CN104376199A - Method for intelligently generating breast report lesion schematic diagram - Google Patents
Method for intelligently generating breast report lesion schematic diagram Download PDFInfo
- Publication number
- CN104376199A CN104376199A CN201410618994.3A CN201410618994A CN104376199A CN 104376199 A CN104376199 A CN 104376199A CN 201410618994 A CN201410618994 A CN 201410618994A CN 104376199 A CN104376199 A CN 104376199A
- Authority
- CN
- China
- Prior art keywords
- schematic diagram
- report
- module
- image
- mammary gland
- 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
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a method for intelligently generating a breast report lesion schematic diagram. A generating system which is mainly composed of a central processing module, a report input module, a display module, a pre-defined lesion image bank module, a BI-RADS term bank module and a breast lesion schematic diagram output module is adopted as a working carrier to record text description of an image seen by a doctor; on the basis of a general computer word distributing matching algorithm and a BI-RADS term bank, the part of content seen from the image can be analyzed, contents about breast masses, calcification and variety information can be matched out, and a corresponding lesion diagram can be found out from the pre-defined lesion image bank; according to the form, the position, the size and other description information, the lesion schematic diagram is processed and put on a breast skeleton diagram, and the breast report lesion schematic diagram is generated. The method solves the technical problem of breast report lesion schematic diagram intelligent generating, the working efficiency of the report doctor is improved, workloads of the doctors are reduced, and the more visual breast report is provided for a clinical doctor and a patient.
Description
Technical field
The present invention relates to focus signal map generalization method in the report of a kind of mammary gland, particularly a kind of mammary gland report focus schematic diagram intelligent generation method, additionally provides a kind of mammary gland report focus schematic diagram intelligent generating system in the present invention simultaneously.
Background technology
A complete mammary gland report is made up of image finding, diagnostic imaging and breast lesion schematic diagram three part, and lump and calcification of a great variety in breast lesion.Wherein lump segments according to form, edge and density, nearly 80 kinds of combinations can be generated, calcification is segmented according to grade malignancy and distribution, nearly 70 kinds of combinations can be generated, schematic diagram also to embody the information such as size of tumor, position and the degree of depth, the situations such as multiple focus (as lump association calcification) appearance may be occurred in addition.Too many owing to combining, be therefore difficult to some focus schematic diagram of predefine and select for user.
But it is abnormal difficult for wanting to represent a lot of lump of kind and calcification focus by the form of pure manual drawing, Freehandhand-drawing schematic diagram can only roughly mark in breast whether there is lump and calcification, the depth and place of rough statement focus, Freehandhand-drawing schematic diagram if there is association calcification phenomenon in lump just more cannot be described, add diagnostician's routine work amount large, do not have carefully go pictorial diagram over head time yet, be difficult to Accurate Expression lesion information, cause focus schematic diagram to be difficult to play signal effect.Except above-mentioned Freehandhand-drawing mode, also useful written form is embedded in picture control at software, puts into mammary gland schematic diagram and adjusts, thus complete whole drawing process by pulling mode.Detailed process is as follows:
1. above interface, can see that written form corresponding to lump calcification pulls control;
2. select corresponding lump and calcification and be drawn in mammary gland schematic diagram;
3. adjust size and the position of lump and calcification.
The maximum shortcoming of this implementation is that efficiency is relatively low, from whole process, doctor not only wants input characters to report, also again will select corresponding picture option, be drawn to lesions position, then adjustment image being carried out to the pattern such as size, the degree of depth is to generate schematic diagram.More consuming time is, because lump and calcification have 80 and 70 kind more than respectively, the corresponding focus of manual selection is just very loaded down with trivial details, and focus is drawn to after in schematic diagram still to be needed manually to carry out adjusting the editor that finally could complete schematic diagram, work efficiency reduces, and the duplication of labour increases.
Therefore, need the routine work amount that a kind of new mammary gland report focus signal drawing generating method reduces report doctor at present badly, and promote the quality of breast lesion schematic diagram.
Summary of the invention
The object of the invention is to provide a kind of mammary gland to report focus schematic diagram intelligent generation method to solve above-mentioned the deficiencies in the prior art.Above-mentioned intelligent generation method can generate breast lesion schematic diagram fast according to the image finding content assist physician of mammary gland report.
To achieve these goals, a kind of mammary gland report focus schematic diagram intelligent generation method designed by the present invention, its adopt mainly comprise central processing module, report load module, display module, predefined lesion image library module and BI-RADS terminology bank module composition generation system be working material, concrete grammar step is as follows:
First step: by report load module in typing mammary gland report in central processing module to text description content seen by image;
Second step: central processing module is based on text description content seen by general computing machine participle matching algorithm and the above-mentioned image of BI-RADS terminology bank module analysis;
Third step: central processing module matches wherein about the content of breast lump, calcification and kind of information;
4th step: find out corresponding focus figure according to the text description of its title and form from predefined lesion image library module again, position is had or/and size descriptor in text description seen by image, then carry out the position of the focus picture found out or/and size modification, be put into after drawing amended focus figure on mammary gland profile diagram, and on display module, demonstrate the mammary gland consistent with image finding text description report focus schematic diagram.
In order to the breast lesion schematic diagram that display module shows being printed paper fast, the generation system that above-mentioned a kind of mammary gland report focus schematic diagram intelligent generation method adopts further comprises breast lesion schematic diagram output module, again by step 5 after above-mentioned 4th step: breast lesion schematic diagram output module prints the mammary gland report focus schematic diagram formed in above-mentioned 4th step.
The manual fine-tuning step of focus figure on mammary gland profile diagram is also comprised after the 4th above-mentioned step; And in above-mentioned manual fine-tuning process, the lesions position on mammary gland profile normotopia, side bitmap sheet is linked.
Find that seen by image, text description is wrong after the 4th above-mentioned step or the 5th step, then increase the step of the image finding word segment content of typing central processing module in first step being carried out to manual modification, then central processing module reanalyses above-mentioned amended image finding word segment content again based on general computing machine participle matching algorithm and BI-RADS terminology bank module, and the breast lesion schematic diagram on display module is then corresponding makes amendment.
Computing machine participle matching algorithm in above-mentioned is roughly divided into three major types: comprise based on the segmenting method of string matching, the segmenting method based on the segmenting method understood and Corpus--based Method.It is the technology known by the computer programmer of this area, therefore about taking central processing module as working material, how realize by distinct methods, program the conventional techniques means that the participle of this segmentation methods and coupling are those skilled in the art, simultaneous computer programming is again the Conventional wisdom of computing machine and various equivalent modifications thereof.Therefore applicant seldom specifically describes foregoing at this.Above-mentioned concrete computing machine participle matching algorithm and programming thereof are not included in protection scope of the present invention yet.
BI-RADS terminology bank in above-mentioned refers to Breast imaging reporting and data system Breast imaging reporting and data system, and this system has been a kind of Essential Terms storehouse in mammary gland medical science industry, therefore applicant is to its also few introduction in detail.
Above-mentioned a kind of mammary gland report focus schematic diagram intelligent generation method, first it alleviate the burden of doctor, improves the formation efficiency of breast lesion schematic diagram, improves the work efficiency of report doctor; Secondly, generate schematic diagram based on focus terminology bank and corresponding lesion image storehouse more accurate and directly perceived, for clinician and patient provide mammary gland report more intuitively, be convenient to reading and the understanding of clinician and patient.No matter so the present invention has quite necessary practical value for patient or doctor, and have the following advantages: 1. under the prerequisite not changing report doctor writing style, schematic diagram is assisted in the generation of intelligence, greatly improves schematic diagram formation efficiency in mammary gland report; 2., during schematic diagram adjustment, positive side bitmap sheet intelligent linkage, controls setting range according to positional information; 3. represent form more clear, directly perceived and unified.
Accompanying drawing explanation
Fig. 1 is the breast lesion schematic diagram that in embodiment, intelligence generates;
Fig. 2 is that the schematic diagram of breast lesion shown in Fig. 1 is through manual amended schematic diagram one;
Fig. 3 is that the schematic diagram of breast lesion shown in Fig. 1 is through manual amended schematic diagram two;
Fig. 4 is the schematic block diagram of a kind of mammary gland report focus schematic diagram intelligent generating system in embodiment.
In figure: central processing module 1, report load module 2, display module 3, lesion image library module 4, BI-RADS terminology bank module 5, breast lesion schematic diagram output module 6.
Embodiment
Below in conjunction with drawings and Examples, the present invention is further described.
A kind of mammary gland report focus schematic diagram intelligent generation method that the present embodiment provides, it adopts the generation system primarily of central processing module 1, report load module 2, display module 3, predefined lesion image library module 4, BI-RADS terminology bank module 5 and breast lesion schematic diagram output module 6 composition to be working material, as shown in Figure 4, its concrete steps are as follows:
First step, by the process of report load module 2 to the image finding word segment content in typing mammary gland report in central processing module 1, suppose the mammary gland report finding that will input as following table 1:
Table 1:
Second step, central processing module 1 carries out semantic analysis by the segmentation methods of BI-RADS terminology bank module 5 to whole section of word, obtains with key message shown in following table 2 and 3:
Lump describes (table 2):
Calcification describes (table 3):
Third step, central processing module 1 does participle matching algorithm to lump wherein and calcification description and obtains the information such as focus desired position, size, form:
Lump partial data: right breast, left upper quadrant, 2cm are dark, size about 4 × 7.5mm, lobulated tubercle shadow.
Calcification part data: left breast, right upper quadrant, sections shape calcification shadow.
4th step, central processing module 1 finds out corresponding focus figure according to the text description of its title and form from predefined lesion image library module 4, after such as central module obtains " oval high density lump shadow; burr shape ", in image library, find the picture of oval lump, then find the picture of its middle-high density and burrs on edges.Seen by image the descriptor such as text description form, position, size above-mentioned focus figure is modified, combine after be put on mammary gland profile diagram, and on display module 3, demonstrate the mammary gland consistent with image finding text description report focus schematic diagram.
5th step, prints the breast lesion schematic diagram formed in above-mentioned 4th step, as shown in Figure 1 by breast lesion schematic diagram output module 6.
After the 4th above-mentioned step, if lack the description as position in " finding ", figure sector-meeting is presented in approximate range, also needs doctor initiatively to go to adjust real position adjustment.Namely carry out the manual fine-tuning of focus figure on mammary gland profile diagram; And the lesions position in manual fine-tuning process on mammary gland profile normotopia, side bitmap sheet links.Report doctor manually operates above-mentioned steps, makes fine setting within the specific limits, thus make breast lesion schematic diagram more accurate according to actual conditions to the focus figure on mammary gland profile diagram.As shown in Figure 2, if find in analysis result that lump position is: right breast, left upper quadrant, and elevation information is not described, therefore this lump can only in mammary gland profile diagram right breast whole left upper quadrant region (in figure red frame) in somewhere show.Depart from if be equipped with from actual bit, doctor can manual shift position, and the figure in left side understands synchronizing moving.
To find wrong to word seen by image after the mammary gland consistent with image finding text description reports focus schematic diagram when the 4th step or the display of the 5th step or print or need to modify, turn back to the image finding text description partial content of typing or amendment central processing module 1 again in first step so again, then central processing module 1 is analyzed above-mentioned amended image finding word segment content again again based on general computing machine participle matching algorithm and BI-RADS terminology bank module 5, and breast lesion schematic diagram is then corresponding makes intelligence amendment.As described the amendment carried out as following table 4 to lump, other each several parts are constant.
Table 4:
After doctor carries out word amendment, breast lesion schematic diagram can recalculate the position residing for lump and size and draw, and effect as shown in Figure 3.
Claims (5)
1. a mammary gland report focus schematic diagram intelligent generation method, it is characterized in that adopting mainly comprise central processing module, report load module, display module, predefined lesion image library module and BI-RADS terminology bank module composition generation system be working material, concrete grammar step is as follows:
First step: by report load module in typing mammary gland report in central processing module to text description content seen by image;
Second step: central processing module is based on text description content seen by general computing machine participle matching algorithm and the above-mentioned image of BI-RADS terminology bank module analysis;
Third step: central processing module matches wherein about the content of breast lump, calcification and kind of information;
4th step: find out corresponding focus figure according to the text description of its title and form from predefined lesion image library module again, position is had or/and size descriptor in text description seen by image, then carry out the position of the focus picture found out or/and size modification, be put into after drawing amended focus figure on mammary gland profile diagram, and on display module, demonstrate the mammary gland consistent with image finding text description report focus schematic diagram.
2. a kind of mammary gland report focus schematic diagram intelligent generation method according to claim 1, it is characterized in that its generation system adopted also comprises breast lesion schematic diagram output module, again by step 5 after above-mentioned 4th step: breast lesion schematic diagram output module prints the mammary gland report focus schematic diagram formed in above-mentioned 4th step.
3. a kind of mammary gland report focus schematic diagram intelligent generation method according to claim 1 and 2, is characterized in that also comprising the manual fine-tuning step of focus figure on mammary gland profile diagram after the 4th above-mentioned step; And in above-mentioned manual fine-tuning process, the lesions position on mammary gland profile normotopia, side bitmap sheet is linked.
4. require a kind of mammary gland report focus schematic diagram intelligent generation method described in 1 or 2 according to power, find that seen by image, text description is wrong after it is characterized in that the 4th above-mentioned step or the 5th step, then increase the step of the image finding word segment content of typing central processing module in first step being carried out to manual modification, then central processing module reanalyses above-mentioned amended image finding word segment content again based on general computing machine participle matching algorithm and BI-RADS terminology bank module, breast lesion schematic diagram on display module is then corresponding makes amendment.
5. require a kind of mammary gland report focus schematic diagram intelligent generation method described in 3 according to power, find that seen by image, text description is wrong after it is characterized in that the 4th above-mentioned step or the 5th step, then increase the step of the image finding word segment content of typing central processing module in first step being carried out to manual modification, then central processing module reanalyses above-mentioned amended image finding word segment content again based on general computing machine participle matching algorithm and BI-RADS terminology bank module, breast lesion schematic diagram on display module is then corresponding makes amendment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410618994.3A CN104376199A (en) | 2014-11-05 | 2014-11-05 | Method for intelligently generating breast report lesion schematic diagram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410618994.3A CN104376199A (en) | 2014-11-05 | 2014-11-05 | Method for intelligently generating breast report lesion schematic diagram |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104376199A true CN104376199A (en) | 2015-02-25 |
Family
ID=52555103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410618994.3A Pending CN104376199A (en) | 2014-11-05 | 2014-11-05 | Method for intelligently generating breast report lesion schematic diagram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104376199A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105912838A (en) * | 2016-04-01 | 2016-08-31 | 深圳市菲森科技有限公司 | Display method, and system for dental examination results and medical equipment |
| CN106874682A (en) * | 2017-02-28 | 2017-06-20 | 北京赛迈特锐医疗科技有限公司 | Based on the system and method for graphically writing structured report |
| CN108537893A (en) * | 2017-03-02 | 2018-09-14 | 南京同仁医院有限公司 | A kind of three-dimensional visualization model generation method of thyroid gland space occupying lesion |
| CN109767820A (en) * | 2018-05-29 | 2019-05-17 | 深圳市智影医疗科技有限公司 | A kind of diagnosis based on image/examining report generation method, device and equipment |
| CN111383328A (en) * | 2020-02-27 | 2020-07-07 | 西安交通大学 | 3D visualization method and system for breast cancer focus |
| CN111415332A (en) * | 2020-03-05 | 2020-07-14 | 北京深睿博联科技有限责任公司 | Mammary gland X-ray image linkage method and device |
| WO2021008213A1 (en) * | 2019-07-12 | 2021-01-21 | 智慧芽信息科技(苏州)有限公司 | Image database establishing method, searching method, electronic device, and storage medium |
| CN112561908A (en) * | 2020-12-24 | 2021-03-26 | 北京医准智能科技有限公司 | Mammary gland image focus matching method, device and storage medium |
| CN113449125A (en) * | 2020-03-26 | 2021-09-28 | 阿里巴巴集团控股有限公司 | Data entry method and device, electronic equipment and computer readable storage medium |
| CN113808101A (en) * | 2021-09-16 | 2021-12-17 | 什维新智医疗科技(上海)有限公司 | Mammary nodule calcification analytical equipment |
| CN115132314A (en) * | 2022-09-01 | 2022-09-30 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Examination impression generation model training method, examination impression generation model training device and examination impression generation model generation method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2169577A1 (en) * | 2008-09-25 | 2010-03-31 | Algotec Systems Ltd. | Method and system for medical imaging reporting |
| CN102915400A (en) * | 2011-08-02 | 2013-02-06 | 西门子公司 | Method and arrangement for computer-assisted representation and/or evaluation of medical examination data |
| CN103262070A (en) * | 2010-12-23 | 2013-08-21 | 皇家飞利浦电子股份有限公司 | Generation of Pictorial Reporting Diagrams of Lesions In Anatomical Structures |
| CN103927160A (en) * | 2013-12-25 | 2014-07-16 | 宁波市科技园区明天医网科技有限公司 | Method and system for intelligent auxiliary generation of electrocardio standardized report |
-
2014
- 2014-11-05 CN CN201410618994.3A patent/CN104376199A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2169577A1 (en) * | 2008-09-25 | 2010-03-31 | Algotec Systems Ltd. | Method and system for medical imaging reporting |
| CN103262070A (en) * | 2010-12-23 | 2013-08-21 | 皇家飞利浦电子股份有限公司 | Generation of Pictorial Reporting Diagrams of Lesions In Anatomical Structures |
| CN102915400A (en) * | 2011-08-02 | 2013-02-06 | 西门子公司 | Method and arrangement for computer-assisted representation and/or evaluation of medical examination data |
| CN103927160A (en) * | 2013-12-25 | 2014-07-16 | 宁波市科技园区明天医网科技有限公司 | Method and system for intelligent auxiliary generation of electrocardio standardized report |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105912838A (en) * | 2016-04-01 | 2016-08-31 | 深圳市菲森科技有限公司 | Display method, and system for dental examination results and medical equipment |
| CN106874682A (en) * | 2017-02-28 | 2017-06-20 | 北京赛迈特锐医疗科技有限公司 | Based on the system and method for graphically writing structured report |
| CN108537893A (en) * | 2017-03-02 | 2018-09-14 | 南京同仁医院有限公司 | A kind of three-dimensional visualization model generation method of thyroid gland space occupying lesion |
| CN109767820A (en) * | 2018-05-29 | 2019-05-17 | 深圳市智影医疗科技有限公司 | A kind of diagnosis based on image/examining report generation method, device and equipment |
| WO2021008213A1 (en) * | 2019-07-12 | 2021-01-21 | 智慧芽信息科技(苏州)有限公司 | Image database establishing method, searching method, electronic device, and storage medium |
| CN111383328A (en) * | 2020-02-27 | 2020-07-07 | 西安交通大学 | 3D visualization method and system for breast cancer focus |
| CN111383328B (en) * | 2020-02-27 | 2022-05-20 | 西安交通大学 | 3D visualization method and system for breast cancer focus |
| CN111415332A (en) * | 2020-03-05 | 2020-07-14 | 北京深睿博联科技有限责任公司 | Mammary gland X-ray image linkage method and device |
| CN111415332B (en) * | 2020-03-05 | 2023-10-24 | 北京深睿博联科技有限责任公司 | Mammary gland X-ray image linkage method and device |
| CN113449125A (en) * | 2020-03-26 | 2021-09-28 | 阿里巴巴集团控股有限公司 | Data entry method and device, electronic equipment and computer readable storage medium |
| CN112561908A (en) * | 2020-12-24 | 2021-03-26 | 北京医准智能科技有限公司 | Mammary gland image focus matching method, device and storage medium |
| CN113808101A (en) * | 2021-09-16 | 2021-12-17 | 什维新智医疗科技(上海)有限公司 | Mammary nodule calcification analytical equipment |
| CN113808101B (en) * | 2021-09-16 | 2023-11-21 | 什维新智医疗科技(上海)有限公司 | Breast nodule calcification analysis device |
| CN115132314A (en) * | 2022-09-01 | 2022-09-30 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Examination impression generation model training method, examination impression generation model training device and examination impression generation model generation method |
| CN115132314B (en) * | 2022-09-01 | 2022-12-20 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Examination impression generation model training method, examination impression generation model training device and examination impression generation model generation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104376199A (en) | Method for intelligently generating breast report lesion schematic diagram | |
| US11790484B2 (en) | Two-dimensional scalar field data visualization method and system based on colormap optimization | |
| CN111430014B (en) | Glandular medical image display method, glandular medical image interaction method and storage medium | |
| CN103258343B (en) | A kind of eyes image disposal route based on picture editting | |
| CN110265141B (en) | Computer-aided diagnosis method for liver tumor CT image | |
| CN102750383A (en) | Spiral abstract generation method oriented to video content | |
| EP1840837A3 (en) | Graphics-rendering apparatus | |
| CN104704534A (en) | Medical image navigation | |
| CN102567381B (en) | Method and device for saving picture information | |
| CN110364250B (en) | Automatic labeling method, system and storage medium for mammary gland molybdenum target image | |
| US20160314502A1 (en) | System and method for streamlining the design and development process of multiple advertising units | |
| Zhou et al. | Interactive deep editing framework for medical image segmentation | |
| US20120206490A1 (en) | Print data creating apparatus, print data creating method, and computer program product | |
| CN116779093B (en) | Method and device for generating medical image structured report and computer equipment | |
| CN108241518A (en) | It is visual to pull layout and intelligent template generation method and system | |
| CN108182965B (en) | Electronic medical record generation system and method | |
| CN103164862B (en) | Based on the plane CAD/CAM drawing practice of Intelligent Recognition drawing instrument | |
| CN107656908A (en) | Method and system for implementing placeholder | |
| EP2410487A1 (en) | Method for automatically modifying a graphics feature to comply with a resolution limit | |
| Jung et al. | Feature of Interest‐Based Direct Volume Rendering Using Contextual Saliency‐Driven Ray Profile Analysis | |
| CN115274099B (en) | Human-intelligent interactive computer-aided diagnosis system and method | |
| CN108257202B (en) | Medical image volume reconstruction optimization method based on use scene | |
| CN103067781B (en) | A kind of multiple dimensioned representation of video shot and browsing method | |
| EP2734147B1 (en) | Method for segmentation of dental images | |
| CN108630301A (en) | A kind of signature method and device, computer storage media |
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 |
Application publication date: 20150225 |
|
| RJ01 | Rejection of invention patent application after publication |