithelial cell, and the calculation formula is:
wherein A is i The area of the ith potential retinal pigment epithelial cell region is represented, i=1, 2, 3..n, N being the total number of potential retinal pigment epithelial cell regions in the image.
5. The method of claim 4, wherein η < 30.
6. The method for image segmentation of retinal pigment epithelial cells according to claim 5, wherein η = 10.
7. The method according to claim 1, wherein the step S4 is performed by shrinking the edges of the potential retinal pigment epithelial cell region into single lines by using an image morphological erosion operation to obtain an optimized image.
8. A retinal pigment epithelial cell image segmentation system, characterized in that it employs the method as set forth in any one of claims 1 to 7 for segmentation of retinal pigment epithelial cell images under a fluorescence confocal microscope, comprising:
an extension module for extending the retinal pigment epithelial cell image;
the segmentation module is used for segmenting the image obtained by the extension module by adopting an adaptive threshold image segmentation algorithm, and taking the segmented dark area as a potential retinal pigment epithelial cell area;
a filtering module for filtering out the area smaller than the threshold value in the potential retinal pigment epithelial cell area obtained by the segmentation module;
an optimizing module for optimizing the potential retinal pigment epithelial cell region obtained by the filtering module by adopting an image morphology processing method;
and an extension area removing module for removing extension parts in the optimized image obtained by the optimizing module to obtain a segmentation result of the lower retinal pigment epithelial cell image.
9. A storage medium having stored thereon a computer program, which when executed is adapted to carry out the method of any of claims 1-7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-7 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310028792.2A CN116091451A (en) | 2023-01-09 | 2023-01-09 | Retinal pigment epithelial cell image segmentation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310028792.2A CN116091451A (en) | 2023-01-09 | 2023-01-09 | Retinal pigment epithelial cell image segmentation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116091451A true CN116091451A (en) | 2023-05-09 |
Family
ID=86213448
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310028792.2A Pending CN116091451A (en) | 2023-01-09 | 2023-01-09 | Retinal pigment epithelial cell image segmentation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116091451A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574374A (en) * | 2014-12-23 | 2015-04-29 | 苏州大学 | Automatic segmentation method for retinal serous pigment epithelial layer detachment |
CN107248161A (en) * | 2017-05-11 | 2017-10-13 | 江西理工大学 | Retinal vessel extracting method is supervised in a kind of having for multiple features fusion |
CN107316077A (en) * | 2017-06-21 | 2017-11-03 | 上海交通大学 | A kind of fat cell automatic counting method based on image segmentation and rim detection |
CN111027511A (en) * | 2019-12-23 | 2020-04-17 | 西安电子科技大学 | Remote sensing image ship detection method based on region of interest block extraction |
CN111837157A (en) * | 2018-03-08 | 2020-10-27 | 株式会社岛津制作所 | Cell image analysis method, cell image analysis device, and learning model creation method |
US20210052157A1 (en) * | 2019-08-21 | 2021-02-25 | Case Western Reserve University | Assessment of endothelial cells and corneas at risk from ophthalmological images |
CN113192082A (en) * | 2021-05-04 | 2021-07-30 | 吴冰 | Epithelial cell image centralization processing segmentation method |
CN114693646A (en) * | 2022-03-31 | 2022-07-01 | 中山大学中山眼科中心 | Corneal endothelial cell active factor analysis method based on deep learning |
CN115187980A (en) * | 2022-06-20 | 2022-10-14 | 汕头大学 | Calcein AM/PI double-staining cell fluorescence image-based cell counting method |
CN115294152A (en) * | 2022-07-11 | 2022-11-04 | 中国科学院苏州生物医学工程技术研究所 | Automatic layering method and system for retina OCT (optical coherence tomography) image |
-
2023
- 2023-01-09 CN CN202310028792.2A patent/CN116091451A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574374A (en) * | 2014-12-23 | 2015-04-29 | 苏州大学 | Automatic segmentation method for retinal serous pigment epithelial layer detachment |
CN107248161A (en) * | 2017-05-11 | 2017-10-13 | 江西理工大学 | Retinal vessel extracting method is supervised in a kind of having for multiple features fusion |
CN107316077A (en) * | 2017-06-21 | 2017-11-03 | 上海交通大学 | A kind of fat cell automatic counting method based on image segmentation and rim detection |
CN111837157A (en) * | 2018-03-08 | 2020-10-27 | 株式会社岛津制作所 | Cell image analysis method, cell image analysis device, and learning model creation method |
US20210052157A1 (en) * | 2019-08-21 | 2021-02-25 | Case Western Reserve University | Assessment of endothelial cells and corneas at risk from ophthalmological images |
CN111027511A (en) * | 2019-12-23 | 2020-04-17 | 西安电子科技大学 | Remote sensing image ship detection method based on region of interest block extraction |
CN113192082A (en) * | 2021-05-04 | 2021-07-30 | 吴冰 | Epithelial cell image centralization processing segmentation method |
CN114693646A (en) * | 2022-03-31 | 2022-07-01 | 中山大学中山眼科中心 | Corneal endothelial cell active factor analysis method based on deep learning |
CN115187980A (en) * | 2022-06-20 | 2022-10-14 | 汕头大学 | Calcein AM/PI double-staining cell fluorescence image-based cell counting method |
CN115294152A (en) * | 2022-07-11 | 2022-11-04 | 中国科学院苏州生物医学工程技术研究所 | Automatic layering method and system for retina OCT (optical coherence tomography) image |
Non-Patent Citations (2)
Title |
---|
JIANYAN HUANG 等: "Comparison of manual automated analysis methods for corneal endothelial cell density measurements by specular microscopy", 《JOURNAL OF OPTOMETRY》 * |
SU JINZHU 等: "Segmentation of choroid neovascularization in OCT images based on convolutional neural network with differential amplification blocks", 《SPIE》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112069874B (en) | Method, system, equipment and storage medium for identifying cells in embryo light microscope image | |
Zong et al. | U-net based method for automatic hard exudates segmentation in fundus images using inception module and residual connection | |
US20070002275A1 (en) | Method and System For Local Adaptive Detection Of Microaneurysms In Digital Fundus Images | |
Piorkowski et al. | Influence of applied corneal endothelium image segmentation techniques on the clinical parameters | |
CN111126180B (en) | Facial paralysis severity automatic detection system based on computer vision | |
CN110633676B (en) | Method for automatically identifying cerebrospinal fluid cell image information | |
CN112991306B (en) | Cleavage stage embryo cell position segmentation and counting method based on image processing | |
CN111476794B (en) | Cervical pathological tissue segmentation method based on UNET | |
CN112528947B (en) | Method, equipment and storage medium for detecting false hyphae by increasing direction dimension | |
CN113436070B (en) | Fundus image splicing method based on deep neural network | |
CN111563884A (en) | Neural network-based fundus disease identification method, computer device, and medium | |
Vimala et al. | Automatic detection of optic disk and exudate from retinal images using clustering algorithm | |
JP6714273B2 (en) | Corneal endothelial cell quality evaluation support system | |
CN106446805A (en) | Segmentation method and system for optic cup in eye ground photo | |
Antal et al. | A multi-level ensemble-based system for detecting microaneurysms in fundus images | |
Lyu et al. | Deep tessellated retinal image detection using Convolutional Neural Networks | |
CN116091451A (en) | Retinal pigment epithelial cell image segmentation method and system | |
CN115272333B (en) | Cup-disk ratio data storage system | |
Poostchi et al. | Diabetic retinopathy dark lesion detection: preprocessing phase | |
Ali et al. | Optic Disc Localization in Retinal Fundus Images Based on You Only Look Once Network (YOLO). | |
Anjanadevi et al. | A framework for the Diagnosis of Diabetic Retinopathy Using Deep Learning Techniques | |
Honale et al. | A review of methods for blood vessel segmentation in retinal images | |
Kumar et al. | Comeal endothelium cell segmentation and count using k-means and watershed algorithms | |
Chandra et al. | Confocal corneal endothelium dystrophy’s analysis using a hybrid algorithm | |
CN113627230B (en) | Retina OCT image automatic segmentation method based on machine vision |
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: 20230509 |