CN105678772A - Digital image processing method for varicose vein of lower limb - Google Patents
Digital image processing method for varicose vein of lower limb Download PDFInfo
- Publication number
- CN105678772A CN105678772A CN201610013856.1A CN201610013856A CN105678772A CN 105678772 A CN105678772 A CN 105678772A CN 201610013856 A CN201610013856 A CN 201610013856A CN 105678772 A CN105678772 A CN 105678772A
- Authority
- CN
- China
- Prior art keywords
- image
- ill
- processing method
- varicose veins
- image processing
- 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
- 210000003141 lower extremity Anatomy 0.000 title claims abstract description 41
- 206010046996 Varicose vein Diseases 0.000 title claims abstract description 24
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000003709 image segmentation Methods 0.000 claims abstract description 10
- 201000010099 disease Diseases 0.000 claims description 28
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 28
- 208000027185 varicose disease Diseases 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 4
- 238000003706 image smoothing Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 210000003414 extremity Anatomy 0.000 description 7
- 210000003462 vein Anatomy 0.000 description 5
- 238000000926 separation method Methods 0.000 description 4
- 210000004204 blood vessel Anatomy 0.000 description 3
- 208000024891 symptom Diseases 0.000 description 3
- 208000025865 Ulcer Diseases 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010992 reflux Methods 0.000 description 2
- 231100000397 ulcer Toxicity 0.000 description 2
- 206010010356 Congenital anomaly Diseases 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- 208000003251 Pruritus Diseases 0.000 description 1
- 208000034189 Sclerosis Diseases 0.000 description 1
- 206010041955 Stasis dermatitis Diseases 0.000 description 1
- 206010043189 Telangiectasia Diseases 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 210000003423 ankle Anatomy 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000019612 pigmentation Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 208000009056 telangiectasis Diseases 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 208000037997 venous disease Diseases 0.000 description 1
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
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- 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
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a digital image processing method for the varicose vein of a lower limb. According to the method, firstly, the illness image of the illness part of a patient is compared with a case image in a case image library, and then the illness part can be determined. Secondly, an illness region in the illness image is subjected to image segmentation, and the shape features and the texture features of the illness region are extracted. Thirdly, the shape features and the texture features are compared with a case image in a standard image library, and then are classified to a corresponding level. According to the technical scheme of the invention, the acquiring, processing and recognizing the images of illness parts, the levels of the illness parts can be accurately classified.
Description
Technical field
The present invention relates to digital image processing method, particularly to the digital image processing method of a kind of varicose veins of the lower extremity.
Background technology
In China, there are about 100,000,000 patients and suffer from varicose venous diseases of lower limbs. The annual neopathy rate of this disease is 0.5%～3.0%, and wherein veins festers about 1.5%. Although the sick less threat limbs survival of veins of lower extremity or threat to life, but there is the features such as PD slow, course of disease length, treatment difficulty, usually make patient lose work and mobility.
6 ranks that varicose veins of the lower extremity can be divided into according to clinical features: I level: suffering limb has visible telangiectasis, reticular veins, ankle flushing, suffering limb has obvious livid purple color or red blood vessel as seen, and this phase can be without obvious blood vessel enhancement symptom. II level: have obvious varicosis symptom, blood vessel enhancement is obvious, and suffering limb has the sensations such as tired, numb, tired, wooden. III level: varicosis develops to some extent, has edema to show, and obvious pain occurs. IV level: varicosis continues development, causes that the skin color of suffering limb changes, and clinical manifestation is for having pigmentation, stasis dermatitis and skin sclerosis etc. Suffering limb has significantly itch pain or pain present. V level: varicosis is serious, causes that skin color changes, be black and the ulcer (always rotten lower limb) healed more. VI level: varicosis is serious, skin color changes and the ulcer symptoms not healed that showing effect. It addition, varicosis grade is also relevant with the cause of disease (congenital, former, secondary), the region of anatomy (superficial veins of lower limb, Deep venou or traffic offshoot) and pathology pathogenesis (vein reflux, obstruction, reflux and obstruction coexist) etc.
Comprehensive yet with patient medical knowledge, to reasons such as cirsoid harm understanding are not enough, causes treatment not in time, and sb.'s illness took a turn for the worse, even severe patient life security. Thus, how to research and develop and a utilize the terminals such as mobile phone, flat board or PC that disease sites carries out shooting image, through automatically processing and identifying image, quickly and accurately ill image is carried out grade separation, becomes problem urgently to be resolved hurrily.
Summary of the invention
It is an object of the invention to, it is provided that the digital image processing method of a kind of varicose veins of the lower extremity.The present invention is by the acquisition of ill image, process and identification, carrying out grade separation to ill image quickly and accurately.
For solving above-mentioned technical problem, technical scheme provided by the invention is as follows: the digital image processing method of a kind of varicose veins of the lower extremity, comprises the following steps successively;
(1) set up the case image library of varicose veins of the lower extremity, and the case image in case image library is classified according to disease site and ill grade;
(2) the ill image of patient's disease sites is obtained;
(3) ill picture quality is judged, if judging qualified entrance step (4), if judging defective repetition step (2);
(4) ill image is contrasted with the case image in case image library, confirm disease site;
(5) affected areas in ill image is carried out image segmentation, extract affected areas shape facility and textural characteristics;
(6) shape facility and textural characteristics are contrasted with the individual features of the case image of corresponding disease site in standard picture storehouse, and be referred to corresponding grade.
In the digital image processing method of above-mentioned varicose veins of the lower extremity, in step (2), user points out according to human body lower limbs schematic diagram, overlaps gathering the disease sites profile with human body lower limbs schematic diagram, obtains ill image again through photographic head, photographing unit.
In the digital image processing method of aforesaid varicose veins of the lower extremity, in step (2), user, after obtaining ill image, selects the ill position at lower limb by legend or text prompt user.
In the digital image processing method of aforesaid varicose veins of the lower extremity, in step (3), ill picture quality is judged, and the object brightness to ill picture centre region and color characteristic judge.
In the digital image processing method of aforesaid varicose veins of the lower extremity, in step (5), first adopt image smoothing method that ill image carries out denoising, then adopt global threshold or OTSU that affected areas in ill image is carried out image segmentation.
In the digital image processing method of aforesaid varicose veins of the lower extremity, in step (5), described shape facility is boundary rectangle size, length-width ratio or circularity; Described textural characteristics is the feature of RBG or HIS component.
In the digital image processing method of aforesaid varicose veins of the lower extremity, in step (5), image segmentation is the pocket that ill image is divided into n × n, determines textural characteristics with the statistical value of the textural characteristics of n × n pocket.
Compared with prior art, the ill image of patient's disease sites is contrasted by the present invention with the case image in case image library, confirms disease site, then affected areas in ill image carries out image segmentation, extracts affected areas shape facility and textural characteristics; Shape facility and textural characteristics are contrasted with the case image of corresponding disease site in standard picture storehouse, is referred to corresponding grade. The present invention is by the acquisition of ill image, process and identification, thus easily, rapidly, accurately helping patient or medical personnel that focus is carried out grade separation.
Accompanying drawing explanation
Fig. 1 is the enforcement block diagram of the present invention;
Fig. 2 is disease site and affected areas schematic diagram.
Detailed description of the invention
Below in conjunction with embodiment, the present invention is further illustrated.
Embodiment: the digital image processing method of a kind of varicose veins of the lower extremity, as shown in Figure 1, comprises the following steps successively:
(1) in the terminals such as mobile phone, flat board or PC or remote server, set up the case image library of varicose veins of the lower extremity, and the case image in case image library is classified according to disease site and grade;Such as, the number positional N of definition lower limb, and divide 6 grades to classify according to the patient's condition degree focus, then set up 6 × N number of property data base and corresponding grader, feature in property data base can include shape facility and textural characteristics, grader can adopt the methods such as KNN, C4.5 decision tree, neutral net, support vector machine, degree of depth network, random forest to obtain 6 graders by training. When classifying, call data base and the grader of correspondence according to the disease sites of input.
(2) video camera of the terminals such as mobile phone, flat board or PC or the ill image (user's input picture) of photographing unit acquisition disease sites are utilized. The mode mode of input picture (judge whether be real-time acquisition) of ill image, execution step 2.1 is obtained according to Real-time Collection; According to importing or upload the mode shooting ill image, perform step 2.2;
2.1 provide human body lower limbs schematic diagram in the shooting picture of the terminals such as mobile phone, flat board or PC, and prompting gathers the profile of disease sites and human body lower limbs schematic diagram and overlaps, and user takes pictures according to operation.
2.2 users import to terminal or upload and shoot ill image, and terminal system selects the ill position at lower limb (system prompts user selection disease site) by legend or text prompt user.
(3) input picture quality and the concrete position of place lower limb are judged. First the object brightness of the affected areas of ill picture, color characteristic etc. are detected, it may be judged whether be suitable for image segmentation and process; Judge whether ill image has human body lower limbs feature (disease sites is automatically analyzed or confirms) simultaneously. Judgment rule can use the case picture in case image library to be obtained by the method for image procossing and machine learning. If it is not, prompting user, go to step (2). If so, step (4) is entered: judge lower limb position, affected area place. Disease site and affected areas can shown in Fig. 2.
(4) ill image is contrasted with the case image in case image library, confirm disease site. Determination methods: if user be by 2.1 obtain pictures, or in 2.2 designated pictures position, then system calling station determination methods confirms; If it is not, use system automatic decision position, and allow user mutual.
(5) area-of-interest in ill image (varicosis affected areas) is carried out image segmentation. The region being partitioned into is carried out shape facility and texture feature extraction (segmentation of disease site image and character selection and abstraction). After first adopting image smoothing method (such as the method such as mean filter, medium filtering) that image is carried out denoising, can adopt and based on the method such as global threshold, OTSU, affected area be split, extract affected areas shape facility (such as, boundary rectangle, length-width ratio, circularity etc.), overall and field color textural characteristics (such as, the statistical nature of RBG, HIS component). The extraction of textural characteristics, it is possible to be, by limbs actual ratio, ill image is divided into n × n pocket, describe affected areas feature with the statistical value of the textural characteristics of n × n pocket.
(6) shape facility and textural characteristics are contrasted with the case image of corresponding disease site in standard picture storehouse, be referred to corresponding ill grade. Thus easily, rapidly, accurately helping patient or medical personnel that focus is carried out grade separation.
Claims (7)
1. the digital image processing method of varicose veins of the lower extremity, it is characterised in that: comprise the following steps successively;
(1) set up the case image library of varicose veins of the lower extremity, and the case image in case image library is classified according to disease site and grade;
(2) the ill image of patient's disease sites is obtained;
(3) ill picture quality is judged, if judging qualified entrance step (4), if judging defective repetition step (2);
(4) ill image is contrasted with the case image in case image library, confirm disease site;
(5) affected areas in ill image is carried out image segmentation, extract affected areas shape facility and textural characteristics;
(6) shape facility and textural characteristics are contrasted with the individual features of the case image of corresponding disease site in standard picture storehouse, and be referred to corresponding grade.
2. the digital image processing method of varicose veins of the lower extremity according to claim 1, it is characterized in that: in step (2), user points out according to human body lower limbs schematic diagram, overlap gathering the disease sites profile with human body lower limbs schematic diagram, obtain ill image again through photographic head, photographing unit.
3. the digital image processing method of varicose veins of the lower extremity according to claim 1, it is characterised in that: in step (2), user, after obtaining ill image, selects the ill position at lower limb by legend or text prompt user.
4. the digital image processing method of varicose veins of the lower extremity according to claim 1, it is characterised in that: in step (3), ill picture quality is judged, and the object brightness to ill picture centre region and color characteristic judge.
5. the digital image processing method of varicose veins of the lower extremity according to claim 1, it is characterized in that: in step (5), first adopt image smoothing method that ill image carries out denoising, then adopt global threshold or OTSU that affected areas in ill image is carried out image segmentation.
6. the digital image processing method of varicose veins of the lower extremity according to claim 1, it is characterised in that: in step (5), described shape facility is boundary rectangle size, length-width ratio or circularity; Described textural characteristics is the feature of RBG or HIS component.
7. the digital image processing method of varicose veins of the lower extremity according to claim 1, it is characterized in that: in step (5), image segmentation is the pocket that ill image is divided into n × n, determines textural characteristics with the statistical value of the textural characteristics of n × n pocket.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610013856.1A CN105678772A (en) | 2016-01-11 | 2016-01-11 | Digital image processing method for varicose vein of lower limb |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610013856.1A CN105678772A (en) | 2016-01-11 | 2016-01-11 | Digital image processing method for varicose vein of lower limb |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105678772A true CN105678772A (en) | 2016-06-15 |
Family
ID=56299755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610013856.1A Pending CN105678772A (en) | 2016-01-11 | 2016-01-11 | Digital image processing method for varicose vein of lower limb |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105678772A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107174212A (en) * | 2017-06-20 | 2017-09-19 | 青岛浦利医疗技术有限公司 | Varication diagnostic device and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7120298B1 (en) * | 2001-08-16 | 2006-10-10 | Kurt Staehle | Method for obtaining and using medical data |
| CN101231662A (en) * | 2008-01-25 | 2008-07-30 | 华中科技大学 | Distributed Medical Image Retrieval System Based on Grid Platform |
| CN103745217A (en) * | 2013-12-31 | 2014-04-23 | 北京工业大学 | Automatic analysis method of tongue color and coating color in traditional Chinese medicine based on image retrieval |
-
2016
- 2016-01-11 CN CN201610013856.1A patent/CN105678772A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7120298B1 (en) * | 2001-08-16 | 2006-10-10 | Kurt Staehle | Method for obtaining and using medical data |
| CN101231662A (en) * | 2008-01-25 | 2008-07-30 | 华中科技大学 | Distributed Medical Image Retrieval System Based on Grid Platform |
| CN103745217A (en) * | 2013-12-31 | 2014-04-23 | 北京工业大学 | Automatic analysis method of tongue color and coating color in traditional Chinese medicine based on image retrieval |
Non-Patent Citations (2)
| Title |
|---|
| 倪豪: "基于颜色和纹理的中医舌像检索技术应用研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 诸薇娜 等: "基于颜色纹理的图像多特征检索技术在中医舌诊中的应用研究", 《中国图象图形学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107174212A (en) * | 2017-06-20 | 2017-09-19 | 青岛浦利医疗技术有限公司 | Varication diagnostic device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11783480B2 (en) | Semi-automated system for real-time wound image segmentation and photogrammetry on a mobile platform | |
| CN109922310B (en) | Target object monitoring method, device and system | |
| CN101359365B (en) | A Method of Iris Location Based on Maximum Inter-class Variance and Gray Level Information | |
| CN110930446B (en) | Pretreatment method and storage device for quantitative analysis of fundus images | |
| CN105426695B (en) | A kind of health status detecting system based on iris | |
| CN109684981A (en) | Glaucoma image recognition method, equipment and screening system | |
| US20150092981A1 (en) | Apparatus and method for providing activity recognition based application service | |
| CN106846293B (en) | Image processing method and device | |
| CN111225611A (en) | System and method for assisting in analyzing a wound in a target object | |
| KR20170106374A (en) | Method and system for detection of surgical gauze during anatomic surgery | |
| CN109727194B (en) | Method for obtaining nose patterns of pets, electronic equipment and storage medium | |
| CN107516004A (en) | The identifying processing method and device of medical image picture | |
| CN112819811A (en) | Image analysis method and related device, electronic equipment and storage medium | |
| KR20080043080A (en) | Human skin region detection device and method | |
| CN104951440B (en) | Image processing method and electronic equipment | |
| CN114982663B (en) | Method and device for managing wandering pets | |
| CN105678772A (en) | Digital image processing method for varicose vein of lower limb | |
| Wang et al. | Building palm vein capturing system for extraction | |
| CN113313050A (en) | Skin intelligent detection system based on video streaming | |
| TWI615130B (en) | Image processing method and non-transitory computer readable medium | |
| CN109359543A (en) | A kind of portrait search method and device based on Skeleton | |
| CN112329606B (en) | Living body detection method, living body detection device, electronic equipment and readable storage medium | |
| CN108074242A (en) | A kind of inflammation recognition methods and device | |
| Shaikha et al. | Optic Disc Detection and Segmentation in Retinal Fundus Image | |
| Raja et al. | Automatic localization of fovea in retinal images based on mathematical morphology and anatomic structures |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160615 |