WO2019047365A1

WO2019047365A1 - Medical cloud platform-based image big data analysis system and method

Info

Publication number: WO2019047365A1
Application number: PCT/CN2017/110476
Authority: WO
Inventors: 姚育东; 钱唯; 郑斌; 马贺; 齐守良; 赵明芳
Original assignee: 深圳市前海安测信息技术有限公司
Priority date: 2017-09-11
Filing date: 2017-11-10
Publication date: 2019-03-14
Also published as: CN107506605A

Abstract

Disclosed in the invention are a medical cloud platform-based image big data analysis system and a method, which is applied to a cloud server. The cloud server is connected with an image collection terminal, a medial cloud platform and a doctor diagnosis and treatment terminal through a communication network. The image collection terminal comprises an input unit, an infrared generator, an infrared receiver, an analog-to-digital converter and a communication port. The image big data analysis system comprises a user information obtaining module, an image collection module, an image processing module, an image analysis module and a body local organ image output module. An examination image of a user is collected through the image collection terminal, so that the user can perform body local organ health screening conveniently and hospital resources are saved; and by performing noise removal and gray-scale hierarchical processing on the examination image, body local organ texture features are extracted from the examination image to provide a reference for a doctor to perform diagnosis and screening on body local organ diseases, thereby assisting the doctor to improve the efficiency and accuracy of screening the body local organ diseases.

Description

Image big data analysis system and method based on medical cloud platform

[0001] The present invention relates to the field of medical image processing and recognition technologies, and in particular, to an image big data analysis system and method based on a medical cloud platform.

Background technique

[0002] At present, the use of examination images for assisted diagnosis has become an important method for screening and diagnosing early stage local organs for cancer. At present, the use of computer-aided detection methods for the detection and screening of body parts in the examination of the image, usually requires the doctor to animate the approximate range of the body part of the suspicious area (ROI) in the body part of the body image, body part organ screening and The detection efficiency is not high, and it is not suitable for the census of a large number of samples of body parts. In the physical examination and census activities of the body parts of the body, the patient needs to personally come to the body part organ census center or hospital, causing people to queue up and making the originally limited hospital resources more tense. In addition, due to the large number of images of local organs in the body, it is difficult for doctors to directly test the ROI of each body part of the body to ensure efficiency and accuracy, which may easily lead to missed diagnosis and misdiagnosis.

technical problem

[0003] The main objective of the present invention is to provide an image big data analysis system and method based on a medical cloud platform, which is convenient for users to perform physical body organ health screening, save limited hospital resources, and can assist doctors to improve body parts. The efficiency and accuracy of organ disease detection and screening.

Problem solution

Technical solution

[0004] In order to achieve the above object, the present invention provides an image big data analysis system based on a medical cloud platform, which is applied to a cloud server, and the cloud server is connected to an image collection terminal, a medical cloud platform, and a doctor diagnosis and treatment terminal through a communication network. The image big data analysis system includes:

[0005] an image acquisition module, configured to acquire image data including information about a local tissue structure of a user body from the image capturing terminal, and process image data including information about the local tissue structure of the user body as an inspection image of the user; [0006] an image processing module, configured to perform a distortion-free noise filtering process and perform gray level layering processing on the inspection image;

[0007] an image analysis module, configured to acquire a normal image of the body part of the user from an image database of the medical cloud platform, and compare a texture distribution difference between the processed inspection image and the body local normal image to perform the inspection from the inspection Extracting the image texture feature area from the image;

[0008] an image output module, configured to mark the organ texture feature area in the grayscale layered inspection image

And transmitting, through the communication unit, the inspection image marked with the characteristic area of the organ to the doctor's diagnosis terminal for the doctor to diagnose and screen the body part of the body for reference.

[0009] Preferably, the image capturing terminal comprises an input unit, an infrared generator, an infrared receiver, an analog to digital converter and a communication port, wherein:

[0010] the infrared generator is configured to generate infrared light and fluoresce the infrared light to a local organ of the user's body; [0011] the infrared receiver is configured to collect infrared light signals transmitted through a local organ of the user's body and process the body part organs Analog electrical signal of organizational structure information;

[0012] the analog-to-digital converter is configured to perform analog-to-digital conversion of an analog electrical signal, which is collected by an infrared receiver, including local body tissue structure information of the user, into image data including local body tissue structure information of the user;

[0013] The communication port is configured to send image data including the body tissue structure information of the user to the cloud server through the communication network.

[0014] Preferably, the image capturing module records image data in the form of a digital file by using digital image processing software to record image data of the user's body tissue structure information, and generates a user's inspection image according to the image data.

[0015] Preferably, the image database stores body part normal images collected by different users in a body part organ health checkup and a general survey, and the body part normal image is a body part organ image in a user's body part organ health state. The difference in texture distribution includes differences in tissue structure, size difference, and contour difference of local organs of the body.

[0016] Preferably, the grayscale layering process comprises dividing the inspection image into different regions according to grayscale and performing color assignment processing on each region.

[0017] The present invention provides an image big data analysis method based on a medical cloud platform, which is applied to a cloud server, and the cloud server is connected to an image capturing terminal, a medical cloud platform, and a doctor's medical treatment through a communication network. End, the method includes the steps of: acquiring image data including information about the local tissue structure of the user body from the image capturing terminal; processing the image data including the local tissue structure information of the user body as the inspection image; and performing the distortion-free noise removal on the inspection image Filtering processing and performing grayscale layering processing; acquiring a normal image of the body part of the user from the image database of the medical cloud platform, and comparing the texture distribution difference between the processed inspection image and the body local normal image to Extracting an organ texture feature region from the image; marking the organ texture feature region in the grayscale layered inspection image, and transmitting the inspection image indicating the organ texture feature region to the doctor diagnosis terminal through the communication unit For the doctor to diagnose and screen the body parts for reference.

[0018] Preferably, the image capturing terminal includes an input unit, an infrared generator, an infrared receiver, an analog-to-digital converter, and a communication port, and the step of acquiring image data including information about the local tissue structure of the user from the image capturing terminal is performed. The method comprises: generating infrared light through an infrared generator and seeing the infrared light on a local organ of the user body; collecting an infrared light signal transmitted through a local organ of the user body through the infrared receiver and processing the analog electrical signal as the tissue structure information of the body part of the body; Using an analog-to-digital converter, the analog electrical signal collected by the infrared receiver and containing the information about the local tissue structure of the user's body is converted into image data containing local body tissue structure information of the user's body; and the user's body tissue structure is included through the communication port. The image data of the information is sent to the cloud server through the communication network.

[0019] Preferably, the step of processing the image data including the user's body tissue structure information as the image inspection comprises: recording the image data of the user's body tissue structure information in the form of a digital file by using digital image processing software Data; generating an inspection image of the user based on the image data.

[0020] Preferably, the image database stores body part normal images collected by different users in a body part organ health checkup and screening, and the body part normal image is a body part organ collected by the user's body part organ health state. The image, the difference in texture distribution includes differences in tissue structure, size difference, and contour difference of body parts of the body.

[0021] Preferably, the grayscale layering process comprises dividing the inspection image into different regions according to grayscale and performing color assignment processing on each region.

Advantageous effects of the invention

Beneficial effect

[0022] Compared with the prior art, the image data analysis system and method based on the medical cloud platform of the present invention are The image collection terminal set up in each community medical workstation collects the user's inspection image, which is convenient for the user to perform physical examination of the body part organ and body part organ screening, thereby saving limited hospital resources. By performing noise removal and grayscale layering processing on the inspection image, the organ texture feature region is extracted from the processed inspection image and the organ texture feature region is marked in the inspection image and sent to the doctor's medical treatment terminal for the doctor. Provide reference for the diagnosis and screening of local organ diseases, so as to help doctors improve the efficiency and accuracy of detection and screening of body parts and diseases, and improve the social efficiency of body partal organ screening.

Brief description of the drawing

DRAWINGS

1 is a schematic diagram of an application environment of a preferred embodiment of a medical big data analysis system based on a medical cloud platform according to the present invention;

2 is a flow chart of a preferred embodiment of the image big data analysis method based on the medical cloud platform of the present invention.

[0025] The objects, features, and advantages of the present invention will be further described in conjunction with the embodiments.

BEST MODE FOR CARRYING OUT THE INVENTION

The specific embodiments, structures, features and functions 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.

[0027] Referring to FIG. 1, FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of an image big data analysis system based on a medical cloud platform according to the present invention. In the embodiment, the image big data analysis system 10 is installed and runs in the cloud server 1. The cloud server 1 establishes a communication connection with the medical cloud platform 2, the 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 can be a server or a server in a medical information system platform, and provides a data interface for a medical inspection institution such as a regional hospital or a community medical workstation, and can receive inspection images of each medical inspection institution. . The medical cloud platform 2 includes an image database 20, and the image database 20 stores body normal images of different body users in the past for performing physical examinations and physical examinations of body parts, and the body part normal images are user body parts. An image of a part of the body collected by the official in a healthy state. 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. The doctor's medical treatment terminal 5 is a doctor's workstation computer installed in a body part organ examination center or a large hospital for displaying an examination image, and the doctor diagnoses and screens the user's body part organ health condition according to the examination image.

[0028] The image capturing terminal 4 is disposed in a medical examination institution such as a community medical workstation, and the image capturing 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 is configured to generate infrared light and fluoresce the infrared light to a local organ of the user's body; the infrared receiver 42 is configured to collect infrared light signals transmitted through the local organs of the user body and process the image information of the body part organs. The analog-to-digital converter 43 is configured to perform analog-to-digital conversion of the analog electrical signal containing the image information of the local body organ of the user collected by the infrared receiver 42 into a digital signal containing image information of the local body organ of the user; The communication port 44 is configured to transmit user information and a digital signal including the user's body part organ image information to the cloud server 1 through 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.

In the embodiment, the cloud server 1 includes, but is not limited to, an image big data 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 perform information interaction with the image big data analysis system 10 through the processing unit 12. The storage unit 11 may be a read only storage unit R OM , an electrically erasable storage unit EEPROM or a flash storage unit FLASH or the like. 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.

In the embodiment, the image big data analyzing system 10 includes, but is not limited to, an image capturing module 101, an image processing module 102, an image analyzing module 103, and an image output module 104. 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 12 of the cloud server 1 and that can perform fixed functions, which are stored in the storage unit 11 of the cloud server 1. Following knot Figure 2 is a detailed description of the functions of the modules of the present invention.

As shown in FIG. 2, FIG. 2 is a flow chart of a preferred embodiment of the image data analysis method based on the medical cloud platform of the present invention. The image big data analysis method based on the medical cloud platform in the embodiment together with FIG. 1 includes the following steps:

[0032] Step S21: Obtain image data including the local tissue structure information of the user body from the image capturing terminal. Specifically, the image capturing module 101 acquires an image including the local tissue structure information of the user body from the image capturing terminal 4 through the communication unit 13. data. The infrared generator 41 of the image capturing terminal 4 generates infrared light and sees the infrared light to a local organ of the user's body; the infrared receiver 42 of the image capturing terminal 4 collects infrared light signals transmitted through the local organs of the user's body and processes them into local organs of the body. The analog electrical signal of the tissue structure information; the infrared light generated by the infrared generator 41 is fluorinated to a local organ of the user's body, and the infrared light signal received by the infrared receiver 42 carries the infrared transmitted light of the body tissue structure information of the body. The analog-to-digital converter 43 of the image capturing terminal 4 converts the analog electrical signal containing the user's body tissue structure information collected by the infrared receiver 42 into analog image data including the user's body tissue structure information (ie, contains the user's body part). The digital video signal of the organizational structure information; the communication port 44 of the image capturing terminal 4 transmits the image data including the body tissue structure information of the user to the communication unit 13 of the cloud server 1 through the communication network 3, and the image capturing module 101 receives the communication unit 13 Reading image data of the local tissue structure information of the user's body.

[0033] Step S22, processing the image data including the local body tissue structure information of the user into the inspection image of the user. Specifically, the image capturing module 101 uses the digital image processing software to record image data of the user's body tissue structure information in the form of a digital file, and then generates a user's inspection image according to the image data, and the image is available for use. Digital image of the body part of the body displayed. The principle of infrared body partal organ detection is: Infrared light illuminates the local organs of the human body. Since the local body tissues of the human body exhibit different absorption characteristics through the infrared spectrum passing through them, the infrared light signal and the normal transmission through the lesions are normal. The intensity of the infrared signal of the local organ tissue of the body will be different. By collecting the gray scale, tissue structure, and external dimensions of the infrared image, especially the optical properties of the body part and body tissues, it is possible to detect the lesion of the local part of the body. Location and size.

[0034] Step S23, performing an error-free noise removal filtering process and performing grayscale layering processing on the inspection image. Specifically, the image processing module 102 performs a distortion-free noise removal by using the Gaussian filter function. The acoustic filtering process removes impurities of the examined image, thereby improving the accuracy of detecting and screening the local organ diseases. The image processing module 102 performs grayscale layering on the uncorrected processed image to obtain a grayscale layered inspection image to enhance the layered display effect of the inspection image. The grayscale layering process is also referred to as density layering processing, which comprises dividing the inspection image into different regions according to grayscale and performing color assignment processing on each region, so that the grayscale image of the body part organ is achieved. The effect of layered display. In this embodiment, the inspection image after the grayscale layering process can more clearly display the texture distribution on the inspection image, such as the tissue structure, size, and contour of the body part of the body.

[0035] Step S24, obtaining a normal image of the body part of the user from the image database of the medical cloud platform, and comparing the texture distribution difference between the processed inspection image and the normal image of the body part to extract the organ from the inspection image. The texture feature area; specifically, the image analysis module 103 acquires the body part normal image of the user from the image database 20. In this embodiment, the image database 20 stores body normal images of different body users who have performed body health examinations and general surveys in the past. The body local normal images are collected by the user's body parts and organs. Local organ image. The image analysis module 103 compares the difference in texture distribution between the test image and the normal image of the body part to extract an organ texture feature region from the test image. The difference in texture distribution includes differences in the structure of the body parts of the body, size differences, and contour differences. The present invention compares the normal breast image as a normal image of the body with the currently scanned body part organ image, and is most effective in detecting abnormalities or abnormalities in the breast tissue, but for infrared images due to parts or individuals There is a big difference, and it is most suitable as a reference image of a past body part organ image that has been diagnosed as abnormal.

[0036] Step S25, marking the organ texture feature area in the inspection image, and transmitting the inspection image marked with the organ texture feature area to the doctor diagnosis terminal through the communication unit for the doctor to diagnose and screen the body part organ reference. Specifically, the image output module 104 marks the organ texture feature area in the inspection image, for example, the image texture feature area is marked with an ellipse in the inspection image, thereby assisting the doctor to improve the detection and screening of the body part disease. Check the efficiency and accuracy. The image output module 104 sends the inspection image marked with the organ texture feature area to the doctor diagnosis terminal 5 through the communication unit 13, so as to provide a reference for the doctor to diagnose and screen the body part disease. [0037] The image data analysis system and method based on the medical cloud platform provided by the invention collects the inspection image of the user through the image collection terminal installed in each community medical workstation, and is convenient for the user to perform physical examination of the body part organ and the body part organ sieve. Check, save limited hospital resources. The invention can perform noise removal and grayscale layering processing on the inspection image, extract the organ texture feature region from the processed inspection image, and mark the organ texture feature region in the inspection image, and send it to the doctor diagnosis terminal to It provides a reference for doctors to diagnose and screen diseases of body parts and organs, thus assisting doctors to improve the efficiency and accuracy of detection and screening of body parts and diseases, and improve the social efficiency of body partal organ 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 image data analysis system and method based on the medical cloud platform of the present invention collects the inspection image of the user through the image collection terminal installed in each community medical workstation, so that the user can perform the local body organ. Health checkups and body partal organ screening save valuable hospital resources. By performing noise removal and grayscale layering processing on the inspection image, the organ texture feature region is extracted from the processed inspection image and the organ texture feature region is marked in the inspection image and sent to the doctor's medical treatment terminal for the doctor. Provide reference for the diagnosis and screening of local organ diseases, so as to help doctors improve the efficiency and accuracy of detection and screening of body parts and diseases, and improve the social efficiency of body partal organ screening.

Claims

Claim

[Claim 1] A medical big data analysis system based on a medical cloud platform, which is applied to a cloud server, wherein the cloud server is connected to an image collection terminal, a medical cloud platform, and a doctor diagnosis and treatment terminal through a communication network, wherein The image big data analysis system comprises: an image acquisition module, configured to acquire image data including information about a local tissue structure of a user body from the image acquisition terminal, and process image data including information about the local tissue structure of the user body as an inspection image of the user; The image processing module is configured to perform the distortion-free noise filtering processing and the gray layer layer processing on the inspection image; the image analysis module is configured to acquire the normal image of the user body from the image database of the medical cloud platform, and compare a texture distribution difference between the processed inspection image and the body local normal image to extract an organ texture feature region from the inspection image; an image output module for marking in the grayscale layered inspection image The organ texture features the area and passes The communication unit sends an inspection image indicating the area of the organ texture to the doctor's treatment terminal for the doctor to diagnose and screen the body part.

[Claim 2] The medical cloud platform-based image big data analysis system according to claim 1, wherein the image capturing terminal comprises an input unit, an infrared generator, an infrared receiver, an analog to digital converter, and a communication a port, wherein: the infrared generator is configured to generate infrared light and fluoresce the infrared light to a local organ of the user's body; the infrared receiver is configured to collect infrared light signals transmitted through a local organ of the user body and process the tissue structure of the body part An analog electrical signal of the information; the analog-to-digital converter is configured to perform analog-to-digital conversion of the analog electrical signal including the information about the local body structure of the user collected by the infrared receiver into image data including local body tissue structure information of the user body; The port is configured to send image data including the body tissue structure information of the user to the cloud server through the communication network.

[Claim 3] The medical cloud platform-based image big data analysis system according to claim 1, wherein the image acquisition module uses digital image processing software to image data of the user's body tissue structure information as a digital file. The image data is recorded in the form, and the inspection image of the user is generated based on the image data.

[Claim 4] The medical cloud platform-based image big data analysis system according to claim 1, characterized in that The image database stores a normal image of a body part collected by a user in a physical examination and a general examination of a body part organ, and the normal image of the body part is a body part image collected by the user's body part organ health state, Differences in texture distribution include differences in tissue structure, size differences, and contour differences of local organs of the body.

[Claim 5] The medical cloud platform-based image big data analysis system according to any one of claims 1 to 4

The gradation layering process includes dividing the inspection image into different regions by gradation and performing color assignment processing for each region.

[Claim 6] A method for analyzing an image big data based on a medical cloud platform, which is applied to a cloud server, wherein the cloud server is connected to an image collection terminal, a medical cloud platform, and a doctor diagnosis and treatment terminal through a communication network, wherein the method The method includes the following steps: acquiring image data including information about the local tissue structure of the user from the image capturing terminal; processing the image data including the local tissue structure information of the user body as the inspection image; performing the distortion-free noise filtering processing and performing the inspection image Grayscale layering processing; obtaining a normal image of the body part of the user from the image database of the medical cloud platform, and comparing the texture distribution difference between the processed inspection image and the body local normal image to be from the inspection image Extracting an organ texture feature region; marking the organ texture feature region in the grayscale layered inspection image, and transmitting the inspection image indicating the organ texture feature region to the doctor diagnosis terminal through the communication unit for the doctor to Local body organs for diagnosis and screening .

[Claim 7] The medical cloud platform-based image big data analysis method according to claim 6, wherein the image capturing terminal comprises an input unit, an infrared generator, an infrared receiver, an analog to digital converter, and a communication The port is characterized in that: the step of acquiring image data including information about the local tissue structure of the user from the image capturing terminal comprises: generating infrared light by the infrared generator and seeing the infrared light to a local organ of the user body; Acquiring an infrared light signal transmitted through a local organ of the user's body and processing the analog electrical signal as body tissue structure information of the body; using an analog-to-digital converter to collect the analog electrical signal modulus of the user's body tissue structure information collected by the infrared receiver The conversion process is image data including user body tissue structure information; image data including the body tissue structure information of the user body is transmitted to the cloud server through the communication network through the communication port.

[Claim 8] The medical cloud platform-based image big data analysis method according to claim 6, wherein the step of processing the image data including the user's body tissue structure information into the inspection image comprises: utilizing The digital image processing software records image data of the user's body tissue structure information in the form of a digital file; and generates a user's inspection image according to the image data.

[Claim 9] The medical cloud platform-based image big data analysis method according to claim 6, wherein the image database stores normal body parts collected by different users in a body part organ health checkup and general survey. The image of the body part is a body part organ image collected by the user's body part organ health state, and the texture distribution difference includes a difference in the tissue structure of the body part organ, a size difference, and a contour difference.

The image data analysis method based on the medical cloud platform according to any one of claims 6 to 9, wherein the gray leveling process comprises dividing the inspection image into grayscales. Make different areas and perform color assignment on each area.