[go: up one dir, main page]

WO2020118535A1 - Procédé et système d'acquisition auxiliaire intelligente ultrasonore en mode b - Google Patents

Procédé et système d'acquisition auxiliaire intelligente ultrasonore en mode b Download PDF

Info

Publication number
WO2020118535A1
WO2020118535A1 PCT/CN2018/120396 CN2018120396W WO2020118535A1 WO 2020118535 A1 WO2020118535 A1 WO 2020118535A1 CN 2018120396 W CN2018120396 W CN 2018120396W WO 2020118535 A1 WO2020118535 A1 WO 2020118535A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
module
detection
human body
effective
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/120396
Other languages
English (en)
Chinese (zh)
Inventor
林江峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Yido Technology Co Ltd
Original Assignee
Guangdong Yido Technology Co Ltd
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 Guangdong Yido Technology Co Ltd filed Critical Guangdong Yido Technology Co Ltd
Priority to PCT/CN2018/120396 priority Critical patent/WO2020118535A1/fr
Priority to CN201880100123.9A priority patent/CN113556978A/zh
Publication of WO2020118535A1 publication Critical patent/WO2020118535A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis

Definitions

  • the present invention relates to the field of medical equipment, and in particular, to a B-ultrasonic intelligent auxiliary collection method and system.
  • B-ultrasound detection is the most direct and accurate detection method for monitoring the internal organs and blood flow information of the human body.
  • Existing B-ultrasound equipment requires professional technicians with professional medical knowledge and detection skills to operate the human body. It is necessary to make a comprehensive judgment based on the placement, angle, and displayed image of the detection head to determine the detection image to be acquired as the detection conclusion.
  • the purpose of the present invention is to provide a B-ultrasound intelligent auxiliary collection method, which aims to solve the technical problems that the existing B-ultrasound can only be operated with the help of professional technicians, thus most of the basic medical institutions cannot perform corresponding detection services.
  • the invention provides a B-mode intelligent auxiliary collection method.
  • the collection method includes:
  • Step 1 Determine the medical imaging standard database, which includes various effective image data formed after B-ultrasound corresponding to various parts, organs and diseases of the human body, and marks are set on the effective image data ;
  • Step 2 After selecting body parts, organs and diseases, use B-mode imaging equipment to detect the human body to form a detection image data stream;
  • Step 3 Divide the detected image data stream into multiple image frames, compare each image frame with the corresponding multiple effective image data, determine the similarity, and output the comparison result;
  • Step 4 When the comparison result is similar, obtain the image frame and save it, or obtain and save the inspection image data stream in the time period before and after the image frame to save the image frame or the inspection image The data stream is used as the detection result; when the comparison result is not similar, go to step 5;
  • Step 5 The operator continuously uses the B-mode imaging device to detect the human body, and manually controls the B-mode imaging device to acquire the inspection image data stream or a part of the inspection images constituting the inspection image data stream, using the manually acquired inspection
  • the image data stream or inspection image is used as the inspection result to complete the acquisition.
  • the B-mode intelligent auxiliary acquisition method disclosed in the present invention first sets up a medical imaging standard database with effective image data, and then uses the B-mode imaging equipment to obtain the detection image data stream of the organ, and at the same time, the detection image data stream and the pre-stored effective image Data comparison. If the comparison is similar, the acquired detection image data stream and the image frame in the data stream at that moment are considered as the detection result, and the part of the detection image data stream and image frame are automatically used as the detection result; if the comparison is not similar, The detection personnel can manually intercept the corresponding detection image data stream and image frame as the detection result.
  • This method enables only the trained personnel to operate the B-mode ultrasound equipment to automatically obtain the test results based on the comparison results, or to manually detect when the test conclusion fails to be obtained, thereby overcoming the prior art, only professional technicians can operate the B Ultra technical problems have expanded the application range of B-ultrasound detection.
  • the invention also discloses a B-mode intelligent auxiliary collection system.
  • the system includes:
  • a remote server which stores a medical imaging standard database, which includes a variety of effective image data that have been formed after B-ultrasound corresponding to various parts of the human body, organs, and diseases. Marks are set on the image data;
  • a host the host is connected to the B-mode imaging device, receives the detected image data stream, and communicates with the remote server;
  • the B-mode imaging device is used to detect the human body, forming a detection image data stream;
  • the host includes a key module, a control module, a data processing module, a communication module, and a cache module.
  • the key module and the communication module are connected to the control module, and the control module is based on the Human body parts, organs and diseases, control and receive the detected image data stream detected by the B-mode imaging device and store them in the cache module, the control module controls the communication module to obtain the data from the remote server Valid image data, and send the acquired valid image data to the data processing module; the data processing module divides the detected image data stream into a plurality of image frames according to the valid image data, compares and judges The similarity between the image frame and the effective image data;
  • the data processing module When determining that the image frame and the effective image data are similar, the data processing module outputs a similar image frame to the control module; the control module sends a control instruction to the cache module according to the comparison result, so that The cache module uses the cached image frame or the detected image data stream in the time period before and after the image frame as a detection result;
  • the key module sends a data entry instruction to the control module under artificial control, and the control module thereby controls the cache module to The detection image at the moment when the key module is pressed or the detection image data stream in the time period before and after the detection image as a detection result;
  • a medical diagnosis system that receives the detection result through the communication module and makes an artificial diagnosis based on the detection result.
  • the B-mode intelligent auxiliary acquisition system disclosed in the present invention stores the medical image standard database with effective image data on a remote server, and obtains the detected image data stream of the human body through the B-mode imaging device, and sends it to the host.
  • the data processing module in the host computer can directly obtain valid image data from the remote server according to the received detected image data stream, and make a comparison conclusion between the image frames in the detected image data stream and the effective image data.
  • the host directly determines that the detected image data stream and part of the image frames in the data stream are the detection results; when the comparison result is not similar, you can directly obtain the key press detection by the control of the key module
  • the detected image data stream in the time period before and after the image or the detected image is used as the detection result.
  • the B-mode intelligent auxiliary acquisition method disclosed by the present invention can minimize the requirements for professional technicians in the process of B-mode ultrasound detection, and can enable anyone who has undergone inspection training to operate the B-mode ultrasound equipment to expand the scope of B-mode ultrasound detection , Overcoming the technical problems in the existing technology, only professional technicians can operate B-mode ultrasound, expanding the application scope of B-mode ultrasound detection.
  • FIG. 1 is a timing diagram of the B-super intelligent auxiliary collection method of the present invention
  • FIG. 2 is a schematic flowchart of the B-super intelligent auxiliary collection method of the present invention.
  • 3 to 5 are schematic diagrams of modules of the B-super intelligent auxiliary acquisition system of the present invention.
  • the present invention discloses a B-mode intelligent auxiliary acquisition method, the method includes the following steps:
  • Step 1 Determine the medical imaging standard database, which includes various effective image data formed after B-ultrasound corresponding to various parts, organs and diseases of the human body, and marks are set on the effective image data .
  • Effective image data refers to a B-mode ultrasound image that can clearly indicate the image, position, blood flow information, size and other information of the corresponding human body parts and organs after detection, and the corresponding mark is made on the B-mode ultrasound image to distinguish For other normal B-mode ultrasound images.
  • Marking includes: at least one of a plurality of marking points, a plurality of marking areas, and a plurality of marking parameters, wherein the marking points mark the location of the lesion or abnormality; the marking area marks the range where the lesion or abnormality is located, or the criticality where different organs are located Boundary, etc.; multiple marking parameters mark the abnormal areas and ranges of various medical parameters detected by ultrasound.
  • abnormalities and diseases in B-mode ultrasound images can be determined based on the content of the mark.
  • the medical imaging standard database is formed by classifying and storing the above-mentioned effective image data according to the human body parts, organs and corresponding disease types or names to be detected, and based on the human body parts, organs and corresponding disease types and names. index.
  • Similarity calculation parameters, mathematical calculation methods, and similarity judgment thresholds of marked points, marked areas, or marked parameters in effective image data of different body parts, organs, and corresponding disease types and names are not completely the same.
  • a medical imaging standard database includes the following methods:
  • Step 11 Use the B-mode ultrasound device to detect the human body to form the detected image data stream
  • Step 12 Manually determine the human body parts, organs and corresponding disease types or names corresponding to the detection content in the detection image data stream;
  • the determination of the detected image data stream in this step requires professional physicians or technicians to operate, and after determining the corresponding body parts, organs, and types and names of diseases, the location of lesions or abnormalities can be marked.
  • Step 13 Divide the detected image data stream into multiple image pictures, and select at least one image picture that best describes the human body part, organ, and disease type and name from the multiple image pictures as effective image data.
  • Step 14 Set a mark on the effective image data, the mark including at least one of a plurality of mark points, a plurality of mark areas, or a plurality of mark parameters.
  • Step 15 Set the attributes of the effective image data, the attributes are the corresponding human body parts, organs and corresponding disease types and names, and then according to the set attributes, all valid image data containing marked points, marked areas or marked parameters Save to form a medical imaging standard database.
  • Step 2 After selecting human body parts, organs and diseases, use the B-mode imaging device 30 to detect the human body to form a detection image data stream.
  • the human body parts, organs and diseases to be detected need to be selected before detection, which is beneficial to select the corresponding effective image data from the medical imaging standard database as a reference and quickly compare abnormalities.
  • the B-mode imaging device 30 collects the detection image data stream at the corresponding position of the human body and transmits the detection image data stream in real time, but it is not directly used as the detection result.
  • Step 3 Divide the detected image data stream into multiple image frames, compare each image frame with the corresponding multiple effective image data, determine the similarity, and output the comparison result.
  • Step 4 When the comparison result is similar, obtain the image frame and save it, or obtain and save the inspection image data stream in the time period before and after the image frame to save the image frame or the inspection image The data stream is used as the detection result; when the comparison result is not similar, go to step 5;
  • the comparison result is similar means that the image frame is compared with multiple valid image data, and the similarity will be formed when the comparison is made.
  • the value of the similarity meets the medical judgment is similar to each other or meets the judgment standard value When it is determined that they are similar to each other.
  • the size of the standard value that meets the similarity of medical judgment may be different according to different medical judgment standards, or a specific doctor may set a specific value.
  • Step 31 Set the similarity calculation parameter, mathematical calculation method, and similarity judgment threshold of the marker on each effective image data in advance.
  • the similarity calculation parameters, mathematical calculation methods, and similarity judgment threshold settings come from the data requirements of different human body parts, organs, and disease types. These contents can be estimated by mathematical estimation methods based on a large number of basic data. These parameters ensure the subsequent continuous calculation.
  • the similarity judgment threshold, similarity calculation parameters, and mathematical calculation methods are not completely the same in different parts, organs, and diseases.
  • Step 32 Select effective image data of priority comparison and general comparison from the effective image data.
  • the distinction between the effective image data of the priority comparison and the general comparison can save the time of the comparison process, and obtain the comparison result quickly and maximumly.
  • the selection method includes:
  • the effective image data for priority comparison is the same data as those of the human body parts, organs, and diseases in the effective image data corresponding to the body parts, organs, and diseases selected before the ultrasound imaging device 30 detects the human body; the general ratio
  • the effective image data of the pair is data in which the human body parts, organs and disease attributes in the effective image data are different from those of the human body parts, organs and diseases selected before the ultrasound imaging apparatus 30 detects the human body.
  • Step 33 Divide the detected image data stream into multiple image frames.
  • Step 34 Use the mathematical calculation method and mathematical calculation parameters to calculate the similarity between the multiple image frames and all the effective comparison image data to form a calculation result, and compare the calculation result with the similarity judgment threshold; when the calculation result When it is not less than the similarity judgment threshold, it is judged as similar; when the calculation result is less than the similarity judgment threshold, it is judged as not similar.
  • Step 35 When it is judged as not similar in step 34, the mathematical calculation method and mathematical calculation parameters are used to calculate the similarity between the multiple image frames and the generally valid priority effective image database to form a calculation result, and the calculation result is similar to Compare the degree judgment threshold; when the calculation result is not less than the similarity judgment threshold, judge it as similar; when the calculation result is less than the similarity judgment threshold, judge as dissimilar, and execute step 5.
  • Step 5 The operator continuously uses the B-mode imaging device 30 to detect the human body, and manually controls the B-mode imaging device 30 to acquire the inspection image data stream or a part of the inspection images constituting the inspection image data stream, using the manual acquisition
  • the inspection image data stream or inspection image is used as the inspection result to complete the collection.
  • the method further includes step 6: after manually completing the collection of the inspection image data stream or the inspection image, directly perform artificial diagnosis on the inspection image data stream or the inspection image Distinguish and set the attributes and marks of the detected image data stream or the detected image including human parts, organs, diseases, etc. according to the results of the diagnostic discrimination, and form new effective image data, and convert the new effective image according to the attributes
  • step 6 after manually completing the collection of the inspection image data stream or the inspection image, directly perform artificial diagnosis on the inspection image data stream or the inspection image Distinguish and set the attributes and marks of the detected image data stream or the detected image including human parts, organs, diseases, etc. according to the results of the diagnostic discrimination, and form new effective image data, and convert the new effective image according to the attributes
  • the data is supplemented to the medical imaging standard database to complete the updating of the medical imaging standard database.
  • a professional doctor makes artificial judgment on the detection image data stream and part of the detection images in the data stream, and also marks the body parts, organs, and diseases to form new effective image data . It can be predicted that when this method is used to perform B-ultrasound detection on the human body, when more human specimen data is detected, the more effective image data in the medical imaging standard database is, the more comprehensive it is.
  • the effective image data is included in all B-ultrasound detection schemes, when this method is used for B-ultrasound detection, it can automatically identify the detection images and detection image data streams in B-ultrasound, so as to directly obtain the detection results, and no longer Need human operation and judgment.
  • the present invention also provides a B-mode intelligent auxiliary acquisition system, which includes:
  • a remote server 10 on which a database of medical imaging standards is stored.
  • the database of medical imaging standards includes various effective image data that have been formed after B-ultrasound corresponding to various parts of the human body, organs, and diseases. A mark is set on the effective image data.
  • the markers further set on the effective image data include: at least one of a plurality of marking points, a plurality of marking areas, or a plurality of marking parameters; each of the effective graphic data is also provided with a similarity calculation parameter and mathematics of the marking The calculation method and the similarity judgment threshold; the medical imaging standard database is based on the attribute classification and storage of the effective image data of the human body parts, organs and corresponding disease types and names.
  • a host 20 which is connected to the B-mode imaging device 30, receives the detected image data stream, and communicates with the remote server 10;
  • the B-mode imaging device 30 is used to detect the human body and form a detected image data stream;
  • the host 20 includes a key module 210, a control module 220, a data processing module 230, a communication module 240, and a cache module 250.
  • the key module 210 and the communication module 240 are connected to the control module 220 and the control module 220 Control and receive the detected image data stream detected by the B-mode imaging device 30 according to the body parts, organs and diseases to be detected entered by the key module 210 and store them in the buffer module 250, the control module 220 Controlling the communication module 240 to acquire the effective image data from the remote server 10, and send the acquired effective image data to the data processing module 230;
  • the data processing module 230 is based on the effective image data Divide the detected image data stream into multiple image frames and compare them, and determine the similarity between the image frames and the effective image data;
  • the data processing module 230 outputs a similar image frame to the control module 220 when determining that the image frame and the effective image data are similar; the control module 220 sends a control instruction to the cache module according to the comparison result 250, causing the cache module 250 to use the cached image frame or the detected image data stream in the time period before and after the image frame as a detection result;
  • the key module 210 sends a data entry instruction to the control module 220 under artificial control, and the control module 220 thereby controls the
  • the cache module 250 uses the detection image at the moment when the key module 210 is pressed or the detection image data stream in the time period before and after the detection image as the detection result;
  • the medical diagnosis system 40 receives the detection result through the communication module 240 and makes an artificial diagnosis according to the detection result.
  • the doctor obtains the test result from the medical test system and makes a diagnosis based on the test result; when the test result is obtained by pressing the human control by pressing the key module 210, the test image and the test image of the test result by the doctor
  • the data stream sets attributes including human body parts, organs, diseases, and markers, and forms new effective image data, and supplements the new effective image data to the medical imaging standard database according to the attributes, thereby completing the update of the medical imaging standard database.
  • the control module 220 includes a judgment selection module 221.
  • the judgment selection module 221 sends a query and a retrieval command to the remote server 10 according to the body parts, organs, and diseases to be detected entered by the key module 210, from the remote
  • the server 10 preferentially retrieves the effective image data having the same body parts, organs and disease attributes as the priority effective image data, and sends the preferential effective image data to the data processing module 230; then it is transferred from the remote server 10
  • the effective image data that does not have the same body parts, organs, and disease attributes is taken as general effective image data, and the general effective image data is sent to the data processing module 230.
  • the data processing module 230 includes:
  • a dividing module 231, the dividing module 231 is used to divide the detected image data stream stored in the buffer module 250 into a plurality of image frames;
  • the calculation module 232 based on the priority effective image data or the general effective image data, the multiple image frames divided by the dividing module 231, according to the pre-set mark points, mark areas or mark parameters on each effective image data Similarity calculation parameters and mathematical calculation methods sequentially calculate the similarity between the image frame and the priority effective image data or general effective image data;
  • a comparison module 233 determines whether the image frame is similar to the effective priority effective image data or general effective image data according to the similarity and a preset similarity judgment threshold, and outputs the judgment result to Control module 220;
  • the control module 220 obtains the corresponding detection result from the cache module 250 according to the judgment result, and sends the detection result to the remote server 10 via the communication module 240.
  • each effective image data is also provided with a similarity calculation of the marking Parameters, mathematical calculation methods and similarity judgment threshold; multiple effective image data are classified and stored according to the attributes of human parts, organs and corresponding disease types and names to form a medical imaging standard database, and the medical imaging standard database is stored in a remote In the server 10; in operation, first the B-mode imaging device 30 acquires the detected image data stream, and divides the detected image data stream into a plurality of image frames, sends the image frames to the host 20, using the data processing module 230 in the host 20 Compare the image frame and the effective image data to complete the comparison result.
  • the control module 220 automatically saves the image frame and the detected image data stream in the time period before and after the image frame, and sends it to the communication module 240, and the communication module 240 sends it to the medical diagnosis system 40.
  • the diagnosis system 40 makes a corresponding diagnosis and treatment conclusion.
  • the key module 210 sends a data entry instruction to the control module 220, and the control module 220 controls the cache module 250 to detect the image or the time period before and after the image
  • the detected image data stream is used as the detection result.
  • the detection result is sent to the medical diagnosis system 40.
  • the doctor obtains the test result from the medical test system and makes a diagnosis based on the test result; when the test result is obtained by pressing the human control by pressing the key module 210, the test image and the test image of the test result by the doctor
  • the data stream sets attributes including human body parts, organs, diseases, and markers, and forms new effective image data, and supplements the new effective image data to the medical imaging standard database according to the attributes, thereby completing the update of the medical imaging standard database.
  • the effective image data in the medical imaging standard database is also formed by artificially marking the detection images intercepted in the detection data stream, filling in attributes, setting similarity calculation parameters and similarity calculation methods. It can also be a medical imaging standard database that is expanded after learning a lot of marked effective graphics data through artificial intelligence.
  • the marked points, marked areas, marked parameters, similarity calculation parameters, and similarity calculation methods of an organ can be learned through artificial intelligence.
  • the human body image model and medical standard database can sufficiently cover all the human body data and the B-ultrasound data corresponding to the human body.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Medical Informatics (AREA)
  • General Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Pathology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Theoretical Computer Science (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

La présente invention concerne un procédé et un système d'acquisition auxiliaire intelligente ultrasonore en mode B, spécifiquement : une base de données de normes d'imagerie médicale comprenant des données d'image valides est d'abord configurée ; puis un flux de données de détection est acquis et un flux de données d'imagerie de détection est ensuite divisé en trames d'image ; les trames d'image sont comparées aux données d'image valides ; lorsque le résultat de la comparaison est qui celles-ci sont similaires, une trame d'image à partir du moment actuel et des flux de données d'imagerie de détection dans des périodes temporelles avant et après que la trame d'image sont automatiquement obtenus en tant que résultat de détection ; lorsque le diagnostic est que celles-ci ne sont pas similaires, l'acquisition de flux de données d'imagerie de détection et de trames d'image est commandée manuellement, qui est ensuite utilisé en tant que résultat de détection. Le procédé et le système d'acquisition auxiliaire intelligente ultrasonore en mode B proposés par la présente invention peuvent réduire les exigences en matière de compétence spécialisée du personnel d'inspection lors de la réalisation d'une inspection ultrasonore en mode B ; dans la plupart des cas, un résultat de détection peut être obtenu automatiquement, et ainsi le problème technique dans la technologie existante selon lequel seuls des techniciens spécialisés peuvent faire fonctionner les ultrasons en mode B est surmonté, et la plage d'application des ultrasons en mode B est élargie.
PCT/CN2018/120396 2018-12-11 2018-12-11 Procédé et système d'acquisition auxiliaire intelligente ultrasonore en mode b Ceased WO2020118535A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/120396 WO2020118535A1 (fr) 2018-12-11 2018-12-11 Procédé et système d'acquisition auxiliaire intelligente ultrasonore en mode b
CN201880100123.9A CN113556978A (zh) 2018-12-11 2018-12-11 一种b超智能辅助采集方法及系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/120396 WO2020118535A1 (fr) 2018-12-11 2018-12-11 Procédé et système d'acquisition auxiliaire intelligente ultrasonore en mode b

Publications (1)

Publication Number Publication Date
WO2020118535A1 true WO2020118535A1 (fr) 2020-06-18

Family

ID=71076153

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/120396 Ceased WO2020118535A1 (fr) 2018-12-11 2018-12-11 Procédé et système d'acquisition auxiliaire intelligente ultrasonore en mode b

Country Status (2)

Country Link
CN (1) CN113556978A (fr)
WO (1) WO2020118535A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024239937A1 (fr) * 2023-05-19 2024-11-28 上海深至信息科技有限公司 Système et procédé de commande de qualité de diagnostic ultrasonore auxiliaire

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670769A (zh) * 2003-11-26 2005-09-21 Ge医疗系统环球技术有限公司 计算机辅助定位目标的方法和系统
CN103324853A (zh) * 2013-06-25 2013-09-25 上海交通大学 基于医学图像特征的相似度计算系统及方法
CN103988204A (zh) * 2011-12-13 2014-08-13 国际商业机器公司 医学图像检索方法、设备和计算机程序
CN105184103A (zh) * 2015-10-15 2015-12-23 清华大学深圳研究生院 基于病历数据库的虚拟名医
CN106557647A (zh) * 2015-09-29 2017-04-05 松下知识产权经营株式会社 控制方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012080957A2 (fr) * 2010-12-15 2012-06-21 Koninklijke Philips Electronics N.V. Système d'imagerie par ultrasons possédant des réglages spécifiques au patient
KR20150068162A (ko) * 2013-12-11 2015-06-19 삼성전자주식회사 3차원 초음파 영상 통합 장치 및 방법
US20150351726A1 (en) * 2014-06-05 2015-12-10 Siemens Medical Solutions Usa, Inc. User event-based optimization of B-mode ultrasound imaging
CN107307883B (zh) * 2016-04-26 2019-12-17 江阴美超门诊部有限公司 一种带有智能图像判读器的多路超声影像诊断系统及其使用方法
CN107194157A (zh) * 2017-05-03 2017-09-22 上海理工大学 医用超声个性化自适应图像处理分析系统
CN107767928A (zh) * 2017-09-15 2018-03-06 深圳市前海安测信息技术有限公司 基于人工智能的医学影像报告生成系统及方法
CN107644419A (zh) * 2017-09-30 2018-01-30 百度在线网络技术（北京）有限公司 用于分析医学影像的方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670769A (zh) * 2003-11-26 2005-09-21 Ge医疗系统环球技术有限公司 计算机辅助定位目标的方法和系统
CN103988204A (zh) * 2011-12-13 2014-08-13 国际商业机器公司 医学图像检索方法、设备和计算机程序
CN103324853A (zh) * 2013-06-25 2013-09-25 上海交通大学 基于医学图像特征的相似度计算系统及方法
CN106557647A (zh) * 2015-09-29 2017-04-05 松下知识产权经营株式会社 控制方法
CN105184103A (zh) * 2015-10-15 2015-12-23 清华大学深圳研究生院 基于病历数据库的虚拟名医

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024239937A1 (fr) * 2023-05-19 2024-11-28 上海深至信息科技有限公司 Système et procédé de commande de qualité de diagnostic ultrasonore auxiliaire

Also Published As

Publication number Publication date
CN113556978A (zh) 2021-10-26

Similar Documents

Publication Publication Date Title
Lin et al. Multi-task learning for quality assessment of fetal head ultrasound images
CN114612389B (zh) 基于多源多尺度特征融合的眼底图像质量评价方法和装置
CN111986784B (zh) 医疗影像的元数据预测装置及方法
CN107895367B (zh) 一种骨龄识别方法、系统及电子设备
CN110634125B (zh) 基于深度学习的胎儿超声图像识别方法及系统
CN114554963A (zh) 用于自动超声图像标记和质量分级的系统和方法
CN109002846B (zh) 一种图像识别方法、装置和存储介质
CN109117890A (zh) 一种图像分类方法、装置和存储介质
RU2005133397A (ru) Автоматическое обнаружение поражений кожи
CN112241961B (zh) 基于深度卷积神经网络的胸部x光片辅助诊断方法及系统
CN110910377B (zh) 一种基于神经网络的脑梗死mri图像识别方法
CN108451500A (zh) 一种用于中医望诊的面色检测和脸型识别设备
WO2023029348A1 (fr) Procédé d'étiquetage d'instance d'image basé sur l'intelligence artificielle, et dispositif associé
CN114694236A (zh) 一种基于循环残差卷积神经网络的眼球运动分割定位方法
CN111528907A (zh) 一种超声影像肺炎辅助诊断方法及系统
CN116825266A (zh) 一种基于医学影像大数据的诊断报告辅助生成系统
US11850090B2 (en) Guided lung coverage and automated detection using ultrasound devices
WO2020118535A1 (fr) Procédé et système d'acquisition auxiliaire intelligente ultrasonore en mode b
CN108427988A (zh) 一种消化道解剖位置识别装置
CN105520712B (zh) 一种阴道镜图像智能采集评估方法及装置
CN114049485B (zh) 胚胎发育期的心脏断面智能识别和异常判断方法及装置
CN118799319B (zh) 一种智能内窥镜的息肉实时检测方法、系统及相关设备
CN118924421B (zh) 一种肺穿刺定位路径规划系统
CN110378333B (zh) 一种sd-oct图像黄斑中央凹中心定位方法
CN113781453B (zh) 一种基于x线片的脊柱侧凸进展预测及方法和装置

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: 18942747

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: 18942747

Country of ref document: EP

Kind code of ref document: A1