CN101441658A - Search method and system facing to radiation image in PACS database based on content - Google Patents
Search method and system facing to radiation image in PACS database based on content Download PDFInfo
- Publication number
- CN101441658A CN101441658A CNA2008102015487A CN200810201548A CN101441658A CN 101441658 A CN101441658 A CN 101441658A CN A2008102015487 A CNA2008102015487 A CN A2008102015487A CN 200810201548 A CN200810201548 A CN 200810201548A CN 101441658 A CN101441658 A CN 101441658A
- Authority
- CN
- China
- Prior art keywords
- image
- report
- radiodiagnosis
- pacs
- module
- 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
Abstract
The invention discloses a content-based retrieval method and a content-based retrieval system facing radiographs in a PACS database. The content-based retrieval to the radiographs is realized by associating a radiodiagnosis report in a radio information system with the radiographs in the PACS database, establishing the reverse index of the radiodiagnosis report and a feature index library of the radiographs, and then using a two-phase search algorithm. The retrieval method, by effectively integrating text retrieval technology and content-based image retrieval technology, overcomes the defect that the prior content-based image retrieval technology is not suitable for large-scale image databases, alleviates the semantic gap in the prior content-based image retrieval technology to a certain extent, and has high application value.
Description
Technical field
The invention belongs to medical information technology and information retrieval technique field, be specifically related to a kind of in the PACS database content-based retrieval method and system of radiation image.
Background technology
Medical image information is learned and engineering key in application core system is medical image filing and communication system (PACS).The collection of PACS collection medical image, communication, processing, storing and be shown in one, is that hospital realizes digitized key message system and technical support platform.Along with the development of medical imaging technology and popularizing of medical information system, one the dept. of radiology of modernized hospital can produce a large amount of radiologic medicine images every day, these images are important objective basis that the doctor carries out clinical diagnosis, state of an illness tracking, surgical planning, prognosis research, antidiastole.The diversity of medical image and importance are demanded medical image search method efficiently urgently, to maximally utilise the information that medical image is provided.CBIR (Content-base Image Retrieval, CBIR) technology has caused concern widely in recent years, its purpose is from the self-contained content of image, associated image in the searching database, its target are that requirement is calculated function and replaced human eye to select the image similar to " master drawing " and feed back to the user from large nuber of images.
CBIR system now generally all adopts following method to retrieve: at first image is carried out feature extraction, obtain describing the proper vector of picture material, calculate distance between the proper vector of image in image to be retrieved and the database according to Euclid distance, related coefficient isometry method then, finally some images of selected distance minimum are exported as result for retrieval.The greatest difficulty that this search method faces is that after image data base reached certain scale, the distance calculation between the characteristics of image vector was very consuming time, and this makes that the CBIR technology can't practicability in extensive image data base.In addition, the function that wants real anthropomorphic dummy's recognition image needs the effective communication between Image Visual Feature and image, semantic feature, and the current feature that is used for image retrieval mainly is some comparatively visual signatures of low layer (as: color, shape, texture etc.), also exists huge " semantic wide gap " between the employed high-level concept of these low-level features and user inquiring (as: Radiologic imaging of focus or pathological diagnosis etc.).Though medically set up many CBIR system at present, but these systems mostly are in experimental study or clinical assessment stage, and the amount of images that these systems stored and managed very limited (several thousand to several ten thousand width of cloth), almost neither one really is applied among the routine work of clinical diagnosis or treatment.
Summary of the invention
The invention provides a kind of in the PACS database content-based retrieval method and system of radiation image, be not suitable for the defective of extensive image data base to solve traditional C BIR technology, and can alleviate " semantic wide gap " phenomenon in the traditional C BIR technology to a certain extent.
The technical solution adopted in the present invention is as follows:
A kind of in the PACS database content-based retrieval method of radiation image, it is characterized in that: integrated by between radiology information system (RIS) and PACS, carry out related with radiation image among the PACS radiodiagnosis among RIS report, and set up the inverted index of radiodiagnosis report and the aspect indexing of radiation image respectively, use two stage searching algorithms that query requests is carried out CBIR then; An effective query requests is made up of example images and example images related text descriptor at least, wherein example images is a width of cloth PACS image of user's appointment, and example images related text descriptor is that the Radiologic imaging of example images is or/and possible pathological diagnosis result's text description;
The detailed process of two stage searching algorithms is: the phase one, use image to be checked the iconography finding or/and the description text of possible pathological diagnosis in radiodiagnosis report inverted index, retrieve, this stage can obtain and image to be checked relevant one group of radiodiagnosis report tabulation on Radiologic imaging or pathological diagnosis, be called the candidate search result set, the report in the candidate search result set is according to the relevancy ranking in the text vector spatial model; Subordinate phase, in the characteristics of image index database, extract the feature of the relevant PACS image collection of reporting in the candidate search result set, image and the distance of image to be checked in characteristic vector space during computed image is gathered then, and the distance that foundation calculates returns to the user with net result then to the rearrangement of candidate search result set.
Described in the PACS database content-based retrieval method of radiation image, it is characterized in that: image during the calculating chart image set closes in the described subordinate phase algorithm and the distance of image to be checked in characteristic vector space, and the distance that foundation calculates returns to the user with net result then from small to large to the rearrangement of candidate search result set.
Described in the PACS database content-based retrieval method of radiation image, it is characterized in that: query requests also comprises basic identity information of patient and image check relevant information.
A kind of in the PACS database content-based retrieval system of radiation image, owing to implement aforesaid method, it is characterized in that: it is made up of image display workstation, query interface module, radiodiagnosis report index module, image characteristics extraction module, radiodiagnosis report retrieval module, images match module, characteristics of image database management module, radiodiagnosis report inverted index, characteristics of image and breviary picture library, radiodiagnosis report database and PACS image data base; Wherein:
The image display workstation: the doctor uses the image display workstation to carry out area-of-interest selection, the input inquiry text of image selection, image and submits query requests to, and result for retrieval also shows in the image display workstation;
The query interface module: image display workstation and search engine carry out mutual interface module;
Radiodiagnosis report index module: the text index that is used for setting up the radiation report of RIS database;
Image characteristics extraction module: be used for the area-of-interest of PACS image or image is carried out feature extraction;
Radiodiagnosis report retrieval module: the text retrieval engine server of radiation report;
Images match module: be used for the similarity between the feature of computed image feature or interesting image regions;
Characteristics of image database management module: be used for feature, and image thumbnails manages to image or interesting image regions.
The present invention has following effect and advantage:
1. report that by the retrieval radiodiagnosis method of inverted index realizes the navigation to extensive PACS image data base, significantly reduce the quantity that needs to carry out the image that distance is calculated between proper vector in the one query process, feasible retrieval to extensive PACS image data base becomes possibility;
2. use radiodiagnosis report text retrieval technique to alleviate " semantic wide gap " phenomenon of CBIR to a certain extent.Because radiodiagnosis report is artificial understanding and description to radiation image, thus the keyword of radiodiagnosis in reporting than image low layer visual signature semantically more near people's search intention;
3. by to the effectively integrating of text retrieval technology and CBIR technology, give full play to the advantage of two kinds of technology, to reach the effect of learning from other's strong points to offset one's weaknesses.With respect to independently text searching method and CBIR method, search method of the present invention has the accuracy of more performance and Geng Gao.
Description of drawings
Fig. 1 is the block architecture diagram of an embodiment of the present invention system;
Fig. 2 is the process flow diagram of the inventive method retrieving.
Embodiment
The invention provides a kind of in the PACS database content-based retrieval method of radiation image.Integrated by between RIS and PACS, carry out related with radiation image among the PACS radiodiagnosis among RIS report, and set up the inverted index of radiodiagnosis report and the aspect indexing of radiation image respectively, use " search of two stages " algorithm that query requests is carried out CBIR then.An effective query requests is made up of example images and example images related text descriptor at least, wherein example images is a width of cloth PACS image of user's appointment, and example images related text descriptor is that the Radiologic imaging of example images is or/and possible pathological diagnosis result's text description.In addition, query requests can also comprise basic identity information of patient (patient's name, sex, date of birth etc.) and image check relevant information (checkout facility type, patient's inspection area etc.).
The detailed process of two stage searching algorithms is: the phase one, use image to be checked the iconography finding or/and the description text of possible pathological diagnosis in radiodiagnosis report inverted index, retrieve, this stage can obtain and image to be checked relevant one group of radiodiagnosis report tabulation on Radiologic imaging or pathological diagnosis, be called the candidate search result set, the report in the candidate search result set is according to the relevancy ranking in the text vector spatial model; Subordinate phase, in the characteristics of image index database, extract the feature of the relevant PACS image collection of reporting in the candidate search result set, image and the distance of image to be checked in characteristic vector space during computed image is gathered then, and the distance that foundation calculates returns to the user with net result then from small to large to the rearrangement of candidate search result set.
Below in conjunction with drawings and Examples the present invention is further specified.
As Fig. 1, this searching system is made up of image display workstation 100, query interface module 101, radiodiagnosis report index module 102, image characteristics extraction module 103, radiodiagnosis report retrieval module 104, images match module 105, characteristics of image database management module 106, radiodiagnosis report inverted index 107, characteristics of image and breviary picture library 108, radiodiagnosis report database 110 and PACS image data base 120.Wherein:
Image display workstation 100: the doctor uses the image display workstation to carry out area-of-interest selection, the input inquiry text of image selection, image and submits query requests to, and result for retrieval also shows in the image display workstation.
Query interface module 101: image display workstation and search engine carry out mutual interface module.
Radiodiagnosis report index module 102: the text index that is used for setting up the radiation report of RIS database.
Image characteristics extraction module 103: be used for the area-of-interest of PACS image or image is carried out feature extraction.
Radiodiagnosis report retrieval module 104: the text retrieval engine server of radiation report.
Images match module 105: be used for the similarity between computed image feature (the perhaps feature of interesting image regions).
Characteristics of image database management module 106: be used for feature, and image thumbnails manages to image or interesting image regions.
This system index process:
1, the doctor finish radiation image diagnosis report write task after, the feature extraction operation of image characteristics extraction module 103 carries out image or interesting image regions (possible mode comprises automatic extraction or manually extracts by the image display workstation), image characteristics extraction module then 103 is deposited the identification number of the radiodiagnosis report of the feature that extracts and image correspondence in characteristics of image and the breviary picture library 108, generate the thumbnail of image simultaneously and be saved in characteristics of image and breviary picture library 108 in;
2, image characteristics extraction module 103 sends the identification number of the radiodiagnosis report that need carry out text index to radiodiagnosis report index module 102;
3, radiodiagnosis report index module 102 receives behind the identification number of radiodiagnosis report and will set up text index for the content of the radiodiagnosis report of correspondence.
The retrieving of this system, as shown in Figure 2:
200, image display workstation 100 is committed to query interface module 101 with query requests;
210,101 pairs of query requests of query interface module are verified, if as query requests be invalid then carry out step 220, be effectively then carry out step 230 as if query requests;
220, query interface module 101 is returned bomp to image display workstation 100, and retrieving finishes;
230, query interface module 101 uses the retrieval in radiodiagnosis report inverted index 107 of radiodiagnosis report searching system 104 to describe the radiodiagnosis report that is complementary with the example images related text in the query requests, and the result that retrieval obtains is called the candidate search result set;
240,101 pairs of candidate search result sets of query interface module are verified, if the candidate search result set then carry out step 250 for empty (promptly finding the radiodiagnosis report of coupling), then carry out steps 260 if the candidate search result set is not empty;
250, query interface module 101 is returned empty search result set to image display workstation 100, and retrieving finishes;
260, query interface module 101 uses characteristics of image base management systems 106 to extract the feature and the thumbnail URL of the image that is associated with radiodiagnosis report in the candidate search result set;
270, query interface module 101 uses image matching system 105 calculated candidate Search Results to concentrate the associated images and the distance of image to be checked in characteristic vector space of radiodiagnosis report, and from small to large the candidate search result is sorted again according to the distance that calculates;
280, query interface module 101 is returned the final search result collection to image display workstation 100, and retrieving finishes.
Every result that the Search Results that the user finally obtains is concentrated is made up of two parts, a part is the text fragments with image to be checked relevant radiodiagnosis report on Radiologic imaging or pathological diagnosis, and another part is the thumbnail to image to be checked the most similar width of cloth PACS image on visual signature.
Claims (4)
1, a kind of in the PACS database content-based retrieval method of radiation image, it is characterized in that: integrated by between RIS and PACS, carry out related with radiation image among the PACS radiodiagnosis among RIS report, and set up the inverted index of radiodiagnosis report and the aspect indexing of radiation image respectively, use two stage searching algorithms that query requests is carried out CBIR then; An effective query requests is made up of example images and example images related text descriptor at least, wherein example images is a width of cloth PACS image of user's appointment, and example images related text descriptor is that the Radiologic imaging of example images is or/and possible pathological diagnosis result's text description;
The detailed process of two stage searching algorithms is: the phase one, use image to be checked the iconography finding or/and the description text of possible pathological diagnosis in radiodiagnosis report inverted index, retrieve, this stage can obtain and image to be checked relevant one group of radiodiagnosis report tabulation on Radiologic imaging or pathological diagnosis, be called the candidate search result set, the report in the candidate search result set is according to the relevancy ranking in the text vector spatial model; Subordinate phase, in the characteristics of image index database, extract the feature of the relevant PACS image collection of reporting in the candidate search result set, image and the distance of image to be checked in characteristic vector space during computed image is gathered then, and the distance that foundation calculates returns to the user with net result then to the rearrangement of candidate search result set.
2, according to claim 1 in the PACS database content-based retrieval method of radiation image, it is characterized in that: image during the calculating chart image set closes in the described subordinate phase algorithm and the distance of image to be checked in characteristic vector space, and the distance that foundation calculates returns to the user with net result then from small to large to the rearrangement of candidate search result set.
3, according to claim 1 and 2 in the PACS database content-based retrieval method of radiation image, it is characterized in that: query requests also comprises basic identity information of patient and image check relevant information.
4, a kind of in the PACS database content-based retrieval system of radiation image, because implement as claim 1 or 2 or 3 described methods, it is characterized in that: it is by image display workstation (100), query interface module (101), radiodiagnosis report index module (102), image characteristics extraction module (103), radiodiagnosis report retrieval module (104), images match module (105), characteristics of image database management module (106), radiodiagnosis report inverted index (107), characteristics of image and breviary picture library (108), radiodiagnosis report database (110) and PACS image data base (120) are formed; Wherein:
Image display workstation (100): the doctor uses the image display workstation to carry out area-of-interest selection, the input inquiry text of image selection, image and submits query requests to, and result for retrieval also shows in the image display workstation;
Query interface module (101): image display workstation and search engine carry out mutual interface module;
Radiodiagnosis report index module (102): the text index that is used for setting up the radiation report of RIS database;
Image characteristics extraction module (103): be used for the area-of-interest of PACS image or image is carried out feature extraction;
Radiodiagnosis report retrieval module (104): the text retrieval engine server of radiation report;
Images match module (105): be used for the similarity between the feature of computed image feature or interesting image regions;
Characteristics of image database management module (106): be used for feature, and image thumbnails manages to image or interesting image regions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008102015487A CN101441658A (en) | 2008-10-22 | 2008-10-22 | Search method and system facing to radiation image in PACS database based on content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008102015487A CN101441658A (en) | 2008-10-22 | 2008-10-22 | Search method and system facing to radiation image in PACS database based on content |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101441658A true CN101441658A (en) | 2009-05-27 |
Family
ID=40726093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2008102015487A Pending CN101441658A (en) | 2008-10-22 | 2008-10-22 | Search method and system facing to radiation image in PACS database based on content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101441658A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794355A (en) * | 2010-03-26 | 2010-08-04 | 中国人民解放军空军工程大学 | Computer extranuclear parallel computing method for electromagnetic radiation and scattering of electric large object |
| CN101794356A (en) * | 2010-03-26 | 2010-08-04 | 中国人民解放军空军工程大学 | Computer extranuclear computing method for electromagnetic radiation and scattering of electric large object |
| CN102194059A (en) * | 2011-05-24 | 2011-09-21 | 中国科学院上海技术物理研究所 | Visual indexing system for medical information system |
| CN102612696A (en) * | 2009-09-28 | 2012-07-25 | 皇家飞利浦电子股份有限公司 | Medical information system with report validator and report augmenter |
| CN102053963B (en) * | 2009-10-28 | 2012-08-08 | 沈阳工业大学 | Retrieval method of chest X-ray image |
| CN102682036A (en) * | 2011-03-18 | 2012-09-19 | 新奥特（北京）视频技术有限公司 | Non-editing based method and system for searching media assets |
| CN102682084A (en) * | 2012-04-11 | 2012-09-19 | 中国科学院上海光学精密机械研究所 | Image retrieval system based on HTM (hierarchical temporal memory) algorithm and image retrieval method thereof |
| CN106897395A (en) * | 2017-02-07 | 2017-06-27 | 青岛海信医疗设备股份有限公司 | A kind of method and device of the data message of inquiry DICOM images |
| CN107038325A (en) * | 2015-07-14 | 2017-08-11 | 浙江格林蓝德信息技术有限公司 | A kind of medical image PACS system and its inspection association management method |
| CN107092774A (en) * | 2017-03-10 | 2017-08-25 | 深圳华大智造科技有限公司 | A kind of method and device that reference information is provided |
| CN107341189A (en) * | 2017-06-09 | 2017-11-10 | 国政通科技股份有限公司 | A kind of indirect labor carries out the method and system of examination, classification and storage to image |
| WO2018129931A1 (en) * | 2017-01-13 | 2018-07-19 | 深圳开立生物医疗科技股份有限公司 | Method and system for screening navigation sections |
| CN112148831A (en) * | 2020-11-26 | 2020-12-29 | 广州华多网络科技有限公司 | Image-text mixed retrieval method and device, storage medium and computer equipment |
| CN109223034B (en) * | 2018-08-07 | 2021-10-26 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging method and ultrasonic imaging apparatus |
| CN115985509A (en) * | 2022-12-14 | 2023-04-18 | 广东省人民医院 | Medical imaging data retrieval system, method, device and storage medium |
-
2008
- 2008-10-22 CN CNA2008102015487A patent/CN101441658A/en active Pending
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102612696A (en) * | 2009-09-28 | 2012-07-25 | 皇家飞利浦电子股份有限公司 | Medical information system with report validator and report augmenter |
| CN102612696B (en) * | 2009-09-28 | 2017-05-17 | 皇家飞利浦电子股份有限公司 | Medical information system with report validator and report augmenter |
| CN102053963B (en) * | 2009-10-28 | 2012-08-08 | 沈阳工业大学 | Retrieval method of chest X-ray image |
| CN101794355A (en) * | 2010-03-26 | 2010-08-04 | 中国人民解放军空军工程大学 | Computer extranuclear parallel computing method for electromagnetic radiation and scattering of electric large object |
| CN101794356A (en) * | 2010-03-26 | 2010-08-04 | 中国人民解放军空军工程大学 | Computer extranuclear computing method for electromagnetic radiation and scattering of electric large object |
| CN101794356B (en) * | 2010-03-26 | 2011-09-07 | 中国人民解放军空军工程大学 | Computer extranuclear computing method for electromagnetic radiation and scattering of electric large object |
| CN101794355B (en) * | 2010-03-26 | 2011-11-09 | 中国人民解放军空军工程大学 | Computer extranuclear parallel computing method for electromagnetic radiation and scattering of electric large object |
| CN102682036A (en) * | 2011-03-18 | 2012-09-19 | 新奥特（北京）视频技术有限公司 | Non-editing based method and system for searching media assets |
| CN102194059A (en) * | 2011-05-24 | 2011-09-21 | 中国科学院上海技术物理研究所 | Visual indexing system for medical information system |
| CN102682084A (en) * | 2012-04-11 | 2012-09-19 | 中国科学院上海光学精密机械研究所 | Image retrieval system based on HTM (hierarchical temporal memory) algorithm and image retrieval method thereof |
| CN107038325B (en) * | 2015-07-14 | 2021-03-23 | 浙江格林蓝德信息技术有限公司 | Medical image PACS system and examination association management method thereof |
| CN107038325A (en) * | 2015-07-14 | 2017-08-11 | 浙江格林蓝德信息技术有限公司 | A kind of medical image PACS system and its inspection association management method |
| CN108305670A (en) * | 2017-01-13 | 2018-07-20 | 深圳开立生物医疗科技股份有限公司 | The method and system of screening navigation section |
| WO2018129931A1 (en) * | 2017-01-13 | 2018-07-19 | 深圳开立生物医疗科技股份有限公司 | Method and system for screening navigation sections |
| CN106897395B (en) * | 2017-02-07 | 2020-01-31 | 青岛海信医疗设备股份有限公司 | method and device for inquiring data information of DICOM image |
| CN106897395A (en) * | 2017-02-07 | 2017-06-27 | 青岛海信医疗设备股份有限公司 | A kind of method and device of the data message of inquiry DICOM images |
| CN107092774A (en) * | 2017-03-10 | 2017-08-25 | 深圳华大智造科技有限公司 | A kind of method and device that reference information is provided |
| CN107341189A (en) * | 2017-06-09 | 2017-11-10 | 国政通科技股份有限公司 | A kind of indirect labor carries out the method and system of examination, classification and storage to image |
| CN109223034B (en) * | 2018-08-07 | 2021-10-26 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging method and ultrasonic imaging apparatus |
| CN112148831A (en) * | 2020-11-26 | 2020-12-29 | 广州华多网络科技有限公司 | Image-text mixed retrieval method and device, storage medium and computer equipment |
| CN112148831B (en) * | 2020-11-26 | 2021-03-19 | 广州华多网络科技有限公司 | Image-text mixed retrieval method and device, storage medium and computer equipment |
| CN115985509A (en) * | 2022-12-14 | 2023-04-18 | 广东省人民医院 | Medical imaging data retrieval system, method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101441658A (en) | Search method and system facing to radiation image in PACS database based on content | |
| Demner-Fushman et al. | Design and development of a multimodal biomedical information retrieval system | |
| Oliveira et al. | Towards applying content-based image retrieval in the clinical routine | |
| El-Kwae et al. | Content-based retrieval in picture archiving and communication systems | |
| Remedios et al. | Classifying magnetic resonance image modalities with convolutional neural networks | |
| Bueno et al. | How to add content-based image retrieval capability in a PACS | |
| Ejaz et al. | An image-based multimedia database and efficient detection though features | |
| CN109885712A (en) | Lung neoplasm image search method and system based on content | |
| Pinapatruni et al. | Learning image representation from image reconstruction for a content-based medical image retrieval | |
| Rinaldi et al. | A content based image retrieval approach based on multiple multimedia features descriptors in e-health environment | |
| Traina et al. | Integrating images to patient electronic medical records through content-based retrieval techniques | |
| Jin et al. | Content and semantic context based image retrieval for medical image grid | |
| Alpkocak et al. | DEMIR at ImageCLEFMed 2011: Evaluation of Fusion Techniques for Multimodal Content-based Medical Image Retrieval. | |
| Gravina et al. | Developing a smart PACS: CBIR system using deep learning | |
| Berber et al. | DEMIR at ImageCLEFwiki 2011: Evaluating Different Weighting Schemes in Information Retrieval. | |
| Gupta et al. | Comparative Analysis of Image Retrieval Techniques in Cyberspace | |
| Antani et al. | Geographically distributed complementary content-based image retrieval systems for biomedical image informatics | |
| He et al. | Combining text retrieval and content-based image retrieval for searching a large-scale medical image database in an integrated RIS/PACS environment | |
| Atnafu et al. | Content-based and metadata retrieval in medical image database | |
| Liu et al. | Design and implementation of content-based medical image retrieval system on mammograms | |
| Li et al. | Computer-aided diagnosis of mammographic masses using geometric verification-based image retrieval | |
| Sannakki et al. | Memory learning framework for retrieval of neural objects | |
| Valente et al. | Content based retrieval Systems in a Clinical Context | |
| Yuan et al. | Diagnosis system of computer-aided brain MRI using content-based image retrieval | |
| Sun et al. | Building high dimensional imaging database for content based image search |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20090527 |