CN103593655A - Method and system for identifying wireless capsule endoscope images - Google Patents
Method and system for identifying wireless capsule endoscope images Download PDFInfo
- Publication number
- CN103593655A CN103593655A CN201310589062.6A CN201310589062A CN103593655A CN 103593655 A CN103593655 A CN 103593655A CN 201310589062 A CN201310589062 A CN 201310589062A CN 103593655 A CN103593655 A CN 103593655A
- Authority
- CN
- China
- Prior art keywords
- image
- impalpable
- capsule endoscope
- mentioned
- service
- 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
Images
Landscapes
- Endoscopes (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method for identifying capsule endoscope images. The method comprises the following steps that digestive tract images of patients are obtained; the obtained images are preprocessed; a lacuna curve chart under HSV space is drawn for the preprocessed images, and a threshold value is set; the images are screened and classified through the set threshold value. The invention further relates to a system for identifying the capsule endoscope images. According to the method and system, the workload of a doctor can be reduced, and identifying accuracy is improved.
Description
Technical field
The present invention relates to a kind of Wireless capsule endoscope image-recognizing method and system.
Background technology
Alimentary canal mucous membrane disease and the alimentary canal canceration further causing are thus one of maximum killer of national health (account for the whole Cancer Mortalities of China 60～70%).According to the statistics of American Cancer Society (American Cancer Society), show, early detection and diagnosis that alimentary canal mucous membrane knurl becomes (neoplasia metastasis) are the key factors that reduces alimentary canal canceration mortality ratio (especially intestinal cancer): if treatment measure is found and taked to the commitment that intestinal cancer patient becomes in knurl, five-year survival rate can surpass 90% conventionally; If fail to find in early days but the middle and advanced stage of developing as one pleases, patient's five-year survival rate only has less than 10%.According to tradition, doctor need to insert in patient body and observe alimentary canal inner case or carry out biopsy by optical fiber type endoscope, to detect pathology and to determine the measure that need to take.Yet due to the physical limitation of optical fiber type endoscope, both for doctor's operation has brought inconvenience, also caused patient's misery, even existed endoscope and wear out the danger that intestines wall causes infection or death.Therefore, many patients are because frightened abandoning checks, this prevention and early treatment for the high disease of digestive tract of the incidences of disease such as cancer of the esophagus, cancer of the stomach, intestinal cancer (the especially unapproachable position of the optical fiber type such as small intestine, duodenum endoscope) is very unfavorable.
At present clinically occur that a kind of low-power consumption can pinpoint multi-functional capsule endoscope above, it provides a kind of miniaturization, no pain, digestive tract examining mode easily.Patient's water as taking medicine is swallowed capsule, it is along with stomach and intestine muscle is wriggled, by built-in micro-camera, record the pathological image in alimentary canal, and image is shown to doctor provides foundation for its diagnosis, but because capsule endoscope is in vivo by intestines peristalsis motion, often encounter obtain image blurring, likely cause the unintelligible and Accurate Diagnosis of having no idea of pathological area area image, for capsule endoscope image, be difficult to the accurately problem of identification, also there is no at present special recognition methods, major part is to identify by doctor's naked eyes, coordinate denoising and the enhancing of image, can improve to a certain extent the accuracy rate of identification, but workload is huge, and artificial identification is difficult to avoid false retrieval and undetected, bring certain difficulty to the diagnosis of disease.
Summary of the invention
In view of this, be necessary to provide a kind of Wireless capsule endoscope image-recognizing method and system.
The invention provides a kind of Wireless capsule endoscope image-recognizing method, the method comprises the steps: that a. obtains patient's alimentary canal image; B. the image obtaining is carried out to pre-service; C. above-mentioned pretreated image is done to lacuna curve map the setting threshold under HSV space; D. by the threshold value of setting, above-mentioned image is carried out to sifting sort.
Wherein, described pre-service comprises: image denoising is processed and image enhancement processing.
Described classifies and refers to described image to be divided into image, the impalpable image of normal image, easily identification above-mentioned image.
Described method also comprises: e. returns to b for described impalpable image and again processes, and the image of easily identification is therefrom separated.
The present invention also provides a kind of Wireless capsule endoscope image identification system, comprises acquisition module, processing module and the screening module of mutual electric connection, wherein: described acquisition module is used for obtaining patient's alimentary canal image; Described processing module is used for the image obtaining to carry out pre-service, and above-mentioned pretreated image is done to lacuna curve map the setting threshold under HSV space; Described screening module is for carrying out sifting sort by the threshold value of setting to above-mentioned image.
Wherein, described pre-service comprises: image denoising is processed and image enhancement processing.
Described classifies and refers to described image to be divided into image, the impalpable image of normal image, easily identification above-mentioned image.
Described processing module is also for carrying out pre-service again for described impalpable image, and does lacuna curve map setting threshold under HSV space.
Described screening module also for from described impalpable image by easily identification separation of images out.
Wireless capsule endoscope image-recognizing method of the present invention and system, having solved endoscopic images needs artificial cognition, and the low problem of accuracy rate, by effective Images Classification, makes the observation work of image become in order simple, and has avoided undetected and false retrieval.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of Wireless capsule endoscope image-recognizing method of the present invention;
Fig. 2 is the hardware structure figure of Wireless capsule endoscope image identification system of the present invention.
Embodiment
Below in conjunction with drawings and the specific embodiments, the present invention is further detailed explanation.
Consulting shown in Fig. 1, is the operation process chart of Wireless capsule endoscope image-recognizing method of the present invention preferred embodiment.
Step S401, obtains patient's alimentary canal image.Particularly, by Wireless capsule endoscope, patient's alimentary canal is taken pictures, to obtain the image in patient's alimentary canal.
Step S402, carries out denoising and strengthens pre-service the image obtaining, for processing and the screening in later stage are prepared.Particularly, the described image obtaining is carried out respectively denoising and strengthens processing, to improve the resolution of image.
Step S403, does the lacuna curve map under HSV space to above-mentioned pretreated image, and setting threshold.It is more accurate that in described HSV, three passages participate in the result that the result of identification participates in identification than single channel simultaneously, and described three passages comprise: passage H, passage S, passage V.Wherein, passage H represents form and aspect, and passage S represents saturation degree, and passage V represents lightness.A large amount of practical experiences show, normal image, the image of easily identification, the lacuna curve map under impalpable image three class image HSV spaces differ 2 percentage points of left and right, therefore can well setting threshold.
Step S404, carries out HSV space lacuna curve by the threshold value of setting to above-mentioned image and screens, and described image is divided three classes: i.e. image, the impalpable image of normal image, easily identification.And described normal image is given up, by the image of described easy identification and described impalpable separation of images out, the image of described easy identification is directly presented to doctor and is observed, and does not need to process again.
Step S405, returns to step S402 for described impalpable image and again processes, and by the separation of images of easily identification out, remaining impalpable image no longer has researching value, gives up.
Consulting shown in Fig. 2, is the hardware structure figure of Wireless capsule endoscope image identification system of the present invention.This system comprises acquisition module, processing module and the screening module of mutual electric connection.
Described acquisition module is used for obtaining patient's alimentary canal image.Particularly, described acquisition module is taken pictures to patient's alimentary canal by Wireless capsule endoscope, to obtain the image in patient's alimentary canal.
Described processing module is for the image obtaining being carried out to denoising and strengthening pre-service, for processing and the screening in later stage are prepared.Particularly, described processing module carries out respectively denoising and strengthens processing to the described image obtaining, to improve the resolution of image.
Described processing module is also for above-mentioned pretreated image is done to the lacuna curve map under HSV space, and setting threshold.It is more accurate that in described HSV, three passages participate in the result that the result of identification participates in identification than single channel simultaneously, and described three passages comprise: passage H, passage S, passage V.Wherein, passage H represents form and aspect, and passage S represents saturation degree, and passage V represents lightness.A large amount of practical experiences show, normal image, the image of easily identification, the lacuna curve map under impalpable image three class image HSV spaces differ 2 percentage points of left and right, therefore can well setting threshold.
Described screening module is screened for above-mentioned image being carried out to HSV space lacuna curve by the threshold value of setting, and described image is divided three classes: i.e. image, the impalpable image of normal image, easily identification.Described screening module is also for described normal image is given up, and by the image of described easy identification and described impalpable separation of images out, the image of described easy identification is directly presented to doctor and observed, and does not need to process again.
Described processing module is also for carrying out denoising again for described impalpable image and strengthening pre-service, and does lacuna curve map the setting threshold under HSV space.
Described screening module is also for from described impalpable image by the separation of images of easily identification out, and remaining impalpable image no longer has researching value, gives up.
Although the present invention is described with reference to current preferred embodiments; but those skilled in the art will be understood that; above-mentioned preferred embodiments is only used for illustrating the present invention; not be used for limiting protection scope of the present invention; any within the spirit and principles in the present invention scope; any modification of doing, equivalence replacement, improvement etc., within all should being included in the scope of the present invention.
Claims (9)
1. a Wireless capsule endoscope image-recognizing method, is characterized in that, the method comprises the steps:
A. obtain patient's alimentary canal image;
B. the image obtaining is carried out to pre-service;
C. above-mentioned pretreated image is done to the lacuna curve map under HSV space, and setting threshold;
D. by the threshold value of setting, above-mentioned image is carried out to sifting sort.
2. the method for claim 1, is characterized in that, described pre-service comprises: image denoising is processed and image enhancement processing.
3. the method for claim 1, is characterized in that, described classifies and refer to described image to be divided into image, the impalpable image of normal image, easily identification above-mentioned image.
4. method as claimed in claim 3, is characterized in that, described method also comprises:
E. for described impalpable image, return to step b and again process, the image of easily identification is therefrom separated.
5. a Wireless capsule endoscope image identification system, is characterized in that, this system comprises acquisition module, processing module and the screening module of mutual electric connection, wherein:
Described acquisition module is used for obtaining patient's alimentary canal image;
Described processing module is used for the image obtaining to carry out pre-service, and above-mentioned pretreated image is done to the lacuna curve map under HSV space, and setting threshold;
Described screening module is for carrying out sifting sort by the threshold value of setting to above-mentioned image.
6. system as claimed in claim 5, is characterized in that, described pre-service comprises: image denoising is processed and image enhancement processing.
7. system as claimed in claim 5, is characterized in that, described classifies and refer to described image to be divided into image, the impalpable image of normal image, easily identification above-mentioned image.
8. system as claimed in claim 7, is characterized in that, described processing module is also for carrying out pre-service again for described impalpable image, and does lacuna curve map setting threshold under HSV space.
9. system as claimed in claim 8, is characterized in that, described screening module also for from described impalpable image by easily identification separation of images out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310589062.6A CN103593655B (en) | 2013-11-20 | 2013-11-20 | Wireless capsule endoscope image-recognizing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310589062.6A CN103593655B (en) | 2013-11-20 | 2013-11-20 | Wireless capsule endoscope image-recognizing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103593655A true CN103593655A (en) | 2014-02-19 |
| CN103593655B CN103593655B (en) | 2017-08-22 |
Family
ID=50083787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310589062.6A Active CN103593655B (en) | 2013-11-20 | 2013-11-20 | Wireless capsule endoscope image-recognizing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103593655B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767365A (en) * | 2017-09-21 | 2018-03-06 | 华中科技大学鄂州工业技术研究院 | A kind of endoscopic images processing method and system |
| CN110991337A (en) * | 2019-12-02 | 2020-04-10 | 山东浪潮人工智能研究院有限公司 | Vehicle detection method based on self-adaptive double-path detection network |
| CN113081075A (en) * | 2021-03-09 | 2021-07-09 | 武汉大学 | Magnetic control capsule with active biopsy and drug delivery functions |
| CN113808137A (en) * | 2021-11-19 | 2021-12-17 | 武汉楚精灵医疗科技有限公司 | Method, device, equipment and storage medium for screening image map of upper gastrointestinal endoscope |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120274743A1 (en) * | 2010-11-08 | 2012-11-01 | Olympus Medical Systems Corp. | Image display device and capsule endoscope system |
| CN102973231A (en) * | 2011-07-29 | 2013-03-20 | 奥林巴斯株式会社 | Image processing device, image processing method and image processing program |
| CN103281951A (en) * | 2011-01-28 | 2013-09-04 | 奥林巴斯医疗株式会社 | Capsule endoscope system |
-
2013
- 2013-11-20 CN CN201310589062.6A patent/CN103593655B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120274743A1 (en) * | 2010-11-08 | 2012-11-01 | Olympus Medical Systems Corp. | Image display device and capsule endoscope system |
| CN103281951A (en) * | 2011-01-28 | 2013-09-04 | 奥林巴斯医疗株式会社 | Capsule endoscope system |
| CN102973231A (en) * | 2011-07-29 | 2013-03-20 | 奥林巴斯株式会社 | Image processing device, image processing method and image processing program |
Non-Patent Citations (3)
| Title |
|---|
| VASILEIOS S.CHARISIS ET AL: "capsule endscopy image analysis using texture information from various colour models", 《COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE》 * |
| 孙宇千 等: "胶囊内窥镜冗余图像数据自动筛选方法", 《计算机应用研究》 * |
| 张栋冰 等: "胶囊内镜绒毛图像自动检测方法", 《计算机工程与应用》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767365A (en) * | 2017-09-21 | 2018-03-06 | 华中科技大学鄂州工业技术研究院 | A kind of endoscopic images processing method and system |
| CN110991337A (en) * | 2019-12-02 | 2020-04-10 | 山东浪潮人工智能研究院有限公司 | Vehicle detection method based on self-adaptive double-path detection network |
| CN110991337B (en) * | 2019-12-02 | 2023-08-25 | 山东浪潮科学研究院有限公司 | Vehicle detection method based on self-adaptive two-way detection network |
| CN113081075A (en) * | 2021-03-09 | 2021-07-09 | 武汉大学 | Magnetic control capsule with active biopsy and drug delivery functions |
| CN113808137A (en) * | 2021-11-19 | 2021-12-17 | 武汉楚精灵医疗科技有限公司 | Method, device, equipment and storage medium for screening image map of upper gastrointestinal endoscope |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103593655B (en) | 2017-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107767365A (en) | A kind of endoscopic images processing method and system | |
| WO2021036863A1 (en) | Deep learning-based diagnosis assistance system for early digestive tract cancer and examination apparatus | |
| JP2020073081A (en) | Image diagnosis assistance apparatus, learned model, image diagnosis assistance method, and image diagnosis assistance program | |
| US7684599B2 (en) | System and method to detect a transition in an image stream | |
| Zhou et al. | Polyp detection and radius measurement in small intestine using video capsule endoscopy | |
| EP1769729B1 (en) | System and method for in-vivo feature detection | |
| Pogorelov et al. | Deep learning and hand-crafted feature based approaches for polyp detection in medical videos | |
| JP5041645B2 (en) | Encapsulated medical imaging device | |
| JP4615963B2 (en) | Capsule endoscope device | |
| CN107145840B (en) | Endoscope expert diagnosis knowledge embedded computer aided WCE sequence image data identification method | |
| CN112789686A (en) | Device and method for diagnosing stomach pathological changes by deep learning of stomach endoscope images | |
| Riegler et al. | Eir—efficient computer aided diagnosis framework for gastrointestinal endoscopies | |
| US20130002842A1 (en) | Systems and Methods for Motion and Distance Measurement in Gastrointestinal Endoscopy | |
| US20090196495A1 (en) | Image processing apparatus, image processing method and image processing program | |
| EP1997076A2 (en) | Cascade analysis for intestinal contraction detection | |
| EP2305091A1 (en) | Image processing apparatus, image processing program, and image processing method | |
| CN103593655A (en) | Method and system for identifying wireless capsule endoscope images | |
| JP2017534322A (en) | Diagnostic mapping method and system for bladder | |
| EP3682791B1 (en) | Medical image processing device | |
| CN111839428A (en) | Method for improving detection rate of colonoscope adenomatous polyps based on deep learning | |
| US20230301503A1 (en) | Artificial intelligence-based gastroscopic image analysis method | |
| Mackiewicz | Capsule endoscopy-state of the technology and computer vision tools after the first decade | |
| CN116542883B (en) | Magnetic control capsule gastroscope image focus mucosa enhancement system | |
| CN108937871A (en) | A kind of alimentary canal micro-optics coherence tomography image analysis system and method | |
| Charisis et al. | Enhanced ulcer recognition from capsule endoscopic images using texture analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |