CN108806774A - Medical image search method based on geometrical constraint and spatial pixel intensity - Google Patents
Medical image search method based on geometrical constraint and spatial pixel intensity Download PDFInfo
- Publication number
- CN108806774A CN108806774A CN201810496727.1A CN201810496727A CN108806774A CN 108806774 A CN108806774 A CN 108806774A CN 201810496727 A CN201810496727 A CN 201810496727A CN 108806774 A CN108806774 A CN 108806774A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel intensity
- feature
- vlad
- spatial pixel
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000013598 vector Substances 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 4
- 230000014509 gene expression Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 2
- 208000003174 Brain Neoplasms Diseases 0.000 abstract description 22
- 230000002708 enhancing effect Effects 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007917 intracranial administration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 206010027191 meningioma Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
Landscapes
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses the medical image search methods based on geometrical constraint and spatial pixel intensity, it is related to technical field of medical image processing, expansion enhancing is carried out to brain tumor image ROI first, expanded later ROI has incorporated the image information of its edge neighborhood, and preferably the ROI of brain tumor image can be described.Then the spatial pixel intensity feature of ROI is extracted under the premise of geometrical constraint, it extracts around it image pixel intensities feature of pixel with certain geometrical relationship therewith while extracting each pixel image pixel intensities feature, describes a pixel information jointly.K-means clusters are carried out to the spatial pixel intensity feature extracted, generate VLAD models.The similitude judged between image finally by the distance between image VLAD vectors is retrieved, and the retrieval performance of brain tumor image retrieval can be effectively improved.
Description
Technical field
The present invention relates to technical field of medical image processing, more particularly to based on geometrical constraint and spatial pixel intensity
Medical image search method.
Background technology
Brain tumor, also referred to as intracranial tumors, according to the difference at incidence tissue position can be divided into spongiocytoma, meningioma,
The types such as hypophysoma, human body brain tumor are also a kind of disease for seriously threatening human health.The brain tumor death rate is high, and
And constantly increase with operating pressure with the quickening pace of modern life, the incidence of brain tumor is also being continuously improved.
Preferable booster action is also played to the diagnosis and treatment of brain tumor based on the medical image retrieval of content, it is many to study
Person is dedicated to the research of brain tumor image retrieval.The researchers such as Quellec have used Wavelet Transformation Algorithm in medical image retrieval,
The researchers such as Yang Xiandong are to color correlogram, color moment, gray level co-occurrence matrixes, pyramid wavelet transformation and tree structured wavelet transform five
Retrieval performance of the kind image characteristic extracting method in brain tumor image retrieval has been Experimental comparison, as a result shows the effect of wavelet transformation
Fruit is more preferable.The researchers such as Huang H K propose a kind of delimitation brain tumor image ROI, extract texture, the shape of image in the roi
And the method that gray feature carries out similarity measurement, this method have used the global characteristics of brain tumor image.Huang on this basis
The researchers such as M propose a kind of brain tumor image search method based on BoW models for brain tumor regiospecificity, by obtaining
The ROI taken divides region, and the image pixel intensities feature of image is extracted in every sub-regions, establishes the mode of vision bag of words to inquiry
Image and database images carry out similarity measurement.
But, in brain tumor image SIFT feature less in the extractible valuable key point of human body brain tumor image-region
The gradient information used does not have in brain tumor image that pixel intensity information is abundant, therefore when stating brain tumor image information with SIFT feature
Resolving ability is not good enough.
Invention content
An embodiment of the present invention provides the medical image search methods based on geometrical constraint and spatial pixel intensity, can solve
Certainly problems of the prior art.
The present invention provides the medical image search method based on geometrical constraint and spatial pixel intensity, this method include with
Lower step:
Step 1, reading database image;
Step 2, the image expansion structural parameters p according to setting creates structural element and is carried out to the database images of reading
Expansion process;
Step 3, the space pixel that the database images Jing Guo expansion process are extracted according to the geometrical constraint parameter n of setting is strong
Feature is spent, d dimensional vectors is used in combination to indicate;
Step 4, it is poly- to carry out K-means to the spatial pixel intensity feature of extraction by the cluster centre number k according to setting
Class generates k cluster centre;
Step 5, it is that every width database images generate VLAD code books:The k cluster centre generated according to step 4 is by database
All spatial pixel intensity features in image are divided into k classes, will belong to the feature and the cluster of all same cluster centres
Difference is added up after making the difference in center obtains d dimension residual vectors, and k d residual vector, which is integrated into k × d, ties up matrix, as VLAD codes
This;
Step 6, input inquiry image;
Step 7, it according to parameter p, creates structural element and expansion process is carried out to query image;
Step 8, the spatial pixel intensity feature of the query image according to the n extractions of geometrical constraint parameter Jing Guo expansion process,
It is used in combination d dimensional vectors to indicate;
Step 9, it is that query image generates VLAD code books:The k cluster centre generated according to step 4 will be in query image
All spatial pixel intensity features are divided into k classes, and the feature for belonging to all same cluster centres is made the difference with the cluster centre
The cumulative d that obtains of difference is tieed up into residual vector afterwards, k d, which is tieed up residual vector, is integrated into k × d dimension matrixes, as VLAD code books;
Step 10, the VLAD code books generated according to step 5 and 9 carry out similarity measurements to query image and database images
Amount, and export retrieval result.
The medical image search method based on geometrical constraint and spatial pixel intensity in the embodiment of the present invention, introduces office
Portion's characteristic aggregation describes sub- VLAD models to quantify brain tumor image.Expansion enhancing carried out to brain tumor image ROI first, it is expanded with
ROI afterwards has incorporated the image information of its edge neighborhood, and preferably the ROI of brain tumor image can be described.Then in geometry
The spatial pixel intensity feature that ROI is extracted under the premise of constraint, i.e., carry while extracting each pixel image pixel intensities feature
It takes around it image pixel intensities feature of pixel with certain geometrical relationship therewith, describes a pixel information jointly.
K-means clusters are carried out to the spatial pixel intensity feature extracted, generate VLAD models.Finally by image VLAD vectors
Between distance retrieved come the similitude judged between image, the retrieval performance of brain tumor image retrieval can be effectively improved.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow of the medical image search method based on geometrical constraint and spatial pixel intensity in the embodiment of the present invention
Figure.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig.1, an embodiment of the present invention provides the medical image retrieval sides based on geometrical constraint and spatial pixel intensity
Method, this approach includes the following steps:
Step 1, reading database image.
Step 2, the image expansion structural parameters p according to setting creates structural element and is carried out at expansion to the image of reading
It manages, the structural element used in the present embodiment is disk.
Step 3, the spatial pixel intensity that the image Jing Guo expansion process is extracted according to the geometrical constraint parameter n of setting is special
Sign, is used in combination d dimensional vectors to indicate.
Step 4, it is poly- to carry out K-means to the spatial pixel intensity feature of extraction by the cluster centre number k according to setting
Class generates k cluster centre.
Step 5, VLAD code books are generated for each image in database:The k cluster centre generated according to step 4 will scheme
All spatial pixel intensity features as in are divided into k classes, will belong in the feature and the cluster of all same cluster centres
The heart, which adds up difference after making the difference, obtains d dimension residual vectors, and k d residual vector, which is integrated into k × d, ties up matrix, as VLAD codes
This.
Step 6, input inquiry image.
Step 7, it according to parameter p, creates structural element and expansion process is carried out to the query image of input.
Step 8, the spatial pixel intensity feature of the query image according to the n extractions of geometrical constraint parameter Jing Guo expansion process,
It is used in combination d dimensional vectors to indicate.
Step 9, it is that query image generates VLAD code books:The k cluster centre generated according to step 4 will be in query image
All spatial pixel intensity features are divided into k classes, and the feature for belonging to all same cluster centres is made the difference with the cluster centre
The cumulative d that obtains of difference is tieed up into residual vector afterwards, k d, which is tieed up residual vector, is integrated into k × d dimension matrixes, as VLAD code books.
Step 10, the VLAD code books generated according to step 5 and 9 carry out similarity measurements to query image and database images
Amount, and export retrieval result.
Wherein, the method for expansion process is in step 2 and 7:Using the central point of structural element as anchor point, by structural element
Anchor point be located in first location of pixels of image and start scan image.By pixel in the covered image-region of structural element
Maximum of intensity replaces the intensity value of anchor point position pixel in image, and it is next that structural element is translated to processing image on the image
Pixel is until structural element scans entire image.
Spatial pixel intensity feature extracting method is in step 3 and 8:With the pixel intensity value and center pixel in neighborhood
Point intensity value forms spatial pixel intensity feature vector to describe central pixel point jointly.
The method of generation VLAD code books is in step 5 and 9:
Sub-step 101, the spatial pixel intensity feature of image is indicated with vector x in database, and vector dimension d, k is poly-
Ith cluster center c in class centeriIt indicates, cluster centre collection shares Cl expressions;
The feature of sub-step 102, query image and the extraction of every width database images has been divided into k classes, every width database diagram
As belonging to cluster centre c in imageiCharacter subset be expressed as:
Sub-step 103 makes the difference the cluster centre of all characteristic points and this feature subset in each character subset, then tires out
All differences are added to generate the residual vector v of d dimensionsi, it is expressed as:
The residual vector calculated all cluster centres is integrated into the vectorial V of k × d dimensions by sub-step 104,
Expression formula is:
Sub-step 105 carries out PCA dimension-reduction treatment to vectorial V;
Sub-step 106 carries out L to the vectorial V of dimension-reduction treatment2Normalized:
By above step, VLAD code books have just been obtained.
Step 10 specifically includes following methods:By the VLAD code books V of query imageqWith the VLAD code books V of database imagesd
Calculate Euclidean distance:
dist(Vq,Vd)=| | Vq-Vd||2 (5)
Ascending sort, selection and query image are carried out according to the query image acquired and all database images Euclidean distances
It is returned as retrieval result image apart from first five shortest width image.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, the present invention can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (5)
1. the medical image search method based on geometrical constraint and spatial pixel intensity, which is characterized in that this method includes following
Step:
Step 1, reading database image;
Step 2, the image expansion structural parameters p according to setting creates structural element and is expanded to the database images of reading
Processing;
Step 3, the spatial pixel intensity that the database images Jing Guo expansion process are extracted according to the geometrical constraint parameter n of setting is special
Sign, is used in combination d dimensional vectors to indicate;
Step 4, the cluster centre number k according to setting carries out K-means clusters to the spatial pixel intensity feature of extraction, raw
At k cluster centre;
Step 5, it is that every width database images generate VLAD code books:The k cluster centre generated according to step 4 is by database images
In all spatial pixel intensity features be divided into k classes, the features of all same cluster centres and the cluster centre will be belonged to
The cumulative d that obtains of difference is tieed up into residual vector after making the difference, k d residual vector, which is integrated into k × d, ties up matrix, as VLAD code books;
Step 6, input inquiry image;
Step 7, it according to parameter p, creates structural element and expansion process is carried out to query image;
Step 8, the spatial pixel intensity feature of the query image according to the n extractions of geometrical constraint parameter Jing Guo expansion process, is used in combination d
Dimensional vector indicates;
Step 9, it is that query image generates VLAD code books:The k cluster centre generated according to step 4 will be all in query image
Spatial pixel intensity feature is divided into k classes, will after the feature for belonging to all same cluster centres and the cluster centre are made the difference
Difference is cumulative to obtain d dimension residual vectors, and k d, which is tieed up residual vector, is integrated into k × d dimension matrixes, as VLAD code books;
Step 10, the VLAD code books generated according to step 5 and 9 carry out similarity measurement to query image and database images, and
Export retrieval result.
2. the medical image search method based on geometrical constraint and spatial pixel intensity, feature exist as described in claim 1
In the method for expansion process is in step 2 and 7:Using the central point of structural element as anchor point, the anchor point of structural element is positioned
Start scan image in first location of pixels of image, by the maximum of intensity of pixel in the covered image-region of structural element
Replace image in anchor point position pixel intensity value, by structural element on the image translate processing the next pixel of image up to
Structural element scans entire image.
3. the medical image search method based on geometrical constraint and spatial pixel intensity, feature exist as described in claim 1
In spatial pixel intensity feature extracting method is in step 3 and 8:With in neighborhood pixel intensity value and central pixel point it is strong
Angle value forms spatial pixel intensity feature vector to describe central pixel point jointly.
4. the medical image search method based on geometrical constraint and spatial pixel intensity, feature exist as described in claim 1
In the method for generating VLAD code books in step 5 and 9 is:
Sub-step 101, the spatial pixel intensity feature of image is indicated with vector x in database, vector dimension d, in k cluster
Ith cluster center c in the heartiIt indicates, cluster centre collection shares Cl expressions;
The feature of sub-step 102, query image and the extraction of every width database images has been divided into k classes, every width database images figure
Belong to cluster centre c as iniCharacter subset be expressed as:
Sub-step 103 makes the difference the cluster centre of all characteristic points and this feature subset in each character subset, and then add up institute
There is difference to generate the residual vector v of d dimensionsi, it is expressed as:
The residual vector calculated all cluster centres is integrated into the vectorial V of k × d dimensions, expression by sub-step 104
Formula is:
Sub-step 105 carries out PCA dimension-reduction treatment to vectorial V;
Sub-step 106 carries out L to the vectorial V of dimension-reduction treatment2Normalized:
By above step, VLAD code books have just been obtained.
5. the medical image search method based on geometrical constraint and spatial pixel intensity, feature exist as claimed in claim 4
In step 10 specifically includes following methods:By the VLAD code books V of query imageqWith the VLAD code books V of database imagesdCalculate Europe
Family name's distance:
dist(Vq,Vd)=| | Vq-Vd||2 (5)
Ascending sort, selection and query image distance are carried out according to the query image acquired and all database images Euclidean distances
First five shortest width image is returned as retrieval result image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810496727.1A CN108806774B (en) | 2018-05-22 | 2018-05-22 | Medical image retrieval method based on geometric constraint and spatial pixel intensity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810496727.1A CN108806774B (en) | 2018-05-22 | 2018-05-22 | Medical image retrieval method based on geometric constraint and spatial pixel intensity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108806774A true CN108806774A (en) | 2018-11-13 |
CN108806774B CN108806774B (en) | 2022-02-01 |
Family
ID=64092820
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810496727.1A Expired - Fee Related CN108806774B (en) | 2018-05-22 | 2018-05-22 | Medical image retrieval method based on geometric constraint and spatial pixel intensity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108806774B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104216949A (en) * | 2014-08-13 | 2014-12-17 | 中国科学院计算技术研究所 | Method and system for expressing clustering of image features by fusion of space information |
CN104951562A (en) * | 2015-07-08 | 2015-09-30 | 天云融创数据科技(北京)有限公司 | Image retrieval method based on VLAD (vector of locally aggregated descriptors) dual self-adaptation |
CN106204545A (en) * | 2016-06-28 | 2016-12-07 | 南方医科大学 | A kind of based on region division and the medical science lesion image feature representation method of Fisher vector |
US20170262478A1 (en) * | 2014-09-09 | 2017-09-14 | Thomson Licensing | Method and apparatus for image retrieval with feature learning |
CN107527058A (en) * | 2017-07-25 | 2017-12-29 | 北京理工大学 | A kind of image search method based on weighting local feature Aggregation Descriptor |
-
2018
- 2018-05-22 CN CN201810496727.1A patent/CN108806774B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104216949A (en) * | 2014-08-13 | 2014-12-17 | 中国科学院计算技术研究所 | Method and system for expressing clustering of image features by fusion of space information |
US20170262478A1 (en) * | 2014-09-09 | 2017-09-14 | Thomson Licensing | Method and apparatus for image retrieval with feature learning |
CN104951562A (en) * | 2015-07-08 | 2015-09-30 | 天云融创数据科技(北京)有限公司 | Image retrieval method based on VLAD (vector of locally aggregated descriptors) dual self-adaptation |
CN106204545A (en) * | 2016-06-28 | 2016-12-07 | 南方医科大学 | A kind of based on region division and the medical science lesion image feature representation method of Fisher vector |
CN107527058A (en) * | 2017-07-25 | 2017-12-29 | 北京理工大学 | A kind of image search method based on weighting local feature Aggregation Descriptor |
Non-Patent Citations (1)
Title |
---|
李清亮: "图像检索中判别性增强研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN108806774B (en) | 2022-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dou et al. | Pnp-adanet: Plug-and-play adversarial domain adaptation network at unpaired cross-modality cardiac segmentation | |
Ali et al. | Brain tumour image segmentation using deep networks | |
Li et al. | Lung nodule detection with deep learning in 3D thoracic MR images | |
Jiang et al. | Learning-based automatic breast tumor detection and segmentation in ultrasound images | |
CN108776962A (en) | A method of the structure good pernicious prediction model of lung neoplasm | |
He et al. | Automatic magnetic resonance image prostate segmentation based on adaptive feature learning probability boosting tree initialization and CNN-ASM refinement | |
CN109886135A (en) | A kind of low resolution face identification method, device and storage medium | |
Fan et al. | Lung nodule detection based on 3D convolutional neural networks | |
CN113506310A (en) | Medical image processing method and device, electronic equipment and storage medium | |
Casanova et al. | Texture analysis using fractal descriptors estimated by the mutual interference of color channels | |
Balaji et al. | Medical image analysis with deep neural networks | |
Moradi et al. | A hybrid learning approach for semantic labeling of cardiac CT slices and recognition of body position | |
Zhang et al. | Application of deep learning method on ischemic stroke lesion segmentation | |
Ibragimov et al. | Accurate landmark-based segmentation by incorporating landmark misdetections | |
Swaraja et al. | Segmentation and detection of brain tumor through optimal selection of integrated features using transfer learning | |
Lei et al. | Deep learning architecture design for multi-organ segmentation | |
Zhang et al. | 3D brain glioma segmentation in MRI through integrating multiple densely connected 2D convolutional neural networks | |
Suresh et al. | Optimization and Deep Learning–Based Content Retrieval, Indexing, and Metric Learning Approach for Medical Images | |
Kekre et al. | Detection of tumor in MRI using vector quantization segmentation | |
Hussain et al. | A comparative analysis of efficient CNN-based brain tumor classification models | |
Kamencay et al. | 3D image reconstruction from 2D CT slices | |
Rehman et al. | Diverse and discrimintative features based breast cancer detection using digital mammography | |
CN108806774A (en) | Medical image search method based on geometrical constraint and spatial pixel intensity | |
CN107871110B (en) | A kind of pedestrian target recognition methods based on Multi-scale model correlation | |
Zamzmi et al. | Trilateral attention network for real-time medical image segmentation |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220201 |
|
CF01 | Termination of patent right due to non-payment of annual fee |