CN103750810A - Method and device for performing characteristic analysis for images acquired by electronic colposcope - Google Patents
Method and device for performing characteristic analysis for images acquired by electronic colposcope Download PDFInfo
- Publication number
- CN103750810A CN103750810A CN201310742603.4A CN201310742603A CN103750810A CN 103750810 A CN103750810 A CN 103750810A CN 201310742603 A CN201310742603 A CN 201310742603A CN 103750810 A CN103750810 A CN 103750810A
- Authority
- CN
- China
- Prior art keywords
- image
- effective coverage
- characteristic area
- acetum
- trial
- 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
- Image Analysis (AREA)
Abstract
The invention relates to a method for performing characteristic analysis for images acquired by an electronic colposcope. The method comprises the steps of acquiring a collected acetic acid solution test image and identifying a valid area of the image and acquiring a first valid area; acquiring a white characteristic area; acquiring a collected acetic acid solution test green light image, identifying a valid area of the image and acquiring a second valid area of the image; acquiring a black characteristic area; acquiring a collected iodine solution test image, identifying a valid area of the image and acquiring a third valid area; and acquiring a non-fuscous characteristic area and overlapping center positions of the valid areas to align the characteristic areas acquired in the steps and acquire an overlapped characteristic area which is composed of overlapped parts of the characteristic areas. The invention also relates to a device for implementing the method. The implementation of the method and the device for performing characteristic analysis for the images acquired by the electronic colposcope hasthe beneficial effects that characteristic points are not omitted; and meanwhile, the subjectivity during observing the characteristic points.
Description
Technical field
The present invention relates to field of medical, more particularly, relate to and a kind of electronic colposcope is obtained to method and the device that image carries out feature analysis.
Background technology
Electronic colposcope inspection can find that the weak and incompetent tumor of cervical erosion, cervical polyp, cervical intraepithelial neoplasia (CIN), cervical cancer, vaginitis, pudendum, vagina or cervix uteri, poison infect and subclinical parillomarvirus infections.Colposcope is not only at diagnosis cervix uteri early carcinomatous change with to distinguish tumor valuable with the aspect such as inflammation, and aspect treatment, the special treatment in cervical intraepithelial neoplasia (CIN) has special applications value.Because colposcope can be seen position and scope that epithelium changes, the video image printing of electronic colposcope or Video Image collection and storage are extremely important to the tracing study of cervical lesions.In electronic colposcope checking process, prior art is exactly mainly doctor according to the colposcope image gathering, and with the naked eye goes to observe the variation of epithelium of cervix uteri after using normal saline, acetum and iodine solution, and finding colposcope image is carried out to interpretation and assessment.Image interpretation and assessment according to being to observe, in normal saline trial image, acetum trial image, iodine solution trial image, there is meaning and the continuous variation characteristic of (stack), by these variation characteristics of comprehensive assessment, obtain clinical diagnosis result.Due to the characteristics of image that doctor relies on each width of perusal to gather completely, easily ignore the feature that naked eyes are difficult for observing, make the interpretation of the image to gathering have deviation, thereby affect comprehensive assessment result; Meanwhile, when comprehensive assessment, also may omit on the basis of feature impact because being subject to subjective experience with certain subjectivity, accuracy and the concordance of the assessment result obtaining thus and biopsy position also can reduce.
Summary of the invention
The technical problem to be solved in the present invention is, for prior art above-mentioned, rely on artificial judgment feature completely and the defect of the assessment result deviation that causes because of the subjectivity compared with strong of may omitting, interpret blueprints provides a kind of automatic decision indicating characteristic, interpreting blueprints comparatively accurately electronic colposcope to be obtained to method and the device that image carries out feature analysis because the subjectivity compared with weak makes assessment result.
The technical solution adopted for the present invention to solve the technical problems is: construct and a kind of electronic colposcope is obtained to the method that image carries out feature analysis, comprise the steps:
A) obtain the acetum trial image collecting, identify its effective coverage and obtain the first effective coverage; Judge the white characteristic area that whether has tone value surpass the first predetermined color tone pitch in described the first effective coverage, if any, execution step B); As nothing, execution step C);
B) obtain the acetum test green glow image collecting, identify its effective coverage and obtain the second effective coverage; Judge the black characteristic area that whether has tone value surpass the second predetermined color tone pitch in described the second effective coverage, if any, execution step D); As nothing, execution step C);
C) obtain the iodine solution trial image collecting, identify its effective coverage and obtain the 3rd effective coverage; Judge the non-dark brown characteristic area that whether has tone value surpass the 3rd predetermined color tone pitch in described the 3rd effective coverage,
D) make overlapping each characteristic area to obtain in alignment above-mentioned steps in the center of each effective coverage, obtain the overlapping characteristic area that the lap by each characteristic area forms.
Further, in above steps, the step of identifying the effective coverage of each image comprises respectively:
Read the view data collecting and enter relief area, and cross mark cross point when this image acquisition is set is its central point, record the coordinate of this central point; Wherein, described image comprises: green glow image and/or the iodine solution trial image of acetum trial image, acetum test;
According to the profile identification of described image, obtain respectively the effective coverage of this image; Wherein, green glow image and the iodine solution trial image by described acetum trial image, acetum test obtains respectively the first effective coverage, the second effective coverage and the 3rd effective coverage; The central point of each image overlaps with the central point of effective coverage therefrom;
Respectively the view data in the described effective coverage obtaining is calculated to color model by RGB and be converted to HIS, and judge whether that tone value surpasses predetermined color tone pitch corresponding to this effective coverage, thereby obtain characteristic of correspondence region; Wherein, corresponding the first predetermined color tone pitch in described the first effective coverage, obtains white characteristic area; Corresponding the second predetermined color tone pitch in described the second effective coverage, obtains black characteristic area; Corresponding the 3rd predetermined color tone pitch in described the 3rd effective coverage, obtains non-dark brown characteristic area.
Further, the effective coverage step of described each image of identification also comprises:
When obtaining any one characteristic area, all its central point is alignd with the central point of cervical biopsy displaing coordinate, and described characteristic area is presented on cervical biopsy displaing coordinate figure.
Further, the effective coverage step of described each image of identification also comprises:
On described cervical biopsy displaing coordinate figure, the characteristic area showing is marked, the described characteristic area central point of take is the center of circle, use a plurality of concentric circulars to divide described image, use many diameters that are evenly distributed on circumference that the image of having divided is divided again, obtain a plurality of regions.
Further, carrying out described steps A) before, also comprise the steps:
The normal saline trial image that extraction collects, and it is carried out to characteristic area analysis; The characteristic area of described normal saline trial image is primitive character region, and the corresponding original tone value in described primitive character region, obtains red characteristic area; Described red characteristic area participation step D) stack.
Further, at described step B) also comprise the steps:
Obtain the green glow image of normal saline trial image, judge its black characteristic area, and with the black characteristic area comparison of described acetum test green glow image, get its lap as last black characteristic area.
The invention still further relates to a kind of device of realizing said method, comprising:
Acetum trial image judge module: for obtaining the acetum trial image collecting, identify its effective coverage and obtain the first effective coverage; Judge the white characteristic area that whether has tone value surpass the first predetermined color tone pitch in described the first effective coverage, if any, acetum test green glow judge module called; As nothing, call iodine solution test judge module;
Acetum test green glow judge module: for obtaining the acetum test green glow image collecting, identify its effective coverage and obtain the second effective coverage; Judge the black characteristic area that whether has tone value surpass the second predetermined color tone pitch in described the second effective coverage, if any, the comprehensive module of characteristic area called; As nothing, call iodine solution test judge module;
Iodine solution test judge module: for obtaining the iodine solution trial image collecting, identify its effective coverage and obtain the 3rd effective coverage; Judge the non-dark brown characteristic area that whether has tone value surpass the 3rd predetermined color tone pitch in described the 3rd effective coverage,
The comprehensive module of characteristic area: for making overlapping each characteristic area obtaining with alignment above-mentioned steps in the center of each effective coverage, obtain the overlapping characteristic area that the lap by each characteristic area forms.
Further, described acetum trial image judge module, acetum test green glow judge module and iodine solution test judge module also comprise respectively:
Image fetching unit: enter relief area for reading the view data collecting, and cross mark cross point when this image acquisition is set is its central point, records the coordinate of this central point; Wherein, described image comprises: green glow image and/or the iodine solution trial image of acetum trial image, acetum test;
Effective coverage judging unit: for obtain the effective coverage of this image according to the profile identification of described image; Wherein, green glow image and the iodine solution trial image by described acetum trial image, acetum test obtains respectively the first effective coverage, the second effective coverage and the 3rd effective coverage; The central point of each image overlaps with the central point of effective coverage therefrom;
Characteristic area judging unit: be converted to HIS for the view data in the described effective coverage obtaining is calculated to color model by RGB, and judge whether that tone value surpasses predetermined color tone pitch corresponding to this effective coverage, thereby obtain characteristic of correspondence region; Wherein, corresponding the first predetermined color tone pitch in described the first effective coverage, obtains white characteristic area; Corresponding the second predetermined color tone pitch in described the second effective coverage, obtains black characteristic area; Corresponding the 3rd predetermined color tone pitch in described the 3rd effective coverage, obtains non-dark brown characteristic area.
Further, also comprise:
Normal saline trial image judge module: for extracting the normal saline trial image collecting, and it is carried out to characteristic area analysis; The characteristic area of described normal saline trial image is primitive character region, and the corresponding original tone value in described primitive character region, obtains red characteristic area.
Further, also comprise:
Black signature verification module: for obtaining the green glow image of normal saline trial image, judge its black characteristic area, and with the black characteristic area comparison of described acetum test green glow image, get its lap as last black characteristic area.
Implement of the present invention electronic colposcope to be obtained to method and the device that image carries out feature analysis, there is following beneficial effect: because the multiple image that electronic colposcope is obtained takes out respectively and carries out the judgement of characteristic area separately, simultaneously, central point (this central point is also the central point of biopsy) mark also align the characteristic area of every kind of image respectively, and be superimposed, make doctor can not omit characteristic point when image is observed, assessed, reduced the subjectivity when observing characteristic point simultaneously.Therefore, its to characteristic area carry out automatic decision, the image evaluation result of using these characteristic areas to carry out is comparatively accurate.
Accompanying drawing explanation
To be the present invention obtain to electronic colposcope the flow chart that image carries out obtaining in the method for feature analysis and device embodiment characteristic area to Fig. 1;
Fig. 2 is feature identification and the mark particular flow sheet of image in described embodiment;
Fig. 3 is the shape schematic diagram of described embodiment image division;
Fig. 4 is the structural representation installing in described embodiment.
The specific embodiment
Below in conjunction with accompanying drawing, embodiments of the present invention is further illustrated.
As shown in Figure 1, of the present invention, electronic colposcope is obtained in the method and device embodiment that image carries out feature analysis, the step that the multiple image that electronic colposcope is obtained carries out feature analysis, obtain characteristic area is as follows:
Step S11 extracts the characteristic area of the acetum trial image of the cervix uteri gathering: in this step, obtain the acetum trial image collecting, identify its effective coverage and obtain the first effective coverage; In described the first effective coverage, search white characteristic area; In this step, white characteristic area is the region that tone value surpasses the first predetermined color tone pitch.As for how obtaining the first effective coverage and white characteristic area, there is after a while comparatively detailed description.
Whether step S12 adularescent feature, if any, execution step S13; As there is no execution step S15;
Step S13 extracts the characteristic area of the acetum test green glow image of the cervix uteri gathering: in this step, obtain the acetum test green glow image collecting, identify its effective coverage and obtain the second effective coverage; In described the second effective coverage, search black characteristic area; In this step, black characteristic area is the region that tone value surpasses the second predetermined color tone pitch.As for how obtaining the second effective coverage and black characteristic area, there is after a while comparatively detailed description.
Whether step S14 has black feature, if any, execution step S16; As there is no execution step S14;
Step S15 extracts the characteristic area of the iodine solution trial image of the cervix uteri gathering: in this step, obtain the iodine solution trial image collecting, identify its effective coverage and obtain the 3rd effective coverage; In described the 3rd effective coverage, search non-dark brown characteristic area; In this step, non-dark brown characteristic area is the region that tone value surpasses the 3rd predetermined color tone pitch.As for how obtaining the 3rd effective coverage and non-dark brown characteristic area, there is after a while comparatively detailed description.
The overlapping characteristic area obtaining of step S16 obtains comprehensive characteristics and shows: in this step, make overlapping each characteristic area to obtain in alignment above-mentioned steps in the center of each effective coverage, obtain the overlapping characteristic area that the lap by each characteristic area forms.Specifically, in this step, the characteristics of image extracting in above-mentioned steps is comprehensively analyzed, calculated the overlapping characteristic area of various characteristic areas.If in this step, there are how many characteristic areas, calculate how many characteristic areas; If without certain characteristic area, this characteristic area does not participate in calculating; For example, may comprise above-mentioned black, white, non-dark brown, even comprise the red characteristic area of mentioning after a while, if obtained when carrying out this step, all will participate in calculating.
In general, for same patient's colposcope image, its effective coverage size is identical.In this step by the centre coordinate alignment of the centre coordinate of the centre coordinate of the first effective coverage, the second effective coverage, the 3rd effective coverage, calculate in white characteristic area in the first effective coverage, the second effective coverage the overlapping characteristic area of non-dark brown characteristic area in black characteristic area, the 3rd effective coverage, obtain overlapping characteristic area; In the present embodiment, the centre coordinate of overlapping effective coverage DA obtained above is alignd with the centre coordinate for cervical biopsy displaing coordinate figure pre-seting; Described for cervical biopsy displaing coordinate figure on effective coverage DA in overlapping characteristic area corresponding position carry out labelling.The mode of concrete labelling, generally speaking, by the effective coverage DA with overlapping characteristic area centered by cross coordinate centre coordinate, from inside to outside, be divided near, in, 3 equal portions far away; Similar to index dial structure, centered by cross coordinate centre coordinate, take clockwise as direction is divided into 12 equal portions, totally 36 regions.To at once, alignd one by one with 36 intersection points on cervical biopsy displaing coordinate figure respectively in 36 regions.
The benefit of doing is like this: the comprehensive characteristics of the cervix uteri image that automatic analysis can be gone out shows in real time, for doctor, consults; , overlapping feature is shown with corresponded manner meanwhile, can for doctor the postdetection recording biopsy of living be organized in the relative position on cervix uteri time provide intuitively, unified labeling method.
In the present embodiment, in above-mentioned steps S11, S13 and S15, be all to obtain its effective coverage and characteristic area in the image of having obtained in advance, only the kind of image is different, and the title of its effective coverage is different with the title of characteristic area and characteristic.For example, for acetum trial image, what obtain is the first effective coverage, in the first effective coverage, by comparing the first tone value, judges white characteristic area; For iodine solution trial image, what obtain is the 3rd characteristic area, in the 3rd characteristic area, by comparing tertiary color tone pitch, obtains non-dark brown characteristic area.That is to say, except the image using, the parameter difference of calling, the step that obtains characteristic area by image in above-mentioned steps is identical.Refer to, these steps comprise:
Step S21 obtains image its central point of labelling: in this step, read the view data collecting and enter relief area, and cross mark cross point when this image acquisition is set is its central point, record the coordinate of this central point; Wherein, the image of obtaining in this step can be that green glow image, normal saline trial image, the normal saline that acetum trial image, acetum are tested tested in green glow image or iodine solution trial image.
Step S22 obtains the effective coverage of image: in this step, obtain the effective coverage of this image according to the profile identification that obtains image in step above; Wherein, green glow image and the iodine solution trial image by described acetum trial image, acetum test obtains respectively the first effective coverage, the second effective coverage and the 3rd effective coverage; The central point of each image overlaps with the central point of effective coverage therefrom;
Characteristic area in step S23 judgement effective coverage: in this step, view data in the effective coverage obtaining is calculated to color model by RGB and be converted to HIS, and judge whether that tone value surpasses predetermined color tone pitch corresponding to this effective coverage, thereby obtain characteristic of correspondence region; Similarly, for acetum trial image, the corresponding first predetermined color tone pitch in its first effective coverage, obtains white characteristic area after carrying out this step; For the green glow image of acetum test, corresponding the second predetermined color tone pitch in the second effective coverage, obtains black characteristic area after carrying out this step; For iodine solution trial image, corresponding the 3rd predetermined color tone pitch in its 3rd effective coverage, obtains non-dark brown characteristic area etc. after carrying out this step.
Acetum trial image take below as example, illustrate in the present embodiment, how an image is specifically carried out to the identification of effective coverage and characteristic area according to the method shown in Fig. 2.Other image, for example acetum test green glow image, iodine solution trial image, normal saline trial image and the effective coverage of normal saline test green glow image and the identification of characteristic area with obtain all similarly to description below, different is view data and judgement parameter difference.
In acetum trial image, Image outline identification method can adopt Mathematical Morphology method (carrying out analysis and the processing of shape and structure by morphological operator (burn into expansion, open and close) and combination thereof), the method based on gradient (to check rate of change and the direction of the neighborhood gray scale of boundary pixel, with this, determine profile border), movable contour model method (interested contour of object in image regard as one continuously, the chain structure of sealing, for it designs a class energy function, with iterative manner, ask for the minima of energy, thereby obtain optimal profile) etc.In the first effective coverage of the acetum trial image of the cervix uteri that then identification gathers, tone value surpasses the distribution of the white characteristic area that presets tone value.
In the present embodiment, tone value refers to HIS(tone (Hue)-brightness (Intensity)-saturation (Saturation)) tone component value in visual color model.Image is calculated to color model from RGB and be converted to HIS, and tone component is analyzed to the dimension that can reduce image, reduce operand.
In the present embodiment, obtain after any one characteristic area, the characteristic area obtaining can also be done to following processing (still take white characteristic area as example):
The intersection point of the cross coordinate during by this image acquisition (central point of the acetum trial image obtaining) aligns with the centre coordinate for follow-up cervical biopsy displaing coordinate figure pre-seting; Described, carry out labelling with the acetum trial image white characteristic area corresponding position of the cervix uteri of colposcope collection on for follow-up cervical biopsy displaing coordinate figure.
The mode of concrete labelling, refers to Fig. 3, and the described characteristic area central point of take is the center of circle, uses a plurality of concentric circulars to divide described image, uses many diameters that are evenly distributed on circumference that the image of having divided is divided again, obtains a plurality of regions.Centered by the cross coordinate centre coordinate of the first effective coverage of acetum trial image that is about to cervix uteri when this image acquisition, from inside to outside, be divided near, in, 3 equal portions far away; Similar to index dial structure, centered by cross coordinate centre coordinate, take clockwise as direction is divided into 12 equal portions, totally 36 regions.To at once, alignd one by one with 36 intersection points on follow-up cervical biopsy displaing coordinate figure respectively in 36 regions.It is worth mentioning that, in the present embodiment, all adopts in this way itself and mark.
The benefit of above-mentioned labelling is that the feature of acetum test (acetum test green glow) image of the cervix uteri that the colposcope that automatic analysis can be gone out gathers shows in real time, and corresponds to for follow-up cervical biopsy displaing coordinate figure, for doctor, consults; If can interrupt in time subsequent analysis in the time of enough can analyzing final result in this step simultaneously, reduce time and the workload analyzed, raise the efficiency.
Certainly, when other images are made to feature analysis, be also often to obtain a characteristic area just to carry out such mark, its benefit is also similar.
In addition in the present embodiment, can also, before carrying out described step S11, extract the normal saline trial image collecting, and it is carried out to characteristic area analysis; The characteristic area of normal saline trial image is primitive character region, and the corresponding original tone value in primitive character region, obtains red characteristic area more afterwards; The red characteristic area obtaining equally can be separately and cervical biopsy displaing coordinate figure stack or/and participate in the stack of last a plurality of characteristic areas.Make like this characteristic area that obtains more, more perfect, be convenient to obtain assessment result accurately.For the analysis of image, the acquisition mode of red characteristic area etc., equal similar to aforesaid way.
In addition, in the present embodiment, in order further to verify black characteristic area, to obtain result more accurately, in the above-mentioned step that obtains black characteristic area, can also comprise a verification step, obtain the green glow image of normal saline trial image, judge its black characteristic area, and with the black characteristic area comparison that obtains acetum test green glow image, get its lap as last black characteristic area.
The invention still further relates to a kind of device of realizing said method, as shown in Figure 4, this device comprises acetum trial image judge module 41, acetum test green glow image judge module 42, iodine solution trial image judge module 43 and the comprehensive module 44 of characteristic area; Wherein, acetum trial image judge module 41, for obtaining the acetum trial image collecting, is identified its effective coverage and is obtained the first effective coverage; Judge the white characteristic area that whether has tone value surpass the first predetermined color tone pitch in described the first effective coverage, if any, acetum test green glow judge module called; As nothing, call iodine solution test judge module; Acetum test green glow image judge module 42, for obtaining the acetum test green glow image collecting, is identified its effective coverage and is obtained the second effective coverage; Judge the black characteristic area that whether has tone value surpass the second predetermined color tone pitch in described the second effective coverage, if any, the comprehensive module of characteristic area called; As nothing, call iodine solution test judge module; Iodine solution trial image judge module 43, for obtaining the iodine solution trial image collecting, is identified its effective coverage and is obtained the 3rd effective coverage; Whether judge in described the 3rd effective coverage has tone value to surpass the non-comprehensive black characteristic area of the 3rd predetermined color tone pitch; The comprehensive module 44 of characteristic area is for making overlapping each characteristic area obtaining with alignment above-mentioned steps in the center of each effective coverage, obtains the overlapping characteristic area that the lap by each characteristic area forms.
In addition, in the present embodiment, above-mentioned acetum trial image judge module 41, acetum test green glow image judge module 42 and iodine solution trial image judge module 43 also comprise respectively image fetching unit, effective coverage judging unit and characteristic area judging unit (not shown) separately.Be that above-mentioned each module comprises this three unit.
Wherein, image fetching unit enters relief area for reading the view data collecting, and cross mark cross point when this image acquisition is set is its central point, records the coordinate of this central point; Image fetching unit in disparate modules is processed different images, and these images can be the green glow image of acetum trial image, acetum test and/or iodine solution trial image etc.Effective coverage judging unit is for obtaining the effective coverage of this image according to the profile identification of described image; Wherein, green glow image and the iodine solution trial image by described acetum trial image, acetum test obtains respectively the first effective coverage, the second effective coverage and the 3rd effective coverage; The central point of each image overlaps with the central point of effective coverage therefrom.Characteristic area judging unit is converted to HIS for the view data in the described effective coverage obtaining is calculated to color model by RGB, and judges whether that tone value surpasses predetermined color tone pitch corresponding to this effective coverage, thereby obtains characteristic of correspondence region; Wherein, corresponding the first predetermined color tone pitch in described the first effective coverage, obtains white characteristic area; Corresponding the second predetermined color tone pitch in described the second effective coverage, obtains black characteristic area; Corresponding the 3rd predetermined color tone pitch in described the 3rd effective coverage, obtains non-dark brown characteristic area.
In the present embodiment, said apparatus also comprises: normal saline trial image judge module 45 and black signature verification module 46.Wherein, normal saline trial image judge module 45 is for extracting the normal saline trial image collecting, and it is carried out to characteristic area analysis; The characteristic area of described normal saline trial image is primitive character region, and the corresponding original tone value in described primitive character region, obtains red characteristic area.
Black signature verification module 46, for obtaining the green glow image of normal saline image, judges its black characteristic area, and with the black characteristic area comparison of described acetum test green glow image, get its lap as last black characteristic area.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. electronic colposcope is obtained to the method that image carries out feature analysis, it is characterized in that, comprise the steps:
A) obtain the acetum trial image collecting, identify its effective coverage and obtain the first effective coverage; Judge the white characteristic area that whether has tone value surpass the first predetermined color tone pitch in described the first effective coverage, if any, execution step B); As nothing, execution step C);
B) obtain the acetum test green glow image collecting, identify its effective coverage and obtain the second effective coverage; Judge the black characteristic area that whether has tone value surpass the second predetermined color tone pitch in described the second effective coverage, if any, execution step D); As nothing, execution step C);
C) obtain the iodine solution trial image collecting, identify its effective coverage and obtain the 3rd effective coverage; Judge the non-dark brown characteristic area that whether has tone value surpass the 3rd predetermined color tone pitch in described the 3rd effective coverage,
D) make overlapping each characteristic area to obtain in alignment above-mentioned steps in the center of each effective coverage, obtain the overlapping characteristic area that the lap by each characteristic area forms.
2. according to claim 1 electronic colposcope is obtained to the method that image carries out feature analysis, it is characterized in that, in above steps, the step of identifying the effective coverage of each image comprises respectively:
Read the view data collecting and enter relief area, and cross mark cross point when this image acquisition is set is its central point, record the coordinate of this central point; Wherein, described image comprises: green glow image and/or the iodine solution trial image of acetum trial image, acetum test;
According to the profile identification of described image, obtain respectively the effective coverage of this image; Wherein, green glow image and the iodine solution trial image by described acetum trial image, acetum test obtains respectively the first effective coverage, the second effective coverage and the 3rd effective coverage; The central point of each image overlaps with the central point of effective coverage therefrom;
Respectively the view data in the described effective coverage obtaining is calculated to color model by RGB and be converted to HIS, and judge whether that tone value surpasses predetermined color tone pitch corresponding to this effective coverage, thereby obtain characteristic of correspondence region; Wherein, corresponding the first predetermined color tone pitch in described the first effective coverage, obtains white characteristic area; Corresponding the second predetermined color tone pitch in described the second effective coverage, obtains black characteristic area; Corresponding the 3rd predetermined color tone pitch in described the 3rd effective coverage, obtains non-dark brown characteristic area.
3. according to claim 2 electronic colposcope is obtained to the method that image carries out feature analysis, it is characterized in that, the effective coverage step of described each image of identification also comprises:
When obtaining any one characteristic area, all its central point is alignd with the central point of cervical biopsy displaing coordinate, and described characteristic area is presented on cervical biopsy displaing coordinate figure.
4. according to claim 3 electronic colposcope is obtained to the method that image carries out feature analysis, it is characterized in that, the effective coverage step of described each image of identification also comprises:
On described cervical biopsy displaing coordinate figure, the characteristic area showing is marked, the described characteristic area central point of take is the center of circle, use a plurality of concentric circulars to divide described image, use many diameters that are evenly distributed on circumference that the image of having divided is divided again, obtain a plurality of regions.
5. according to claim 4 electronic colposcope is obtained to the method that image carries out feature analysis, it is characterized in that, carrying out described steps A) before, also comprise the steps:
The normal saline trial image that extraction collects, and it is carried out to characteristic area analysis; The characteristic area of described normal saline trial image is primitive character region, and the corresponding original tone value in described primitive character region, obtains red characteristic area; Described red characteristic area participation step D) stack.
6. according to claim 5 electronic colposcope is obtained to the method that image carries out feature analysis, it is characterized in that, at described step B) also comprise the steps:
Obtain the green glow image of normal saline trial image, judge its black characteristic area, and with the black characteristic area comparison of described acetum test green glow image, get its lap as last black characteristic area.
7. realize a device for method as claimed in claim 1, it is characterized in that, comprising:
Acetum trial image judge module: for obtaining the acetum trial image collecting, identify its effective coverage and obtain the first effective coverage; Judge the white characteristic area that whether has tone value surpass the first predetermined color tone pitch in described the first effective coverage, if any, acetum test green glow judge module called; As nothing, call iodine solution test judge module;
Acetum test green glow judge module: for obtaining the acetum test green glow image collecting, identify its effective coverage and obtain the second effective coverage; Judge the black characteristic area that whether has tone value surpass the second predetermined color tone pitch in described the second effective coverage, if any, the comprehensive module of characteristic area called; As nothing, call iodine solution test judge module;
Iodine solution test judge module: for obtaining the iodine solution trial image collecting, identify its effective coverage and obtain the 3rd effective coverage; Whether judge in described the 3rd effective coverage has tone value to surpass the non-dark brown characteristic area of the 3rd predetermined color tone pitch;
The comprehensive module of characteristic area: for making overlapping each characteristic area obtaining with alignment above-mentioned steps in the center of each effective coverage, obtain the overlapping characteristic area that the lap by each characteristic area forms.
8. device according to claim 7, is characterized in that: described acetum trial image judge module, acetum test green glow judge module and iodine solution test judge module also comprise respectively:
Image fetching unit: enter relief area for reading the view data collecting, and cross mark cross point when this image acquisition is set is its central point, records the coordinate of this central point; Wherein, described image comprises: green glow image and/or the iodine solution trial image of acetum trial image, acetum test;
Effective coverage judging unit: for obtain the effective coverage of this image according to the profile identification of described image; Wherein, green glow image and the iodine solution trial image by described acetum trial image, acetum test obtains respectively the first effective coverage, the second effective coverage and the 3rd effective coverage; The central point of each image overlaps with the central point of effective coverage therefrom;
Characteristic area judging unit: be converted to HIS for the view data in the described effective coverage obtaining is calculated to color model by RGB, and judge whether that tone value surpasses predetermined color tone pitch corresponding to this effective coverage, thereby obtain characteristic of correspondence region; Wherein, corresponding the first predetermined color tone pitch in described the first effective coverage, obtains white characteristic area; Corresponding the second predetermined color tone pitch in described the second effective coverage, obtains black characteristic area; Corresponding the 3rd predetermined color tone pitch in described the 3rd effective coverage, obtains non-dark brown characteristic area.
9. device according to claim 8, is characterized in that, also comprises:
Normal saline trial image judge module: for extracting the normal saline trial image collecting, and it is carried out to characteristic area analysis; The characteristic area of described normal saline trial image is primitive character region, and the corresponding original tone value in described primitive character region, obtains red characteristic area.
10. device according to claim 9, is characterized in that, also comprises:
Black signature verification module: for obtaining the green glow image of normal saline trial image, judge its black characteristic area, and with the black characteristic area comparison of described acetum test green glow image, get its lap as last black characteristic area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310742603.4A CN103750810B (en) | 2013-12-30 | 2013-12-30 | Method and the device that image carries out feature analysis is obtained to electronic colposcope |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310742603.4A CN103750810B (en) | 2013-12-30 | 2013-12-30 | Method and the device that image carries out feature analysis is obtained to electronic colposcope |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103750810A true CN103750810A (en) | 2014-04-30 |
| CN103750810B CN103750810B (en) | 2015-10-07 |
Family
ID=50518257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310742603.4A Active CN103750810B (en) | 2013-12-30 | 2013-12-30 | Method and the device that image carries out feature analysis is obtained to electronic colposcope |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103750810B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108319977A (en) * | 2018-01-30 | 2018-07-24 | 浙江大学 | Cervical biopsy area recognizing method based on the multi-modal network of channel information and device |
| CN109117890A (en) * | 2018-08-24 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of image classification method, device and storage medium |
| CN110123254A (en) * | 2018-02-09 | 2019-08-16 | 深圳市理邦精密仪器股份有限公司 | Electronic colposcope picture adjustment methods, system and terminal device |
| CN110786818A (en) * | 2018-08-01 | 2020-02-14 | 深圳市理邦精密仪器股份有限公司 | Cervical canal mirror and electronic colposcope integrated system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050054936A1 (en) * | 2000-03-28 | 2005-03-10 | Constantinos Balas | Method and system for characterization and mapping of tissue lesions |
| US20090034824A1 (en) * | 2007-08-03 | 2009-02-05 | Sti Medical Systems Llc | Computerized image analysis for acetic acid induced Cervical Intraepithelial Neoplasia |
| US20090046905A1 (en) * | 2005-02-03 | 2009-02-19 | Holger Lange | Uterine cervical cancer computer-aided-diagnosis (CAD) |
| CN102920423A (en) * | 2011-08-12 | 2013-02-13 | 三维医疗科技江苏股份有限公司 | Digital colposcope taking single chip microcomputer as core |
| CN103096786A (en) * | 2010-05-03 | 2013-05-08 | 国际科学技术医疗系统有限责任公司 | Image analysis for cervical neoplasia detection and diagnosis |
| WO2013084123A2 (en) * | 2011-12-05 | 2013-06-13 | Koninklijke Philips Electronics N.V. | Selection of images for optical examination of the cervix |
| CN103325128A (en) * | 2013-05-16 | 2013-09-25 | 深圳市理邦精密仪器股份有限公司 | Method and device intelligently identifying characteristics of images collected by colposcope |
-
2013
- 2013-12-30 CN CN201310742603.4A patent/CN103750810B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050054936A1 (en) * | 2000-03-28 | 2005-03-10 | Constantinos Balas | Method and system for characterization and mapping of tissue lesions |
| US20090046905A1 (en) * | 2005-02-03 | 2009-02-19 | Holger Lange | Uterine cervical cancer computer-aided-diagnosis (CAD) |
| US20090034824A1 (en) * | 2007-08-03 | 2009-02-05 | Sti Medical Systems Llc | Computerized image analysis for acetic acid induced Cervical Intraepithelial Neoplasia |
| CN103096786A (en) * | 2010-05-03 | 2013-05-08 | 国际科学技术医疗系统有限责任公司 | Image analysis for cervical neoplasia detection and diagnosis |
| CN102920423A (en) * | 2011-08-12 | 2013-02-13 | 三维医疗科技江苏股份有限公司 | Digital colposcope taking single chip microcomputer as core |
| WO2013084123A2 (en) * | 2011-12-05 | 2013-06-13 | Koninklijke Philips Electronics N.V. | Selection of images for optical examination of the cervix |
| CN103325128A (en) * | 2013-05-16 | 2013-09-25 | 深圳市理邦精密仪器股份有限公司 | Method and device intelligently identifying characteristics of images collected by colposcope |
Non-Patent Citations (3)
| Title |
|---|
| RENGASWAMY SANKARANARAYANAN等: "TEST CHARACTERISTICS OF VISUAL INSPECTION WITH 4% ACETIC ACID (VIA) AND LUGOL’S IODINE (VILI) IN CERVICAL CANCER SCREENING IN KERALA, INDIA", 《INT. J. CANCER》, 31 December 2003 (2003-12-31) * |
| ROGER J. RAND等: "Schistosomiasis of the uterine cervix", 《BRITISH JOURNAL OF OBSTETRICS AND GYNAECOLOGY》, 31 December 1998 (1998-12-31) * |
| WENJING LI等: "Computer-Aided Diagnosis (CAD) for Cervical Cancer Screening and Diagnosis: A New System Design in Medical Image Processing", 《CVBIA 2005》, 31 December 2005 (2005-12-31) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108319977A (en) * | 2018-01-30 | 2018-07-24 | 浙江大学 | Cervical biopsy area recognizing method based on the multi-modal network of channel information and device |
| CN108319977B (en) * | 2018-01-30 | 2020-11-10 | 浙江大学 | Cervical biopsy region identification method and device based on channel information multi-mode network |
| CN110123254A (en) * | 2018-02-09 | 2019-08-16 | 深圳市理邦精密仪器股份有限公司 | Electronic colposcope picture adjustment methods, system and terminal device |
| CN110786818A (en) * | 2018-08-01 | 2020-02-14 | 深圳市理邦精密仪器股份有限公司 | Cervical canal mirror and electronic colposcope integrated system and method |
| CN109117890A (en) * | 2018-08-24 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of image classification method, device and storage medium |
| CN109117890B (en) * | 2018-08-24 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Image classification method and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103750810B (en) | 2015-10-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9107569B2 (en) | Medical instrument for examining the cervix | |
| CN103325128B (en) | A kind of method and device of Intelligent Recognition gynecatoptron acquired image feature | |
| CN107483014B (en) | A kind of photovoltaic panel failure automatic detection method | |
| Young Park et al. | Automated image analysis of digital colposcopy for the detection of cervical neoplasia | |
| Bai et al. | Automatic segmentation of cervical region in colposcopic images using K-means | |
| CN110458821A (en) | A kind of sperm morphology analysis method based on deep neural network model | |
| CN108257129A (en) | The recognition methods of cervical biopsy region aids and device based on multi-modal detection network | |
| CN112465772B (en) | Fundus colour photographic image blood vessel evaluation method, device, computer equipment and medium | |
| CN103750810B (en) | Method and the device that image carries out feature analysis is obtained to electronic colposcope | |
| CN104361314A (en) | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion | |
| CN103975364B (en) | Selection of images for optical examination of the cervix | |
| CN105740750A (en) | Fingerprint in-vivo detection and identification method and apparatus | |
| CN104537373A (en) | Multispectral sublingual image feature extraction method for sublingual microvascular complication diagnosis | |
| Moshavegh et al. | Automated segmentation of free-lying cell nuclei in pap smears for malignancy-associated change analysis | |
| Sivasankar et al. | Retracted: FCM based iris image analysis for tissue imbalance stage identification | |
| CN106778495A (en) | Ship Detection in remote sensing image under complicated sea background | |
| CN112102332A (en) | Cancer WSI segmentation method based on local classification neural network | |
| Shi et al. | Towards algorithm‐enabled home wound monitoring with smartphone photography: a hue‐saturation‐value colour space thresholding technique for wound content tracking | |
| CN110412257B (en) | Test paper block positioning method combining manual calibration and star ray algorithm | |
| CN102297833A (en) | Method for determination of content of various cells in human blood or bone marrow | |
| US20240065540A1 (en) | Apparatus and method for detecting cervical cancer | |
| CN109214433A (en) | A kind of method that convolutional neural networks distinguish liver cancer differentiation grade | |
| CN112464871A (en) | Deep learning-based traditional Chinese medicine tongue image processing method and system | |
| CN101091649A (en) | Method for picking-up gray-scaled images of fruit flies | |
| CN103932665B (en) | A kind of display packing of electronic colposcope image and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |