CN107049249A - Mammary gland examination image intelligent identifying system and method - Google Patents
Mammary gland examination image intelligent identifying system and method Download PDFInfo
- Publication number
- CN107049249A CN107049249A CN201710185298.1A CN201710185298A CN107049249A CN 107049249 A CN107049249 A CN 107049249A CN 201710185298 A CN201710185298 A CN 201710185298A CN 107049249 A CN107049249 A CN 107049249A
- Authority
- CN
- China
- Prior art keywords
- image
- recognition result
- identification
- breast
- instruction
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
- A61B5/0013—Medical image data
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
- A61B5/743—Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Physiology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention discloses a kind of mammary gland examination image intelligent identifying system and method, and applied in medical terminal device, the method comprising the steps of：The breast image signal of person to be detected is obtained from breast image acquisition terminal；It is mammary gland examination image by breast image signal transacting；Personal information and the image identification instruction of person to be checked is received from input block；Corresponding word is matched as image recognition result in instruction identification storehouse according to image identification instruction；Image identification report is generated according to image recognition result, and personal information is added to image identification report；Matching and breast image data of the mammary gland examination image similarity in presetting range in Medical Imaging Database of Breast, and breast image data are added to corresponding image identification report.Implement the present invention, doctor, which need to only input simple image identification instruction, just can obtain the recognition result of mammary gland examination image, simplify the operation of mammary gland examination image identification, improve the efficiency and accuracy of image identification.
Description
Technical field
The present invention relates to medical image processing and identification technology field, more particularly to a kind of mammary gland examination image Intelligent Recognition
System and method.
Background technology
Mammary gland disease is one of multiple illness of women, in particular with the quickening of modern metropolitan cities rhythm of life, women face
To life stress, operating pressure aggravate, the incidence of disease of mammary gland disease raising year by year, and serious mammary gland disease may cause breast
Gland cancer.Shown according to incomplete investigation statisticses, the morbidity and mortality of mammary gland disease are also all into ascendant trend.In fact, it is most of
The cause of death of breast cancer person to be checked is exactly, because not finding in time, best occasion for the treatment to be missed, therefore, to numerous female
Property carry out breast screening, mammary gland disease early find, early diagnosis be very necessary for women's health.
At present, carry out auxiliary diagnosis using mammary gland examination image and have become the examination being widely adopted and diagnosis early stage breast
The important method of gland cancer.Doctor is when checking mammary gland examination image, it is impossible to synchronous to write report, but to be switched to report and write
Interface or program in carry out；Also, when writing report, it is necessary to which content is word for word input in computer.For
Some relatively conventional inspection results (such as a part no abnormality seen), it is still desirable to carry out cumbersome input, be so accomplished by
The suitable energy and time of consumption, easily occurs the phenomenon that maloperation causes mammary gland screening efficiency to decline, and is not suitable for a large amount of mammary gland
The generaI investigation situation of sample.Further, since breast image quantity is a lot, doctor directly every width breast image is identified and manual
Write report and be difficult to ensure that efficiency and accuracy, so as to easily cause the situation generation failed to pinpoint a disease in diagnosis with mistaken diagnosis.
The content of the invention
It is a primary object of the present invention to provide a kind of mammary gland examination image intelligent identifying system and method, only need doctor defeated
Entering simple image identification instruction just can obtain the recognition result of mammary gland examination image, simplify the behaviour of mammary gland examination image identification
Make, improve the efficiency and accuracy of image identification.
To achieve the above object, the invention provides a kind of mammary gland examination image intelligent identifying system, applied to medical whole
In end equipment, the medical terminal device is connected to breast image acquisition terminal and medical information platform by communication network, described
Mammary gland examination image intelligent identifying system includes：Image acquiring module, for obtaining person to be detected from breast image acquisition terminal
Breast image signal, be mammary gland examination image by the breast image signal transacting of person to be detected, and from medical terminal device
Input block receive input person to be checked personal information and image identification instruction；Image identification module, for according to shadow
As identification instruction, matching is known with the image identification corresponding word of instruction as image in the instruction identification storehouse of medical information platform
Other result；Report generation module, for generating the shadow for showing image recognition result according to the image recognition result matched
It is added to as identification report, and by the personal information of person to be checked in image identification report；Image Matching module, in medical treatment
Matching and breast image data of the mammary gland examination image similarity in presetting range in the Medical Imaging Database of Breast of information platform,
And the breast image data that this is matched are added in corresponding image identification report.
It is preferred that, the breast image acquisition terminal includes infrared emittance, infrared remote receiver, analog-digital converter and led to
Believe port, wherein：The infrared emittance is used to produce infrared light and by the mammary gland of infrared x ray fluoroscopy x to person to be detected；It is described
Infrared remote receiver is used to gather the breast tissue that the infrared signal for passing through the mammary gland of person to be detected is processed as including person to be detected
The analog electrical signal of structural information；The analog-digital converter is used for the simulation of the mammary structure information comprising person to be detected
Electric signal analog-to-digital conversion is the breast image signal of digital signal form；The COM1 is used for the mammary gland shadow of person to be detected
As signal is sent to the medical terminal device.
It is preferred that, the image recognizes instruction for the first distinguishing mark, the second distinguishing mark or the 3rd distinguishing mark, described
Image recognition result is the image recognition result of normal image recognition result, the image recognition result of reference or exception, wherein：
When image identification instruction is the first distinguishing mark, the image identification module judges the image identification of mammary gland examination image
As a result it is normal, and matching is tied with the normal corresponding word of Breast health as the identification of normal image in instruction identification storehouse
Really；When image identification instruction is the second distinguishing mark, the image identification module is according to the second distinguishing mark in instruction
Identification matches corresponding word as the image recognition result of reference in storehouse；When image identification instruction is the 3rd distinguishing mark
When, the image identification module judges that image recognition result is abnormal image recognition result, and is existed according to the 3rd distinguishing mark
Instruction identification matches corresponding word as abnormal image recognition result in storehouse.
It is preferred that, the mammary gland examination image intelligent identifying system also includes result and indicates module, result sign module
For recognizing the normal image recognition result in report, abnormal image recognition result to image or referring to image recognition result
It is identified, shows normal in image identification report in the display unit of medical terminal device with preset display mode
Image recognition result, abnormal image recognition result refer to image recognition result.
It is preferred that, image recognition result corresponding with image identification instruction is not matched in storehouse when the instruction is recognized
When, the image identification module is additionally operable to receive the image recognition result of doctor's input and described in from the input block
In image identification report, and the image recognition result of input is recognized in storehouse added to the instruction.
The present invention also provides a kind of mammary gland examination image intelligent identification Method, applied in medical terminal device, the medical treatment
Terminal device is connected to breast image acquisition terminal and medical information platform by communication network, and the method comprising the steps of：From breast
Gland image collection terminal obtains the breast image signal of person to be detected；The breast image signal transacting of person to be detected is sieved for mammary gland
Look into image；Personal information and the image identification instruction of the person to be checked of input is received from the input block of medical terminal device；Root
Recognize that instruction matching in the instruction identification storehouse of medical information platform is used as shadow with the image identification corresponding word of instruction according to image
As recognition result；The image that image recognition result according to matching is generated for showing image recognition result recognizes report, and
The personal information of person to be checked is added in image identification report；Matched in the Medical Imaging Database of Breast of medical information platform
With breast image data of the mammary gland examination image similarity in presetting range, and the breast image data that this is matched add
Into the identification report of corresponding image.
It is preferred that, it is described person to be detected is obtained from breast image acquisition terminal breast image signal the step of include：Profit
Infrared light is produced with the infrared emittance of breast image acquisition terminal and by the mammary gland of infrared x ray fluoroscopy x to person to be detected；Pass through
The infrared remote receiver collection of breast image acquisition terminal is processed as comprising to be checked through the infrared signal of the mammary gland of person to be detected
The analog electrical signal of the mammary structure information of survey person；It will be included using the analog-digital converter of breast image acquisition terminal to be checked
The analog electrical signal analog-to-digital conversion of the mammary structure information of survey person is the breast image signal of digital signal form；Pass through breast
The COM1 of gland image collection terminal is used to send the breast image signal of person to be detected to the medical terminal device.
It is preferred that, the image recognizes instruction for the first distinguishing mark, the second distinguishing mark or the 3rd distinguishing mark, described
Image recognition result is the image recognition result of normal image recognition result, the image recognition result of reference or exception, wherein：
When image identification instruction is the first distinguishing mark, judge that the image recognition result of mammary gland examination image is normal, and
Matching is used as normal image recognition result with the normal corresponding word of Breast health in instruction identification storehouse；When image identification
When instructing as the second distinguishing mark, corresponding word is matched as the shadow of reference in instruction identification storehouse according to the second distinguishing mark
As recognition result；When image identification instruction is three distinguishing mark, it is that abnormal image is known to judge image recognition result
Other result, and corresponding word is matched as abnormal image recognition result in instruction identification storehouse according to the 3rd distinguishing mark.
It is preferred that, the mammary gland examination image intelligent identification Method also comprises the following steps：To in image identification report
Normal image recognition result, abnormal image recognition result are identified with reference to image recognition result, with preset display
Mode shows normal image recognition result, abnormal shadow in image identification report in the display unit of medical terminal device
As recognition result or with reference to image recognition result.
It is preferred that, the mammary gland examination image intelligent identification Method also comprises the following steps：When in the instruction identification storehouse
When not matching with the image identification corresponding image recognition result of instruction, the shadow of doctor's input is received from the input block
In being reported as recognition result and added to image identification, and the image recognition result of input is added in the instruction identification storehouse
Compared to prior art, mammary gland examination image intelligent identifying system of the present invention and method can entered in doctor
During row mammary gland examination image is recognized, the image identification instruction inputted according to doctor is matched in preset instruction recognizes storehouse
Image recognition result corresponding with image identification instruction, matching and mammary gland examination image phase in preset Medical Imaging Database of Breast
Like breast image data of the degree in presetting range, and according to image recognition result and the generation image identification of breast image data
Report.The recognition result of mammary gland examination image just can be obtained because doctor need to only input simple image identification instruction, without
Doctor inputs cumbersome inspection conclusion, so as to simplify the operation of breast image identification, improves the efficiency of breast image identification
And accuracy, auxiliary doctor raising is to the efficiency and accuracy of mammary gland disease detection and examination, and the society for improving mammary gland examination imitates
Rate.
Brief description of the drawings
Fig. 1 is the application environment schematic diagram of mammary gland examination image intelligent identifying system preferred embodiment of the present invention；
Fig. 2 is the flow chart of mammary gland examination image intelligent identification Method preferred embodiment of the present invention.
The object of the invention is realized, functional characteristics and advantage will combine embodiment, is described further referring to the drawings.
Embodiment
Further to illustrate the present invention to reach the technological means and effect that above-mentioned purpose is taken, below in conjunction with accompanying drawing
And preferred embodiment, embodiment, structure, feature and its effect to the present invention are described in detail.It should be appreciated that this
The specific embodiment of place description is not intended to limit the present invention only to explain the present invention.
Shown in reference picture 1, Fig. 1 is that the application environment of mammary gland examination image intelligent identifying system preferred embodiment of the present invention is shown
It is intended to.In the present embodiment, the mammary gland examination image intelligent identifying system 10 is installed and run in medical terminal device 1.
The medical terminal device 1 sets up communication link by communication network 3 and medical information platform 2 and breast image acquisition terminal 4
Connect.The medical terminal device 1 is arranged on the tool such as doctor workstation computer, server of mammary gland medical center or large hospital
There is the computing device of data processing and communication function.During the medical information platform 2 can be a kind of medical information system platform
A server, the medical information platform 2 includes instruction identification storehouse 21 and Medical Imaging Database of Breast 22.In the present embodiment
In, have collected in advance in the preset instruction identification storehouse 21 the conventional medical terminology of Breast health examination, radiologic term with
And common image recognition result masterplate, under normal conditions, corresponding to masterplate for normal image recognition result.The breast
Conventional various normal or abnormal breast image data are stored in gland image database 22 to receive mammary gland for reference
After examination image, similarity mode can be carried out to the breast image data in mammary gland examination image and Medical Imaging Database of Breast.
The communication network 3 can be a kind of world-wide web including LAN, wide area network, or it is a kind of include GSM, GPRS,
CDMA wireless-transmission network.
The galactophore image acquisition terminal 4 is arranged in the medical examination such as community medicine work station mechanism, and whole with medical treatment
End equipment 1 sets up network service connection.In the present embodiment, the galactophore image acquisition terminal 4 includes infrared emittance 41, red
Outer receiver 42, analog-digital converter 43 and COM1 44.The infrared emittance 41 produces infrared light and infrared light is saturating
Depending on the mammary gland to person to be detected；The collection of infrared remote receiver 42 passes through the infrared signal of the mammary gland of person to be detected and is processed as breast
The analog electrical signal of glandular tissue structural information；The infrared x ray fluoroscopy x that infrared emittance 41 is produced is infrared on person's mammary gland to be detected
The infrared signal that receiver 42 is received carries the infrared transmission light of mammary structure information.Analog-digital converter 43 will be infrared
The analog electrical signal analog-to-digital conversion process comprising person's mammary structure information to be detected that receiver 42 is collected is believed for numeral
The breast image signal of number form；The COM1 44 is used for the mammary gland figure by person's information to be detected and comprising person to be detected
As the data signal of information is sent to Cloud Server 1 by communication network 3.The COM1 44 can have remotely to be a kind of
The wireless communication interface of wireless communication function, for example, support GSM, GPRS, CDMA communication interface.
In the present embodiment, the medical terminal device 1 is include but not limited to, mammary gland examination image Intelligent Recognition system
System 10, input block 11, memory cell 12, processing unit 13, communication unit 14 and display unit 15.The input block 11,
Memory cell 12, processing unit 13, communication unit 14 and display unit 15 are connected to processing unit 13 by data/address bus, and
Information exchange can be carried out by processing unit 13 and mammary gland examination image intelligent identifying system 10.The input block 11 can be
The hardware devices such as keyboard, touch-screen or mouse.The memory cell 12 is a kind of read-only memory unit ROM, electrically-erasable storage
The memory such as unit EEPROM or flash memory cell FLASH.The processing unit 13 is a kind of central processing unit (CPU), micro-
Processor, microcontroller (MCU), data processing chip or the information process unit with data processing function.The communication
Unit 14 can be a kind of wireless communication interface with long-distance radio communication function, for example, support GSM, GPRS, CDMA's logical
Communication interface.The display unit 15 is display, for showing that the breast examination of person to be checked is reported.
In the present embodiment, the mammary gland examination image intelligent identifying system 10 includes, but are not limited to, image capturing mould
Block 101, image identification module 102, report generation module 103, Image Matching module 104 and result sign module 105.This hair
Bright alleged module refers to a kind of to be performed by the processing unit 13 of the medical terminal device 1 and can complete to fix work(
The series of computation machine programmed instruction section of energy, it is stored in the memory cell 12 of the medical terminal device 1.
The image acquiring module 101 is used for the breast image signal that person to be detected is obtained from breast image acquisition terminal 4.
In the present embodiment, the infrared emittance 41 produces infrared light and by the mammary gland of infrared x ray fluoroscopy x to person to be detected；It is described
The collection of infrared remote receiver 42 passes through the infrared signal of the mammary gland of person to be detected and is processed as the simulation of mammary structure information
Electric signal；The mould for including person's mammary structure information to be detected that the analog-digital converter 43 collects infrared remote receiver 42
Intend the breast image signal that electric signal analog-to-digital conversion process is digital signal form；The COM1 44 is by the breast of person to be detected
Gland image signal transmitting delivers to image acquiring module 101.
It is mammary gland examination image that the image acquiring module 101, which is additionally operable to the breast image signal transacting of person to be detected,.
Specifically, image acquiring module 101 handles software by the breast image signal of person to be detected with digital document using digitized video
Form recording image data, the mammary gland examination image of person to be detected is then produced according to the image data.In the present embodiment,
The principle of infrared breast cancer is：Infrared light irradiation human breast position, because human breast's tissue is to by therein red
External spectrum shows different absorption characteristics, thus through diseased region infrared signal with it is red through normal galactophore tissue
The intensity of external signal can be different, passes through the gray scale, institutional framework, appearance and size particularly mammary gland of the infrared image that collects
The optical characteristics of tissue, it is possible to detect the positions and dimensions that lesion occurs for mammary gland position.
The image acquiring module 101 is additionally operable to receive the personal information and shadow of the person to be checked inputted from input block 11
As identification instruction.In the present embodiment, doctor inputs the personal information of mammary gland examination person to be checked, including surname from input block 11
The information such as name, age, sex, medical history.When recognizing mammary gland examination image, doctor need to also be used for input checking from input block 11
The image identification instruction of Breast health situation.
The image identification module 102 is used to recognize that instruction recognizes storehouse 21 in the instruction of medical information platform 2 according to image
Middle matching is used as image recognition result with the image identification corresponding word of instruction.In the present embodiment, the image identification instruction
Can be the first distinguishing mark, the second distinguishing mark or the 3rd distinguishing mark；The image recognition result can be normal shadow
As the image recognition result of recognition result, the image recognition result of reference or exception.Specifically, as described in image identification instruction
Including the first preset distinguishing mark, first distinguishing mark is as judging whether image recognition result is normal indicateing arm
Will, i.e., when image identification instruction includes first distinguishing mark, image identification module 102 judges the shadow of mammary gland examination image
Picture recognition result is normal, and the content of first distinguishing mark is ordinarily selected to different from related medical terminology and radiologic term
Word.For example, when image identification instruction includes " click+mammary gland ", then the image recognition result for showing mammary gland examination image is
Normally, now, matching it can be tied in instruction identification storehouse 21 with the normal corresponding word of Breast health as the identification of normal image
Really, for example matching " mammary gland no abnormality seen " is used as normal image recognition result.Image identification instruction includes preset as described
The second distinguishing mark, second distinguishing mark as judge image recognition result whether be reference image recognition result finger
Indicating will, i.e., when image identification instruction includes second distinguishing mark, expression now needs matching and mammary gland examination image pair
The image recognition result for the reference answered, image identification module 102 according to the second distinguishing mark instruction identification storehouse 21 in matching with
The corresponding word of mammary gland examination image as reference image recognition result.The content of second distinguishing mark may be configured as " referring to "
Etc. can substantially determine its indicate image recognition result for reference image recognition result word.For example, when image identification
Instruct as " reference ", then matching recognizes the corresponding word of the conclusion reported with image in instruction identification storehouse, using the word as
The image recognition result of reference.Image identification as described instructs the 3rd distinguishing mark, then image identification module 102 can determine whether image
Recognition result is not normal image recognition result, and according to the 3rd distinguishing mark instruction identification storehouse in match it is corresponding
Word.The corresponding word of the 3rd distinguishing mark such as matched is unrelated with the image recognition result to mammary gland examination image, then table
The bright image identification instruction ignore received；On the contrary, then showing that the corresponding image recognition result of image identification instruction is abnormal
Image recognition result.For example, identify image identification instruction for " the visible several soft-tissue density's stoves in breast both sides, form with
Breast cancer is consistent ", then corresponding word is matched in instruction identification storehouse, regard the word as abnormal image recognition result.
In the present embodiment, the image identification module 102 is not matched in instruction identification storehouse 21 such as and recognized with image
Corresponding image recognition result is instructed, then shows the corresponding word that is not stored with instruction identification storehouse 21, now, doctor can lead to
Cross input block 11 and input corresponding image recognition result into image identification report, image identification module 102 is then by input
Image recognition result is recognized in storehouse 21 added to instruction, during in case receiving same or analogous image identification instruction in next time,
Corresponding image recognition result is matched from instruction identification storehouse 21.
The report generation module 103 is used to be generated for showing image identification knot according to the image recognition result matched
The image identification report of fruit, and the personal information of person to be checked is added in image identification report.When image recognition result is
When normal, then show that person's Breast health situation to be detected is normal；When image recognition result is exception, then doctor's input is received
The sign of abnormal position is instructed and indicated in the abnormal position of the mammary gland examination image, so that doctor enters one to mammary gland disease
Step carries out diagnosis and provides reference with examination.When generating image identification report, report generation module 103 can be by person's to be checked
The information such as name, age, sex, medical history are embedded into the front portion of image identification report in a modular fashion, and can be in image
The end of identification report automatically generates timestamp；Meanwhile, doctor can sign the name of oneself in image identification report.In report
Accuse after the generation image identification report of generation module 103, such as find that the image recognition result in image identification report is wrong, then can be right
The content of mistake is modified or deletion action.
The Image Matching module 104 is used for matching and mammary gland examination image phase in preset Medical Imaging Database of Breast 22
Corresponding image identification is added to like breast image data of the degree in presetting range, and by the breast image data that this is matched
In report.When similarity within a preset range when, obtain Medical Imaging Database of Breast 22 in similar view data sieved as mammary gland
The corresponding breast image data of image are looked into, preset range can set according to breast region of interest is self-defined, for example, be set to big
In 80%.After Image Matching module 104 matches mammary gland examination image corresponding breast image data, the mammary gland that will match to
Image data is added in corresponding image identification report.Not only the image including mammary gland examination image is recognized for image identification report
As a result, the breast image data of the mammary gland examination image are included, for doctor and person to be checked reference.
The result sign module 105 is used to recognize image the normal image recognition result in report, abnormal shadow
It is identified as recognition result or with reference to image recognition result, image identification is shown in display unit 15 with preset display mode
Normal image recognition result in report, abnormal image recognition result refer to image recognition result.Specifically, as a result mark
Show that module 105 is normal according to image recognition result or abnormal recognized to normal image recognition result and abnormal image is tied
Fruit carries out different marks, while reference result can be designated to what can be distinguished with normal or abnormal image recognition result
Other marks, are such as labeled as different fonts or different colors by different image recognition results, so as in display, with pre-
The display mode put is shown, for example, the word content of abnormal image recognition result is shown or carried out in overstriking form
Highlight.In the present embodiment, recognize that the image recognition result in report is normal image recognition result such as image, then may be used
After matching and representing image recognition result as normal identification masterplate, to be designated to the corresponding word content of identification masterplate
Blue font, and normally show；, then can be with as image recognizes that the image recognition result in report is abnormal image recognition result
It is red font by the word content identification after the abnormal corresponding word of image recognition result is matched, and in display
The word content of the red font is shown or highlighted in overstriking form, to remind person to be checked to note.In generation
During image identification report, recognize that the image recognition result of the normal image recognition result in report or exception is carried out not to image
Same mark, and normal image recognition result or abnormal image recognition result are shown with preset display mode so that shadow
As identification report display is relatively sharp, doctor and person to be detected is facilitated to read.
Present invention also offers a kind of mammary gland examination image intelligent identification Method, applied in medical terminal device.Such as Fig. 2
Shown, Fig. 2 is the flow chart of mammary gland examination image intelligent identification Method preferred embodiment of the present invention.The present embodiment combines figure in the lump
Shown in 1, the mammary gland examination image intelligent identification Method includes step：
Step S21, image acquiring module 101 obtains the breast image signal of person to be detected from breast image acquisition terminal 4,
And be mammary gland examination image by the breast image signal transacting of person to be detected；In the present embodiment, infrared emittance 41 produces red
Outer light and by the mammary gland of infrared x ray fluoroscopy x to person to be detected；The collection of infrared remote receiver 42 is through the infrared of the mammary gland of person to be detected
Optical signal and the analog electrical signal for being processed as mammary structure information；Analog-digital converter 43 collects infrared remote receiver 42
Analog electrical signal analog-to-digital conversion process comprising person's mammary structure information to be detected is the breast image of digital signal form
Signal；COM1 44 sends the breast image signal of person to be detected to image acquiring module 101.Image acquiring module 101
Using digitized video processing software by the breast image signal of person to be detected recording image data in the form of digital files, then
The mammary gland examination image of person to be detected is produced according to the image data.
Step S22, image acquiring module 101 receives the personal information and image of the person to be checked of input from input block 11
Identification instruction.In the present embodiment, doctor inputs the personal information of mammary gland examination person to be checked, including surname from input block 11
The information such as name, age, sex, medical history.When recognizing mammary gland examination image, doctor need to also be used for input checking from input block 11
The image identification instruction of Breast health situation.
Step S23, according to image identification instruction, the matching in instruction identification storehouse 21 is recognized image identification module 102 with image
Corresponding word is instructed as image recognition result.In the present embodiment, the image identification instruction can be the first identification mark
Will, the second distinguishing mark or the 3rd distinguishing mark；The image recognition result can be normal image recognition result, reference
The image recognition result of image recognition result or exception.Specifically, image identification instruction includes the first preset knowledge as described
Do not indicate, first distinguishing mark is as judging whether image recognition result is normal Warning Mark, i.e., when image identification refers to
When order includes first distinguishing mark, image identification module 102 judge the image recognition result of mammary gland examination image be it is normal,
The content of first distinguishing mark is ordinarily selected to the word different from related medical terminology and radiologic term.For example, working as shadow
Include " click+mammary gland " as identification is instructed, then the image recognition result for showing mammary gland examination image is normal, now, can referred to
Matching and the normal corresponding word of Breast health, for example, match " mammary gland no abnormality seen " and be used as normal image in order identification storehouse 21
Recognition result.Image identification instruction includes the second preset distinguishing mark as described, and second distinguishing mark is as judging shadow
As recognition result whether be reference image recognition result Warning Mark, i.e., when image identification instruction include this second recognize
During mark, expression now needs to match the image recognition result of reference corresponding with mammary gland examination image, image identification module 102
According to the second distinguishing mark, matching word corresponding with mammary gland examination image is recognized as the image of reference in instruction identification storehouse 21
As a result.The content of second distinguishing mark, which may be configured as " referring to " etc., can substantially determine that its image recognition result indicated is reference
Image recognition result word.For example, when image recognizes that instruction is " reference ", then being matched and image in instruction identification storehouse 21
Recognize report the corresponding word of conclusion, using the word as reference image recognition result.Image identification instruction the as described
Three distinguishing marks, then image identification module 102 can determine whether that image recognition result is not normal image recognition result, and according to
Three distinguishing marks match corresponding word in instruction identification storehouse 21.Now, the 3rd distinguishing mark correspondence such as matched
Word it is unrelated with the image recognition result to mammary gland examination image, then the image identification instruction ignore for showing to receive；On the contrary,
Then show that the corresponding image recognition result of image identification instruction is abnormal image recognition result.For example, the image identified is known
Zhi Ling be " the visible several soft-tissue density's stoves in breast both sides, form is consistent with breast cancer ", then instruction recognize storehouse 21 in
With corresponding word, the word is regard as abnormal image recognition result.
In the present embodiment, image identification module 102 does not match in instruction identification storehouse 21 such as and recognizes instruction with image
Corresponding image recognition result, then show the corresponding word that is not stored with instruction identification storehouse 21, now, doctor can be by defeated
Enter unit 11 and input corresponding image recognition result into image identification report, image identification module 102 is then by the image of input
Recognition result is recognized in storehouse 21 added to instruction, during in case receiving same or analogous image identification instruction in next time, from finger
Order identification matches corresponding image recognition result in storehouse 21.
Step S24, report generation module 103 is generated for showing image identification knot according to the image recognition result matched
The image identification report of fruit, and the personal information of person to be checked is added in image identification report.When image recognition result is
When normal, then show that person's Breast health situation to be detected is normal；When image recognition result is exception, then doctor's input is received
The sign of abnormal position is instructed and indicated in the abnormal position of the mammary gland examination image, so that doctor enters one to mammary gland disease
Step carries out diagnosis and provides reference with examination.When generating image identification report, report generation module 103 can be by person's to be checked
The information such as name, age, sex, medical history are embedded into the front portion of image identification report in a modular fashion, and can be in image
The end of identification report automatically generates timestamp；Meanwhile, doctor can sign the name of oneself in image identification report.Report
After the generation image identification report of generation module 103, such as find that the image recognition result in image identification report is wrong, doctor then may be used
Content to mistake is modified or deletion action.
Step S25, Image Matching module 104 matches similar to mammary gland examination image in preset Medical Imaging Database of Breast
The breast image data in presetting range are spent, and the breast image data matched are added to corresponding image identification and are reported
In.In the present embodiment, conventional various normal or abnormal breast image number is stored in the Medical Imaging Database of Breast 22
According to can for reference, after mammary gland examination image is received, Image Matching module 104 can be to mammary gland examination image and breast image
Breast image data in database carry out similarity mode.When similarity within a preset range when, obtain breast image data
Similar view data in storehouse are as the corresponding breast image data of mammary gland examination image, and preset range can be according to breast phase
The self-defined setting in position is closed, for example, is set greater than 80%.Image Matching module 104 is to match mammary gland examination image corresponding
After breast image data, it is added to according to the breast image data in corresponding image identification report.The image identification report
Not only include the image recognition result of mammary gland examination image, include the breast image data of the mammary gland examination image, for doctor
Raw and person to be checked reference.
Step S26, as a result indicates module 105 and the normal image recognition result in report, abnormal shadow is recognized to image
It is identified as recognition result or with reference to image recognition result, the image is shown in display unit 15 with preset display mode
Recognize the normal image recognition result in report, abnormal image recognition result or refer to image recognition result.Specifically, tie
Fruit sign module 105 is normal according to image recognition result or exception is known to normal image recognition result and abnormal image
Other result carries out different marks, can be with normal or abnormal image recognition result area while can be designated reference result
Point other mark, such as by different image recognition results be labeled as different fonts or different colors, so as to show when,
Shown with preset display mode display unit 15, for example, to the word content of abnormal image recognition result with overstriking
Form shows or highlighted.
In the present embodiment, recognize that the image recognition result in report is normal image recognition result such as image, then may be used
After matching and representing image recognition result as normal identification masterplate, to be designated to the corresponding word content of identification masterplate
Blue font, and normally show；, then can be with as image recognizes that the image recognition result in report is abnormal image recognition result
It is red font by the word content identification after the abnormal corresponding word of image recognition result is matched, and in display
The word content of the red font is shown or highlighted in overstriking form, to remind person to be checked to note.In generation
During image identification report, recognize that the image recognition result of the normal image recognition result in report or exception is carried out not to image
Same mark, and normal image recognition result or abnormal image recognition result are shown with preset display mode so that shadow
As identification report display is relatively sharp, doctor and person to be checked is facilitated to read.
Mammary gland examination intelligent identifying system of the present invention and method, can carry out the identification of mammary gland examination image in doctor
During, simple image identification is inputted according to doctor and instructs the matching in preset instruction recognizes storehouse to recognize instruction with image
Corresponding image recognition result, matching and mammary gland examination image similarity are in presetting range in preset Medical Imaging Database of Breast
Interior breast image data, and reported according to image recognition result and the generation image identification of breast image data, due to doctor
Simple image identification instruction, which need to only be inputted, just can obtain the recognition result of mammary gland examination image, be inputted without doctor cumbersome
Conclusion is checked, so as to simplify the operation of breast image identification, the efficiency and accuracy of breast image identification are improved, so that auxiliary
Help doctor to improve the efficiency and accuracy detected to mammary gland disease with examination, improve the social efficiency of mammary gland examination.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or the equivalent function conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of mammary gland examination image intelligent identifying system, applied in medical terminal device, the medical terminal device passes through logical
Communication network is connected to breast image acquisition terminal and medical information platform, it is characterised in that the mammary gland examination image is intelligently known
Other system includes：
Image acquiring module, the breast image signal for obtaining person to be detected from breast image acquisition terminal, by person to be detected
Breast image signal transacting be mammary gland examination image, and receive the to be checked of input from the input block of medical terminal device
Personal information and image the identification instruction of person；
Image identification module, for recognizing that instruction matching in the instruction of medical information platform recognizes storehouse is known with image according to image
Corresponding word is not instructed as image recognition result；
Report generation module, the image for being generated according to the image recognition result matched for showing image recognition result is known
Do not report, and the personal information of person to be checked is added in image identification report；
Image Matching module, for the matching in the Medical Imaging Database of Breast of medical information platform and mammary gland examination image similarity
Breast image data in presetting range, and the breast image data that this is matched are added to corresponding image identification report
In.
2. mammary gland examination image intelligent identifying system as claimed in claim 1, it is characterised in that the breast image collection is eventually
End includes infrared emittance, infrared remote receiver, analog-digital converter and COM1, wherein：
The infrared emittance is used to produce infrared light and by the mammary gland of infrared x ray fluoroscopy x to person to be detected；
The infrared remote receiver is used for collection and is processed as through the infrared signal of the mammary gland of person to be detected comprising person to be detected
The analog electrical signal of mammary structure information；
The analog-digital converter is used for
The breast image signal of digital signal form；
The COM1 is used to send the breast image signal of person to be detected to the medical terminal device.
3. mammary gland examination image intelligent identifying system as claimed in claim 1, it is characterised in that the image recognizes that instruction is
First distinguishing mark, the second distinguishing mark or the 3rd distinguishing mark, the image recognition result be normal image recognition result,
The image recognition result of reference or the image recognition result of exception, wherein：
When image identification instruction is the first distinguishing mark, the image identification module judges the image of mammary gland examination image
Recognition result is normal, and matching is recognized with the normal corresponding word of Breast health as normal image in instruction identification storehouse
As a result；
When image identification instruction is the second distinguishing mark, the image identification module is according to the second distinguishing mark in instruction
Identification matches corresponding word as the image recognition result of reference in storehouse；
When image identification instruction is three distinguishing mark, the image identification module judges that image recognition result is abnormal
Image recognition result, and corresponding word matched in instruction identification storehouse according to the 3rd distinguishing mark known as abnormal image
Other result.
4. mammary gland examination image intelligent identifying system as claimed in claim 3, it is characterised in that the system also includes result mark
Show module, for recognizing the normal image recognition result in report, abnormal image recognition result to image or referring to image
Recognition result is identified, and is shown with preset display mode in the display unit of medical terminal device in image identification report
Normal image recognition result, abnormal image recognition result or refer to image recognition result.
5. mammary gland examination image intelligent identifying system as claimed in claim 1, it is characterised in that when in the instruction identification storehouse
When not matching with the image identification corresponding image recognition result of instruction, the image identification module is additionally operable to from described defeated
Enter unit to receive the image recognition result of doctor's input and recognize in report added to the image, and the image of input is recognized
As a result recognized added to the instruction in storehouse.
6. a kind of mammary gland examination image intelligent identification Method, applied in medical terminal device, the medical terminal device passes through logical
Communication network is connected to breast image acquisition terminal and medical information platform, it is characterised in that the method comprising the steps of：
The breast image signal of person to be detected is obtained from breast image acquisition terminal；
It is mammary gland examination image by the breast image signal transacting of person to be detected；
Personal information and the image identification instruction of person to be checked is received from the input block of medical terminal device；
Recognize that instruction matching in the instruction identification storehouse of medical information platform recognizes the corresponding word of instruction with image according to image
It is used as image recognition result；
The image that image recognition result according to matching generates for showing image recognition result recognizes report, and will be to be checked
The personal information of person is added in image identification report；
Matching and breast of the mammary gland examination image similarity in presetting range in the Medical Imaging Database of Breast of medical information platform
Gland image data, and the breast image data that this is matched are added in corresponding image identification report.
7. mammary gland examination image intelligent identification Method as claimed in claim 6, it is characterised in that described from breast image collection
The step of terminal obtains the breast image signal of person to be detected includes：
Infrared light is produced using the infrared emittance of breast image acquisition terminal and by the mammary gland of infrared x ray fluoroscopy x to person to be detected
On；
It is processed as by the infrared remote receiver collection of breast image acquisition terminal through the infrared signal of the mammary gland of person to be detected
The analog electrical signal of mammary structure information comprising person to be detected；
It is using the analog-digital converter of breast image acquisition terminal that the simulation of the mammary structure information comprising person to be detected is electric
Signal modulus is converted to the breast image signal of digital signal form；
It is used to send the breast image signal of person to be detected to the medical treatment by the COM1 of breast image acquisition terminal
Terminal device.
8. mammary gland examination image intelligent identification Method as claimed in claim 6, it is characterised in that the image recognizes that instruction is
First distinguishing mark, the second distinguishing mark or the 3rd distinguishing mark, the image recognition result be normal image recognition result,
The image recognition result of reference or the image recognition result of exception, wherein：
When the image identification instruction be the first distinguishing mark when, the image recognition result for judging mammary gland examination image be it is normal,
And matching is used as normal image recognition result with the normal corresponding word of Breast health in instruction identification storehouse；
When image identification instruction is the second distinguishing mark, and according to the matching pair in instruction identification storehouse of the second distinguishing mark
The word answered as reference image recognition result；
When image identification instruction is three distinguishing mark, it is abnormal image recognition result to judge image recognition result,
And corresponding word is matched as abnormal image recognition result in instruction identification storehouse according to the 3rd distinguishing mark.
9. mammary gland examination image intelligent identification Method as claimed in claim 8, it is characterised in that this method also includes following step
Suddenly：
The normal image recognition result in report, abnormal image recognition result are recognized to image or image recognition result is referred to
It is identified；
Normal image in image identification report is shown in the display unit of medical terminal device with preset display mode
Recognition result, abnormal image recognition result refer to image recognition result.
10. mammary gland examination image intelligent identification Method as claimed in claim 6, it is characterised in that this method also includes as follows
Step：When do not matched in the instruction identification storehouse recognize instruction corresponding image recognition result with the image when, from described
The image recognition result of input block reception doctor's input is simultaneously recognized in report, and the image identification of input is tied added to image
Fruit is recognized in storehouse added to the instruction.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710185298.1A CN107049249A (en) | 2017-03-25 | 2017-03-25 | Mammary gland examination image intelligent identifying system and method |
| PCT/CN2017/096132 WO2018176718A1 (en) | 2017-03-25 | 2017-08-05 | Intelligent identification system and method for mammary gland screening image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710185298.1A CN107049249A (en) | 2017-03-25 | 2017-03-25 | Mammary gland examination image intelligent identifying system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107049249A true CN107049249A (en) | 2017-08-18 |
Family
ID=59620576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710185298.1A Pending CN107049249A (en) | 2017-03-25 | 2017-03-25 | Mammary gland examination image intelligent identifying system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107049249A (en) |
| WO (1) | WO2018176718A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305251A (en) * | 2018-02-01 | 2018-07-20 | 四川大学 | A kind of breast cancer detection method and apparatus |
| WO2019047366A1 (en) * | 2017-09-11 | 2019-03-14 | 深圳市前海安测信息技术有限公司 | Artificial intelligence-based image recognition system and method |
| WO2019047365A1 (en) * | 2017-09-11 | 2019-03-14 | 深圳市前海安测信息技术有限公司 | Medical cloud platform-based image big data analysis system and method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI229281B (en) * | 2003-04-11 | 2005-03-11 | Ebm Technologies Inc | Medical graphics report generation method and device thereof |
| CN101658413A (en) * | 2009-06-19 | 2010-03-03 | 中卫莱康科技发展（北京）有限公司 | Mobile communication terminal, diagnosis server and breast disease detecting system |
| KR101747300B1 (en) * | 2010-10-21 | 2017-06-15 | 삼성전자주식회사 | Method for processing image, image processing apparatus and medical image system for performing the same |
| TW201301075A (en) * | 2011-06-29 | 2013-01-01 | Medincom Technology Corp | Knowledge management system for medical images and method for generating knowledge therefor |
| CN104361245B (en) * | 2014-11-22 | 2018-03-23 | 张姬娟 | Measurement data-processing system and method |
| CN105559749A (en) * | 2015-11-19 | 2016-05-11 | 小红象医疗科技有限公司 | Breast health automatic analysis system and method based on infrared medical imaging |
| CN105956391A (en) * | 2016-04-28 | 2016-09-21 | 深圳市前海安测信息技术有限公司 | Breast screening system and method based on big data |
-
2017
- 2017-03-25 CN CN201710185298.1A patent/CN107049249A/en active Pending
- 2017-08-05 WO PCT/CN2017/096132 patent/WO2018176718A1/en active Application Filing
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019047366A1 (en) * | 2017-09-11 | 2019-03-14 | 深圳市前海安测信息技术有限公司 | Artificial intelligence-based image recognition system and method |
| WO2019047365A1 (en) * | 2017-09-11 | 2019-03-14 | 深圳市前海安测信息技术有限公司 | Medical cloud platform-based image big data analysis system and method |
| CN108305251A (en) * | 2018-02-01 | 2018-07-20 | 四川大学 | A kind of breast cancer detection method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018176718A1 (en) | 2018-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | A systematic review of automated melanoma detection in dermatoscopic images and its ground truth data | |
| Decenciere et al. | TeleOphta: Machine learning and image processing methods for teleophthalmology | |
| JP5128154B2 (en) | Report creation support apparatus, report creation support method, and program thereof | |
| CN102908135B (en) | ECG diagnosis system and operating method of ECG diagnosis system | |
| US10127665B1 (en) | Intelligent assistant judgment system for images of cervix uteri and processing method thereof | |
| CN109858540B (en) | Medical image recognition system and method based on multi-mode fusion | |
| CN109615633A (en) | Crohn disease assistant diagnosis system and method under a kind of colonoscopy based on deep learning | |
| CN107506604A (en) | Image recognition system and method based on artificial intelligence | |
| US20090252392A1 (en) | System and method for analyzing medical images | |
| CN103975364B (en) | Selection of images for optical examination of the cervix | |
| CN107049249A (en) | Mammary gland examination image intelligent identifying system and method | |
| CN112927179A (en) | Intelligent analysis method for liver tumor | |
| CN110141219A (en) | Myocardial infarction automatic testing method based on lead fusion deep neural network | |
| CN110991536A (en) | Training method of early warning model of primary liver cancer | |
| CN113205490A (en) | Mask R-CNN network-based auxiliary diagnosis system and auxiliary diagnosis information generation method | |
| CN107506605A (en) | Image big data analysis system and method based on medical cloud platform | |
| CN105930639A (en) | Intelligent medical information science popularization system and method | |
| CN107049248A (en) | Mammary gland examination image analysis system and method based on medical cloud platform | |
| CN112802000A (en) | Intelligent auxiliary diagnosis and treatment system for multi-modal medical images | |
| CN110969623A (en) | Lung CT multi-symptom automatic detection method, system, terminal and storage medium | |
| CN109698024A (en) | A kind of processing method of operating process, device and ultrasonic device | |
| CN112562816A (en) | System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image report | |
| CN114663735B (en) | Dual-bone age assessment method based on joint global and local convolutional neural network characteristics | |
| CN105512473A (en) | Intelligent identification method and device of colposcope images | |
| CN113520317A (en) | OCT-based endometrial detection and analysis method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170818 |