WO2018176717A1 - 基于医疗云平台的乳腺筛查影像分析系统及方法 - Google Patents

基于医疗云平台的乳腺筛查影像分析系统及方法 Download PDF

Info

Publication number
WO2018176717A1
WO2018176717A1 PCT/CN2017/096131 CN2017096131W WO2018176717A1 WO 2018176717 A1 WO2018176717 A1 WO 2018176717A1 CN 2017096131 W CN2017096131 W CN 2017096131W WO 2018176717 A1 WO2018176717 A1 WO 2018176717A1
Authority
WO
WIPO (PCT)
Prior art keywords
breast
image
screening
user
information
Prior art date
Application number
PCT/CN2017/096131
Other languages
English (en)
French (fr)
Inventor
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 (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市前海安测信息技术有限公司 filed Critical 深圳市前海安测信息技术有限公司
Publication of WO2018176717A1 publication Critical patent/WO2018176717A1/zh

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

Definitions

  • the present invention relates to the field of medical image processing and recognition technologies, and in particular, to a breast screening image analysis system and method based on a medical cloud platform.
  • 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, the cause of death in most breast cancer patients is because they have not found the best treatment for the disease. Therefore, it is necessary for women to have a breast screening, early detection of breast disease, and early diagnosis for women's health.
  • breast screening images for assisted diagnosis has become an important method for screening and diagnosing early breast cancer.
  • computer-aided detection methods for mammography screening and screening of breast screening images usually require doctors to manually animate the approximate range of breast cancer suspicious area (ROI) in the breast image, breast screening and detection efficiency is not high, no A census for a large number of breast samples.
  • ROI breast cancer suspicious area
  • female friends need to come to the breast census center or hospital in person, causing people to queue up and make the limited hospital resources more tense.
  • the main object of the present invention is to provide a breast screening imaging analysis system and method based on a medical cloud platform, which is convenient for users to perform breast health screening, saves limited hospital resources, and can assist doctors to improve breast disease detection. And the efficiency and accuracy of screening.
  • the present invention provides a breast screening image analysis system based on a medical cloud platform. And applied to the cloud server, the cloud server is connected to the breast image acquisition terminal, the medical cloud platform, and the doctor diagnosis and treatment terminal through a communication network, and the breast screening image analysis system comprises:
  • a user information obtaining module configured to receive a breast screening number input by a breast screening user through a breast image capturing terminal
  • a mammography image acquisition module configured to acquire breast image data including information on a structure of a user's breast tissue from a breast image acquisition terminal, and process breast image data including information on the structure of the breast tissue of the user as a breast screening image of the user;
  • a mammography image processing module configured to perform a distortion-free noise filtering process on a breast screening image and perform grayscale layering processing
  • a mammography image analysis module configured to obtain a normal breast image of the user from a breast image database of the medical cloud platform according to the user's breast screening number, and compare the processed breast screening image with the normal breast image. a texture distribution difference to extract a breast texture feature region from the breast screening image;
  • a breast image output module configured to mark the breast texture feature region in a grayscale layered breast screening image, and The breast screening image marked with the characteristic area of the mammary gland is sent to the doctor's diagnosis terminal through the communication unit for the doctor to diagnose and screen the breast for reference.
  • the breast image acquisition terminal comprises an input unit, an infrared generator, an infrared receiver, an analog to digital converter and a communication port, wherein:
  • the input unit is configured to allow a user to input a breast screening number
  • the infrared generator is configured to generate infrared light and fluoresce the infrared light onto the user's breast;
  • the infrared receiver is configured to collect an infrared light signal transmitted through a user's breast and process it as an analog electrical signal of breast tissue structure information;
  • the analog-to-digital converter is configured to perform analog-to-digital conversion of an analog electrical signal containing information about a user's breast tissue collected by an infrared receiver into breast image data including information about a user's breast tissue structure;
  • the communication port is configured to send the breast image data including the information about the structure of the breast tissue of the user to the cloud server through the communication network.
  • the breast image acquisition module records the image data of the breast image data of the user's breast tissue structure information in the form of a digital file by using digital image processing software, and generates a breast screening image of the user according to the image data.
  • the breast image database stores normal breast images collected by different users in a breast health examination and a general examination, wherein the normal breast image is a breast image in a user's breast health state, and the texture distribution difference includes Differences in tissue structure, size, and contour of the mammary gland.
  • the grayscale layering process comprises dividing the breast screening image into different regions according to gray scales and performing color assignment processing on each region.
  • the present invention provides a breast screening imaging analysis method based on a medical cloud platform, which is applied to a cloud server, and the cloud server is connected to a breast image acquisition terminal, a medical cloud platform, and a doctor diagnosis and treatment terminal through a communication network, the method
  • the method comprises the steps of: receiving a breast screening number input by a breast screening user through a breast image collecting terminal; acquiring breast image data containing information about a user's breast tissue structure from the breast image capturing terminal; processing the breast image data including the information of the user's breast tissue structure as The breast is screened for image; the breast screening image is subjected to distortion-free noise filtering processing and grayscale layering processing; the normal breast image of the user is obtained from the breast image database of the medical cloud platform according to the user's breast screening number, and Comparing the texture distribution difference between the processed breast screening image and the normal breast image to extract the breast texture feature region from the breast screening image; marking the breast in the gray layered breast screening image Texture feature area, and communicate Element labeled with the
  • the breast image acquisition terminal comprises an input unit, an infrared generator, an infrared receiver, an analog-to-digital converter and a communication port, and the breast image acquisition terminal acquires breast image data including information about the structure of the user's breast tissue.
  • the steps include: generating infrared light through the infrared generator and seeing the infrared light on the user's breast; collecting infrared light signals transmitted through the user's breast through the infrared receiver and processing the analog electrical signals as breast tissue structure information; using analog to digital conversion
  • the analog electrical signal collected by the infrared receiver and containing the information about the structure of the user's breast tissue is converted into mammography data containing the information of the user's breast tissue structure; the breast image data containing the information of the user's breast tissue structure is passed through the communication port.
  • the communication network is sent to the cloud server.
  • the step of processing the breast image data including the information about the structure of the user's breast tissue into the breast screening image comprises: recording the breast image data of the user's breast tissue structure information in the form of a digital file by using digital image processing software Image data; generating a breast screening image of the user based on the image data.
  • the breast image database stores normal breast images collected by different users in the breast health examination and screening, and the normal breast image is a breast image collected by the user in a healthy state of the breast, and the texture distribution is different. Includes differences in tissue structure, size differences, and contour differences in the mammary gland.
  • the gray leveling process comprises dividing the breast screening image into different regions according to gray scales and performing color assignment processing on each region.
  • the breast screening imaging analysis system and method based on the medical cloud platform of the present invention collects the user's mammary gland screening image through the mammography image collection terminal installed in each community medical workstation, which is convenient for the user to perform.
  • Breast health checkup and breast cancer screening saves limited hospital resources.
  • the breast texture feature region is extracted from the processed breast screening image and the breast texture feature region is marked in the breast screening image and sent to the doctor diagnosis terminal. It provides a reference for doctors to diagnose and screen breast diseases, so as to help doctors improve the efficiency and accuracy of breast disease detection and screening, and improve the social efficiency of breast screening.
  • FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of a breast screening image analysis system based on a medical cloud platform of the present invention
  • FIG. 2 is a flow chart of a preferred embodiment of a breast screening image analysis method based on a medical cloud platform according to the present invention
  • FIG. 3 is a schematic diagram of a mammary gland image comparing a breast texture feature region with a normal breast image.
  • FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of a breast screening image analysis system based on a medical cloud platform according to the present invention.
  • the breast screening image analysis system 10 is installed and operated in the cloud server 1.
  • the cloud server 1 establishes a communication connection with the medical cloud platform 2, the breast image capturing terminal 4, and the doctor's medical treatment terminal 5 via the communication network 3.
  • the cloud server 1 can be a computing device having data processing and communication functions, such as a computer or a server.
  • the medical cloud platform 2 may be a server or a server in a medical information system platform, and provide a data interface for medical inspection institutions such as regional hospitals or community medical workstations, and can receive breast screening of each medical inspection institution. image.
  • the medical cloud platform 2 includes a breast image database 20, which stores normal breast images collected by different users in the past for performing breast health examinations and screenings, and the normal breast images are collected by the user in a healthy state of the mammary gland. image.
  • 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, CDMA.
  • the doctor's medical treatment terminal 5 is a doctor's workstation computer installed in a breast examination center or a large hospital for displaying breast screening images, and the doctor diagnoses and screens the user's breast health according to the breast screening image.
  • the breast image capturing terminal 4 is disposed in a medical examination institution such as a community medical workstation, and the breast image capturing terminal 4 includes an input unit 40, an infrared generator 41, an infrared receiver 42, an analog to digital converter 43, and communication. Port 44.
  • the input unit 41 may be an input device such as a keyboard or a handwriting touch screen for the breast screening user to input user information.
  • the user's breast screening number (such as an ID number or a medical certificate number) may be input on the input unit 41.
  • the infrared generator 41 is configured to generate infrared light and fluoresce the infrared light onto the user's mammary gland
  • the infrared receiver 42 is configured to collect infrared light signals transmitted through the user's breast and process the image into a mammary gland
  • the analog-to-digital signal of the information is configured to perform analog-to-digital conversion of the analog electrical signal containing the user's mammography information collected by the infrared receiver 42 into a digital signal including user breast image information
  • the communication port 44 is for transmitting user information and digital signals containing the user's breast image information 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, and CDMA.
  • the cloud server 1 includes, but is not limited to, a mammography screening image analysis system 10, a storage unit 11, a processing unit 12, and a communication unit 13.
  • the storage unit 11, the processing unit 12 and the communication unit 13 are all connected to the processing unit 12 via a data bus, and can be processed by the processing unit 12
  • the breast screening image analysis system 10 performs information interaction.
  • the storage unit 11 can be a read only memory unit ROM, an electrically erasable memory unit EEPROM or a flash memory unit FLASH.
  • the processing unit 12 can be 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 13 can be a wireless communication interface with remote wireless communication functions, such as a communication interface supporting GSM, GPRS, CDMA.
  • the breast screening image analysis system 10 includes, but is not limited to, a user information acquisition module 101, a breast image acquisition module 102, a breast image processing module 103, a breast image analysis module 104, and a breast.
  • Image output module 105 refers to a series of computer program instruction segments which can be executed by the processing unit 12 of the cloud server 1 and which are capable of performing a fixed function, which are stored in the storage unit 11 of the cloud server 1.
  • the user information obtaining module 101 is configured to receive a breast screening number input by the breast screening user through the input unit 41 of the breast image capturing terminal 4.
  • the user manually activates the breast image acquisition terminal 4 and inputs information such as the user's breast screening number (e.g., ID number or medical certificate number) or user name from the input unit 41.
  • the communication port 44 of the mammography image acquisition terminal 4 transmits the mammary screening number input by the user to the user information acquisition module 101 via the communication network 3.
  • the mammography image acquisition module 102 is configured to obtain, by the communication unit 13, the mammography image data including the information about the structure of the breast tissue of the user from the mammography image acquisition terminal 4, and process the mammography data including the information about the structure of the mammary tissue of the user as The user's breast screening image.
  • the infrared generator 41 generates infrared light and fluoresces the infrared light onto the user's breast; the infrared receiver 42 collects an infrared light signal transmitted through the user's breast and processes it as an analog electrical signal of the breast tissue structure information;
  • the infrared light generated by the generator 41 is seen through the user's mammary gland, 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 converts the analog electrical signal collected by the infrared receiver 42 and contains the information of the user's breast tissue structure into mammography data (including the digital image signal including the information of the user's breast tissue structure).
  • the communication port 44 transmits the breast image data including the user's breast tissue structure information to the communication unit 13 of the cloud server 1 through the communication network 3, and the breast image acquisition module 102 reads the breast image of the user's breast tissue structure information from the communication unit 13. data.
  • the mammography image acquisition module 102 is further configured to process breast image data including user breast tissue structure information into a breast screening image of the user. Specifically, the mammography image acquisition module 102 records the image data of the breast image data of the user's breast tissue structure information in the form of a digital file by using digital image processing software, and then generates a breast screening image of the user according to the image data, and the breast screening image is imaged. It is a digital image of the breast that can be used for display.
  • infrared breast detection Infrared light illuminates the human breast, because the human breast tissue exhibits different absorption characteristics through the infrared spectrum, so the infrared light signal passing through the lesion and the infrared signal passing through the normal breast tissue The intensity will vary.
  • the location and size of the lesion in the breast can be detected by the grayscale, histological structure, and external dimensions of the acquired infrared image, especially the optical properties of the breast tissue.
  • the mammography processing module 103 is configured to perform a distortion-free noise filtering process on the mammography screening image and perform grayscale layering processing. Specifically, the mammography processing module 103 performs a distortion-free noise filtering process on the breast screening image by using a Gaussian filter function to remove impurities of the breast screening image, thereby improving the accuracy of detecting and screening the breast disease.
  • the mammography image processing module 103 performs gray scale layering on the non-distortion processed mammary gland image to obtain a mammography screening image after grayscale layering, so as to enhance the layered display effect of the mammary gland screening image.
  • the grayscale layering process is also referred to as density layering processing, which comprises dividing the breast screening image into different regions according to the gray scale and performing color assignment processing on each region, thereby achieving the effect of layered display of the grayscale image of the breast.
  • density layering processing comprises dividing the breast screening image into different regions according to the gray scale and performing color assignment processing on each region, thereby achieving the effect of layered display of the grayscale image of the breast.
  • the mammary gland screening image after gray layering treatment can more clearly show the texture distribution on the mammary gland screening image, such as the tissue structure, size and contour of the mammary gland.
  • the breast image analysis module 104 is configured to obtain a normal breast image of the user from the breast image database 20 according to the user's breast screening number.
  • the breast image database 20 stores normal breast images that have been subjected to breast health examinations and general surveys by different users in the past.
  • the normal breast images are breast images in a user's breast health state.
  • the breast image analysis module 104 is further configured to compare the texture distribution difference between the breast screening image and the normal breast image to extract the breast texture feature region from the breast screening image.
  • the texture distribution differences include differences in tissue structure, size differences, and contour differences of the breast. Referring to Figure 3, Figure 3 is a schematic illustration of a mammary gland image compared to a normal mammary gland image.
  • A represents the user's normal breast image
  • B represents the user's breast screening image.
  • the present invention uses the image of normal breast tissue as a normal breast image and when Pre-screening of breast images for comparison is most effective in detecting abnormalities or abnormalities in breast tissue, but there are large differences in infrared images due to parts or individuals, and it is most suitable to have been diagnosed as abnormal.
  • the past mammary gland image is a reference image of the normal breast.
  • the breast image output module 105 is configured to mark a breast texture characteristic area in the breast screening image, thereby assisting a doctor to improve the efficiency and accuracy of detecting and screening breast diseases. As shown in Fig. 3, the elliptical region in the mammary gland screening image B is the marked mammographic texture feature region.
  • the mammography image output module 105 is further configured to send a breast screening image marked with a characteristic area of the mammary gland to the doctor's medical treatment terminal 5 through the communication unit 13 for providing a reference for the doctor to diagnose and screen the breast disease.
  • the present invention also provides a breast screening image analysis method based on a medical cloud platform, which is applied to a cloud server.
  • Fig. 2 is a flow chart showing a preferred embodiment of the breast screening image analysis method based on the medical cloud platform of the present invention.
  • the embodiment of the present invention, together with FIG. 1, the medical cloud platform-based breast screening image analysis method includes the following steps:
  • Step S21 The user information acquiring module 101 receives the breast screening number input by the breast screening user through the input unit 41 of the breast image capturing terminal 4.
  • the user manually activates the breast image capturing terminal 4 and inputs the user's breast screening number (such as an ID number or a medical certificate number) or a user name from the input unit 41 of the breast image capturing terminal 4.
  • the communication port 44 of the mammography image acquisition terminal 4 transmits the mammary gland screening number input by the user to the user information acquisition module 101 via the communication network 3.
  • Step S22 acquiring breast image data including the information about the structure of the breast tissue of the user from the breast image capturing terminal; specifically, the breast image capturing module 102 acquires information about the structure of the breast tissue of the user from the breast image capturing terminal 4 through the communication unit 13. Mammography data.
  • the infrared generator 41 of the breast image capturing terminal 4 generates infrared light and sees the infrared light on the user's breast; the infrared receiver 42 of the breast image capturing terminal 4 collects the infrared light signal transmitted through the user's breast and processes it into the breast tissue structure information.
  • the analog electric signal; the infrared light generated by the infrared generator 41 is fluorinated to the user's breast, 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 of the mammography image acquisition terminal 4 converts the analog electrical signal collected by the infrared receiver 42 and contains the information of the user's breast tissue structure into mammography data containing the information of the user's breast tissue structure (ie, contains the user's breast tissue).
  • the digital video signal of the structural information); the communication port 44 of the breast image capturing terminal 4 transmits the breast image data including the information of the user's breast tissue structure to the communication unit 1 of the cloud server 1 through the communication network 3.
  • the mammography image acquisition module 102 reads the mammography data of the user's breast tissue structure information from the communication unit 13.
  • Step S23 processing the breast image data including the information about the structure of the breast tissue of the user as a breast screening image of the user.
  • the mammography image acquisition module 102 records the image data of the breast image data of the user's breast tissue structure information in the form of a digital file by using digital image processing software, and then generates a breast screening image of the user according to the image data, and the breast screening image is imaged. It is a digital image of the breast that can be used for display.
  • infrared breast detection Infrared light illuminates the human breast, because the human breast tissue exhibits different absorption characteristics through the infrared spectrum, so the infrared light signal passing through the lesion and the infrared signal passing through the normal breast tissue The intensity will vary.
  • the location and size of the lesion in the breast can be detected by the grayscale, histological structure, and external dimensions of the acquired infrared image, especially the optical properties of the breast tissue.
  • Step S24 performing a distortion-free noise filtering process and performing grayscale layering processing on the breast screening image; specifically, the breast image processing module 103 uses a Gaussian filter function to perform the distortion-free noise removal on the breast screening image.
  • the filtering process removes the impurities of the breast screening image, thereby improving the accuracy of detecting and screening the breast disease.
  • the mammography image processing module 103 performs gray scale layering on the mammographic screening image without distortion processing to obtain a mammography screening image after grayscale layering, so as to enhance the layered display effect of the mammary gland screening image.
  • the grayscale layering process is also referred to as density layering processing, which comprises dividing the breast screening image into different regions according to gray scale and performing color assignment processing on each region, thereby achieving the grayscale image of the breast.
  • density layering processing comprises dividing the breast screening image into different regions according to gray scale and performing color assignment processing on each region, thereby achieving the grayscale image of the breast.
  • the effect of the layer display is also referred to as density layering processing, which comprises dividing the breast screening image into different regions according to gray scale and performing color assignment processing on each region, thereby achieving the grayscale image of the breast.
  • the effect of the layer display the mammography screening image after grayscale layering can more clearly show the texture distribution on the mammary gland screening image, such as the tissue structure, size and contour of the mammary gland.
  • Step S25 obtaining a normal breast image of the user from the breast image database of the medical cloud platform according to the user's breast screening number, and comparing the texture distribution difference between the processed breast screening image and the normal breast image.
  • the breast texture feature region is extracted from the breast screening image; specifically, the breast image analysis module 104 obtains the normal breast image of the user from the breast image database 20 according to the user's breast screening number.
  • the breast image database 20 stores normal breast images collected by different users in the past for breast health examination and general examination, and the normal breast images are breast images collected by the user in a healthy state of the breast.
  • the mammography image analysis module 104 displays the breast screening image and the normal breast image.
  • the texture distribution differences were compared to extract the mammographic texture feature regions from the breast screening image.
  • the texture distribution differences include differences in tissue structure, size differences, and contour differences of the breast.
  • the present invention compares the image of normal breast tissue as a normal breast image with the currently screened breast image, and is most effective in detecting abnormalities or abnormalities in breast tissue, but for infrared images due to parts or individuals Large differences ⁇ are best suited for use as a reference image of past breast images that have been diagnosed as abnormal.
  • Step S26 marking the breast texture feature area in the breast screening image, and transmitting the breast screening image indicating the characteristic area of the mammary gland to the doctor diagnosis and treatment terminal through the communication unit for the doctor to diagnose and screen the breast reference.
  • the mammography image output module 105 marks the mammary gland texture feature area in the breast screening image.
  • the elliptical area in the mammary gland screening image B is the marked mammographic texture characteristic area, thereby Auxiliary doctors improve the efficiency and accuracy of testing and screening for breast diseases.
  • the mammography output module 105 sends a mammography screening image marked with a characteristic area of the mammary gland to the doctor's medical treatment terminal 5 via the communication unit 13 for the doctor to provide a reference for diagnosis and screening of the breast disease.
  • the medical cloud platform-based mammography screening image analysis system and method provided by the invention collects the user's mammary gland screening image through the mammography image collection terminal set in each community medical workstation, and is convenient for the user to perform the breast health examination and the breast cancer screening. Check, save limited hospital resources.
  • the invention can perform noise removal and gray layer stratification on the breast screening image, extract the breast texture feature area from the processed breast screening image and mark the breast texture feature area in the breast screening image, and send it to the doctor.
  • the diagnosis and treatment terminal provides a reference for doctors to diagnose and screen breast diseases, thereby assisting doctors to improve the efficiency and accuracy of breast disease detection and screening, and improve the social efficiency of breast screening.
  • the breast screening imaging analysis system and method based on the medical cloud platform of the present invention collects the user's mammary gland screening image through the mammography image collection terminal set in each community medical workstation, which is convenient for the user to perform.
  • Breast health checkup and breast cancer screening saves limited hospital resources.
  • extracting mammary gland texture features from the processed breast screening images and marking the mammary gland texture features in the mammography screening image and sending them to the doctor's treatment terminal for the doctor Provide reference for diagnosis and screening of breast diseases, so as to help doctors improve the efficiency and accuracy of breast disease detection and screening, and improve the social efficiency of breast screening.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Pathology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Physiology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

一种基于医疗云平台的乳腺筛查影像分析系统（10）及方法，应用于云服务器（1）中，云服务器（1）通过通信网络（3）连接乳腺影像采集终端（4）、医疗云平台（2）和医生诊疗终端（5）。乳腺影像采集终端（4）包括输入单元（40）、红外发生器（41）、红外接收器（42）、模数转换器（43）和通信端口（44）。乳腺筛查影像分析系统（10）包括用户信息获取模块（101）、乳腺影像采集模块（102）、乳腺影像处理模块（103）、乳腺影像分析模块（104）和乳腺影像输出模（105）。通过乳腺影像采集终端（4）采集用户的乳腺筛查影像，方便用户进行乳腺健康筛查，节省医院资源，通过对乳腺筛查影像进行去除噪音及灰度分层处理，在乳腺筛查影像中提取乳腺纹理特征以供医生对乳腺疾病进行诊断与筛查提供参考，从而辅助医生提高对乳腺疾病筛查的效率及准确性。

Description

基于医疗云平台的 ¥L腺筛査影像分析系统及方法 技术领域
[0001] 本发明涉及医学影像处理与识别技术领域， 尤其涉及一种基于医疗云平台的乳 腺筛査影像分析系统及方法。
背景技术
[0002] 乳腺疾病是女性的多发病症之一， 特别是随着现代都市生活节奏的加快， 女性 面对的生活压力、 工作压力加重， 乳腺疾病的发病率在逐年升高， 严重的乳腺 疾病可能导致乳腺癌。 据不完全调査统计显示， 乳腺疾病的发病率和死亡率也 都成上升趋势。 其实， 大部分乳腺癌患者的死亡原因就是因为没有及吋发现， 错过了最佳治疗吋机， 因此， 对广大女性进行乳腺普査、 乳腺疾病早发现、 早 期诊断对于女性健康是十分必要的。
[0003] 目前， 利用乳腺筛査影像进行辅助诊断已经成为被广泛采用的筛査和诊断早期 乳腺癌的重要方法。 目前， 利用计算机辅助检测方法对乳腺筛査影像进行乳腺 检测与筛査吋， 通常需要医生在乳腺影像上手动画出乳腺癌可疑区域 （ROI) 的 大致范围， 乳腺筛査与检测效率不高， 不适合大量乳腺样本的普査情况。 在女 性乳腺癌的体检和普査活动中， 女性朋友们需要亲自来到乳腺普査中心或医院 ， 造成人多需要排队， 并且使原本有限的医院资源更加紧张。 此外， 由于乳腺 影像数量很多， 医生直接对每幅乳腺影像手动画出 ROI进行检测难以保证效率及 准确性， 从而容易造成漏诊和误诊的情况发生。
技术问题
[0004] 本发明的主要目的在于提供一种基于医疗云平台的乳腺筛査影像分析系统及方 法， 既方便用户进行乳腺健康筛査， 节省有限的医院资源， 又能够辅助医生提 高对乳腺疾病检测与筛査的效率及准确性。
问题的解决方案
技术解决方案
[0005] 为实现上述目的， 本发明提供了一种基于医疗云平台的乳腺筛査影像分析系统 ， 应用于云服务器中， 该云服务器通过通信网络连接至乳腺影像采集终端、 医 疗云平台以及医生诊疗终端， 所述乳腺筛査影像分析系统包括：
[0006] 用户信息获取模块， 用于通过乳腺影像采集终端接收乳腺筛査用户输入的乳腺 筛査编号；
[0007] 乳腺影像采集模块， 用于从乳腺影像采集终端获取包含用户乳腺组织结构信息 的乳腺影像数据， 以及将包含该用户乳腺组织结构信息的乳腺影像数据处理为 用户的乳腺筛査影像；
[0008] 乳腺影像处理模块， 用于将乳腺筛査影像进行无失真去除噪声滤波处理以及进 行灰度分层处理；
[0009] 乳腺影像分析模块， 用于根据用户的乳腺筛査编号从医疗云平台的乳腺影像数 据库中获取该用户的正常乳腺影像， 以及比较处理后的乳腺筛査影像与正常乳 腺影像两者的纹理分布差异以从所述乳腺筛査影像中提取乳腺纹理特征区域； [0010] 乳腺影像输出模块， 用于在灰度分层后的乳腺筛査影像中标示出所述乳腺纹理 特征区域， 并通过通信单元将标示有乳腺纹理特征区域的乳腺筛査影像发送至 医生诊疗终端以供医生对乳腺进行诊断与筛査参考。
[0011] 优选的， 所述乳腺影像采集终端包括输入单元、 红外发生器、 红外接收器、 模 数转换器以及通信端口， 其中：
[0012] 所述输入单元用于供用户输入乳腺筛査编号；
[0013] 所述红外发生器用于产生红外光并将红外光透视至用户乳腺上；
[0014] 所述红外接收器用于采集透过用户乳腺的红外光信号并处理为乳腺组织结构信 息的模拟电信号；
[0015] 所述模数转换器用于将红外接收器采集到的包含用户乳腺组织结构信息的模拟 电信号模数转换处理为包含用户乳腺组织结构信息的乳腺影像数据；
[0016] 所述通信端口用于将包含该用户乳腺组织结构信息的乳腺影像数据通过通信网 络发送至云服务器。
[0017] 优选的， 所述乳腺影像采集模块利用数字影像处理软件将用户乳腺组织结构信 息的乳腺影像数据以数字文件的形式记录影像数据， 并根据所述影像数据产生 用户的乳腺筛査影像。 [0018] 优选的， 所述乳腺影像数据库存储有不同用户在乳腺健康体检和普査吋采集的 正常乳腺影像， 所述正常乳腺影像为用户乳腺健康状态下的乳腺影像， 所述纹 理分布差异包括乳腺的组织结构差异、 尺寸大小差异及外形轮廓差异。
[0019] 优选的， 所述灰度分层处理包括将所述乳腺筛査影像按灰度分割成不同的区域 并对每个区域进行色彩赋值处理。
[0020] 本发明提供了一种基于医疗云平台的乳腺筛査影像分析方法， 应用于云服务器 中， 该云服务器通过通信网络连接至乳腺影像采集终端、 医疗云平台以及医生 诊疗终端， 该方法包括步骤： 通过乳腺影像采集终端接收乳腺筛査用户输入的 乳腺筛査编号； 从乳腺影像采集终端获取包含用户乳腺组织结构信息的乳腺影 像数据； 将包含用户乳腺组织结构信息的乳腺影像数据处理为乳腺筛査影像； 将乳腺筛査影像进行无失真去除噪声滤波处理以及进行灰度分层处理； 根据用 户的乳腺筛査编号从医疗云平台的乳腺影像数据库中获取该用户的正常乳腺影 像， 并比较处理后的乳腺筛査影像与正常乳腺影像两者的纹理分布差异以从所 述乳腺筛査影像中提取乳腺纹理特征区域； 在灰度分层后的乳腺筛査影像中标 示出所述乳腺纹理特征区域， 并通过通信单元将标示有乳腺纹理特征区域的乳 腺筛査影像发送至医生诊疗终端以供医生对乳腺进行诊断与筛査参考。
[0021] 优选的， 所述乳腺影像采集终端包括输入单元、 红外发生器、 红外接收器、 模 数转换器以及通信端口， 所述从乳腺影像采集终端获取包含用户乳腺组织结构 信息的乳腺影像数据的步骤包括： 通过红外发生器产生红外光并将红外光透视 至用户乳腺上； 通过红外接收器采集透过用户乳腺的红外光信号并处理为乳腺 组织结构信息的模拟电信号； 利用模数转换器将红外接收器采集到的包含用户 乳腺组织结构信息的模拟电信号模数转换处理为包含用户乳腺组织结构信息的 乳腺影像数据； 通过通信端口将包含该用户乳腺组织结构信息的乳腺影像数据 通过通信网络发送至云服务器。
[0022] 优选的， 所述将包含用户乳腺组织结构信息的乳腺影像数据处理为乳腺筛査影 像的步骤包括： 利用数字影像处理软件将用户乳腺组织结构信息的乳腺影像数 据以数字文件的形式记录影像数据； 根据所述影像数据产生用户的乳腺筛査影 像。 [0023] 优选的， 所述乳腺影像数据库存储有不同用户在乳腺健康体检和普査吋采集的 正常乳腺影像， 所述正常乳腺影像为用户乳腺健康状态下采集的乳腺影像， 所 述纹理分布差异包括乳腺的组织结构差异、 尺寸大小差异以及外形轮廓差异。
[0024] 优选的， 所述灰度分层处理包括将所述乳腺筛査影像按灰度分割成不同的区域 并对每个区域进行色彩赋值处理。
发明的有益效果
有益效果
[0025] 相较于现有技术， 本发明所述基于医疗云平台的乳腺筛査影像分析系统及方法 通过设置在各社区医疗工作站的乳腺影像采集终端采集用户的乳腺筛査影像， 方便用户进行乳腺健康体检及乳腺癌筛査， 节省有限的医院资源。 通过对乳腺 筛査影像进行去除噪音及灰度分层处理， 从处理后的乳腺筛査影像中提取乳腺 纹理特征区域并在乳腺筛査影像中标示出乳腺纹理特征区域， 并发送至医生诊 疗终端以供医生对乳腺疾病进行诊断与筛査提供参考， 从而辅助医生提高对乳 腺疾病检测与筛査的效率及准确性， 提高乳腺筛査的社会效率。
对附图的简要说明
附图说明
[0026] 图 1是本发明基于医疗云平台的乳腺筛査影像分析系统优选实施例的应用环境 示意图；
[0027] 图 2是本发明基于医疗云平台的乳腺筛査影像分析方法优选实施例的流程图； [0028] 图 3是乳腺筛査影像与正常乳腺影像比较乳腺纹理特征区域的示意图。
[0029] 本发明目的实现、 功能特点及优点将结合实施例， 参照附图做进一步说明。
实施该发明的最佳实施例
本发明的最佳实施方式
[0030] 为更进一步阐述本发明为达成上述目的所采取的技术手段及功效， 以下结合附 图及较佳实施例， 对本发明的具体实施方式、 结构、 特征及其功效进行详细说 明。 应当理解， 此处所描述的具体实施例仅仅用以解释本发明， 并不用于限定 本发明。 [0031] 参照图 1所示， 图 1是本发明基于医疗云平台的乳腺筛査影像分析系统优选实施 例的应用环境示意图。 在本实施例中， 所述乳腺筛査影像分析系统 10安装并运 行于云服务器 1中。 所述云服务器 1通过通信网络 3与医疗云平台 2、 乳腺影像采 集终端 4以及医生诊疗终端 5建立通信连接。 所述云服务器 1可以为一种计算机、 服务器等具有数据处理和通信功能的计算装置。 所述医疗云平台 2可以是一种医 疗信息系统平台中的一台或服务器， 并为各地区医院或社区医疗工作站等医疗 检査机构提供数据接口， 可以接收各医疗检査机构的乳腺筛査影像。 该医疗云 平台 2包括乳腺影像数据库 20， 所述乳腺影像数据库 20存储有不同用户过去进行 乳腺健康体检和普査吋采集的正常乳腺影像， 所述正常乳腺影像为用户乳腺健 康状态下采集的乳腺影像。 所述通信网络 3可以是一种包括局域网、 广域网的网 际网络， 或者是一种包括 GSM、 GPRS. CDMA的无线传输网络。 医生诊疗终端 5为设置在乳腺体检中心或大型医院的医生工作站计算机， 用于显示乳腺筛査影 像， 医生根据乳腺筛査影像对用户的乳腺健康状况诊断与筛査。
[0032] 所述乳腺影像采集终端 4设置在社区医疗工作站等医疗检査机构内， 该乳腺影 像采集终端 4包括输入单元 40、 红外发生器 41、 红外接收器 42、 模数转换器 43以 及通信端口 44。 所述输入单元 41可以为键盘或手写触摸屏等输入设备， 用于供 乳腺筛査用户输入用户信息， 例如， 可以在输入单元 41上输入用户的乳腺筛査 编号 （例如身份证号或者医疗证号） 或者用户名等信息； 所述红外发生器 41用 于产生红外光并将红外光透视至用户乳腺上； 所述红外接收器 42用于采集透过 用户乳腺的红外光信号并处理为乳腺影像信息的模拟电信号； 所述模数转换器 4 3用于将红外接收器 42采集到的包含了用户乳腺影像信息的模拟电信号模数转换 处理为包含用户乳腺影像信息的数字信号； 所述通信端口 44用于将用户信息以 及包含该用户乳腺影像信息的数字信号通过通信网络 3发送至云服务器 1。 所述 通信端口 44可以为一种具有远程无线通讯功能的无线通讯接口， 例如支持 GSM 、 GPRS、 CDMA的通讯接口。
[0033] 在本实施例中， 所述云服务器 1包括， 但不仅限于， 乳腺筛査影像分析系统 10 、 存储单元 11、 处理单元 12以及通信单元 13。 所述存储单元 11、 处理单元 12以 及通信单元 13均通过数据总线连接至处理单元 12， 并能通过处理单元 12与所述 乳腺筛査影像分析系统 10进行信息交互。 所述存储单元 11可以为一种只读存储 单元 ROM, 电可擦写存储单元 EEPROM或快闪存储单元 FLASH等存储器。 所述 处理单元 12可以为一种中央处理器 （CPU) 、 微处理器、 微控制器 （MCU) 、 数据处理芯片、 或者具有数据处理功能的信息处理单元。 所述通信单元 13可以 为一种具有远程无线通讯功能的无线通讯接口， 例如支持 GSM、 GPRS. CDMA 的通讯接口。
[0034] 在本实施例中， 所述乳腺筛査影像分析系统 10包括， 但不局限于， 用户信息获 取模块 101、 乳腺影像采集模块 102、 乳腺影像处理模块 103、 乳腺影像分析模块 104以及乳腺影像输出模块 105。 本发明所称的模块是指一种能够被所述云服务 器 1的处理单元 12执行并且能够完成固定功能的一系列计算机程序指令段， 其存 储在所述云服务器 1的存储单元 11中。
[0035] 所述用户信息获取模块 101用于通过乳腺影像采集终端 4的输入单元 41接收乳腺 筛査用户输入的乳腺筛査编号。 在本实施例中， 用户手动幵启乳腺影像采集终 端 4并从输入单元 41上输入用户的乳腺筛査编号 （例如身份证号或者医疗证号） 或者用户名等信息。 乳腺影像采集终端 4的通信端口 44将用户输入的乳腺筛査编 号通过通信网络 3发送至用户信息获取模块 101。
[0036] 所述乳腺影像采集模块 102用于通过通信单元 13从乳腺影像采集终端 4获取包含 该用户乳腺组织结构信息的乳腺影像数据， 以及将包含该用户乳腺组织结构信 息的乳腺影像数据处理为用户的乳腺筛査影像。 在本实施例中， 红外发生器 41 产生红外光并将红外光透视至用户乳腺上； 红外接收器 42采集透过用户乳腺的 红外光信号并处理为乳腺组织结构信息的模拟电信号； 上述红外发生器 41产生 的红外光透视至用户乳腺上， 红外接收器 42接收的红外光信号携带了乳腺组织 结构信息的红外透射光。 模数转换器 43将红外接收器 42采集到的包含用户乳腺 组织结构信息的模拟电信号模数转换处理为包含用户乳腺组织结构信息的乳腺 影像数据 （即包含用户乳腺组织结构信息的数字影像信号） ； 通信端口 44将包 含该用户乳腺组织结构信息的乳腺影像数据通过通信网络 3发送至云服务器 1的 通信单元 13， 乳腺影像采集模块 102从通信单元 13读取用户乳腺组织结构信息的 乳腺影像数据。 [0037] 所述乳腺影像采集模块 102还用于将包含用户乳腺组织结构信息的乳腺影像数 据处理为用户的乳腺筛査影像。 具体地， 乳腺影像采集模块 102利用数字影像处 理软件将用户乳腺组织结构信息的乳腺影像数据以数字文件的形式记录影像数 据， 然后根据该影像数据产生用户的乳腺筛査影像， 该乳腺筛査影像是可用于 显示的乳腺数字影像。 红外乳腺检测的原理是： 红外光线照射人体乳腺部位， 由于人体乳腺组织对通过其中的红外光谱呈现出不同的吸收特性， 所以透过病 变部位的红外光信号与透过正常乳腺组织的红外信号的强度会有所不同， 通过 采集到的红外影像的灰度、 组织结构、 外形尺寸特别是乳腺组织的光学特性， 就可以检测到乳腺部位发生病变的位置和尺寸。
[0038] 所述乳腺影像处理模块 103用于将乳腺筛査影像进行无失真去除噪声滤波处理 以及进行灰度分层处理。 具体地， 乳腺影像处理模块 103采用高斯滤波函数将所 述乳腺筛査影像进行无失真去除噪声滤波处理清除所述乳腺筛査影像的杂质， 从而提高对乳腺疾病进行检测与筛査的准确性。 乳腺影像处理模块 103将无失真 处理后的乳腺筛査影像进行灰度分层处理得到灰度分层后的乳腺筛査影像， 以 增强乳腺筛査影像的分层显示效果。 所述灰度分层处理也称谓密度分层处理， 包括将乳腺筛査影像按灰度分割成不同的区域并对每个区域进行色彩赋值处理 ， 从而使乳腺灰度影像达到分层显示的效果。 在本实施例中， 经过灰度分层处 理后的乳腺筛査影像更能够明显地显示出乳腺筛査影像上的纹理分布情况， 例 如乳腺的组织结构、 尺寸大小及外形轮廓等。
[0039] 所述乳腺影像分析模块 104用于根据用户的乳腺筛査编号从乳腺影像数据库 20 中获取该用户的正常乳腺影像。 在本实施例中， 所述乳腺影像数据库 20存储有 不同用户过去进行乳腺健康体检和普査吋采集的正常乳腺影像， 所述正常乳腺 影像为用户乳腺健康状态下的乳腺影像。 所述乳腺影像分析模块 104还用于将乳 腺筛査影像与正常乳腺影像两者的纹理分布差异进行比较以从乳腺筛査影像中 提取乳腺纹理特征区域。 所述纹理分布差异包括乳腺的组织结构差异、 尺寸大 小差异及外形轮廓差异。 参考图 3所示， 图 3是乳腺筛査影像与正常乳腺影像比 较乳腺纹理特征区域的示意图。 其中" A"代表用户的正常乳腺影像， "B"代表用 户的乳腺筛査影像。 本发明通过将正常乳房组织的影像作为正常乳腺影像与当 前筛査的乳腺影像进行比较， 对在乳房组织中检测出异常或没有异常是最有效 的， 但是对于红外影像因部位或者个人而有很大的差异吋， 最适合以已经被诊 断为无异常的过去乳腺影像为正常乳腺的参考影像。
[0040] 所述乳腺影像输出模块 105用于在所述乳腺筛査影像中标示出乳腺纹理特征区 域， 从而辅助医生提高对乳腺疾病进行检测与筛査的效率及准确性。 如图 3所示 ， 乳腺筛査影像 B中的椭圆形区域即为标示出的乳腺纹理特征区域。 所述乳腺影 像输出模块 105还用于将标示有乳腺纹理特征区域的乳腺筛査影像通过通信单元 13发送至医生诊疗终端 5， 以供医生对乳腺疾病进行诊断与筛査提供参考依据。
[0041] 本发明还提供了一种基于医疗云平台的乳腺筛査影像分析方法， 应用于云服务 器中。 如图 2所示， 图 2是本发明基于医疗云平台的乳腺筛査影像分析方法优选 实施例的流程图。 本实施例一并结合图 1所示， 所述基于医疗云平台的乳腺筛査 影像分析方法包括如下步骤：
[0042] 步骤 S21， 用户信息获取模块 101通过乳腺影像采集终端 4的输入单元 41接收乳 腺筛査用户输入的乳腺筛査编号。 在本实施例中， 用户手动幵启乳腺影像采集 终端 4并从该乳腺影像采集终端 4的输入单元 41上输入用户的乳腺筛査编号 （例 如身份证号或者医疗证号） 或者用户名等信息。 乳腺影像采集终端 4的通信端口 44将用户输入的乳腺筛査编号通过通信网络 3发送至用户信息获取模块 101。
[0043] 步骤 S22， 从乳腺影像采集终端获取包含该用户乳腺组织结构信息的乳腺影像 数据； 具体地， 乳腺影像采集模块 102通过通信单元 13从乳腺影像采集终端 4获 取包含该用户乳腺组织结构信息的乳腺影像数据。 乳腺影像采集终端 4的红外发 生器 41产生红外光并将红外光透视至用户乳腺上； 乳腺影像采集终端 4的红外接 收器 42采集透过用户乳腺的红外光信号并处理为乳腺组织结构信息的模拟电信 号； 上述红外发生器 41产生的红外光透视至用户乳腺上， 红外接收器 42接收的 红外光信号携带了乳腺组织结构信息的红外透射光。 乳腺影像采集终端 4的模数 转换器 43将红外接收器 42采集到的包含用户乳腺组织结构信息的模拟电信号模 数转换处理为包含用户乳腺组织结构信息的乳腺影像数据 （即包含用户乳腺组 织结构信息的数字影像信号） ； 乳腺影像采集终端 4的通信端口 44将包含该用户 乳腺组织结构信息的乳腺影像数据通过通信网络 3发送至云服务器 1的通信单元 1 3， 乳腺影像采集模块 102从通信单元 13读取用户乳腺组织结构信息的乳腺影像 数据。
[0044] 步骤 S23， 将包含该用户乳腺组织结构信息的乳腺影像数据处理为用户的乳腺 筛査影像。 具体地， 乳腺影像采集模块 102利用数字影像处理软件将用户乳腺组 织结构信息的乳腺影像数据以数字文件的形式记录影像数据， 然后根据该影像 数据产生用户的乳腺筛査影像， 该乳腺筛査影像是可用于显示的乳腺数字影像 。 红外乳腺检测的原理是： 红外光线照射人体乳腺部位， 由于人体乳腺组织对 通过其中的红外光谱呈现出不同的吸收特性， 所以透过病变部位的红外光信号 与透过正常乳腺组织的红外信号的强度会有所不同， 通过采集到的红外影像的 灰度、 组织结构、 外形尺寸特别是乳腺组织的光学特性， 就可以检测到乳腺部 位发生病变的位置和尺寸。
[0045] 步骤 S24， 将乳腺筛査影像进行无失真去除噪声滤波处理以及进行灰度分层处 理； 具体地， 乳腺影像处理模块 103采用高斯滤波函数将所述乳腺筛査影像进行 无失真去除噪声滤波处理清除所述乳腺筛査影像的杂质， 从而提高对乳腺疾病 进行检测与筛査的准确性。 乳腺影像处理模块 103将无失真处理后的乳腺筛査影 像进行灰度分层处理得到灰度分层后的乳腺筛査影像， 以增强乳腺筛査影像的 分层显示效果。 所述灰度分层处理也称谓密度分层处理， 包括将所述乳腺筛査 影像按灰度分割成不同的区域并对每个区域进行色彩赋值处理， 从而使所述乳 腺灰度影像达到分层显示的效果。 在本实施例中， 经过灰度分层处理后的乳腺 筛査影像更能够明显地显示出乳腺筛査影像上的纹理分布情况， 例如乳腺的组 织结构、 尺寸大小及外形轮廓等。
[0046] 步骤 S25， 根据用户的乳腺筛査编号从医疗云平台的乳腺影像数据库中获取该 用户的正常乳腺影像， 并比较处理后的乳腺筛査影像与正常乳腺影像两者的纹 理分布差异以从乳腺筛査影像中提取乳腺纹理特征区域； 具体地， 乳腺影像分 析模块 104根据用户的乳腺筛査编号从乳腺影像数据库 20中获取该用户的正常乳 腺影像。 在本实施例中， 所述乳腺影像数据库 20存储有不同用户过去进行乳腺 健康体检和普査吋采集的正常乳腺影像， 所述正常乳腺影像为用户乳腺健康状 态下采集的乳腺影像。 乳腺影像分析模块 104将乳腺筛査影像与正常乳腺影像两 者的纹理分布差异进行比较以从乳腺筛査影像中提取乳腺纹理特征区域。 所述 纹理分布差异包括乳腺的组织结构差异、 尺寸大小差异及外形轮廓差异。 本发 明通过将正常乳房组织的影像作为正常乳腺影像与当前筛査的乳腺影像进行比 较， 对在乳房组织中检测出异常或没有异常是最有效的， 但是对于红外影像因 部位或者个人而有很大的差异吋， 最适合以已经被诊断为无异常的过去乳腺影 像作为参考影像。
[0047] 步骤 S26， 在乳腺筛査影像中标示出乳腺纹理特征区域， 并通过通信单元将标 示有乳腺纹理特征区域的乳腺筛査影像发送至医生诊疗终端以供医生对乳腺进 行诊断与筛査参考。 具体地， 乳腺影像输出模块 105在所述乳腺筛査影像中标示 出乳腺纹理特征区域， 如图 3所示， 乳腺筛査影像 B中的椭圆形区域即为标示出 的乳腺纹理特征区域， 从而辅助医生提高对乳腺疾病进行检测与筛査的效率及 准确性。 乳腺影像输出模块 105将标示有乳腺纹理特征区域的乳腺筛査影像通过 通信单元 13发送至医生诊疗终端 5， 以供医生对乳腺疾病进行诊断与筛査提供参 考依据。
[0048] 本发明提供的基于医疗云平台的乳腺筛査影像分析系统及方法通过设置在各社 区医疗工作站的乳腺影像采集终端采集用户的乳腺筛査影像， 方便用户进行乳 腺健康体检及乳腺癌筛査， 节省有限的医院资源。 本发明能够对乳腺筛査影像 进行去除噪音及灰度分层处理， 从处理后的乳腺筛査影像中提取乳腺纹理特征 区域并在乳腺筛査影像中标示出乳腺纹理特征区域， 并发送至医生诊疗终端以 供医生对乳腺疾病进行诊断与筛査提供参考， 从而辅助医生提高对乳腺疾病检 测与筛査的效率及准确性， 提高乳腺筛査的社会效率。
[0049] 以上仅为本发明的优选实施例， 并非因此限制本发明的专利范围， 凡是利用本 发明说明书及附图内容所作的等效结构或等效功能变换， 或直接或间接运用在 其他相关的技术领域， 均同理包括在本发明的专利保护范围内。
工业实用性
[0050] 相较于现有技术， 本发明所述基于医疗云平台的乳腺筛査影像分析系统及方法 通过设置在各社区医疗工作站的乳腺影像采集终端采集用户的乳腺筛査影像， 方便用户进行乳腺健康体检及乳腺癌筛査， 节省有限的医院资源。 通过对乳腺 筛査影像进行去除噪音及灰度分层处理， 从处理后的乳腺筛査影像中提取乳腺 纹理特征区域并在乳腺筛査影像中标示出乳腺纹理特征区域， 并发送至医生诊 疗终端以供医生对乳腺疾病进行诊断与筛査提供参考， 从而辅助医生提高对乳 腺疾病检测与筛査的效率及准确性， 提高乳腺筛査的社会效率。

Claims

权利要求书
[权利要求 1] 一种基于医疗云平台的乳腺筛査影像分析系统， 应用于云服务器中， 该云服务器通过通信网络连接至乳腺影像采集终端、 医疗云平台以及 医生诊疗终端， 其特征在于， 所述乳腺筛査影像分析系统包括： 用户 信息获取模块， 用于通过乳腺影像采集终端接收乳腺筛査用户输入的 乳腺筛査编号； 乳腺影像采集模块， 用于从乳腺影像采集终端获取包 含用户乳腺组织结构信息的乳腺影像数据， 以及将包含该用户乳腺组 织结构信息的乳腺影像数据处理为用户的乳腺筛査影像； 乳腺影像处 理模块， 用于将乳腺筛査影像进行无失真去除噪声滤波处理以及进行 灰度分层处理； 乳腺影像分析模块， 用于根据用户的乳腺筛査编号从 医疗云平台的乳腺影像数据库中获取该用户的正常乳腺影像， 以及比 较处理后的乳腺筛査影像与正常乳腺影像两者的纹理分布差异以从所 述乳腺筛査影像中提取乳腺纹理特征区域； 乳腺影像输出模块， 用于 在灰度分层后的乳腺筛査影像中标示出所述乳腺纹理特征区域， 并通 过通信单元将标示有乳腺纹理特征区域的乳腺筛査影像发送至医生诊 疗终端以供医生对乳腺进行诊断与筛査参考。
[权利要求 2] 如权利要求 1所述的基于医疗云平台的乳腺筛査影像分析系统， 其特 征在于， 所述乳腺影像采集终端包括输入单元、 红外发生器、 红外接 收器、 模数转换器以及通信端口， 其中： 所述输入单元用于供用户输 入乳腺筛査编号； 所述红外发生器用于产生红外光并将红外光透视至 用户乳腺上； 所述红外接收器用于采集透过用户乳腺的红外光信号并 处理为乳腺组织结构信息的模拟电信号； 所述模数转换器用于将红外 接收器采集到的包含用户乳腺组织结构信息的模拟电信号模数转换处 理为包含用户乳腺组织结构信息的乳腺影像数据； 所述通信端口用于 将包含该用户乳腺组织结构信息的乳腺影像数据通过通信网络发送至 云服务器。
[权利要求 3] 如权利要求 1所述的基于医疗云平台的乳腺筛査影像分析系统， 其特 征在于， 所述乳腺影像采集模块利用数字影像处理软件将用户乳腺组 织结构信息的乳腺影像数据以数字文件的形式记录影像数据， 并根据 所述影像数据产生用户的乳腺筛査影像。
[权利要求 4] 如权利要求 1所述的基于医疗云平台的乳腺筛査影像分析系统， 其特 征在于， 所述乳腺影像数据库存储有不同用户在乳腺健康体检和普査 吋采集的正常乳腺影像， 所述正常乳腺影像为用户乳腺健康状态下采 集的乳腺影像， 所述纹理分布差异包括乳腺的组织结构差异、 尺寸大 小差异及外形轮廓差异。
[权利要求 5] 如权利要求 1至 4任一项所述的基于医疗云平台的乳腺筛査影像分析系 统， 其特征在于， 所述灰度分层处理包括将所述乳腺筛査影像按灰度 分割成不同的区域并对每个区域进行色彩赋值处理。
[权利要求 6] —种基于医疗云平台的乳腺筛査影像分析方法， 应用于云服务器中， 该云服务器通过通信网络连接至乳腺影像采集终端、 医疗云平台以及 医生诊疗终端， 其特征在于， 该方法包括步骤： 通过乳腺影像采集终 端接收乳腺筛査用户输入的乳腺筛査编号； 从乳腺影像采集终端获取 包含该用户乳腺组织结构信息的乳腺影像数据； 将包含用户乳腺组织 结构信息的乳腺影像数据处理为乳腺筛査影像； 将乳腺筛査影像进行 无失真去除噪声滤波处理以及进行灰度分层处理； 根据用户的乳腺筛 査编号从医疗云平台的乳腺影像数据库中获取该用户的正常乳腺影像 ， 并比较处理后的乳腺筛査影像与正常乳腺影像两者的纹理分布差异 以从所述乳腺筛査影像中提取乳腺纹理特征区域； 在灰度分层后的乳 腺筛査影像中标示出所述乳腺纹理特征区域， 并通过通信单元将标示 有乳腺纹理特征区域的乳腺筛査影像发送至医生诊疗终端以供医生对 乳腺进行诊断与筛査参考。
[权利要求 7] 如权利要求 6所述的基于医疗云平台的乳腺筛査影像分析方法， 所述 乳腺影像采集终端包括输入单元、 红外发生器、 红外接收器、 模数转 换器以及通信端口， 其特征在于， 所述从乳腺影像采集终端获取包含 用户乳腺组织结构信息的乳腺影像数据的步骤包括： 通过红外发生器 产生红外光并将红外光透视至用户乳腺上； 通过红外接收器采集透过 用户乳腺的红外光信号并处理为乳腺组织结构信息的模拟电信号； 利 用模数转换器将红外接收器采集到的包含用户乳腺组织结构信息的模 拟电信号模数转换处理为包含用户乳腺组织结构信息的乳腺影像数据 ； 通过通信端口将包含该用户乳腺组织结构信息的乳腺影像数据通过 通信网络发送至云服务器。
[权利要求 8] 如权利要求 6所述的基于医疗云平台的乳腺筛査影像分析方法， 其特 征在于， 所述将包含用户乳腺组织结构信息的乳腺影像数据处理为乳 腺筛査影像的步骤包括： 利用数字影像处理软件将用户乳腺组织结构 信息的乳腺影像数据以数字文件的形式记录影像数据； 根据所述影像 数据产生用户的乳腺筛査影像。
[权利要求 9] 如权利要求 6所述的基于医疗云平台的乳腺筛査影像分析方法， 其特 征在于， 所述乳腺影像数据库存储有不同用户在乳腺健康体检和普査 吋采集的正常乳腺影像， 所述正常乳腺影像为用户乳腺健康状态下采 集的乳腺影像， 所述纹理分布差异包括乳腺的组织结构差异、 尺寸大 小差异及外形轮廓差异。
[权利要求 10] 如权利要求 6至 9任一项所述的基于医疗云平台的乳腺筛査影像分析方 法， 其特征在于， 所述灰度分层处理包括将所述乳腺筛査影像按灰度 分割成不同的区域并对每个区域进行色彩赋值处理。
PCT/CN2017/096131 2017-03-25 2017-08-05 基于医疗云平台的乳腺筛查影像分析系统及方法 WO2018176717A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710185289.2A CN107049248A (zh) 2017-03-25 2017-03-25 基于医疗云平台的乳腺筛查影像分析系统及方法
CN201710185289.2 2017-03-25

Publications (1)

Publication Number Publication Date
WO2018176717A1 true WO2018176717A1 (zh) 2018-10-04

Family

ID=59620562

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/096131 WO2018176717A1 (zh) 2017-03-25 2017-08-05 基于医疗云平台的乳腺筛查影像分析系统及方法

Country Status (2)

Country Link
CN (1) CN107049248A (zh)
WO (1) WO2018176717A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107506604A (zh) * 2017-09-11 2017-12-22 深圳市前海安测信息技术有限公司 基于人工智能的影像识别系统及方法
CN107506605A (zh) * 2017-09-11 2017-12-22 深圳市前海安测信息技术有限公司 基于医疗云平台的影像大数据分析系统及方法
CN108172276A (zh) * 2017-12-01 2018-06-15 杭州远舟医疗科技有限公司 一种红外影像自动评估方法、电子设备及存储介质
CN109377491A (zh) * 2018-11-22 2019-02-22 惠州学院 一种基于影像数据分析的医疗辅助诊疗系统
CN110675398B (zh) * 2019-10-22 2022-05-17 深圳瀚维智能医疗科技有限公司 乳腺超声筛查方法、装置及计算机设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080152204A1 (en) * 2006-12-22 2008-06-26 Zhimin Huo Enhanced display of medical images
CN101404062A (zh) * 2008-11-14 2009-04-08 南京大学 一种基于决策树的数字乳腺图像自动筛查方法
CN101986333A (zh) * 2010-12-01 2011-03-16 福州维胜信息技术有限公司 一种医院辅助决策支持系统
CN103020466A (zh) * 2012-12-26 2013-04-03 海信集团有限公司 一种计算机诊断方法及电子设备
CN105975785A (zh) * 2016-05-13 2016-09-28 深圳市前海安测信息技术有限公司 乳腺筛查图像自动处理系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080152204A1 (en) * 2006-12-22 2008-06-26 Zhimin Huo Enhanced display of medical images
CN101404062A (zh) * 2008-11-14 2009-04-08 南京大学 一种基于决策树的数字乳腺图像自动筛查方法
CN101986333A (zh) * 2010-12-01 2011-03-16 福州维胜信息技术有限公司 一种医院辅助决策支持系统
CN103020466A (zh) * 2012-12-26 2013-04-03 海信集团有限公司 一种计算机诊断方法及电子设备
CN105975785A (zh) * 2016-05-13 2016-09-28 深圳市前海安测信息技术有限公司 乳腺筛查图像自动处理系统及方法

Also Published As

Publication number Publication date
CN107049248A (zh) 2017-08-18

Similar Documents

Publication Publication Date Title
WO2019047365A1 (zh) 基于医疗云平台的影像大数据分析系统及方法
WO2018176717A1 (zh) 基于医疗云平台的乳腺筛查影像分析系统及方法
CN110996789B (zh) 执行筛查、诊断或其他基于图像的分析任务的系统和方法
Okuboyejo et al. Automating skin disease diagnosis using image classification
US7664300B2 (en) Uterine cervical cancer computer-aided-diagnosis (CAD)
TWI667996B (zh) 乳房腫瘤輔助檢測模型及乳房腫瘤輔助檢測系統
CN109615633A (zh) 一种基于深度学习的肠镜下克罗恩病辅助诊断系统及方法
CN111310851A (zh) 一种人工智能超声辅助系统及其应用
US20160228008A1 (en) Image diagnosis device for photographing breast by using matching of tactile image and near-infrared image and method for aquiring breast tissue image
Wani et al. Computer-aided diagnosis systems for osteoporosis detection: a comprehensive survey
WO2019047366A1 (zh) 基于人工智能的影像识别系统及方法
CN111785363A (zh) 一种基于ai引导的慢性病辅助诊断系统
CN105232050B (zh) 一种人体舌苔厚度的无创检测装置
JP3964795B2 (ja) パノラマｘ線画像を用いた骨粗鬆症診断支援装置
CN103300872A (zh) 一种分析骨龄的方法及检测装置
WO2017193581A1 (zh) 乳腺筛查图像自动处理系统及方法
EP3038051B1 (en) Diagnostic apparatus and image processing method in the same apparatus
WO2018176718A1 (zh) 乳腺筛查影像智能识别系统及方法
Makarovskikh et al. Automatic classification Infectious disease X-ray images based on Deep learning Algorithms
KR101546403B1 (ko) 유방 초음파 영상 및 탄성도 영상 획득 및 분석 방법 및 장치
CN112002407A (zh) 一种基于超声视频的乳腺癌诊断装置及其方法
CN103164599A (zh) 基于腹部ct图像传输的肝硬化远程会诊系统
Lange et al. Computer-aided-diagnosis (CAD) for colposcopy
CN108960305A (zh) 一种内镜影像判定系统及方法
CN113593667A (zh) 一种社区两癌筛查健康管理方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17903669

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17903669

Country of ref document: EP

Kind code of ref document: A1