CN107220646A - A kind of medical image Text region Enhancement Method for going ambient interferences - Google Patents
A kind of medical image Text region Enhancement Method for going ambient interferences Download PDFInfo
- Publication number
- CN107220646A CN107220646A CN201710376310.7A CN201710376310A CN107220646A CN 107220646 A CN107220646 A CN 107220646A CN 201710376310 A CN201710376310 A CN 201710376310A CN 107220646 A CN107220646 A CN 107220646A
- Authority
- CN
- China
- Prior art keywords
- medical image
- text region
- medical
- going
- ambient interferences
- 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
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000006243 chemical reaction Methods 0.000 claims abstract description 5
- 238000003325 tomography Methods 0.000 abstract description 5
- 238000002595 magnetic resonance imaging Methods 0.000 description 6
- 230000002490 cerebral effect Effects 0.000 description 3
- 210000001370 mediastinum Anatomy 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention relates to a kind of medical image Text region Enhancement Method for going ambient interferences, its step includes：Two adjacent and similar former medical images are first chosen in same sequence according to rule set in advance；Then anti-phase processing is carried out to a medical image RGB color, generates new medical image；Again new medical image subtract each other taking absolute value with another former medical image；Finally by binary conversion treatment, the enhanced medical image of Text region is obtained.The inventive method subtracts each other the ambient interferences for removing tomography medical image by crossing to inversely add, and high-quality medical science text information is obtained, consequently facilitating the classification of medical image, patient, the identification of doctor.
Description
Technical field
Know the present invention relates to medical image recognition technical field, more particularly to a kind of medical image word for going ambient interferences
Other Enhancement Method.
Background technology
CT scan, i.e. CT（Computed Tomography）, it is X-ray beam, the γ using Accurate collimation
Make continuous profile scanning in ray, ultrasonic wave etc., a certain position with the high detector of sensitivity together around human body.Magnetic is total to
Shake imaging, i.e. MRI（Magnetic Resonance Imaging）, it is also one kind of fault imaging, it utilizes electromagnetic induction phenomenon
Electromagnetic signal is obtained from human body, and reconstructs human body information.
In practice, most of CT, MRI can not be identified text information stratified storage, system in medical image
Four corners, partial stack influences the accurate extraction of text information, so as to have influence on the classification of medical image on image.Institute
State text information include but is not limited to patient's name, the age, sex, check number, medical number, the time, capture apparatus, CT values, window
Wide window position, FOV, KV, mAs, matrix etc..In order to accurately extract these text informations, it is necessary to the interference of reduction image as far as possible.
Based on the continuity of CT, MRI tomoscan, the image for all including one or more sequences is checked every time, and it is each
Sequence has tens of or hundreds of medical images, the slice thickness/slice distance that the quantity comprising image is set when being shot with doctor.Its
In, thickness refers to the thickness of scanning slice, and layer is away from referring to the distance between two layers center, and general thickness is arranged on 2-5mm, and layer is away from being continuous
, so adjacent two reconstruct the image spacing come between 0-10mm.CT, MRI are the changes using tissue density
Change or the change of water content forms image, and the change of the density of tissue or water content is also continuous.Therefore two
The profile and internal image of individual continuous scanning slice have larger similarity, and thickness is thinner, layer is higher away from smaller similarity.
In view of the characteristic of this tomography medical image of CT, MRI：The inspection number of homotactic picture mark, medical number, surname
Name, age, this kind of sex are all identicals, and the color value of absolute position and the size of single image and these information is fixed
's.The inventive method proposes the ambient interferences subtracted each other by inversely adding and remove tomography medical image, to improve medical science word
The discrimination of information.
The content of the invention
To solve the above problems, the present invention proposes a kind of medical image Text region Enhancement Method for going ambient interferences,
By removing the ambient interferences of tomography medical image, the identification of medical image text information is greatly increased.
The present invention has been achieved through the following technical solutions a kind of medical image Text region Enhancement Method for going ambient interferences,
It includes：
Two adjacent and similar former medical images are chosen in same sequence according to rule set in advance；
Anti-phase processing is carried out to a medical image RGB color, new medical image is generated；
And subtract each other taking absolute value with another former medical image；
Binary conversion treatment is carried out, the enhanced medical image of Text region is obtained；
The anti-phase processing refers to the color form and aspect reversion of medical image.
Further, the rule set in advance refers to according to the characteristic for shooting position, chooses two similar medical science figures
Picture.
The present invention subtracts each other the ambient interferences for removing tomography medical image by inversely adding, and obtains high-quality medical science word
Information, consequently facilitating the classification of medical image, patient, the identification of doctor.
Brief description of the drawings
Fig. 1：The cerebral CT figure of embodiment one.
Fig. 2：The mediastinum window CT figures of embodiment two.
Embodiment
Further detailed description is done to the present invention with reference to embodiment and accompanying drawing, but embodiments of the present invention are not limited
In this.
A cerebral CT figure is described in detail to the inventive method in conjunction with the embodiments.Its step includes：
（1）Choose two adjacent medical images of the same sequence of patient's cranium brain CT examination, its system of selection：Based on head
It is the spheroid of ellipse, the start-up portion of its same sequence and changing greatly for latter end sectional area, and the present invention is provided
Method be that two pictures more similar effects are better, so at this moment choose the continuous sectioning image in center section two it is more excellent.
Such as Fig. 1, the partially sliced of cerebral CT sequence for containing 25 images have chosen.Wherein A and B are the continuous of start-up portion
Two, C and D are continuous two of center section, and E and F are continuous two of latter end.By contrast it can be seen that initial part
The A and the E and F of B and latter end similarity divided is relatively low, and C the and D similarities of center section are higher.So we are suitable
Close selection C and D and be used as process object.
（2）Anti-phase processing is carried out to a medical image RGB color, new medical image is generated.
（3）New medical image and step（1）In another former medical image carry out phase by the rgb value of the pixel of same coordinate
Subtract and take absolute value.
（4）By step（3）The image that processing is completed does binary conversion treatment, and threshold value is 255, is set to 0 less than 255, obtains
The enhanced medical image of Text region.
Two mediastinum window CT figures are described in detail to the inventive method in conjunction with the embodiments.Its step includes：
（1）Choose two adjacent medical images of the same sequence of patient's mediastinum window CT examination, its system of selection：Based on vertical diaphragm
The image of window is changed greatly in start-up portion, smaller in the change close to latter end, so choosing two close to closing position
Open continuous section more excellent.Such as accompanying drawing 2, the part in the vertical diaphragm window sequence of a lung CT for containing 65 images have chosen
Section.Wherein A and B are continuous two of start-up portion, and C and D are continuous two of center section, and E and F are the companies of latter end
It is continuous two.It can be seen that the A and B of start-up portion and the C and D of center section similarity are relatively low by contrast, and end portion
E the and F similarities divided are higher.So we are adapted to selection E and F and are used as process object.
（2）Anti-phase processing is carried out to a medical image RGB color, new medical image is generated.
（3）New medical image and step（1）In another former medical image carry out phase by the rgb value of the pixel of same coordinate
Subtract and take absolute value.
（4）By step（3）The image that processing is completed does binary conversion treatment, and threshold value is 255, is set to 0 less than 255, obtains
The enhanced medical image of Text region.
It is upper described, only it is preferable two embodiments of the present invention, any formal limitation not is made to the present invention,
Although the present invention is disclosed as above with preferred embodiment, but is not limited to the present invention, any those skilled in the art,
Without departing from the scope of the present invention, when the technology contents using the disclosure above make a little change or are modified to
The equivalent embodiment of equivalent variations, as long as be without departing from technical solution of the present invention content, according to the present invention technical spirit to
Any brief introduction modification, equivalent variations and modification that upper embodiment is made, still fall within the scope of technical solution of the present invention.
Claims (2)
1. a kind of medical image Text region Enhancement Method for going ambient interferences, it is characterised in that comprise the following steps：
Two adjacent and similar former medical images are chosen in same sequence according to rule set in advance；
Anti-phase processing is carried out to a medical image RGB color, new medical image is generated；
And subtract each other taking absolute value with another former medical image；
Binary conversion treatment is carried out, the enhanced medical image of Text region is obtained；
The anti-phase processing refers to the color form and aspect reversion of medical image.
2. a kind of medical image Text region Enhancement Method for going ambient interferences according to claim 1, it is characterised in that
The rule set in advance refers to, according to the characteristic for shooting position, choose two similar medical images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710376310.7A CN107220646B (en) | 2017-05-25 | 2017-05-25 | Medical image character recognition enhancing method for removing background interference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710376310.7A CN107220646B (en) | 2017-05-25 | 2017-05-25 | Medical image character recognition enhancing method for removing background interference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107220646A true CN107220646A (en) | 2017-09-29 |
| CN107220646B CN107220646B (en) | 2020-04-14 |
Family
ID=59944541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710376310.7A Active CN107220646B (en) | 2017-05-25 | 2017-05-25 | Medical image character recognition enhancing method for removing background interference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220646B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785940A (en) * | 2018-12-28 | 2019-05-21 | 苏州承泽医疗科技有限公司 | A kind of method of medical image film typesetting |
| CN110060022A (en) * | 2019-03-12 | 2019-07-26 | 杭州华卓信息科技有限公司 | A kind of medicine film Intelligent printing method and system |
| CN110909674A (en) * | 2019-11-21 | 2020-03-24 | 清华大学苏州汽车研究院（吴江） | Traffic sign identification method, device, equipment and storage medium |
| CN111028186A (en) * | 2019-11-25 | 2020-04-17 | 泰康保险集团股份有限公司 | Image enhancement method and device |
| CN112348023A (en) * | 2020-10-28 | 2021-02-09 | 南阳柯丽尔科技有限公司 | Background and character separation method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003058826A (en) * | 2001-08-10 | 2003-02-28 | Konica Corp | Character information extraction device and its method, program and storage medium |
| CN1811794A (en) * | 2006-03-03 | 2006-08-02 | 清华大学 | Greyscale image partition method based on light distribution character of reflection or penetrance |
| CN102982238A (en) * | 2012-11-13 | 2013-03-20 | 深圳市环球博洋机电科技有限公司 | Three-dimensional kidney neoplasm surgery simulation method and platform based on computed tomography (CT) film |
| CN103337175A (en) * | 2013-06-22 | 2013-10-02 | 太仓博天网络科技有限公司 | Vehicle type recognition system based on real-time video steam |
| CN106683085A (en) * | 2016-12-23 | 2017-05-17 | 浙江大学 | CT image spine and spinal dura mater automation detection method |
-
2017
- 2017-05-25 CN CN201710376310.7A patent/CN107220646B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003058826A (en) * | 2001-08-10 | 2003-02-28 | Konica Corp | Character information extraction device and its method, program and storage medium |
| CN1811794A (en) * | 2006-03-03 | 2006-08-02 | 清华大学 | Greyscale image partition method based on light distribution character of reflection or penetrance |
| CN102982238A (en) * | 2012-11-13 | 2013-03-20 | 深圳市环球博洋机电科技有限公司 | Three-dimensional kidney neoplasm surgery simulation method and platform based on computed tomography (CT) film |
| CN103337175A (en) * | 2013-06-22 | 2013-10-02 | 太仓博天网络科技有限公司 | Vehicle type recognition system based on real-time video steam |
| CN106683085A (en) * | 2016-12-23 | 2017-05-17 | 浙江大学 | CT image spine and spinal dura mater automation detection method |
Non-Patent Citations (2)
| Title |
|---|
| 涂咏涛: "CT 图像压缩在远程医疗传输系统中的应用研究", 《自动化与仪器仪表》 * |
| 田小平 等: "基于塔型结构和ＬＩＰ模型的图像增强方法", 《西安邮电大学学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785940A (en) * | 2018-12-28 | 2019-05-21 | 苏州承泽医疗科技有限公司 | A kind of method of medical image film typesetting |
| CN110060022A (en) * | 2019-03-12 | 2019-07-26 | 杭州华卓信息科技有限公司 | A kind of medicine film Intelligent printing method and system |
| CN110909674A (en) * | 2019-11-21 | 2020-03-24 | 清华大学苏州汽车研究院（吴江） | Traffic sign identification method, device, equipment and storage medium |
| CN110909674B (en) * | 2019-11-21 | 2024-01-05 | 清华大学苏州汽车研究院（吴江） | Traffic sign recognition method, device, equipment and storage medium |
| CN111028186A (en) * | 2019-11-25 | 2020-04-17 | 泰康保险集团股份有限公司 | Image enhancement method and device |
| CN111028186B (en) * | 2019-11-25 | 2023-07-04 | 泰康保险集团股份有限公司 | Image enhancement method and device |
| CN112348023A (en) * | 2020-10-28 | 2021-02-09 | 南阳柯丽尔科技有限公司 | Background and character separation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107220646B (en) | 2020-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220646A (en) | A kind of medical image Text region Enhancement Method for going ambient interferences | |
| Wang et al. | Conditional generative adversarial networks for metal artifact reduction in CT images of the ear | |
| US11232543B2 (en) | System and method for image correction | |
| Leynes et al. | Direct pseudoCT generation for pelvis PET/MRI attenuation correction using deep convolutional neural networks with multi-parametric MRI: zero echo-time and dixon deep pseudoCT (ZeDD-CT) | |
| US9336613B2 (en) | Apparatus for generating assignments between image regions of an image and element classes | |
| US20130190602A1 (en) | 2d3d registration for mr-x ray fusion utilizing one acquisition of mr data | |
| Tao et al. | Pseudo CT image synthesis and bone segmentation from MR images using adversarial networks with residual blocks for MR-based attenuation correction of brain PET data | |
| JP2016116867A (en) | Medical image processing apparatus, medical image diagnostic apparatus and medical image processing program | |
| CN114881848A (en) | Method for converting multi-sequence MR into CT | |
| Liang et al. | Artificial intelligence‐based framework in evaluating intrafraction motion for liver cancer robotic stereotactic body radiation therapy with fiducial tracking | |
| Senthil et al. | Enhancement Sushisen algorithms in images analysis technologies to increase computerized tomography images | |
| US9672600B2 (en) | Clavicle suppression in radiographic images | |
| Kim et al. | Automatic localization of anatomical landmarks in cardiac MR perfusion using random forests | |
| Brückner et al. | Comparison of rigid and elastic matching of dynamic magnetic resonance mammographic images by mutual information | |
| Lee et al. | Study on Optimal Generative Network for Synthesizing Brain Tumor‐Segmented MR Images | |
| von Spiczak et al. | 3D image fusion of whole‐heart dynamic cardiac MR perfusion and late gadolinium enhancement: intuitive delineation of myocardial hypoperfusion and scar | |
| Arsic et al. | Image segmentation of the pulmonary acinus imaged by synchrotron X-ray tomography | |
| Vijayalakshmi | An enhanced Seeded region growing based techniques for hippocampus segmentation | |
| Longuefosse et al. | Lung CT Synthesis Using GANs with Conditional Normalization on Registered Ultrashort Echo-Time MRI | |
| Madhi et al. | Detection of Brain Tumors in Brain Images Based on Pseudo Coloring and Spatial Methods | |
| US20230419455A1 (en) | System and method for image correction | |
| US20220392077A1 (en) | Organ segmentation in image | |
| US20220398752A1 (en) | Medical image registration method and apparatus | |
| US20230214952A1 (en) | Methods and systems for vascular image processing | |
| How | Deep learning application on head CT images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder |
Address after: 311200 floor 4-6, East Building e, Hangzhou Bay Information Port, Xiaoshan District, Hangzhou City, Zhejiang Province Patentee after: HANGZHOU JIANPEI TECHNOLOGY Co.,Ltd. Address before: 310018 No. 3, No. 3, Hangzhou economic and Technological Development Zone, Hangzhou, Zhejiang Patentee before: HANGZHOU JIANPEI TECHNOLOGY Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder |