CN108961249A - One cervical cancer cells identifying and diagnosing method again - Google Patents
One cervical cancer cells identifying and diagnosing method again Download PDFInfo
- Publication number
- CN108961249A CN108961249A CN201810793772.3A CN201810793772A CN108961249A CN 108961249 A CN108961249 A CN 108961249A CN 201810793772 A CN201810793772 A CN 201810793772A CN 108961249 A CN108961249 A CN 108961249A
- Authority
- CN
- China
- Prior art keywords
- sample
- image
- cell
- vector
- cancerous tumor
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/259—Fusion by voting
-
- 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
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (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)
- Image Analysis (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention discloses cervical cancer cells identifying and diagnosing method again, includes the following steps: step 1, pre-processes to collected cervical cell image, extracts cellular morphology and chromaticity, and be expressed as vector;Step 2, training sample, training recognition mechanism M are obtained1And M2, constitute balanced neighborhood classifier M, wherein M1For discriminating whether as cancerous tumor cell, M2For determining canceration type;Step 3, cervical cell image to be identified is pre-processed, extracts cellular morphology and chromaticity, and be expressed as vector;Step 4, its vector parameter is inputted in balanced neighborhood classifier M and is differentiated, first with M1It discriminates whether as cancerous tumor cell, M is recycled to cancerous tumor cell2Determine canceration type.Pathological diagnosis and computer technology are effectively combined by such diagnostic method, realize higher overall discrimination and lower false alarm rate.
Description
Technical field
The invention belongs to image recognition, field of biomedicine, in particular to cervical cancer cells identifying and diagnosing side again
Method.
Background technique
Whole world cancer morbidity just rises year by year at present, wherein cervix cancer is the pernicious of serious harm women's health
Disease.The early diagnosis of cervix cancer is that it cures key.In general, the diagnostic method of cervix cancer includes detachment of cervix
Cytolgical examination, human papilloma virus etiological diagnosis, cervical tissue pathological examination etc., wherein cervical smear screening
It is vital measure, i.e., by being sampled to obtain cell smear or tissue smear to cervical cell, under the microscope
It is observed, finds paramorph cell or cell mass, obtain diagnosis knot according to its analysis such as quantity, degree of variation that make a variation
Fruit.Currently, the pathological analysis under microscope is usually completed by veteran doctor.In clinical diagnosis, due to experienced
Doctor's number it is limited, and Artificial Diagnosis is influenced by factors such as the subjectivity of people, fatigue, experiences, is examined reliable pathology is obtained
It is disconnected to have certain restriction.
With the rapid development of image procossing and mode identification technology, Computer assisted identification can greatly improve diagnosis effect
Rate.But so far, the diagnostic method of the automatic screening of area of computer aided cervical cell image is also rare is related to.As can universal son
The identifying and diagnosing of cervical smear automates, and while realizing accurate screening, reduces doctor's workload, eliminates artificial detection drawback
It caused mistaken diagnosis and fails to pinpoint a disease in diagnosis, false negative rate can be reduced to a certain extent.
Summary of the invention
The purpose of the present invention is to provide cervical cancer cells identifying and diagnosing method again, effectively examines pathology
It is disconnected to be combined with computer technology, realize higher overall discrimination and lower false alarm rate.
In order to achieve the above objectives, solution of the invention is:
One cervical cancer cells identifying and diagnosing method again, includes the following steps:
Step 1, collected cervical cell image is pre-processed, extracts cellular morphology and chromaticity, and table
It is shown as vector;
Step 2, training sample, training recognition mechanism M are obtained1And M2, constitute balanced neighborhood classifier M, wherein M1For
It discriminates whether as cancerous tumor cell, M2For determining canceration type;
Step 3, cervical cell image to be identified is pre-processed, extracts cellular morphology and chromaticity, and table
It is shown as vector;
Step 4, its vector parameter is inputted in balanced neighborhood classifier M and is differentiated, first with M1Discriminate whether for
Cancerous tumor cell recycles M to cancerous tumor cell2Determine canceration type.
After adopting the above scheme, the present invention is first handled collected cervical smear, extract cellular morphology,
Coloration, Texture eigenvalue carry out Parametric Analysis to it using digital image processing techniques, are denoted as feature vector.So
Afterwards by a kind of specific cervical cell image-recognizing method, classification is carried out to possible cancerous tumor cell and is identified again, thus
Reliable diagnostic result out.It is adjacent to first proposed a kind of balance when carrying out specific cervical cell image recognition by the present invention
Domain classifier solves the class imbalance problem of data set classification, classifies to cell data set, finds out the cell of possible canceration
Data set;Then the cell image of possible canceration is identified again, obtains last diagnostic result.Application effect shows the party
Pathological diagnosis and computer technology are effectively combined by method, realize higher overall discrimination and lower false alarm rate.
Detailed description of the invention
Fig. 1 is flow chart of the invention;
Fig. 2 is cell image process flow diagram;
Fig. 3 is trained recognition mechanism flow chart;
Fig. 4 is that balanced neighborhood classifier utilizes recognition mechanism M1Process flowchart;
Fig. 5 is to utilize recognition mechanism M2Carry out cell image identification process figure again.
Specific embodiment
Below with reference to attached drawing, technical solution of the present invention and beneficial effect are described in detail.
Method flow provided by the invention is as shown in Figure 1, step 0 is initial actuating;Step 1 pre-processes image,
For training process, which will be specifically introduced part below in conjunction with Fig. 2;Step 2 obtains training sample, and training is known
Other mechanism;Step 5 enters in balanced neighborhood classifier, utilizes recognition mechanism M1Classify to cell image, filters out canceration
Cell image;Step 8 utilizes recognition mechanism M2Identification process again is carried out, determines canceration type.Step 5 will be rear with step 8
The part in face combines Fig. 4 and Fig. 5 to be specifically introduced.
Cervical smear sample process process is as shown in Figure 2.Firstly, cervical cell smear is obtained by cell sampling,
Using collecting image of computer software, the vision signal on patient uterine's neck cancer cell smear is obtained in real time, carries out Image Acquisition
With red (R), green (G), blue (B) true color image are converted into after processing;Then by original RGB color image from three-dimensional color space
Project to one-dimensional linear space, its gray level image is split, is denoised, smoothly, sharpen and a series of processing such as shape filtering,
Obtain the preferable bianry image of effect;Morphological feature finally is carried out to the target area of cell image with morphology and colorimetry
With the extraction of chromaticity.It by the image feature representation extracted is vector by characteristic extracting module, as training sample, into
Enter and is trained in balanced neighborhood classifier.
The process of trained recognition mechanism is described in detail in Fig. 3, the specific steps are as follows:
(1) normal cell vector set is set as L1, possible cancerous tumor cell vector set is L2, initially set
(2) cell image for obtaining tape label carries out feature extraction and is denoted as vector;
(3) check that current cell image is known as a result, when image is normal cell image, current cell image institute is right
L is added in the feature vector answered1;When image be possible cancerous tumor cell image, feature vector corresponding to current cell image is added
Enter L2, L2=L21∪L22∪…∪L2c, c is cervical cancer cell category number;
(4) judge whether there are also other images, if it is thening follow the steps (2);It is no to then follow the steps (5);
(5) by L1In vector be labeled as 0, L2In vector be labeled as 1;
(6) L is used1、L2Training recognition mechanism M1;
(7) by L2iIn vector be labeled as the i-th class, training recognition mechanism M2;
(8) terminate.
Fig. 4 is described in detail in balanced neighborhood classifier using recognition mechanism M1The process differentiated.In acquisition
In cell image data set, in general, the accounting of normal cell is more in human body, and the accounting of cancer cell is few, this is just caused
The class imbalance problem of data set classification.To solve the problems, such as such, a kind of recognition mechanism M of balanced neighborhood classifier is proposed1、M2,
Identifying and diagnosing is carried out to it, the specific steps are as follows:
(1) the part sample set for extracting cell characteristic in cell image is marked, is denoted as marker samples collection L;Not
The sample set of label is denoted as unmarked sample set U;
(2) using selected distance metric function, sample to be tested x ∈ U to all training sample x is calculatedjThe distance of ∈ L.
Generally use three metric function d1, d2, d∞:
Wherein, aiIndicate ith feature, m indicates total characteristic number, and (x a) indicates the value of feature a in x sample to f;
(3) class c is calculatediMaximum distanceAnd minimum range
(4) class c in calculated equilibrium neighborhood classification deviceiThreshold value δi;
Wherein, ω is that the radius of neighbourhood and maximum radius set ratio certainly.
(5) class c is collectediThe sample set X of middle sample to be tested x neighborhoodi:
Xi={ xj|xj∈Li, d (x, xj)≤δi}
Wherein,Indicate class ciIn total sample number, NiIndicate LiIn subset sample number;d(x,
xj) indicate sample x to xjDistance, RmIndicate the space characteristic m.
(6) sample to be tested x to every class sample set X is calculatediThe local distance at center;In formula, | Xi| it is XiIn sample number:
(7) sample to be tested x is attributed to the corresponding class of local distance minimum value:
C (x)=argminDi
(8) when such for L1, then the diagnostic result for providing sample to be tested x is normal cell, terminates identification;
(9) when such for L2, then the diagnostic result for providing sample to be tested x is cancerous tumor cell, into cognitive phase again.
Fig. 5 is described in detail using recognition mechanism M2Identification process again.Specific step is as follows for identification process again:
(1) the sample set L for the cancerous tumor cell that input obtains2;
(2) to L2It carries out n times duplicate sampling and obtains D1,D2,…,DnTraining set;
(3) in DiUpper trained decision tree obtains base classifier mi, wherein i=1,2 ..., n;
(4) classifier m is detectediError rate ei;
(5) Search Error rate is less than the classifier m* for making threshold value by oneself, is added to set M2In, until having searched for all bases point
Class device:
(6) integrated using Voting principle f to classifier M:
(7) sample to be tested is inputted, classifier M is used2To its identifying and diagnosing, canceration type is obtained.
It can be seen that from the above specific embodiment, a cervical cancer cells provided by the invention identifying and diagnosing method again,
Collected cervical smear is handled first, Parametric Analysis is carried out simultaneously to its feature using digital image processing techniques
It is expressed as feature vector.Then by a kind of specific cervical cell image automatic screening method, sick cell is divided
It class and identifies again.Application effect shows that this method realizes higher overall discrimination and lower false alarm rate.
The above examples only illustrate the technical idea of the present invention, and this does not limit the scope of protection of the present invention, all
According to the technical idea provided by the invention, any changes made on the basis of the technical scheme each falls within the scope of the present invention
Within.
Claims (6)
1. cervical cancer cells identifying and diagnosing method again, it is characterised in that include the following steps:
Step 1, collected cervical cell image is pre-processed, extracts cellular morphology and chromaticity, and be expressed as
Vector;
Step 2, training sample, training recognition mechanism M are obtained1And M2, constitute balanced neighborhood classifier M, wherein M1For differentiating
It whether is cancerous tumor cell, M2For determining canceration type;
Step 3, cervical cell image to be identified is pre-processed, extracts cellular morphology and chromaticity, and be expressed as
Vector;
Step 4, its vector parameter is inputted in balanced neighborhood classifier M and is differentiated, first with M1Discriminate whether for canceration it is thin
Born of the same parents recycle M to cancerous tumor cell2Determine canceration type.
2. a cervical cancer cells as described in claim 1 identifying and diagnosing method again, it is characterised in that: the step 1 and
In step 3, pretreated process is: firstly, obtaining cervical cell smear by cell sampling, utilizing collecting image of computer
Software, obtains the vision signal that patient uterine's neck cell applies on piece in real time, and it is very color to be converted into RGB after progress Image Acquisition and processing
Chromatic graph picture;Then, original RGB color image is projected into one-dimensional linear space from three-dimensional color space, to its gray level image into
Row segmentation, denoising, smooth, sharpening and shape filtering processing, obtain bianry image;Finally, to the target area of cell image into
The extraction of row morphological feature and chromaticity.
3. a cervical cancer cells as described in claim 1 identifying and diagnosing method again, it is characterised in that: the step 2
Detailed process is:
Step 21, ifWherein, L1For normal cell vector set, L2For possible cancerous tumor cell vector set;
Step 22, the cell image of tape label is obtained, feature extraction is carried out and is denoted as vector;
Step 23, check that current cell image is known as a result, when image is normal cell image, current cell image institute is right
L is added in the feature vector answered1;When image be possible cancerous tumor cell image, feature vector corresponding to current cell image is added
Enter L2, L2=L21∪L22∪...∪L2c, c is cervical cancer cell category number;
Step 24, judge whether there are also other images, it is no to then follow the steps 25 if it is thening follow the steps 22;
Step 25, by L1In vector be labeled as 0, L2In vector be labeled as 1;
Step 26, using L1、L2Training recognition mechanism M1;
Step 27, by L2iIn vector be labeled as the i-th class, training recognition mechanism M2。
4. a cervical cancer cells as described in claim 1 identifying and diagnosing method again, it is characterised in that: in the step 4,
Utilize M1Discriminate whether be for the detailed process of cancerous tumor cell:
Step a41, the part sample in optional cell image are marked, and are denoted as marker samples collection L;Remaining unlabelled sample
Collection is denoted as unmarked sample set U;
Step a42 calculates sample to be tested x ∈ U to all training sample x using distance metric functionjThe distance of ∈ L;
Step a43 calculates class ciMaximum distanceAnd minimum range
Step a44, class c in calculated equilibrium neighborhood classification deviceiThreshold value δi;
Step a45 collects class ciThe sample set X of middle sample to be tested x neighborhoodi;
Step a46 calculates sample to be tested x to every class sample set XiThe local distance at center;
Sample to be tested x is attributed to the corresponding class of local distance minimum value by step a47;
Step a48, when such for L1, then the diagnostic result for providing sample to be tested x is normal cell, terminates diagnosis process;When such
For L2, then the diagnostic result for providing sample to be tested x is cancerous tumor cell.
5. a cervical cancer cells as claimed in claim 4 identifying and diagnosing method again, it is characterised in that: the step a42
In, distance metric function uses three metric function d1, d2, d∞:
Wherein, aiIndicate ith feature, m indicates total characteristic number, and (x a) indicates the value of feature a in x sample to f.
6. a cervical cancer cells as described in claim 1 identifying and diagnosing method again, it is characterised in that: in the step 4,
Utilize M2Determine comprising the concrete steps that for canceration type:
Step b41 inputs the sample set L of the cancerous tumor cell of acquisition2;
Step b42, to L2It carries out n times duplicate sampling and obtains D1, D2..., DnTraining set;
Step b43, in DiUpper trained decision tree obtains base classifier mi;
Step b44 detects classifier miError rate ei;
Step b45, Search Error rate are less than the classifier m* for making threshold value by oneself, are added to set M2In, until having searched for all bases point
Class device:
Step b46, to M2It is integrated using Voting principle f:
Step b47 inputs sample to be tested, uses classifier M2To its identifying and diagnosing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810793772.3A CN108961249A (en) | 2018-07-19 | 2018-07-19 | One cervical cancer cells identifying and diagnosing method again |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810793772.3A CN108961249A (en) | 2018-07-19 | 2018-07-19 | One cervical cancer cells identifying and diagnosing method again |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108961249A true CN108961249A (en) | 2018-12-07 |
Family
ID=64481940
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810793772.3A Withdrawn CN108961249A (en) | 2018-07-19 | 2018-07-19 | One cervical cancer cells identifying and diagnosing method again |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108961249A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113588521A (en) * | 2021-07-12 | 2021-11-02 | 武汉大学 | Blood detector, blood detection identification system and identification method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1462884A (en) * | 2003-06-24 | 2003-12-24 | 南京大学 | Method of recognizing image of lung cancer cells with high accuracy and low rate of false negative |
CN103907023A (en) * | 2011-09-13 | 2014-07-02 | 皇家飞利浦有限公司 | System and method for the detection of abnormalities in a biological sample |
CN104834914A (en) * | 2015-05-15 | 2015-08-12 | 广西师范大学 | Uterine neck cell image characteristic identification method and uterine neck cell characteristic identification apparatus |
CN105894490A (en) * | 2015-11-05 | 2016-08-24 | 广西师范大学 | Fuzzy integration multiple classifier integration-based uterine neck cell image identification method and device |
CN107609503A (en) * | 2017-09-05 | 2018-01-19 | 刘宇红 | Intelligent cancerous tumor cell identifying system and method, cloud platform, server, computer |
CN108038056A (en) * | 2017-12-07 | 2018-05-15 | 厦门理工学院 | A kind of software defect detecting system based on asymmetric classification assessment |
-
2018
- 2018-07-19 CN CN201810793772.3A patent/CN108961249A/en not_active Withdrawn
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1462884A (en) * | 2003-06-24 | 2003-12-24 | 南京大学 | Method of recognizing image of lung cancer cells with high accuracy and low rate of false negative |
CN103907023A (en) * | 2011-09-13 | 2014-07-02 | 皇家飞利浦有限公司 | System and method for the detection of abnormalities in a biological sample |
CN104834914A (en) * | 2015-05-15 | 2015-08-12 | 广西师范大学 | Uterine neck cell image characteristic identification method and uterine neck cell characteristic identification apparatus |
CN105894490A (en) * | 2015-11-05 | 2016-08-24 | 广西师范大学 | Fuzzy integration multiple classifier integration-based uterine neck cell image identification method and device |
CN107609503A (en) * | 2017-09-05 | 2018-01-19 | 刘宇红 | Intelligent cancerous tumor cell identifying system and method, cloud platform, server, computer |
CN108038056A (en) * | 2017-12-07 | 2018-05-15 | 厦门理工学院 | A kind of software defect detecting system based on asymmetric classification assessment |
Non-Patent Citations (3)
Title |
---|
SHUNZHI ZHU等: ""Balanced Neighborhood Classifiers for Imbalanced Data Sets"", 《IEICE TRANSACTION ON INFORMATION AND SYSTEM》 * |
罗微等: ""基于细胞核特征的宫颈癌细胞图像的识别与分类"", 《自动化与仪器仪表》 * |
赵理莉等: ""结合层次法与主成分分析特征变换的宫颈细胞识别"", 《国防科技大学学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113588521A (en) * | 2021-07-12 | 2021-11-02 | 武汉大学 | Blood detector, blood detection identification system and identification method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Khan et al. | Classification of melanoma and nevus in digital images for diagnosis of skin cancer | |
George et al. | Remote computer-aided breast cancer detection and diagnosis system based on cytological images | |
Song et al. | A deep learning based framework for accurate segmentation of cervical cytoplasm and nuclei | |
Filipczuk et al. | Computer-aided breast cancer diagnosis based on the analysis of cytological images of fine needle biopsies | |
Dundar et al. | Computerized classification of intraductal breast lesions using histopathological images | |
Akram et al. | Detection of neovascularization in retinal images using multivariate m-Mediods based classifier | |
CN111986150B (en) | The method comprises the following steps of: digital number pathological image Interactive annotation refining method | |
US9567651B2 (en) | System and method for the detection of abnormalities in a biological sample | |
CN111028206A (en) | Prostate cancer automatic detection and classification system based on deep learning | |
CN109858540B (en) | Medical image recognition system and method based on multi-mode fusion | |
US9743824B2 (en) | Accurate and efficient polyp detection in wireless capsule endoscopy images | |
CN108257129A (en) | The recognition methods of cervical biopsy region aids and device based on multi-modal detection network | |
Xu et al. | Adjustable adaboost classifier and pyramid features for image-based cervical cancer diagnosis | |
Fang et al. | On the accurate counting of tumor cells | |
CN106778047A (en) | A kind of traditional Chinese medical science facial diagnosis integrated system based on various dimensions medical image | |
Beevi et al. | Detection of mitotic nuclei in breast histopathology images using localized ACM and Random Kitchen Sink based classifier | |
Rahman et al. | Automatic detection of white blood cells from microscopic images for malignancy classification of acute lymphoblastic leukemia | |
Kuse et al. | A classification scheme for lymphocyte segmentation in H&E stained histology images | |
CN108961222A (en) | A kind of cervical carcinoma early screening recognition methods based on gynecatoptron image | |
CN108550148A (en) | Nucleus in histotomy micro-image divides automatically and classifying identification method | |
Qu et al. | Two-step segmentation of Hematoxylin-Eosin stained histopathological images for prognosis of breast cancer | |
Kudva et al. | Pattern classification of images from acetic acid–based cervical cancer screening: A review | |
Anari et al. | Computer-aided detection of proliferative cells and mitosis index in immunohistichemically images of meningioma | |
Akselrod-Ballin et al. | An integrated segmentation and classification approach applied to multiple sclerosis analysis | |
Dey et al. | Red-plane asymmetry analysis of breast thermograms for cancer detection |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181207 |