WO2018176718A1

WO2018176718A1 - Intelligent identification system and method for mammary gland screening image

Info

Publication number: WO2018176718A1
Application number: PCT/CN2017/096132
Authority: WO
Inventors: 王德峰; 郑斌; 钱唯; 石林; 韩鸿宾
Original assignee: 深圳市前海安测信息技术有限公司
Priority date: 2017-03-25
Filing date: 2017-08-05
Publication date: 2018-10-04
Also published as: CN107049249A

Abstract

An intelligent identification system and method for a mammary gland screening image, applied to a medical terminal device. The method comprises the steps of: acquiring a mammary gland image signal of a person to be examined from a mammary gland image acquisition terminal, and processing the mammary gland image signal into a mammary gland screening image (S21); receiving personal information of the person to be examined and an image identification instruction from an input unit (S22); matching, in an instruction identification library, the image identification instruction with corresponding text, and using the text as an image identification result (S23); generating an image identification report according to the image identification result, and adding the personal information into the image identification report (S24); and matching the mammary gland screening image with mammary gland image data in a mammary gland image database, wherein the similarity between the mammary gland screening image and the mammary gland image data is within a preset range, and adding the mammary gland image data into the corresponding image identification report (S25). A doctor can obtain an identification result of a mammary gland screening image only by inputting a simple image identification instruction, thus simplifying the operation of identifying the mammary gland screening image and improving the efficiency and the accuracy of image identification.

Description

Title of the Invention: Learning L-Graph Screening Image Intelligent Identification System and Method

Technical field

[0001] The present invention relates to the field of medical image processing and recognition technology, and in particular, to a breast screening image intelligent identification system and method.

Background technique

[0002] Breast disease is one of the most common diseases in women. Especially with the accelerated pace of modern urban life, women's life pressure and work pressure are increasing. The incidence of breast diseases is increasing year by year. Serious breast diseases may be serious. Lead to breast cancer. According to incomplete survey statistics, the incidence and mortality of breast diseases are also on the rise. In fact, most of the patients who died of breast cancer were killed because they did not find the best treatment opportunity. Therefore, it is necessary for women to have a breast screening, early detection of breast diseases, and early diagnosis for women's health.

[0003] At present, the use of breast screening images for assisted diagnosis has become an important method for screening and diagnosing early breast cancer. When doctors view the breast screening image, they cannot write the report synchronously, but switch to the interface or program of the report writing; and, when writing the report, the content needs to be input to the computer word by word. For some of the more common test results (such as no abnormalities in a certain part), still need to make cumbersome input, which requires considerable energy and time, which is prone to misuse and cause the efficiency of breast screening to decline. A census for a large number of breast samples. In addition, due to the large number of breast images, it is difficult for doctors to directly identify each breast image and manually report it. It is difficult to ensure efficiency and accuracy, which may lead to missed diagnosis and misdiagnosis.

technical problem

[0004] The main object of the present invention is to provide a breast screening image intelligent recognition system and method, which can obtain the breast screening image recognition result by simply inputting a simple image recognition instruction, and simplify the operation of the breast screening image recognition. Improve the efficiency and accuracy of image recognition.

Problem solution

Technical solution

[0005] In order to achieve the above object, the present invention provides an intelligent screening system for breast screening images, which is applied to medical treatment. In the terminal device, the medical terminal device is connected to the breast image capturing terminal and the medical information platform through a communication network, and the breast screening image intelligent recognition system comprises: an image acquiring module, configured to acquire the object to be detected from the breast image collecting terminal The mammography image signal processes the mammary gland image signal of the subject to be detected as a mammography screening image, and receives the input personal information and image recognition instruction of the subject to be inspected from the input unit of the medical terminal device; the image recognition module is configured to identify the image according to the image The instruction matches the text corresponding to the image recognition instruction in the instruction recognition library of the medical information platform as the image recognition result; the report generation module is configured to generate an image recognition report for displaying the image recognition result according to the matched image recognition result, and The personal information of the inspector is added to the image recognition report; the image matching module is configured to match the breast image data with the similarity of the breast screening image in the preset range in the breast image database of the medical information platform, and the Matching breast image data is added Go to the corresponding image recognition report.

[0006] Preferably, the breast image collection terminal comprises an infrared generator, an infrared receiver, an analog to digital converter, and a communication port, wherein: the infrared generator is configured to generate infrared light and inspect the infrared light to the person to be detected The infrared receiver is configured to collect infrared light signals transmitted through the breast of the subject to be processed into an analog electrical signal containing breast tissue structure information of the subject to be detected; the analog-to-digital converter is configured to include the to-be-detected The analog electrical signal modulus of the breast tissue structure information is converted into a breast image signal in the form of a digital signal; the communication port is configured to transmit a breast image signal of the subject to be detected to the medical terminal device.

[0007] Preferably, the image recognition instruction is a first identification mark, a second identification mark or a third identification mark, and the image recognition result is a normal image recognition result, a reference image recognition result or an abnormal image recognition result. Wherein: when the image recognition command is the first identification mark 吋, the image recognition module determines that the image recognition result of the breast screening image is normal, and matches the text corresponding to the normal health of the breast in the instruction recognition library as a normal Image recognition result; when the image recognition instruction is the second identification mark 吋, the image recognition module matches the corresponding text in the instruction recognition library as a reference image recognition result according to the second identification mark; when the image recognition instruction is The third identification mark 吋, the image recognition module determines that the image recognition result is an abnormal image recognition result, and matches the corresponding character in the instruction recognition library as an abnormal image recognition result according to the third identification mark.

[0008] Preferably, the breast screening image intelligent recognition system further comprises a result indication module, wherein the result indication module is used for normal image recognition result in the image recognition report, abnormal image recognition result or reference The image recognition result is marked, and the normal image recognition result, the abnormal image recognition result or the reference image recognition result in the image recognition report is displayed in the display unit of the medical terminal device in a preset display manner.

[0009] Preferably, when the image recognition result corresponding to the image recognition instruction is not matched in the instruction identification library, the image recognition module is further configured to receive the image recognition result input by the doctor from the input unit. Adding to the image recognition report, and adding the input image recognition result to the instruction recognition library.

[0010] The present invention also provides a method for intelligently identifying a breast screening image, which is applied to a medical terminal device, and the medical terminal device is connected to a breast image capturing terminal and a medical information platform through a communication network, the method comprising the steps of: from the breast image The collecting terminal acquires the mammography image signal of the subject to be detected; processes the mammary gland image signal of the subject to be detected into a mammary gland screening image; receives the input personal information of the subject to be inspected and the image recognition instruction from the input unit of the medical terminal device; The recognition instruction matches the text corresponding to the image recognition instruction in the instruction recognition library of the medical information platform as the image recognition result; and generates an image recognition report for displaying the image recognition result according to the matched image recognition result, and the image to be inspected is The personal information is added to the image recognition report; the breast image data with the similarity of the breast screening image in the preset range is matched in the breast image database of the medical information platform, and the matched breast image data is added to the corresponding image. Identification report.

[0011] Preferably, the step of acquiring the mammography image signal of the to-be-detected person from the mammography image collection terminal comprises: generating infrared light by using an infrared generator of the mammography image acquisition terminal and inspecting the infrared light to the mammary gland of the subject to be detected The infrared receiver through the breast image collection terminal collects the infrared light signal passing through the breast of the subject to be processed into an analog electrical signal containing the breast tissue structure information of the subject to be detected; the analog to digital converter using the breast image acquisition terminal Converting an analog electrical signal modulus containing the breast tissue structure information of the subject to be detected into a breast image signal in the form of a digital signal; transmitting a breast image signal of the subject to be detected to the medical through the communication port of the breast image collecting terminal Terminal Equipment.

[0012] Preferably, the image recognition instruction is a first identification mark, a second identification mark or a third identification mark, and the image recognition result is a normal image recognition result, a reference image recognition result or an abnormal image recognition result. , wherein: when the image recognition instruction is the first identification mark 吋, determining that the image recognition result of the breast screening image is normal, and matching the text corresponding to the normal health of the breast in the instruction recognition library The image recognition result is a normal image recognition result; when the image recognition instruction is the second identification mark, the image recognition result is matched with the corresponding text in the instruction recognition library as a reference according to the second identification mark; The identification mark 吋 determines that the image recognition result is an abnormal image recognition result, and matches the corresponding character in the instruction recognition library as an abnormal image recognition result according to the third identification mark.

[0013] Preferably, the breast screening image intelligent recognition method further comprises the following steps: identifying a normal image recognition result, an abnormal image recognition result or a reference image recognition result in the image recognition report, and displaying the preset image The method displays a normal image recognition result, an abnormal image recognition result, or a reference image recognition result in the image recognition report in the display unit of the medical terminal device.

[0014] Preferably, the method for intelligently identifying the breast screening image further comprises the steps of: receiving a doctor from the input unit when the image recognition result corresponding to the image recognition instruction is not matched in the instruction recognition library; The input image recognition result is added to the image recognition report, and the input image recognition result is added to the instruction recognition library.

Advantageous effects of the invention

Beneficial effect

[0015] Compared with the prior art, the breast screening image intelligent recognition system and method of the present invention can identify a preset instruction according to a doctor's input image recognition instruction during a process of performing breast screening image recognition by a doctor. The image matching result corresponding to the image recognition instruction is matched in the library, and the breast image data with the similarity of the breast screening image in the preset range is matched in the preset breast image database, and the image is generated according to the image recognition result and the breast image data. Identify the report. Because the doctor only needs to input a simple image recognition command to obtain the recognition result of the breast screening image, without the doctor inputting the cumbersome examination conclusion, the operation of the breast image recognition is simplified, and the efficiency and accuracy of the image recognition of the breast are improved. , assisting doctors to improve the efficiency and accuracy of breast disease detection and screening, and improve the social efficiency of breast screening. Brief description of the drawing

DRAWINGS

1 is a schematic diagram of an application environment of a preferred embodiment of the breast screening image intelligent identification system of the present invention;

2 is a flow chart of a preferred embodiment of the method for intelligently identifying breast screening images of the present invention.

[0018] The objects, features, and advantages of the present invention will be further described in conjunction with the specific embodiments. BEST MODE FOR CARRYING OUT THE INVENTION

BEST MODE FOR CARRYING OUT THE INVENTION

The specific embodiments, structures, features and utilities of the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to FIG. 1, FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of the breast screening image intelligent recognition system of the present invention. In the present embodiment, the breast screening image intelligent recognition system 10 is installed and operated in the medical terminal device 1. The medical terminal device 1 establishes a communication connection with the medical information platform 2 and the mammography image collecting terminal 4 via the communication network 3. The medical terminal device 1 is provided with a computing device having a data processing and communication function, such as a doctor workstation computer or a server of a breast medical center or a large hospital. The medical information platform 2 may be a server in a medical information system platform, and the medical information platform 2 includes an instruction recognition library 21 and a breast image database 22. In this embodiment, the preset instruction recognition library 21 pre-collects medical terms, radiology terms, and common image recognition result templates commonly used for breast health screening. Under normal circumstances, the template corresponds to normal. Image recognition results. The breast image database 22 stores various commonly used normal or abnormal breast image data for reference. After receiving the breast screening image, the breast imaging image and the breast image data in the breast image database can be similar. Degree matching. The communication network 3 may be an internet network including a local area network, a wide area network, or a wireless transmission network including GSM, GPRS, and CDMA.

[0021] The breast image collection terminal 4 is disposed in a medical examination institution such as a community medical workstation, and establishes a network communication connection with the medical terminal device 1. In the present embodiment, the breast image collecting terminal 4 includes an infrared generator 41, an infrared receiver 42, an analog to digital converter 43, and a communication port 44. The infrared generator 41 generates infrared light and sees the infrared light on the mammary gland of the subject to be detected; the infrared receiver 42 collects the infrared light signal passing through the breast of the subject to be detected and processes the analog electric energy of the breast tissue structure information. The infrared light generated by the infrared generator 41 is fluorinated to the mammary gland of the subject to be detected, and the infrared light signal received by the infrared receiver 42 carries the infrared transmitted light of the breast tissue structure information. The analog-to-digital converter 43 performs analog-to-digital conversion of the analog electrical signal containing the information of the breast tissue structure of the object to be detected collected by the infrared receiver 42 into a breast image signal in the form of a digital signal; the communication port 44 is used to information about the person to be detected. And the mammary gland containing the person to be tested The digital signal of the image information is transmitted to the cloud server 1 via the communication network 3. The communication port 44 can be a wireless communication interface with remote wireless communication functions, such as a communication interface supporting GSM, GPRS, CDMA.

[0022] In the present embodiment, the medical terminal device 1 includes, but is not limited to, a breast screening image intelligent recognition system 10, an input unit 11, a storage unit 12, a processing unit 13, a communication unit 14, and a display unit 15. The input unit 11, the storage unit 12, the processing unit 13, the communication unit 14, and the display unit 15 are all connected to the processing unit 13 via a data bus, and can perform information interaction with the breast screening image intelligent recognition system 10 through the processing unit 13. The input unit 11 can be a hardware device such as a keyboard, a touch screen or a mouse. The storage unit 12 is a read only memory unit ROM, an electrically erasable memory unit EEPROM or a flash memory unit FLASH. The processing unit 13 is a central processing unit (CPU), a microprocessor, a microcontroller (MCU), a data processing chip, or an information processing unit having data processing functions. The communication unit 14 can be a wireless communication interface with remote wireless communication functions, such as a communication interface supporting GSM, GPRS, and CDMA. The display unit 15 is a display for displaying a breast examination report of the person to be examined.

[0023] In the embodiment, the breast screening image intelligent recognition system 10 includes, but is not limited to, an image acquisition module 101, an image recognition module 102, a report generation module 103, an image matching module 104, and a result indication module _105. . The module referred to in the present invention refers to a series of computer program instruction segments that can be executed by the processing unit 13 of the medical terminal device 1 and that can perform a fixed function, which are stored in the storage unit 12 of the medical terminal device 1. .

[0024] The image acquisition module 101 is configured to acquire a mammography image signal of the subject to be detected from the mammography image acquisition terminal 4. In this embodiment, the infrared generator 41 generates infrared light and sees the infrared light onto the mammary gland of the subject to be detected; the infrared receiver 42 collects an infrared light signal that passes through the breast of the subject to be detected and processes it into a mammary gland. An analog electrical signal of the tissue structure information; the analog-to-digital converter 43 converts the analog electrical signal collected by the infrared receiver 42 and contains the information of the breast tissue structure to be detected into a mammography signal in the form of a digital signal; The communication port 44 transmits the mammography image signal of the subject to be detected to the image acquisition module 101.

[0025] The image acquisition module 101 is further configured to process the breast image signal of the subject to be detected into a breast screening image. Specifically, the image acquisition module 101 uses the digital image processing software to image the breast image of the object to be detected. The image data is recorded in the form of a digital file, and then the breast screening image of the subject to be detected is generated based on the image data. In the present embodiment, the principle of infrared breast detection is: Infrared light illuminates the human breast region, and since the human breast tissue exhibits different absorption characteristics through the infrared spectrum, the infrared light signal and the normal transmission through the lesion portion are normal. The intensity of the infrared signal of the breast tissue will be different. The location and size of the lesion in the breast can be detected by the gray scale, tissue structure, and external dimensions of the infrared image collected, especially the optical properties of the breast tissue.

The image acquisition module 101 is further configured to receive the input personal information of the subject to be inspected and the image recognition instruction from the input unit 11. In the present embodiment, the doctor inputs the personal information of the subject to be examined from the input unit 11, including information such as name, age, gender, medical history, and the like. When identifying the breast screening image, the doctor also needs to input an image recognition command for checking the health of the breast from the input unit 11.

[0027] The image recognition module 102 is configured to match the text corresponding to the image recognition instruction in the instruction recognition library 21 of the medical information platform 2 as the image recognition result according to the image recognition instruction. In this embodiment, the image recognition instruction may be a first identification mark, a second identification mark or a third identification mark; the image recognition result may be a normal image recognition result, a reference image recognition result, or an abnormal image. Identify the results. Specifically, the image recognition instruction includes a preset first identification mark, and the first identification mark is used as an indicator for determining whether the image recognition result is normal, that is, when the first identification mark is included in the image recognition instruction, The image recognition module 102 determines that the image recognition result of the breast screening image is normal, and the content of the first identification mark is generally selected as a word different from related medical terms and radiological terms. For example, when the image recognition command includes "click + breast", it indicates that the image recognition result of the breast screening image is normal. At this time, the text corresponding to the normal breast health can be matched in the instruction recognition library 21 as a normal image recognition result. For example, matching "no abnormalities in the mammary gland" is used as a normal image recognition result. The image recognition instruction includes a preset second identification mark, and the second identification mark is used as an indication mark for determining whether the image recognition result is a reference image recognition result, that is, when the second identification mark is included in the image recognition instruction. The image recognition module 102 needs to match the image recognition result corresponding to the breast screening image, and the image recognition module 102 matches the image corresponding to the breast screening image in the instruction recognition library 21 as the reference image recognition result according to the second identification mark. The content of the second identification mark may be set as a "reference" or the like which can clearly determine the image recognition result whose indication is the reference image recognition result. For example, when the image recognition instruction is "reference", the text corresponding to the conclusion of the image recognition report is matched in the instruction recognition library, The word recognition result of the word as a reference. If the image recognition instruction is the third identification mark, the image recognition module 102 may determine that the image recognition result is not a normal image recognition result, and match the corresponding text in the instruction recognition library according to the third identification mark. If the matching text corresponding to the third identification mark has nothing to do with the image recognition result of the breast screening image, it indicates that the received image recognition instruction is invalid; on the contrary, it indicates that the image recognition result corresponding to the image recognition instruction is abnormal image recognition. result. For example, if the recognized image recognition command is "a number of soft tissue density lesions on both sides of the breast, and the morphology is consistent with breast cancer", the corresponding text is matched in the instruction recognition library, and the text is used as an abnormal image recognition result.

[0028] In the embodiment, if the image recognition module 102 does not match the image recognition result corresponding to the image recognition instruction in the instruction recognition library 21, it indicates that the corresponding character is not stored in the instruction recognition library 21. At this time, the doctor can input the corresponding image recognition result into the image recognition report through the input unit 11, and the image recognition module 102 adds the input image recognition result to the instruction recognition library 21, so as to receive the same or similar next time. In the case of the image recognition command, the corresponding image recognition result is matched from the command recognition library 21.

[0029] The report generation module 103 is configured to generate an image recognition report for displaying the image recognition result according to the matched image recognition result, and add the personal information of the to-be-inspected to the image recognition report. When the image recognition result is normal, the health status of the breast to be detected is normal; when the image recognition result is abnormal, the doctor receives the indication instruction of the abnormal part and marks the abnormal part of the breast screening image to Provide a reference for doctors to further diagnose and screen breast diseases. After generating the image recognition report, the report generation module 103 can embed the name, age, gender, medical history and the like of the object to be inspected into the front part of the image recognition report in a modular form, and can automatically be at the end of the image recognition report. A timestamp is generated; at the same time, the doctor can sign his or her name in the image recognition report. After the report generation module 103 generates the image recognition report, if the image recognition result in the image recognition report is found to be incorrect, the erroneous content may be modified or deleted.

[0030] The image matching module 104 is configured to match the breast image data with the similarity of the breast screening image in the preset breast image database 22, and add the matched breast image data to the corresponding image data. In the image recognition report. When the similarity is within the preset range, the similar image data in the breast image database 22 is acquired as the breast image data corresponding to the breast screening image, and the preset range may be customized according to the breast related portion, for example, set to be greater than 80%. When the image matching module 104 is matched to the mammary screen After checking the image data of the breast corresponding to the image, the matched breast image data is added to the corresponding image recognition report. The image recognition report includes not only the image recognition results of the breast screening images, but also the breast image data of the breast screening images for reference by the doctor and the examinee.

[0031] The result indication module 105 is configured to identify a normal image recognition result, an abnormal image recognition result or a reference image recognition result in the image recognition report, and display the image recognition report on the display unit 15 in a preset display manner. Normal image recognition results, abnormal image recognition results, or reference image recognition results. Specifically, the result indication module 105 performs different identification on the normal image recognition result and the abnormal image recognition result according to whether the image recognition result is normal or abnormal, and can identify the reference result as being distinguishable from the normal or abnormal image recognition result. Other identifiers, such as marking different image recognition results as different fonts or different colors, so that when displayed, the display is displayed in a preset manner, for example, the text content of the abnormal image recognition result is displayed in bold form. Or highlight it. In this embodiment, if the image recognition result in the image recognition report is a normal image recognition result, the text content corresponding to the recognition template may be identified as blue after matching the recognition template indicating that the image recognition result is normal. If the image recognition result in the image recognition report is abnormal image recognition result, the text content may be identified as a red font after matching the text corresponding to the abnormal image recognition result, and displayed The text content of the red font is displayed in bold or highlighted to remind the examinee to pay attention. When generating the image recognition report, the normal image recognition result or the abnormal image recognition result in the image recognition report is differently identified, and the normal image recognition result or the abnormal image recognition result is displayed in a preset display manner, so that The image recognition report is more clear and easy for doctors and subjects to read.

[0032] The present invention also provides a method for intelligently identifying a breast screening image, which is applied to a medical terminal device. As shown in Fig. 2, Fig. 2 is a flow chart showing a preferred embodiment of the method for intelligently identifying the breast screening image of the present invention. The embodiment of the present invention is combined with FIG. 1, and the method for intelligently identifying the breast screening image includes the following steps:

[0033] Step S21, the image acquisition module 101 acquires the mammography image signal of the to-be-detected person from the mammography image acquisition terminal 4, and processes the mammary gland image signal of the object to be detected into a mammary gland screening image; in this embodiment, the infrared generator 41 generates infrared light and fluoresces the infrared light onto the mammary gland of the subject to be detected; the infrared receiver 42 collects an infrared light signal that passes through the mammary gland of the subject to be detected and processes the analog electrical signal as information of the mammary gland structure; the analog to digital converter 43 A simulation of the tissue structure of the breast containing the subject to be detected collected by the infrared receiver 42 The electrical signal analog-to-digital conversion process is a breast image signal in the form of a digital signal; the communication port 44 transmits the breast image signal of the subject to be detected to the image acquisition module 101. The image acquisition module 101 records the image data of the breast image signal of the object to be detected in the form of a digital file by using digital image processing software, and then generates a breast screening image of the object to be detected according to the image data.

[0034] Step S22, the image acquisition module 101 receives the input personal information of the subject to be inspected and the image recognition instruction from the input unit 11. In the present embodiment, the doctor inputs the breast information from the input unit 11 to screen the personal information of the examinee, including information such as name, age, gender, medical history, and the like. When identifying the breast screening image, the doctor also needs to input an image recognition command for checking the health of the breast from the input unit 11.

[0035] Step S23, the image recognition module 102 matches the text corresponding to the image recognition instruction in the command recognition library 21 as the image recognition result according to the image recognition instruction. In this embodiment, the image recognition instruction may be a first identification mark, a second identification mark or a third identification mark; the image recognition result may be a normal image recognition result, a reference image recognition result, or an abnormal image. Identify the results. Specifically, the image recognition instruction includes a preset first identification mark, and the first identification mark is used as an indicator for determining whether the image recognition result is normal, that is, when the first identification mark is included in the image recognition instruction, The image recognition module 102 determines that the image recognition result of the breast screening image is normal, and the content of the first identification mark is generally selected as a word different from related medical terms and radiological terms. For example, when the image recognition command includes "click + mammary gland", it indicates that the image recognition result of the breast screening image is normal, and therefore, the text corresponding to the normal health of the breast can be matched in the instruction recognition library 21, for example, matching" No abnormalities in the mammary gland" as a result of normal image recognition. The image recognition instruction includes a preset second identification mark, and the second identification mark is used as an indication mark for determining whether the image recognition result is a reference image recognition result, that is, when the second identification mark is included in the image recognition instruction. The image recognition module 102 needs to match the image recognition result corresponding to the breast screening image, and the image recognition module 102 matches the image corresponding to the breast screening image in the instruction recognition library 21 as the reference image recognition result according to the second identification mark. The content of the second identification mark may be set as a "reference" or the like which can clearly determine the image recognition result whose indication is the reference image recognition result. For example, when the image recognition command is "reference", the character corresponding to the conclusion of the image recognition report is matched in the command recognition library 21, and the character is used as a reference image recognition result. If the image recognition instruction is the third identification mark, the image recognition module 102 may determine that the image recognition result is not a normal image recognition result, and match the corresponding text in the instruction recognition library 21 according to the third identification mark. At this time, if the matching text corresponding to the third identification mark has nothing to do with the image recognition result of the breast screening image, it indicates that the received image recognition instruction is invalid; on the contrary, it indicates that the image recognition result corresponding to the image recognition instruction is abnormal. Image recognition results. For example, if the recognized image recognition command is "a plurality of soft tissue density lesions on both sides of the breast, and the morphology is consistent with breast cancer", the corresponding recognition text is matched in the instruction recognition library 21, and the character is used as an abnormal image recognition result.

[0036] In this embodiment, if the image recognition module 102 does not match the image recognition result corresponding to the image recognition instruction in the instruction recognition library 21, it indicates that the corresponding file is not stored in the instruction recognition library 21. The doctor can input the corresponding image recognition result into the image recognition report through the input unit 11, and the image recognition module 102 adds the input image recognition result to the instruction recognition library 21, so as to receive the same or similar image recognition next time. At the time of the instruction, the corresponding image recognition result is matched from the instruction recognition library 21.

[0037] Step S24, the report generation module 103 generates an image recognition report for displaying the image recognition result according to the matched image recognition result, and adds the personal information of the object to be inspected to the image recognition report. When the image recognition result is normal, the health status of the breast to be detected is normal; when the image recognition result is abnormal, the doctor receives the indication instruction of the abnormal part and marks the abnormal part of the breast screening image to Provide a reference for doctors to further diagnose and screen breast diseases. When the image recognition report is generated, the report generation module 103 can embed the name, age, gender, medical history, and the like of the object to be inspected into the front of the image recognition report in a modular form, and can automatically be at the end of the image recognition report. Generate a postmark; peers, the doctor can sign his or her name in the image recognition report. After the report generation module 103 generates the image recognition report, if the image recognition result in the image recognition report is found to be incorrect, the doctor can modify or delete the wrong content.

[0038] Step S25, the image matching module 104 matches the breast image data with the similarity of the breast screening image in the preset breast image database, and adds the matched breast image data to the corresponding image recognition. In the report. In this embodiment, the breast image database 22 stores various commonly used normal or abnormal breast image data for reference. After receiving the breast screening image, the image matching module 104 can screen the image of the breast and The mammography data in the mammography database is similarly matched. When the similarity is within the preset range, the similar image data in the breast image database is acquired as the breast image data corresponding to the breast screening image, and the preset range may be customized according to the breast related part, for example, set to be greater than 80<3⁄4 . The image matching module 104 matches the mammary gland corresponding to the breast screening image After the data is like, the breast image data is added to the corresponding image recognition report. The image recognition report includes not only the image recognition result of the breast screening image, but also the breast image data of the breast screening image for reference by the doctor and the examinee.

[0039] Step S26, the result indication module 105 identifies the normal image recognition result, the abnormal image recognition result or the reference image recognition result in the image recognition report, and displays the image recognition on the display unit 15 in a preset display manner. Normal image recognition results, abnormal image recognition results, or reference image recognition results in the report. Specifically, the result indication module 105 performs different identification on the normal image recognition result and the abnormal image recognition result according to whether the image recognition result is normal or abnormal, and can identify the reference result as being distinguishable from the normal or abnormal image recognition result. Other identifiers, such as marking different image recognition results as different fonts or different colors, so that when displayed, the display unit 15 displays in a preset display manner, for example, the text content of the abnormal image recognition result is added. Displayed in bold form or highlighted.

[0040] In this embodiment, if the image recognition result in the image recognition report is a normal image recognition result, the text content identifier corresponding to the recognition template may be matched after matching the recognition template representing that the image recognition result is normal. It is a blue font and is displayed normally; if the image recognition result in the image recognition report is an abnormal image recognition result, the text content may be identified as a red font after matching the text corresponding to the abnormal image recognition result, and In the display, the text content of the red font is displayed in bold or highlighted to remind the examinee to pay attention. After the image recognition report is generated, the normal image recognition result or the abnormal image recognition result in the image recognition report is differently identified, and the normal image recognition result or the abnormal image recognition result is displayed in a preset display manner, so that The image recognition report is more clear and easy for doctors and examiners to read.

[0041] The breast screening intelligent identification system and method of the present invention can match and image recognition in a preset instruction recognition library according to a doctor inputting a simple image recognition instruction during a process of performing breast screening image recognition by a doctor. The image recognition result corresponding to the instruction matches the breast image data in the preset breast image database with the similarity of the breast screening image in the preset range, and generates the image recognition report according to the image recognition result and the breast image data, since the doctor only A simple image recognition command is required to obtain a breast screening image recognition result without requiring a doctor to input a cumbersome examination result, thereby simplifying the operation of the breast image recognition, improving the efficiency and accuracy of the breast image recognition, thereby assisting Doctor raises the milk The efficiency and accuracy of gland disease detection and screening, and improve the social efficiency of breast screening.

The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent function changes made by the description of the present invention and the contents of the drawings, or directly or indirectly applied to other related The technical field is equally included in the scope of patent protection of the present invention.

Industrial applicability

Compared with the prior art, the breast screening image intelligent recognition system and method of the present invention can identify a preset instruction according to a doctor's input image recognition instruction during a process of performing breast screening image recognition by a doctor. The image matching result corresponding to the image recognition instruction is matched in the library, and the breast image data with the similarity of the breast screening image in the preset range is matched in the preset breast image database, and the image is generated according to the image recognition result and the breast image data. Identify the report. Because the doctor only needs to input a simple image recognition command to obtain the recognition result of the breast screening image, without the doctor inputting the cumbersome examination conclusion, the operation of the breast image recognition is simplified, and the efficiency and accuracy of the image recognition of the breast are improved. , assisting doctors to improve the efficiency and accuracy of breast disease detection and screening, and improve the social efficiency of breast screening.

Claims

[Claim 1] A breast screening image intelligent recognition system, which is applied to a medical terminal device, wherein the medical terminal device is connected to a breast image acquisition terminal and a medical information platform through a communication network, wherein the breast screening image is The intelligent identification system comprises: an image acquisition module, configured to acquire a breast image signal of the to-be-detected person from the breast image acquisition terminal, process the breast image signal of the to-be-tested person into a breast screening image, and receive from the input unit of the medical terminal device Inputting the personal information of the person to be inspected and the image recognition instruction; the image recognition module is configured to match the text corresponding to the image recognition instruction in the instruction recognition library of the medical information platform as the image recognition result according to the image recognition instruction; the report generation module, The image recognition report for displaying the image recognition result is generated according to the matched image recognition result, and the personal information of the object to be inspected is added to the image recognition report; the image matching module is used for the breast image on the medical information platform Database matching and mammography Breast imaging in the similarity image data within a preset range, and adding the matched breast image identification to the image data corresponding to the report.

[Claim 2] The breast screening image intelligent identification system according to claim 1, wherein the breast image acquisition terminal comprises an infrared generator, an infrared receiver, an analog to digital converter, and a communication port, wherein: The infrared generator is configured to generate infrared light and fluoresce the infrared light onto the mammary gland of the subject to be detected; the infrared receiver is configured to collect the infrared light signal transmitted through the breast of the subject to be detected to include the mammary gland structure of the subject to be detected An analog electrical signal of the information; the analog-to-digital converter is configured to convert an analog electrical signal containing the information of the breast tissue structure of the subject to be converted into a breast image signal in the form of a digital signal; the communication port is used for the person to be detected A mammography image signal is sent to the medical terminal device.

[Claim 3] The breast screening image intelligent identification system according to claim 1, wherein the image recognition command is a first identification mark, a second identification mark or a third identification mark, and the image recognition result is a normal image recognition result, a reference image recognition result, or an abnormal image recognition result, wherein: when the image recognition instruction is the first identification mark, the image recognition module determines that the image recognition result of the breast screening image is normal And matching the text corresponding to the normal health of the breast in the instruction recognition library as a normal image recognition result; The image recognition instruction is a second identification mark 吋, and the image recognition module matches the corresponding character in the instruction recognition library as a reference image recognition result according to the second identification mark; and when the image recognition instruction is the third identification mark 吋The image recognition module determines that the image recognition result is an abnormal image recognition result, and matches the corresponding text in the instruction recognition library as an abnormal image recognition result according to the third identification mark.

[Claim 4] The breast screening image intelligent identification system according to claim 3, wherein the system further comprises a result indication module, configured for normal image recognition result in the image recognition report, and abnormal image recognition The result or the reference image recognition result is identified, and the normal image recognition result, the abnormal image recognition result or the reference image recognition result in the image recognition report is displayed in the display unit of the medical terminal device in a preset display manner.

[Claim 5] The breast screening image intelligent recognition system according to claim 1, wherein when the image recognition result corresponding to the image recognition instruction is not matched in the instruction recognition library

The image recognition module is further configured to receive the image recognition result input by the doctor from the input unit and add the image recognition result to the image recognition report, and add the input image recognition result to the instruction recognition library.

[Claim 6] A method for intelligently identifying a breast screening image, which is applied to a medical terminal device, wherein the medical terminal device is connected to a breast image collecting terminal and a medical information platform through a communication network, wherein the method comprises the steps of: Obtaining the mammary gland image signal of the subject to be detected from the mammography image capturing terminal; processing the mammary gland image signal of the subject to be detected as a mammary gland screening image; receiving the personal information and the image recognizing instruction of the subject to be inspected from the input unit of the medical terminal device; The recognition instruction matches the text corresponding to the image recognition instruction in the instruction recognition library of the medical information platform as the image recognition result; and generates an image recognition report for displaying the image recognition result according to the matched image recognition result, and the image to be inspected is The personal information is added to the image recognition report; the breast image data with the similarity of the breast screening image in the preset range is matched in the breast image database of the medical information platform, and the matched breast image data is added to the corresponding image. Identification report.

[Claim 7] The method for intelligently identifying a breast screening image according to claim 6, wherein the step of acquiring a mammography image signal of the subject to be detected from the mammography image capturing terminal comprises: utilizing The infrared generator of the breast image acquisition terminal generates infrared light and sees the infrared light on the breast of the person to be detected; the infrared light receiver of the breast image acquisition terminal collects the infrared light signal transmitted through the breast of the person to be detected to be included to be detected An analog electrical signal of the breast tissue structure information; an analog-to-digital converter of the breast image acquisition terminal converts the analog electrical signal modulus containing the breast tissue structure information of the subject to be converted into a breast image signal in the form of a digital signal; The communication port of the collection terminal is configured to send a breast image signal of the person to be detected to the medical terminal device.

The method for intelligently identifying a breast screening image according to claim 6, wherein the image recognition command is a first identification mark, a second identification mark or a third identification mark, and the image recognition result is normal image recognition. a result, a reference image recognition result, or an abnormal image recognition result, wherein: when the image recognition instruction is the first identification mark, determining that the image recognition result of the breast screening image is normal, and matching and mammary gland in the instruction recognition library The text corresponding to the normal health is a normal image recognition result; when the image recognition instruction is the second identification mark 吋, and matching the corresponding text in the instruction recognition library as the reference image recognition result according to the second identification mark; When the image recognition command is the third identification mark, it is determined that the image recognition result is an abnormal image recognition result, and the corresponding character is matched in the command recognition library according to the third identification mark as an abnormal image recognition result.

The method for intelligently identifying a breast screening image according to claim 8, wherein the method further comprises the steps of: identifying a normal image recognition result, an abnormal image recognition result or a reference image recognition result in the image recognition report. Displaying the normal image recognition result, the abnormal image recognition result or the reference image recognition result in the image recognition report in the display unit of the medical terminal device in a preset display manner.

The method for intelligently identifying a breast screening image according to claim 6, wherein the method further comprises the following steps: when the image recognition result corresponding to the image recognition instruction is not matched in the instruction recognition library, The input unit receives the image recognition result input by the doctor and adds it to the image recognition report, and adds the input image recognition result to the instruction recognition library.