WO2017185727A1 - 基于大数据的乳腺筛查系统和方法 - Google Patents

基于大数据的乳腺筛查系统和方法 Download PDF

Info

Publication number
WO2017185727A1
WO2017185727A1 PCT/CN2016/106744 CN2016106744W WO2017185727A1 WO 2017185727 A1 WO2017185727 A1 WO 2017185727A1 CN 2016106744 W CN2016106744 W CN 2016106744W WO 2017185727 A1 WO2017185727 A1 WO 2017185727A1
Authority
WO
WIPO (PCT)
Prior art keywords
breast
screening
information
patient
different parts
Prior art date
Application number
PCT/CN2016/106744
Other languages
English (en)
French (fr)
Inventor
张贯京
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 WO2017185727A1 publication Critical patent/WO2017185727A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass

Definitions

  • the present invention relates to the field of data processing technologies, and in particular, to a breast data screening system and method based on big data.
  • Breast cancer is one of the most common malignant masses in women, with more than 900,000 new cases worldwide each year.
  • CR digital mammography (“Mammography”) is the first choice for the diagnosis of breast diseases. It is the most reliable, direct and simple non-invasive detection method. It is simple and easy to perform, with high resolution and good repeatability. The images you have left are available for comparison before and after.
  • the existing breast screening system is checked by the patient and the doctor performs a one-time diagnosis, the accuracy of the diagnosis depends on the experience of the doctor. Different levels of doctors have inconsistent diagnosis results of the patient's condition, and there is a waiting time. Lead to delays in the disease.
  • a primary object of the present invention is to provide a breast cancer screening system and method based on big data, which aims to solve the problem that doctors' work experience leads to inconsistent diagnosis results of doctors at different levels.
  • the present invention provides a breast data screening system based on big data.
  • the big data-based mammography screening system runs in a server, and includes a request information receiving module, a request information parsing module, an image matching module, and a result generating module, wherein:
  • the request information receiving module is configured to receive the request assistance screening information
  • the request information parsing module is configured to parse the request assisted screening information to generate a comprehensive encoding of image information of different parts of the patient's breast;
  • the image matching module is configured to match an image set corresponding to the coding level from a pre-established mammography screening level determination standard library according to a comprehensive coding of image information of different parts of the patient's breast;
  • the result generating module is configured to output an image set corresponding to image information of different parts of the patient's breast to the company Connect to the doctor's workstation on the server.
  • the requesting auxiliary screening information includes image information of different parts of the patient's breast collected by the doctor after being applied to different parts of the patient's breast according to the standard steps of the breast examination.
  • the request assistance screening information further includes patient identification information.
  • the integrated code includes a first sub-code including patient identification information and a second sub-code including breast part information.
  • the second sub-code is coded according to different parts of the breast, and the coding rule of the second sub-code is consistent with the image coding rule adopted in the pre-established breast screening level determination standard library.
  • the present invention also provides a breast data screening method based on big data, which is applied to a server, and the method comprises the following steps:
  • the requesting auxiliary screening information includes image information of different parts of the breast of the patient collected by the doctor after being applied to different parts of the patient's breast according to the standard steps of the breast examination.
  • the request assistance screening information further includes patient identification information.
  • the integrated code includes a first sub-code including patient identification information and a second sub-code including breast part information.
  • the second sub-code is coded according to different parts of the breast, and the coding rule of the second sub-code is consistent with the image coding rule adopted in the pre-established breast screening level determination standard library.
  • the big data-based breast screening system and method provided by the present invention can use the pre-established breast screening grade determination standard library as a basis for big data breast screening, by presetting preset coding rules.
  • the image information of different parts of the collected breast of the patient is encoded, and the quick match is made out of the patient's breast.
  • the image information of the same part corresponds to the image set of the level, so that the doctor can assist in judging the breast screening level of the image of the breast part of the patient, and avoiding the delay of the patient's work experience by the doctor's work experience.
  • FIG. 1 is a schematic diagram of a system architecture of a preferred embodiment of a large data-based breast screening system operating environment according to the present invention
  • FIG. 2 is a schematic diagram of a functional module of a server according to a preferred embodiment of the present invention.
  • FIG. 3 is a schematic flow chart of a preferred embodiment of a breast data screening method based on big data according to the present invention.
  • the present invention provides a breast data screening system and method based on big data, which is quickly and accurately determined by a preset coding rule by using a pre-established mammography screening criteria.
  • the image information of different parts of the patient's breast is encoded, and the image set corresponding to the image information of different parts of the patient's breast is quickly matched, so that the doctor can assist in judging the breast screening level of the image of the breast part of the patient, avoiding the doctor's Work experience on the occurrence of delays in the patient's condition
  • FIG. 1 is a schematic diagram of a system architecture of a preferred embodiment of a large data-based breast screening system operating environment according to the present invention.
  • the big data-based breast screening system 30 operates in the server 3, and the server 3 establishes a communication connection through the network 4 doctor workstation 2.
  • the doctor workstation 2 establishes a communication connection with the mammography screening device 1 by wire or wirelessly.
  • the network 4 is a wired network or a wireless network.
  • the breast screening device 1 is configured to collect image information of a breast part, and send image information of the collected breast part to the doctor workstation 2; the image information of the breast part includes a doctor according to the breast A collection of image information of different parts of the patient's breast collected after the standard step is applied to different parts of the patient's breast.
  • the doctor workstation 2 is configured to receive an image of a breast site and display it in turn for viewing by a doctor according to different parts, and when receiving a breast screening level input by a doctor, output a prompt message prompting the doctor whether an auxiliary sieve is needed.
  • the doctor workstation 2 sends the request assistance screening information including the image information of the breast part to the server 3, otherwise, the doctor workstation 2 outputs the screening result.
  • the server 3 is configured to receive the request assistance screening information ⁇ including the image information of the breast part sent by the doctor workstation 2, and match the breast part according to a pre-established breast screening level determination standard library. A corresponding set of images of the image, and a set of images corresponding to the image of the breast site is sent to the doctor workstation 2 for medical reference.
  • the Breast Screening Rating Criteria Gallery is a collection of massive information that aggregates images of breast lesions in previously diagnosed cases. As the number of cases continues to increase, the image information in the breast screening grade determination standard database will become more and more perfect.
  • the network 4 may be a wired communication network or a wireless communication network.
  • the network 4 is preferably a wireless communication network including, but not limited to, a GSM network, a GPRS network, a CDMA network, a TD-SCDMA network, a WiMAX network, a TD-LTE network, an FDD-LTE network, and the like.
  • FIG. 2 is a schematic diagram of functional modules of a preferred embodiment of a server according to the present invention.
  • the server 3 includes a large data based breast screening system 30, and further includes a storage unit 32, a processing unit 34, and a communication unit 36.
  • the storage unit 32 may be a read only storage unit ROM, an electrically erasable storage unit EEPRO M, a flash storage unit FLASH or a solid hard disk.
  • the processing unit 34 may be a central processing unit (CPU), a microcontroller (MCU), a data processing chip, or an information processing unit having data processing functions.
  • the communication unit 36 is a wireless communication interface or a wired interface with a remote communication function, for example, wireless or wired supporting communication technologies such as GSM, GPRS, WCDMA, CDMA, TD-SCDMA WiMAX, TD-LTE, FDD-LTE, and the like. Communication Interface
  • a module referred to in the present invention refers to a module that can be executed by the processing unit 34 and can perform a fixed function.
  • a series of computer program instruction segments are stored in storage unit 32.
  • the big data based breast screening system 30 includes a request information receiving module 301, a request information parsing module 302, an image matching module 303, and a result generating module 304.
  • the request information receiving module 301 is configured to receive the doctor workstation 2 to send the request assistance screening information.
  • the request assisted screening information includes image information of different parts of the patient's breast collected by the doctor after being applied to different parts of the patient's breast according to the standard steps of the breast examination.
  • the request assistance screening information further includes patient identification information, including but not limited to, name, age, sex, J, region (including but not limited to country, province, city, district) .
  • the request information parsing module 302 is configured to parse the request assisted screening information to generate a comprehensive encoding of image information of different parts of the patient's breast.
  • the integrated code includes a first sub-code including patient identification information and a second sub-code including breast part information.
  • the second sub-code is coded according to different parts of the breast, and is consistent with the image coding rules adopted in the pre-established breast screening level determination standard library, so that image matching is performed, and quick matching is facilitated.
  • the image matching module 303 is configured to match an image set corresponding to the coding corresponding level from a pre-established mammography screening level determination standard library according to a comprehensive coding of image information of different parts of the patient's breast.
  • the coding of the image whose matching degree is within the preset range is matched from the pre-established breast screening level determination standard library set.
  • an image comparison method is used to calculate the degree of similarity between the image information of each part of the patient and each image of the part in the standard library. If the degree of similarity is within a preset range, the coded column of the image is Into the set of codes that match the second subcode.
  • an image set corresponding to the image information of the different parts is generated according to the code set.
  • the result generating module 304 is configured to output an image set corresponding to the image information of different parts of the patient's breast to the doctor workstation 2 for the doctor to assist in determining the breast screening lesion level of the image of the breast portion of the patient.
  • the doctor receives image information of different parts of the patient's breast transmitted by the server 3 at the doctor workstation 2 After the corresponding image collection, the patient's breast can be quickly and accurately determined What level of lesions are there in the site.
  • the big data-based breast screening system can use the pre-established breast screening grade determination standard library as the basis of big data breast screening, and image information of different parts of the collected patient breast by preset coding rules. Coding, quickly matching the image set corresponding to the image information of different parts of the patient's breast, for the doctor to assist in judging the breast screening level of the image of the breast part of the patient, avoiding the delay of the doctor's work experience on the patient's condition happened.
  • FIG. 3 is a schematic flow chart of a preferred embodiment of a breast screening method based on big data according to the present invention.
  • the big data-based breast screening method is run in the server 3, and includes the following steps:
  • the request information receiving module 301 receives the doctor workstation 2 to send the request assistance screening information.
  • the request-assisted screening information includes image information of different parts of the patient's breast collected by the doctor after applying to the different parts of the patient's breast according to the standard steps of the breast examination.
  • the request assistance screening information further includes basic information of the patient, and the basic information of the patient includes, but is not limited to, name, age, gender, and region (including but not limited to country, province, city, district).
  • S20 Parsing the request assistance screening information to generate a comprehensive code of image information of different parts of the patient's breast.
  • the request information analysis module 302 parses the request assistance screening information to generate a comprehensive code of image information of different parts of the patient's breast.
  • the integrated code includes a first sub-code including patient identification information and a second sub-code including breast part information.
  • the second sub-code is coded according to different parts of the breast, and is consistent with the image coding rules adopted in the pre-established breast screening level determination standard library, so as to facilitate image matching and facilitate quick matching.
  • S30 matching the image set corresponding to the coding level in the pre-established mammography screening level criterion library according to the comprehensive coding of the image information of different parts of the patient's breast.
  • the image matching module 303 specifically matches an image set corresponding to the encoding corresponding level from a pre-established mammography screening level determination standard library according to a comprehensive encoding of image information of different parts of the patient's breast.
  • the second sub-code in the integrated coding of the image information of each part is matched from the pre-established mammography screening level criterion library to the coding set of the image whose degree of similarity is within the preset range.
  • an image comparison method is used to calculate the degree of similarity between the image information of each part of the patient and each image of the part in the standard library. If the degree of similarity is within a preset range, the coded column of the image is Into the set of codes that match the second subcode. Next, an image set corresponding to the image information of the different parts is generated according to the code set.
  • S40 output an image collection corresponding to image information of different parts of the patient's breast to a doctor workstation, for the doctor to assist in judging the breast screening level of the image of the breast part of the patient.
  • the result generation module 304 outputs an image set corresponding to the image information of different parts of the patient's breast to the doctor's workstation 2 for the doctor to assist in determining the breast screening lesion level of the image of the breast portion of the patient. Since the image collection is a collection of image information that is highly similar to the image information of the different parts of the collected breast of the patient, the doctor can receive the image collection corresponding to the image information of different parts of the patient's breast after the doctor workstation 2 receives the image information corresponding to the image information of the different parts of the patient's breast. Quickly and accurately determine which level of lesions the patient's breast has.
  • the big data-based breast screening method provided by the present invention can use the pre-established breast screening grade determination standard library as the basis of big data breast screening, and image information of different parts of the collected patient breast by preset coding rules. Coding, quickly matching the image set corresponding to the image information of different parts of the patient's breast, for the doctor to assist in judging the breast screening level of the image of the breast part of the patient, avoiding the delay of the doctor's work experience on the patient's condition happened.
  • the image matching and/or comparison process of the present invention is an image processing technology in the prior art, which is not limited and described herein.
  • the big data based breast screening system and method provided by the present invention can be pre-
  • the established breast screening grade determination standard library is used as the basis of big data breast screening.
  • the image information of different parts of the collected breast of the patient is encoded by preset coding rules, and the image corresponding to the image level of different parts of the patient's breast is quickly matched.
  • the collection for the doctor to assist in judging the breast lesion image level of the image of the patient's breast, avoiding the delay in the patient's condition due to the doctor's work experience.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Library & Information Science (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • General Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

本发明公开了一种基于大数据的乳腺筛查系统和方法。所述方法包括如下步骤：接收请求辅助筛查信息；解析所述请求辅助筛查信息，生成患者乳房不同部位的图像信息的综合编码；根据患者乳房不同部位的图像信息的综合编码从预先建立的乳腺筛查等级判定标准图库中匹配该编码对应级别的图像集合；输出患者乳房不同部位的图像信息对应的图像集合至医生工作站。本发明以预先建立的乳腺筛查等级判定标准图库作为大数据乳腺筛查基础，通过预设编码规则对采集的患者乳房不同部位的图像信息进行编码，快速匹配出于患者乳房不同部位的图像信息对应级别的图像集合，避免了医生的工作经验对患者病情的延误情况的发生。

Description

基于大数据的 ¥L腺筛査系统和方法 技术领域
[0001] 本发明涉及数据处理技术领域， 尤其涉及一种基于大数据的乳腺筛査系统和方 法。
背景技术
[0002] 乳腺癌是妇女常见的恶性肿块之一， 全世界每年新发病例超过 90万人。 目前， CR数字化乳腺高频钼靶 X线检査 （简称 "乳腺钼靶检査"） 是诊断乳腺疾病的首选 ， 是最可靠、 最直接、 最简便的无创性检测手段， 痛苦相对较小， 简便易行， 且分辨率高， 重复性好， 留取的图像可供前后对比， 已作为常规检査。 但是由 于现有的乳腺筛査系统针对患者进行检査后， 由医生进行一次性诊断， 诊断结 果的准确性取决于医生的经验， 不同级别的医生对患者病情的诊断结果不一致 ， 有吋候会导致延误病情。
技术问题
[0003] 本发明的主要目的在于提供一种基于大数据的乳腺筛査系统和方法， 旨在解决 因医生的工作经验导致不同级别的医生对患者病情的诊断结果不一致的问题。 问题的解决方案
技术解决方案
[0004] 为实现上述目的， 本发明提供了一种基于大数据的乳腺筛査系统。
[0005] 所述基于大数据的乳腺筛査系统运行于服务器中， 包括请求信息接收模块、 请 求信息解析模块、 图像匹配模块以及结果生成模块， 其中：
[0006] 所述请求信息接收模块用于接收请求辅助筛査信息；
[0007] 所述请求信息解析模块用于解析所述请求辅助筛査信息， 生成患者乳房不同部 位的图像信息的综合编码；
[0008] 所述图像匹配模块用于根据患者乳房不同部位的图像信息的综合编码从预先建 立的乳腺筛査等级判定标准图库中匹配该编码对应级别的图像集合；
[0009] 所述结果生成模块用于输出患者乳房不同部位的图像信息对应的图像集合至连 接至所述服务器上的医生工作站。
[0010] 优选地， 所述请求辅助筛査信息包括医生根据乳腺检査标准步骤作用于患者乳 房不同部位后采集到的患者乳房不同部位的图像信息。
[0011] 优选地， 所述请求辅助筛査信息还包括患者身份识别信息。
[0012] 优选地， 所述综合编码包括包含患者身份识别信息的第一子编码以及包含乳房 部位信息的第二子编码。
[0013] 优选地， 所述第二子编码根据乳房不同部位进行编码， 所述第二子编码的编码 规则与预先建立的乳腺筛査等级判定标准图库中采用的图像编码规则一致。
[0014] 本发明还提供了一种基于大数据的乳腺筛査方法， 应用于服务器中， 所述方法 包括如下步骤：
[0015] 接收请求辅助筛査信息；
[0016] 解析所述请求辅助筛査信息， 生成患者乳房不同部位的图像信息的综合编码； [0017] 根据患者乳房不同部位的图像信息的综合编码从预先建立的乳腺筛査等级判定 标准图库中匹配该编码对应级别的图像集合；
[0018] 输出患者乳房不同部位的图像信息对应的图像集合至连接至所述服务器上的医 生工作站。
[0019] 优选地， 所述请求辅助筛査信息包括医生根据乳腺检査标准步骤作用于患者乳 房不同部位后采集到的患者乳房不同部位的图像信息。
[0020] 优选地， 所述请求辅助筛査信息还包括患者身份识别信息。
[0021] 优选地， 所述综合编码包括包含患者身份识别信息的第一子编码以及包含乳房 部位信息的第二子编码。
[0022] 优选地， 所述第二子编码根据乳房不同部位进行编码， 所述第二子编码的编码 规则与预先建立的乳腺筛査等级判定标准图库中采用的图像编码规则一致。 发明的有益效果
有益效果
[0023] 相较于现有技术， 本发明提供的基于大数据的乳腺筛査系统和方法能够以预先 建立的乳腺筛査等级判定标准图库作为大数据乳腺筛査基础， 通过预设编码规 则对采集的患者乳房不同部位的图像信息进行编码， 快速匹配出于患者乳房不 同部位的图像信息对应级别的图像集合， 以供医生辅助判断该患者乳房部位的 图像的乳腺筛査病灶级别， 避免了医生的工作经验对患者病情的延误情况的发 生。
对附图的简要说明
附图说明
[0024] 图 1为本发明基于大数据的乳腺筛査系统运行环境较佳实施例的系统架构示意 图；
[0025] 图 2为图 2为本发明服务器较佳实施例的功能模块示意图；
[0026] 图 3为本发明基于大数据的乳腺筛査方法较佳实施例的流程示意图。
实施该发明的最佳实施例
本发明的最佳实施方式
[0027] 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。
[0028] 为实现本发明目的， 本发明提供了一种基于大数据的乳腺筛査系统和方法， 通 过以预先建立的乳腺筛査等级判定标准图库快速并准确地， 通过预设编码规则 对采集的患者乳房不同部位的图像信息进行编码， 快速匹配出于患者乳房不同 部位的图像信息对应级别的图像集合， 以供医生辅助判断该患者乳房部位的图 像的乳腺筛査病灶级别， 避免了医生的工作经验对患者病情的延误情况的发生
[0029] 参照图 1所示， 图 1为本发明基于大数据的乳腺筛査系统运行环境较佳实施例的 系统架构示意图。
[0030] 在本实施例中， 所述基于大数据的乳腺筛査系统 30运行于服务器 3中， 所述服 务器 3通过网络 4医生工作站 2建立通讯连接。 所述医生工作站 2通过有线或无线 的方式与乳腺筛査设备 1建立通讯连接。 所述网络 4为有线网络或无线网络。
[0031] 所述乳腺筛査设备 1用于采集乳房部位的图像信息， 并将采集后的乳房部位的 图像信息发送至所述医生工作站 2; 所述乳房部位的图像信息包括医生根据乳腺 检査标准步骤作用于患者乳房不同部位后采集到的患者乳房不同部位的图像信 息的集合。
[0032] 所述医生工作站 2用于接收乳房部位的图像并按照不同部位依次显示出来供医 生査看， 并当接收到医生输入的乳腺筛査病灶级别吋输出提示信息提示医生是 否需要进行辅助筛査； 当判断出医生输入的答复为是吋， 所述医生工作站 2发送 包含所述乳房部位的图像信息的请求辅助筛査信息至服务器 3， 否则， 所述医生 工作站 2输出筛査结果。
[0033] 所述服务器 3用于当接收到医生工作站 2发送的包含所述乳房部位的图像信息的 请求辅助筛査信息吋， 根据预先建立的乳腺筛査等级判定标准图库匹配所述乳 房部位的图像的对应级别的图像集合， 并将所述乳房部位的图像对应级别的图 像集合发送至医生工作站 2供医生参考。 所述乳腺筛査等级判定标准图库是一种 集合以往确诊病例中的乳房病灶图像的海量信息分类集合。 随着病例的不断增 多， 该乳腺筛査等级判定标准数据库中的图像信息将越来越完善。
[0034] 所述网络 4可以是有线通讯网络或无线通讯网络。 所述网络 4优选为无线通讯网 络， 包括但不限于， GSM网络、 GPRS网络、 CDMA网络、 TD-SCDMA网络、 W iMAX网络、 TD-LTE网络、 FDD-LTE网络等无线传输网络。
[0035]
[0036] 参照图 2所示， 图 2为本发明服务器较佳实施例的功能模块示意图。
[0037] 所述服务器 3包括基于大数据的乳腺筛査系统 30， 还包括存储单元 32、 处理单 元 34和通讯单元 36。
[0038] 所述的存储单元 32可以为一种只读存储单元 ROM, 电可擦写存储单元 EEPRO M、 快闪存储单元 FLASH或固体硬盘等。 所述的处理单元 34可以为一种中央处 理器 （Central Processing Unit, CPU) 、 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。 所述通讯单元 36为一种具有远程通讯功 能的无线通讯接口或有线接口， 例如， 支持 GSM、 GPRS、 WCDMA、 CDMA、 TD-SCDMA WiMAX、 TD-LTE ^ FDD-LTE等通讯技术的无线或有线通讯接口
[0039] 本发明所称的模块是指一种能够被所述处理单元 34执行并且能够完成固定功能 的一系列计算机程序指令段， 其存储在存储单元 32中。
[0040] 所述基于大数据的乳腺筛査系统 30包括请求信息接收模块 301、 请求信息解析 模块 302、 图像匹配模块 303以及结果生成模块 304。
[0041] 所述请求信息接收模块 301用于接收医生工作站 2发送请求辅助筛査信息。
[0042] 所述请求辅助筛査信息包括医生根据乳腺检査标准步骤作用于患者乳房不同部 位后采集到的患者乳房不同部位的图像信息。 所述请求辅助筛査信息中还包括 患者身份识别信息， 所述患者身份识别信息包括但不仅限于， 姓名、 年齢、 性 另 |J、 所在区域 （包括但不限于国家、 省、 市、 区） 。
[0043] 所述请求信息解析模块 302用于解析所述请求辅助筛査信息， 生成患者乳房不 同部位的图像信息的综合编码。
[0044] 所述综合编码包括包含患者身份识别信息的第一子编码以及包含乳房部位信息 的第二子编码。 所述第二子编码根据乳房不同部位进行编码， 与预先建立的乳 腺筛査等级判定标准图库中采用的图像编码规则一致， 以便在进行图像匹配吋 方便快速匹配。
[0045] 所述图像匹配模块 303用于根据患者乳房不同部位的图像信息的综合编码从预 先建立的乳腺筛査等级判定标准图库中匹配该编码对应级别的图像集合。
[0046] 具体地， 首先， 根据每一个部位的图像信息的综合编码中的第二子编码从所述 预先建立的乳腺筛査等级判定标准图库中匹配相似程度在预设范围内的图像的 编码集合。 具体地， 采用图像比对法计算该患者每一个部位的图像信息与标准 图库中该部位每个图像之间的相似程度， 若相似程度在预设的范围之内， 则将 该图像的编码列入与所述第二子编码匹配的编码集合中。 其次， 根据所述编码 集合生成所述不同部位的图像信息对应级别的图像集合。
[0047] 所述结果生成模块 304用于输出患者乳房不同部位的图像信息对应的图像集合 至所述医生工作站 2， 以供医生辅助判断该患者乳房部位的图像的乳腺筛査病灶 级别。
[0048] 由于该图像集合为与采集到的该患者乳房不同部位的图像信息相似程度较高的 图像信息的集合， 因此， 医生在医生工作站 2接收到服务器 3发送的患者乳房不 同部位的图像信息对应的图像集合后， 能够快速并准确地判断出该患者乳房哪 个部位具有哪种级别的病灶。
[0049] 本发明提供的基于大数据的乳腺筛査系统能够以预先建立的乳腺筛査等级判定 标准图库作为大数据乳腺筛査基础， 通过预设编码规则对采集的患者乳房不同 部位的图像信息进行编码， 快速匹配出于患者乳房不同部位的图像信息对应级 别的图像集合， 以供医生辅助判断该患者乳房部位的图像的乳腺筛査病灶级别 ， 避免了医生的工作经验对患者病情的延误情况的发生。
[0050]
[0051] 本发明的另外一个方面， 提供了一种与上述基于大数据的乳腺筛査系统对应的 方法。
[0052] 参照图 3所示， 图 3为本发明基于大数据的乳腺筛査方法较佳实施例的流程示意 图。
[0053] 在本实施例中， 结合图 1和图 2所示， 所述基于大数据的乳腺筛査方法运行于服 务器 3中， 包括如下步骤：
[0054] S10: 接收请求辅助筛査信息。
[0055] 请求信息接收模块 301接收医生工作站 2发送请求辅助筛査信息。 所述请求辅助 筛査信息包括医生根据乳腺检査标准步骤作用于患者乳房不同部位后采集到的 患者乳房不同部位的图像信息。 所述请求辅助筛査信息中还包括患者的基本信 息， 所述患者的基本信息包括但不仅限于， 姓名、 年齢、 性别、 所在区域 （包 括但不限于国家、 省、 市、 区） 。
[0056] S20: 解析所述请求辅助筛査信息， 生成患者乳房不同部位的图像信息的综合 编码。
[0057] 请求信息解析模块 302解析所述请求辅助筛査信息， 生成患者乳房不同部位的 图像信息的综合编码。 所述综合编码包括包含患者身份识别信息的第一子编码 以及包含乳房部位信息的第二子编码。 所述第二子编码根据乳房不同部位进行 编码， 与预先建立的乳腺筛査等级判定标准图库中采用的图像编码规则一致， 以便在进行图像匹配吋方便快速匹配。
[0058] S30: 根据患者乳房不同部位的图像信息的综合编码从预先建立的乳腺筛査等 级判定标准图库中匹配该编码对应级别的图像集合。 [0059] 图像匹配模块 303具体地， 根据患者乳房不同部位的图像信息的综合编码从预 先建立的乳腺筛査等级判定标准图库中匹配该编码对应级别的图像集合。 首先 ， 根据每一个部位的图像信息的综合编码中的第二子编码从所述预先建立的乳 腺筛査等级判定标准图库中匹配相似程度在预设范围内的图像的编码集合。 具 体地， 采用图像比对法计算该患者每一个部位的图像信息与标准图库中该部位 每个图像之间的相似程度， 若相似程度在预设的范围之内， 则将该图像的编码 列入与所述第二子编码匹配的编码集合中。 其次， 根据所述编码集合生成所述 不同部位的图像信息对应级别的图像集合。
[0060] S40: 输出患者乳房不同部位的图像信息对应的图像集合至医生工作站， 以供 医生辅助判断该患者乳房部位的图像的乳腺筛査病灶级别。
[0061] 结果生成模块 304输出患者乳房不同部位的图像信息对应的图像集合至医生工 作站 2， 以供医生辅助判断该患者乳房部位的图像的乳腺筛査病灶级别。 由于该 图像集合为与采集到的该患者乳房不同部位的图像信息相似程度较高的图像信 息的集合， 因此， 医生在医生工作站 2接收到患者乳房不同部位的图像信息对应 的图像集合后， 能够快速并准确地判断出该患者乳房哪个部位具有哪种级别的 病灶。
[0062] 本发明提供的基于大数据的乳腺筛査方法能够以预先建立的乳腺筛査等级判定 标准图库作为大数据乳腺筛査基础， 通过预设编码规则对采集的患者乳房不同 部位的图像信息进行编码， 快速匹配出于患者乳房不同部位的图像信息对应级 别的图像集合， 以供医生辅助判断该患者乳房部位的图像的乳腺筛査病灶级别 ， 避免了医生的工作经验对患者病情的延误情况的发生。
[0063] 本发明所述图像匹配和 /或比对过程为现有技术中的图像处理技术， 在此不做 限定和赘述。
[0064] 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
[0065] 相较于现有技术， 本发明提供的基于大数据的乳腺筛査系统和方法能够以预先 建立的乳腺筛査等级判定标准图库作为大数据乳腺筛査基础， 通过预设编码规 则对采集的患者乳房不同部位的图像信息进行编码， 快速匹配出于患者乳房不 同部位的图像信息对应级别的图像集合， 以供医生辅助判断该患者乳房部位的 图像的乳腺筛査病灶级别， 避免了医生的工作经验对患者病情的延误情况的发 生。

Claims

权利要求书
一种基于大数据的乳腺筛査系统， 其特征在于， 所述基于大数据的乳 腺筛査系统运行于服务器中， 包括请求信息接收模块、 请求信息解析 模块、 图像匹配模块以及结果生成模块， 其中： 所述请求信息接收模 块用于接收请求辅助筛査信息； 所述请求信息解析模块用于解析所述 请求辅助筛査信息， 生成患者乳房不同部位的图像信息的综合编码； 所述图像匹配模块用于根据患者乳房不同部位的图像信息的综合编码 从预先建立的乳腺筛査等级判定标准图库中匹配该编码对应级别的图 像集合； 所述结果生成模块用于输出患者乳房不同部位的图像信息对 应的图像集合至连接至所述服务器上的医生工作站。
如权利要求 1所述的基于大数据的乳腺筛査系统， 其特征在于， 所述 请求辅助筛査信息包括医生根据乳腺检査标准步骤作用于患者乳房不 同部位后采集到的患者乳房不同部位的图像信息。
如权利要求 2所述的基于大数据的乳腺筛査系统， 其特征在于， 所述 请求辅助筛査信息还包括患者身份识别信息。
如权利要求 1所述的基于大数据的乳腺筛査系统， 其特征在于， 所述 综合编码包括包含患者身份识别信息的第一子编码以及包含乳房部位 信息的第二子编码。
如权利要求 4所述的基于大数据的乳腺筛査系统， 其特征在于， 所述 第二子编码根据乳房不同部位进行编码， 所述第二子编码的编码规则 与预先建立的乳腺筛査等级判定标准图库中采用的图像编码规则一致
[权利要求 6] —种基于大数据的乳腺筛査方法， 应用于服务器中， 其特征在于， 所 述方法包括如下步骤： 接收请求辅助筛査信息； 解析所述请求辅助筛 査信息， 生成患者乳房不同部位的图像信息的综合编码； 根据患者乳 房不同部位的图像信息的综合编码从预先建立的乳腺筛査等级判定标 准图库中匹配该编码对应级别的图像集合； 输出患者乳房不同部位的 图像信息对应的图像集合至连接至所述服务器上的医生工作站。 [权利要求 7] 如权利要求 6所述的基于大数据的乳腺筛査方法， 其特征在于， 所述 请求辅助筛査信息包括医生根据乳腺检査标准步骤作用于患者乳房不 同部位后采集到的患者乳房不同部位的图像信息。
[权利要求 8] 如权利要求 7所述的基于大数据的乳腺筛査方法， 其特征在于， 所述 请求辅助筛査信息还包括患者身份识别信息。
[权利要求 9] 如权利要求 6所述的基于大数据的乳腺筛査方法， 其特征在于， 所述 综合编码包括包含患者身份识别信息的第一子编码以及包含乳房部位 信息的第二子编码。
[权利要求 10] 如权利要求 9所述的基于大数据的乳腺筛査方法， 其特征在于， 所述 第二子编码根据乳房不同部位进行编码， 所述第二子编码的编码规则 与预先建立的乳腺筛査等级判定标准图库中采用的图像编码规则一致
PCT/CN2016/106744 2016-04-28 2016-11-22 基于大数据的乳腺筛查系统和方法 WO2017185727A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610272735.9 2016-04-28
CN201610272735.9A CN105956391A (zh) 2016-04-28 2016-04-28 基于大数据的乳腺筛查系统和方法

Publications (1)

Publication Number Publication Date
WO2017185727A1 true WO2017185727A1 (zh) 2017-11-02

Family

ID=56916980

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/106744 WO2017185727A1 (zh) 2016-04-28 2016-11-22 基于大数据的乳腺筛查系统和方法

Country Status (2)

Country Link
CN (1) CN105956391A (zh)
WO (1) WO2017185727A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105956391A (zh) * 2016-04-28 2016-09-21 深圳市前海安测信息技术有限公司 基于大数据的乳腺筛查系统和方法
CN107049249A (zh) * 2017-03-25 2017-08-18 深圳市前海安测信息技术有限公司 乳腺筛查影像智能识别系统及方法
CN110101361B (zh) * 2019-04-23 2022-07-12 深圳市新产业眼科新技术有限公司 基于大数据在线智能诊断平台及其运行方法和存储介质
CN112890869B (zh) * 2021-03-04 2022-02-15 山东第一医科大学附属省立医院(山东省立医院) 一种基于大数据的乳腺外科智能检测系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101373479A (zh) * 2008-09-27 2009-02-25 华中科技大学 一种乳腺x线摄片计算机图像检索方法及系统
CN102156715A (zh) * 2011-03-23 2011-08-17 中国科学院上海技术物理研究所 面向医学影像数据库的基于多病灶区域特征的检索系统
CN103678504A (zh) * 2013-11-19 2014-03-26 西安华海盈泰医疗信息技术有限公司 基于相似度的乳腺图像的匹配图像检索方法及检索系统
CN105956391A (zh) * 2016-04-28 2016-09-21 深圳市前海安测信息技术有限公司 基于大数据的乳腺筛查系统和方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101373479A (zh) * 2008-09-27 2009-02-25 华中科技大学 一种乳腺x线摄片计算机图像检索方法及系统
CN102156715A (zh) * 2011-03-23 2011-08-17 中国科学院上海技术物理研究所 面向医学影像数据库的基于多病灶区域特征的检索系统
CN103678504A (zh) * 2013-11-19 2014-03-26 西安华海盈泰医疗信息技术有限公司 基于相似度的乳腺图像的匹配图像检索方法及检索系统
CN105956391A (zh) * 2016-04-28 2016-09-21 深圳市前海安测信息技术有限公司 基于大数据的乳腺筛查系统和方法

Also Published As

Publication number Publication date
CN105956391A (zh) 2016-09-21

Similar Documents

Publication Publication Date Title
WO2017185727A1 (zh) 基于大数据的乳腺筛查系统和方法
US11471095B2 (en) Tongue-image-based diagnostic system and diagnostic method
CN109741806B (zh) 一种医学影像诊断报告辅助生成方法及其装置
JP6034192B2 (ja) 報告検証器及び報告増強器を有する医療情報システム
RU2604698C2 (ru) Способ и система интеллектуального связывания медицинских данных
KR100739570B1 (ko) 의료정보 서비스 시스템 및 방법
CN106021915B (zh) 基于大数据面向自动诊疗的医疗数据分析系统和装置
US20150356258A1 (en) Real-time national radiation dose database and monitoring radiation dosages using this database
WO2021151302A1 (zh) 基于机器学习的药品质控分析方法、装置、设备及介质
WO2019047366A1 (zh) 基于人工智能的影像识别系统及方法
JP2019204247A (ja) 被験者候補抽出方法および被験者候補抽出システム
CN110600107A (zh) 医学图像的筛选方法、计算机设备及可读存储介质
Declerck et al. Bridging data models and terminologies to support adverse drug event reporting using EHR data
CN111899845A (zh) 基于影像检查目的dicom图像路由管理系统及方法
CN109117871A (zh) 一种通过深度学习获取肺部病灶恶性概率的系统和方法
CN104732086A (zh) 基于云计算的疾病计算机辅助检测系统
CN111080583A (zh) 医学图像检测方法、计算机设备和可读存储介质
JP2009078082A (ja) 医用情報処理システム、医用情報処理方法、及びプログラム
WO2018129911A1 (zh) 辅助医生诊疗的系统和方法
Ho et al. Validation of two case definitions to identify pressure ulcers using hospital administrative data
EP3503112A1 (en) Method and system for validating parameters in a medical study
WO2018176718A1 (zh) 乳腺筛查影像智能识别系统及方法
US20220277577A1 (en) Document creation support apparatus, document creation support method, and document creation support program
CN111753831A (zh) 一种图像分析方法、装置、图像采集设备及存储介质
Goins et al. Individual Participant Data Meta-Analysis of LR-5 in LI-RADS Version 2018 versus Revised LI-RADS for Hepatocellular Carcinoma Diagnosis

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16900234

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC, EPO FORM 1205A DATED 14.05.19

122 Ep: pct application non-entry in european phase

Ref document number: 16900234

Country of ref document: EP

Kind code of ref document: A1