CN112102277A - Device and method for detecting tumor cells in pleural fluid fluorescence image - Google Patents
Device and method for detecting tumor cells in pleural fluid fluorescence image Download PDFInfo
- Publication number
- CN112102277A CN112102277A CN202010948676.9A CN202010948676A CN112102277A CN 112102277 A CN112102277 A CN 112102277A CN 202010948676 A CN202010948676 A CN 202010948676A CN 112102277 A CN112102277 A CN 112102277A
- Authority
- CN
- China
- Prior art keywords
- image
- cell
- module
- tumor cells
- carrying
- 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
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- 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
- G06T2207/10064—Fluorescence image
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a device and a method for detecting tumor cells in a pleural effusion fluorescence image, which relate to the technical field of medical treatment and comprise the following steps: s1, CCD acquisition is carried out on the prepared cell smear to obtain a cell image, S2, the obtained cell image is preprocessed, S3, the preprocessed cell image is segmented, S4, feature extraction preprocessing is carried out on the segmented cell image, S5, feature extraction is carried out on the preprocessed cell image, and S6, the condition of the tumor cell is judged according to the features extracted from the cell image. According to the invention, the tumor cells can be rapidly screened and detected through the pleural effusion fluorescence image, the time can be saved, the work of tumor cell image preprocessing and image feature extraction can be saved, and a large amount of effective feature data can be provided for the subsequent identification work, so that a better tumor cell classification effect can be achieved.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a device and a method for detecting tumor cells in a pleural effusion fluorescence image.
Background
The tumor cell parenchyma is a tumor. The tumor tissue is composed of parenchyma and stroma, and the tumor parenchyma is tumor cells, is a main component of the tumor and has tissue source specificity. It determines the biological characteristics of the tumor and the specificity of each tumor.
When detecting, generally can detect tumor cells through pleural effusion fluorescence image, but present main detection mode is to carrying out artifical comprehensive screening, because total cell quantity is too much, artifical screening a sample usually needs several hours, and efficiency is very low, is difficult to satisfy medical personnel's demand.
Disclosure of Invention
The invention aims to provide a device and a method for detecting tumor cells in a pleural effusion fluorescence image, which can rapidly screen and detect the tumor cells through the pleural effusion fluorescence image, save time, pre-process the tumor cell image and extract image characteristics, and provide a large amount of effective characteristic data for subsequent identification so as to achieve better tumor cell classification effect.
In order to achieve the purpose, the invention is realized by the following technical scheme: a method for detecting tumor cells in a pleural fluid fluorescence image, comprising the steps of:
and S1, carrying out CCD acquisition on the prepared cell smear to obtain a cell image.
And S2, preprocessing the acquired cell image.
And S3, performing image segmentation on the preprocessed cell image.
And S4, performing feature extraction preprocessing on the segmented cell image.
And S5, performing feature extraction on the preprocessed cell image.
And S6, judging the condition of the tumor cells according to the characteristics extracted from the cell images.
Further, according to the operation step in S2, the method includes the following steps:
s201, carrying out gray level processing on the acquired cell image;
and S202, performing on-off filtering on the gray image by taking a square image with the size 2 times that of the lymphocyte as a structural element.
Further, according to the operation procedure in S3, when image segmentation is performed, the cell nucleus, the cytoplasm, and the background region are distinguished.
Further, according to the operation step in S4, the feature extraction preprocessing of the cell image includes the steps of:
s401, binarization processing is carried out on the segmented image.
S402, different marked parts in the cell image are respectively taken out, partition processing is carried out, and coordinates of each group are stored in an array.
And S403, calculating the pixel area occupied by the cell nucleus and the cell cytoplasm in each region, and recording the pixel area in a corresponding array.
And S404, marking the cell nucleus part in each area.
Further, according to the operation step in S4, the feature extraction preprocessing of the cell image further includes the steps of:
s405, carrying out corrosion treatment on the obtained cell nucleus binary image, finding out the center coordinates of the cell nucleus, and judging whether the partition is composed of single cells or cell clusters.
Further, according to the operation procedure in S5, the feature extraction includes the nuclear-to-cytoplasmic ratio, whether the cell size is uniform, and nuclear staining abnormality.
An apparatus for detecting tumor cells in a pleural fluid fluorescence image, comprising:
and the cell image acquisition module (1) is used for carrying out CCD (charge coupled device) processing on the prepared cell smear to acquire an image.
And the cell image preprocessing module (2) is used for preprocessing the cell image.
And the image segmentation module (3) is used for carrying out segmentation processing on the image.
And the characteristic pre-extraction module (4) is used for pre-extracting the characteristics of the segmented image.
And the final feature extraction module (5), wherein the final feature extraction module (5) extracts required information according to the features.
Further, the method also comprises the following steps:
and the judging module (6) is used for measuring whether the nuclear spacing of the clustered aggregated cells is uniform and consistent, analyzing the sectional pictures one by one and judging whether the clustered aggregated cells are cancerous aggregated cells.
Further, the feature pre-extraction module (5) comprises:
the image binarization module is used for carrying out binarization processing on the segmented image;
and the extracting module is used for extracting the parts of different marks in the image and overhauling and storing the coordinates of each group.
And the marking module is used for marking out the cell nucleus part in each area.
Further, the feature pre-extraction module (5) further comprises:
and the image erosion module is used for carrying out erosion processing on the obtained cell nucleus binary image and judging whether the subarea is composed of single cells or cell clusters.
The invention provides a device and a method for detecting tumor cells in a pleural effusion fluorescence image. The method has the following beneficial effects:
in the invention, in the aspect of image preprocessing, cell images are denoised, small normal discrete cells and impurities or fragments left in the process of making cell smears can be removed at the same time of removing general point-like noise, so that the processing speed of subsequent work is greatly improved, and the accuracy of feature extraction and classification identification is improved.
Drawings
FIG. 1 is a general flow chart of the method for detecting tumor cells in a pleural fluid fluorescence image according to the present invention;
FIG. 2 is a flow chart of the cell image preprocessing of the method for detecting tumor cells in a pleural fluid fluorescence image according to the present invention;
FIG. 3 is a flow chart of a feature extraction pre-process of a cell image of the method of detecting tumor cells in a pleural fluid fluorescence image according to the present invention;
FIG. 4 is a schematic diagram of the detection of tumor cells in a pleural fluid fluorescence image according to the present invention.
In the figure: 1. a cell image acquisition module; 2. a cell image preprocessing module; 3. an image segmentation module; 4. a feature pre-extraction module; 5. a final feature extraction module; 6. and a judging module.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention; it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive work are within the scope of the present invention.
In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "top/bottom", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "sleeved/connected," "connected," and the like are to be construed broadly, e.g., "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; the two components can be directly connected or indirectly connected through an intermediate medium, and the two components can be communicated with each other; the specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Referring to fig. 1-4, a method for detecting tumor cells in a pleural fluid fluorescence image, comprising the steps of:
(1) and performing CCD acquisition on the prepared cell smear to obtain a cell image.
(2) The method comprises the following steps of (201) carrying out gray scale processing on the acquired cell image, (202) carrying out on-off filtering on the gray scale image by taking a square image with the size 2 times that of lymphocytes as a structural element, wherein the on-off filtering firstly selects a proper structural element B, removes pepper-shaped noise in the background by using on operation, and then removes trachoma noise by using off operation, and has good effect of filtering and recovering the image for most images.
(3) And performing image segmentation on the preprocessed cell image, and distinguishing a cell nucleus, a cell cytoplasm and a background area when performing image segmentation.
(4) And performing feature extraction pretreatment on the segmented cell image, wherein the feature extraction pretreatment of the cell image comprises the following steps: (401) binary processing is carried out on the segmented image, the nucleus and the cytoplasm are target images and are assigned with 0, other backgrounds are assigned with 1, binary marking is carried out on the obtained binary image, the positions of clustered cells and single cells are found out, (402) different marked parts in the cell image are respectively taken out, partition processing is carried out, the coordinates of each group are stored in an array, (403) the pixel area occupied by the nucleus and the cytoplasm in each partition is calculated and recorded in the corresponding array, 0 value is also assigned to the cytoplasm as the background, (404) the nucleus part in each partition is marked, (405) the obtained nucleus binary image is corroded, the center coordinates of the nucleus are found, whether the partition is formed by single cells or cell clusters is judged, and the partition is divided into the parts of the single cells and the clustered cells, for the clustered cells, if the characteristics such as the nuclear distance and the like of the clustered cells are extracted, the central position of each nucleus needs to be found first, and the method for finding the nuclear center is a mathematical morphology limit corrosion method.
B is an Euclidean disc with a constant radius r and a center at the origin, for a given image A, W is repeated, B is used for corrosion operation, a layer with the thickness of r of the image is continuously peeled off, disconnected areas are continuously generated in the process of continuous corrosion, meanwhile, some areas are continuously disappeared, the last step of a connected component before disappearance is called a final connected component, the sum of all final connected components is called the limit corrosion of the relative radius r, and Uit (A) is used for representing the limit corrosion.
In the digital case, the erosion structuring element is not a circle with a radius r, but a small digital structuring element.
The nuclear center position of each cell in the clustered cells can be obtained through the limit corrosion operation, and therefore whether the nuclear distance in the clustered cells is uniform or not can be calculated.
(5) And performing feature extraction on the preprocessed cell image, wherein the feature extraction comprises the nuclear-to-cytoplasmic ratio, whether the cell size is uniform or not and abnormal nuclear staining.
(6) And judging the condition of the tumor cells according to the characteristics extracted from the cell images.
An apparatus for detecting tumor cells in a pleural fluid fluorescence image, comprising: cell image acquisition module 1 for carrying out CCD with the cell smear of making and handling and obtain the image, cell image preprocessing module 2, carry out the preliminary treatment to the cell image, image segmentation module 3, be used for carrying out segmentation to the image, characteristic pre-extraction module 4, be used for carrying out the characteristic pre-extraction to the image after cutting apart, the final module 5 that draws of characteristic draws required information according to the characteristic extraction, judge module 6 measures its nuclear distance of its nuclear distance to clump of aggregated cells and be even unanimous, carry out analysis one by one to the subregion picture, judge whether for canceration aggregate cell, characteristic pre-extraction module 4 includes: the system comprises an image binarization module, a taking-out module and an image corrosion module, wherein the image binarization module is used for carrying out binarization processing on a segmented image, the taking-out module is used for taking out parts marked by different marks in the image and overhauling and storing coordinates of each group, the marking module is used for marking out the cell nucleus part in each area, and the image corrosion module is used for carrying out corrosion processing on the obtained cell nucleus binarization image and judging whether the area is formed by a single cell or a cell group.
In the invention, in the aspect of image preprocessing, cell images are denoised, so that small normal discrete cells and impurities or fragments left in the process of making cell smears can be removed at the same time of removing general point-like noise, the processing speed of subsequent work is greatly improved, and the accuracy of feature extraction and classification identification is improved.
The above is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, many variations and modifications can be made without departing from the inventive concept of the present invention, which falls into the protection scope of the present invention.
Claims (10)
1. A method for detecting tumor cells in a pleural fluid fluorescence image, comprising the steps of:
s1, carrying out CCD acquisition on the prepared cell smear to obtain a cell image;
s2, preprocessing the acquired cell image;
s3, carrying out image segmentation on the preprocessed cell image;
s4, performing feature extraction pretreatment on the segmented cell image;
s5, extracting the characteristics of the preprocessed cell image;
and S6, judging the condition of the tumor cells according to the characteristics extracted from the cell images.
2. The method of claim 1, wherein the method comprises the following steps according to the operation step in S2:
s201, carrying out gray level processing on the acquired cell image;
and S202, performing on-off filtering on the gray image by taking a square image with the size 2 times that of the lymphocyte as a structural element.
3. The method of claim 1, wherein the image segmentation is performed according to the operation of S3 to distinguish between cell nucleus, cytoplasm and background region.
4. The method according to claim 1, wherein the feature extraction preprocessing of the cell image according to the operation step in S4 includes the steps of:
s401, performing binarization processing on the segmented image;
s402, respectively taking out different marked parts in the cell image, carrying out partition processing, and storing the coordinates of each group into an array;
s403, calculating the pixel area occupied by the cell nucleus and the cell cytoplasm in each region, and recording the pixel area in a corresponding array;
and S404, marking the cell nucleus part in each area.
5. The method according to claim 4, wherein the feature extraction preprocessing of the cell image further comprises the steps of, according to the operation step in S4:
s405, carrying out corrosion treatment on the obtained cell nucleus binary image, finding out the center coordinates of the cell nucleus, and judging whether the partition is composed of single cells or cell clusters.
6. The method of claim 1, wherein the feature extraction includes a nuclear-to-cytoplasmic ratio, whether the cell size is uniform, and abnormal nuclear staining according to the operation of S5.
7. An apparatus for detecting tumor cells in a pleural fluid fluorescence image, comprising:
the cell image acquisition module (1) is used for carrying out CCD (charge coupled device) processing on the prepared cell smear to acquire an image;
the cell image preprocessing module (2) is used for preprocessing the cell image;
an image segmentation module (3) for performing segmentation processing on the image;
the characteristic pre-extraction module (4) is used for pre-extracting the characteristics of the segmented image;
and the final feature extraction module (5), wherein the final feature extraction module (5) extracts required information according to the features.
8. The apparatus for detecting tumor cells in a pleural fluid fluorescence image of claim 7, further comprising:
and the judging module (6) is used for measuring whether the nuclear spacing of the clustered aggregated cells is uniform and consistent, analyzing the sectional pictures one by one and judging whether the clustered aggregated cells are cancerous aggregated cells.
9. The apparatus for detecting tumor cells in a pleural fluid fluorescence image according to claim 7, wherein the feature pre-extraction module (4) comprises:
the image binarization module is used for carrying out binarization processing on the segmented image;
the extraction module is used for extracting parts of different marks in the image and overhauling and storing the coordinates of each group;
and the marking module is used for marking out the cell nucleus part in each area.
10. The apparatus for detecting tumor cells in a pleural fluid fluorescence image according to claim 9, wherein the feature pre-extraction module (4) further comprises:
and the image erosion module is used for carrying out erosion processing on the obtained cell nucleus binary image and judging whether the subarea is composed of single cells or cell clusters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010948676.9A CN112102277A (en) | 2020-09-10 | 2020-09-10 | Device and method for detecting tumor cells in pleural fluid fluorescence image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010948676.9A CN112102277A (en) | 2020-09-10 | 2020-09-10 | Device and method for detecting tumor cells in pleural fluid fluorescence image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112102277A true CN112102277A (en) | 2020-12-18 |
Family
ID=73751182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010948676.9A Pending CN112102277A (en) | 2020-09-10 | 2020-09-10 | Device and method for detecting tumor cells in pleural fluid fluorescence image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112102277A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703917A (en) * | 2023-08-07 | 2023-09-05 | 广州盛安医学检验有限公司 | Female genital tract cell pathology intelligent analysis system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296635A (en) * | 2015-05-29 | 2017-01-04 | 厦门鹭佳生物科技有限公司 | A kind of fluorescence in situ hybridization (FISH) image Parallel Processing and the method for analysis |
| CN107274386A (en) * | 2017-05-18 | 2017-10-20 | 深思考人工智能机器人科技（北京）有限公司 | A kind of cervical cell liquid-based smear artificial intelligence aids in diagosis system |
| CN108334860A (en) * | 2018-03-01 | 2018-07-27 | 北京航空航天大学 | The treating method and apparatus of cell image |
| CN110378313A (en) * | 2019-07-26 | 2019-10-25 | 玖壹叁陆零医学科技南京有限公司 | Cell mass recognition methods, device and electronic equipment |
-
2020
- 2020-09-10 CN CN202010948676.9A patent/CN112102277A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296635A (en) * | 2015-05-29 | 2017-01-04 | 厦门鹭佳生物科技有限公司 | A kind of fluorescence in situ hybridization (FISH) image Parallel Processing and the method for analysis |
| CN107274386A (en) * | 2017-05-18 | 2017-10-20 | 深思考人工智能机器人科技（北京）有限公司 | A kind of cervical cell liquid-based smear artificial intelligence aids in diagosis system |
| CN108334860A (en) * | 2018-03-01 | 2018-07-27 | 北京航空航天大学 | The treating method and apparatus of cell image |
| CN110378313A (en) * | 2019-07-26 | 2019-10-25 | 玖壹叁陆零医学科技南京有限公司 | Cell mass recognition methods, device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703917A (en) * | 2023-08-07 | 2023-09-05 | 广州盛安医学检验有限公司 | Female genital tract cell pathology intelligent analysis system |
| CN116703917B (en) * | 2023-08-07 | 2024-01-26 | 广州盛安医学检验有限公司 | Female genital tract cell pathology intelligent analysis system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107844683B (en) | Method for calculating concentration of digital PCR (polymerase chain reaction) liquid drops | |
| CN111739010B (en) | Method and device for detecting abnormal circulating cells | |
| EP2191417B1 (en) | Methods and systems for processing biological specimens utilizing multiple wavelengths | |
| WO1996009598A1 (en) | Cytological slide scoring apparatus | |
| EP2199776B1 (en) | Cell image analysis apparatus, cell image analysis method, and program | |
| WO2018106691A1 (en) | Automated slide assessments and tracking in digital microscopy | |
| CN109147932B (en) | Cancer cell HER2 gene amplification analysis method and system | |
| JP4864709B2 (en) | A system for determining the staining quality of slides using a scatter plot distribution | |
| CN112102277A (en) | Device and method for detecting tumor cells in pleural fluid fluorescence image | |
| CN114387596A (en) | Automatic interpretation system for cytopathology smear | |
| CN113723314A (en) | Sugarcane stem node identification method based on YOLOv3 algorithm | |
| CN113552126A (en) | Reticulocyte detection method and system | |
| Taher et al. | Identification of lung cancer based on shape and color | |
| KR101106386B1 (en) | System for classifying slides using scatter plot distributions | |
| CN111311628A (en) | Full-automatic high-performance leukocyte segmentation method | |
| CN115375679A (en) | Edge finding and point searching positioning method and device for defective chip | |
| CN114140417A (en) | Cigarette filter stick identification method and system based on machine vision | |
| CN112634338A (en) | Cerebrospinal fluid cell feature extraction method based on gray level co-occurrence matrix | |
| Del Bimbo et al. | Accurate evaluation of HER-2 amplification in FISH images | |
| US7769547B2 (en) | Karyometry-based method for prediction of cancer event recurrence | |
| CN113945558B (en) | Method for judging myeloproliferation degree | |
| WO2020184462A1 (en) | System for manufacturing metal material and method of manufacturing metal material | |
| CN113537181A (en) | CB microkernel microscopic image identification and analysis method and system based on neural network | |
| CN100588941C (en) | System for determining the stain quality of slides using scatter plot distributions | |
| CN117576687A (en) | Cervical cancer cytology screening system and method based on image analysis |
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 |