CN110197722B - AI-CPU system platform - Google Patents

AI-CPU system platform Download PDF

Info

Publication number
CN110197722B
CN110197722B CN201910467880.6A CN201910467880A CN110197722B CN 110197722 B CN110197722 B CN 110197722B CN 201910467880 A CN201910467880 A CN 201910467880A CN 110197722 B CN110197722 B CN 110197722B
Authority
CN
China
Prior art keywords
information
module
picture
association
marking
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.)
Active
Application number
CN201910467880.6A
Other languages
Chinese (zh)
Other versions
CN110197722A (en
Inventor
宋嘉颖
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.)
Guizhou Precision Health Data Co ltd
Original Assignee
Guizhou Precision Health Data 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 Guizhou Precision Health Data Co ltd filed Critical Guizhou Precision Health Data Co ltd
Priority to CN201910467880.6A priority Critical patent/CN110197722B/en
Publication of CN110197722A publication Critical patent/CN110197722A/en
Application granted granted Critical
Publication of CN110197722B publication Critical patent/CN110197722B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/41—Analysis of document content
    • G06V30/413—Classification of content, e.g. text, photographs or tables
    • 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
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Public Health (AREA)
  • Multimedia (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Primary Health Care (AREA)
  • Biomedical Technology (AREA)
  • Epidemiology (AREA)
  • Artificial Intelligence (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention relates to the technical field of information and communication for processing medical data, in particular to an AI-CPU system platform which comprises a background server, wherein the background server is used for acquiring an image picture, generating a bottom picture, identifying a suspicious region in the image picture and marking a marked region with the same position as the suspicious region in the bottom picture, and the background server is used for acquiring patient information, generating treatment information according to the patient information and the image picture, converting the treatment information in a text format into a required picture format, dividing the treatment information in the picture format into a plurality of information blocks and establishing contact among the information blocks. By adopting the scheme, the focus of the patient can be marked under the condition of ensuring that the image picture is not distorted, and a doctor is assisted in diagnosing the state of an illness.

Description

AI-CPU system platform
Technical Field
The invention relates to the technical field of information and communication for processing medical data, in particular to an AI-CPU system platform.
Background
AI is commonly called artificial intelligence, and mainly refers to a computer for simulating some thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, and the like) of a person, and along with the development of the artificial intelligence by people, part of the artificial intelligence is applied to our lives, such as smart home, so that our lives are more convenient and faster, for example, image recognition is performed by using the artificial intelligence, the recognition accuracy is higher, and the learning can be continuously performed along with the image recognition to improve the recognition accuracy.
The most common detection devices in hospitals are known as "radiography", in which a human body is usually scanned by an X-ray machine, a CT machine, a PET machine, or other devices to obtain radiography images of the interior of the human body, and a doctor determines the condition of a patient according to the radiography images in combination with other detection information of the patient. In the prior art, it is described that a shot image is identified by using an image identification method, and a focus is marked on the shot image for a doctor to view, but the identification accuracy of the adopted image identification technology is not high, and meanwhile, marking is performed on the shot image, which causes data change to the original shot image, possibly causes distortion of the shot image, and the doctor can diagnose by integrating the overall condition of the patient during diagnosis, and the marking can shield the content of a certain part of the shot image, possibly affecting the judgment of the doctor.
Disclosure of Invention
The invention aims to provide an AI-CPU system platform which can mark the focus of a patient and assist a doctor in diagnosing the state of an illness under the condition of ensuring that an image picture is not distorted.
The present invention provides a basic scheme: the AI-CPU system platform comprises a background server, wherein the background server is used for acquiring an image picture, generating a bottom picture, identifying a suspicious region in the image picture and marking a marked region with the same position as the suspicious region in the bottom picture.
The basic scheme has the following working principle and beneficial effects: the method comprises the steps of generating a bottom picture according to an image picture, identifying the image picture, determining a suspicious region where a focus is located after the focus is identified, marking the suspicious region at the same position as the suspicious region in the bottom picture as a marking region, superposing the bottom picture and the image picture when a doctor diagnoses, checking the image picture superposed with the bottom picture by the doctor, and ensuring that the image picture is not distorted because the marking region is not directly marked in the image picture, wherein the marking region marked on the bottom picture can obviously display the focus and assist the doctor in diagnosing the state of an illness of a patient.
Further, the background server stores a focus information data model, and is used for identifying suspicious regions in the image picture according to the focus information data model.
Description of the drawings: the focus information data model is the existing data model for identifying the focus.
Has the advantages that: and identifying suspicious regions in the image picture according to the focus information data model, so as to facilitate subsequent marking of the marked regions.
Further, the background server is used for acquiring the detection type, acquiring a matching threshold value according to the detection type, generating a matching value when a suspicious region in the image picture is identified, and taking the suspicious region as a focus region when the matching value is larger than the matching threshold value.
Description of the drawings: the detection type comprises physical examination or special examination, and the matching value is percentage.
Has the advantages that: judging whether the suspicious region is taken as a focus region according to the matching value, wherein the matching value is higher when a special examination of a certain disease is carried out, the matching value is lower when a physical examination is carried out, the matching value is related to different purposes of a patient, when the patient carries out the special examination, a doctor needs to confirm the illness state of the patient, a focus information data model is formed by learning a sample of the special examination, the suspicious region of the patient is marked as the focus region only when the matching value is higher so as to assist the doctor to confirm the illness state, and when the patient carries out the examination, the patient wants to know all the physical conditions of the patient, so that the matching value is lower at this moment, and all the suspicious regions are marked as the focus regions.
Further, the background server is used for establishing the same coordinate system in the image picture and the bottom picture, acquiring a coordinate set of a focus area in the image picture according to the coordinate system, and marking a marking area in the bottom picture according to the coordinate set.
Has the advantages that: and establishing a coordinate system in the same direction of the same origin in the image picture and the bottom picture, and marking the same coordinate in the bottom picture according to the coordinate of the focus area so as to mark a marking area with the same position as the focus area in the bottom picture.
The background server comprises a case generation module, a format conversion module, an information division module and a contact establishment module, wherein the case generation module is used for acquiring patient information and generating treatment information according to the patient information and the image picture, the format conversion module is used for converting the treatment information in the text format into a required picture format, the information division module is used for dividing the treatment information in the picture format into a plurality of information blocks, and the contact establishment module is used for establishing contact among the information blocks.
Description of the drawings: the patient information includes information that can confirm the identity of the patient, such as the patient's name, the patient's age, the patient's sex, and the patient's identification number.
Has the advantages that: the case generation module is used for generating the patient information and the image picture into the diagnosis information, namely the diagnosis information of the patient currently examined, the diagnosis information is in a text format, the text format is converted into the picture format through the format conversion module, the diagnosis information is conveniently divided subsequently, the diagnosis information in the picture format is divided through the information division module, compared with the diagnosis information in the text format, when the diagnosis information in the text format is divided, the dividing dimension can only be the length of data, when the diagnosis information in the picture format is divided, the division is carried out on the basis of space, the dividing dimension is more than that of the division in the text format, and the diagnosis information is divided into information blocks so as to reduce the possibility that the diagnosis information of the patient leaks from a server.
Further, the format conversion module is also used for converting the picture format into the text format.
Has the advantages that: when a doctor needs to check the treatment information of a patient, the information blocks need to be spliced, the treatment information formed after splicing is in a picture format, the doctor cannot directly check the treatment information at the moment, and the treatment information in the picture format needs to be converted into a text format for checking.
Further, the background server stores all information templates, association algorithms and association rules, the information dividing module is used for acquiring any one information template and dividing the information about the doctor into a plurality of information blocks according to the information template, and the association establishing module is used for generating a unique association value of each information block according to the association algorithms and establishing association between the information blocks according to the association values and the association rules.
Description of the drawings: all the information templates comprise a plurality of information templates and are used for segmenting and splicing the information about the doctor.
Has the advantages that: the information of seeing a doctor is divided into a plurality of information blocks through the acquired information template, the correlation value corresponding to each information block is generated through a correlation algorithm, the information blocks are not changed, the correlation values generated through the correlation algorithm are the same, the correlation values generated by the information blocks are different, the relation is established for all the information blocks according to the correlation values and the correlation rules of the information blocks, and when one information block is acquired, all the information blocks can be acquired.
Further, the association rule generates the same number of mark labels according to the number of the information blocks, and randomly marks the areas corresponding to the information blocks on the information template according to the mark labels; the association rule is to acquire the association value of the information block corresponding to the specified mark label, and take the association value as the file header of the information block corresponding to the next mark label according to the sequence of the mark labels, and take the association value of the information block corresponding to the tail mark label as the file header of the information template.
Has the advantages that: when the number of the information blocks is 5, 5 areas which are the same as the division of the information blocks are arranged on the information template, 5 mark labels are generated, for example, the mark numbers 1-5, randomly marks 5 areas on the information template according to the mark numbers, namely, each area has a unique mark number, the mark number is assigned to be 1, the associated value of the information block corresponding to the area with the mark number of 1 is obtained, the associated value is used as the file header of the information block corresponding to the area marked with the label number 2 according to the sequence of the label numbers, namely, when the association value is known, the information block corresponding to the area marked with the number 2 can be known, the process is carried out in sequence until the association value of the information block corresponding to the area marked with the number 5 at the end is obtained, the association value of the information block corresponding to the area marked with the number 5 at the end is used as the file header of the information template, that is, when the associated value of the information block corresponding to the area marked with the end mark number 5 is known, the information template can be known.
Further, the association algorithm is a hash algorithm, and the association establishing module is configured to generate a hash value of the information block as the association value according to the hash algorithm.
Has the advantages that: the hash algorithm has short calculation time, the same output cannot be obtained through the hash algorithm, namely, the hash values obtained through the hash operation of different information blocks are different, the input data or information cannot be obtained through the hash values according to the characteristics of the hash algorithm, and the hash values obtained through the hash algorithm are used as the associated values to further ensure the safety of the patient information.
Further, the background server is used for screening all the information blocks and the information template according to the patient information, generating splicing labels according to the number of the information blocks, sequentially marking the information blocks according to the screening sequence, and sequentially splicing all the information blocks into the information template according to the splicing labels and the marking labels.
Has the advantages that: the first information block is screened out according to the patient information, and all information blocks and information templates can be screened out through the information blocks due to the fact that the relation is established among the information blocks. And generating splicing labels according to the number of the information blocks, wherein when the number of the information blocks is 5, the splicing labels are 1-5, and all the information blocks are marked in sequence according to the screening sequence, namely the splicing label of the first screened information block label is 1, and the splicing label of the second screened information block label is 2. And when the mark number is 1-5 and the corresponding splicing mark number is 1-5, sequentially corresponding the information block and the area on the information template according to the mark number and the splicing mark number until all the information blocks are spliced into the information template to form complete information for treatment.
Drawings
FIG. 1 is a logic block diagram of an AI-CPU system platform according to a first embodiment of the invention.
FIG. 2 is a logic block diagram of a second embodiment of the AI-CPU system platform of the present invention.
Detailed Description
The following is further detailed by way of specific embodiments:
example one
An AI-CPU system platform, as shown in fig. 1, includes a background server, an acquisition end and a doctor end, where the background server includes a region identification module, a region judgment module, a region marking module, an information storage module and a database, and a focus information data model, type and matching threshold value contact table is stored in the database. The lesion information data model is a data model of a lesion in the digestive tract described in, for example, a system and a method for recognizing a lesion image under publication No. CN106097335B, which is known in the art and can be selected by those skilled in the art as needed.
The acquisition end is used for acquiring an image picture of a patient and sending the image picture to the background server, and in this embodiment, the acquisition end is a CT machine. The doctor end is used for obtaining the patient information and the detection type and sending the patient information and the detection type to the background server.
The region identification module is used for acquiring a focus information data model from a database, identifying a suspicious region in the image picture according to the focus information data model, generating a matching value of the suspicious region, and sending the image picture after identifying the suspicious region and the matching value to the region judgment module. The area judgment module is used for screening out a matching threshold value from the type and matching threshold value contact table according to the detection type, judging the matching value and the matching threshold value, neglecting a suspicious area corresponding to the matching value when the matching value is smaller than or equal to the matching threshold value, taking the suspicious area corresponding to the matching value as a focus area when the matching value is larger than the matching threshold value, and sending the judged image picture to the area marking module.
In this embodiment, the detection types are physical examination and lung cancer, the matching threshold corresponding to the physical examination is 30%, and the matching threshold corresponding to the lung cancer is 80%. When the detection type is physical examination, the matching threshold is 30%, when the matching value of the suspicious region is 20% or 30%, the suspicious region is ignored, and when the suspicious region is 50%, the suspicious region is taken as a focus region.
The region marking module is used for generating a bottom layer picture according to the image, establishing a coordinate system by taking the lower left corner of the image picture and the bottom layer picture as an original point, taking the horizontal right side of the original point as an X positive coordinate axis and taking the vertical upward side of the original point as a Y positive coordinate axis, and endowing each pixel point in the image picture and the bottom layer picture with coordinates. All coordinates of pixel points of the focus area in the image are obtained to form a coordinate set, a marked area is marked in the bottom picture according to the coordinate set, and the marked bottom picture is sent to the information storage module. The information storage module is used for storing the patient information, the bottom layer picture and the image picture sent by the acquisition end in a database.
Example two
The difference between the present embodiment and the first embodiment is: as shown in fig. 2, the background server further includes a case generation module, a format conversion module, an information division module, a connection establishment module, an information screening module, an information splicing module, and an auxiliary diagnosis module, and the database further stores all information templates, association algorithms, and association rules, where all the information templates are a plurality of information templates, and in this embodiment, the association algorithm is a hash algorithm.
When the patient information, the bottom picture and the image picture sent by the acquisition terminal are stored, the information storage module is used for establishing a contact according to the patient information and the bottom picture, generating an information and negative film contact table and storing the information and negative film contact table and the bottom picture in a database. The case generation module is used for generating the current examination information of the patient according to the patient information and the image picture, and sending the examination information to the format conversion module, wherein the examination information is in a text format. The format conversion module is used for converting the doctor seeing information in the text format into a required picture format and sending the picture format to the information division module.
The information division module is used for acquiring any information template from the database, dividing the information about diagnosis into a plurality of information blocks according to the information template, and sending the information template and all the information blocks to the contact establishment module. The association establishing module is used for acquiring the association algorithm and the association rule from the database, generating a unique association value of each information block according to the association algorithm, establishing association between the information blocks according to the association value and the association rule, and sending the information blocks and the information modules which establish the association to the information storage module. The information storage module is used for storing the information block and the information template in a database.
Specifically, the contact establishing process is that a contact establishing module is used for generating the same number of marking labels according to the number of the information blocks and randomly marking the areas corresponding to the information blocks on the information template according to the marking labels; and acquiring the associated value of the information block corresponding to the appointed mark label according to an associated algorithm, taking the associated value as the file header of the information block corresponding to the next mark label according to the sequence of the mark labels, and taking the associated value of the information block corresponding to the tail mark label as the file header of the information template.
In this embodiment, the doctor end is further configured to acquire patient information and a viewing signal, and send the patient information and the viewing signal to the background server. The information screening module is used for screening a first information block from the database according to the patient information after receiving the checking signal, generating a hash value corresponding to the information block as an associated value through a hash algorithm, screening a second information block according to the associated value until the last information block is screened, generating an associated value corresponding to the last information block, and screening an information template from the database; and generating splicing labels with the same number as the information blocks, sequentially marking all the information blocks according to the screening sequence, and sending the marked information blocks and the information template to an information splicing module. The information splicing module is used for acquiring any mark label on the information template, sequentially acquiring picture splicing labels of all information blocks, splicing the information blocks to the area corresponding to the mark label of the information template when the picture splicing labels of the information blocks are the same as the mark label, sequentially splicing all the information blocks into the information template, and sending the spliced information blocks to the format conversion module, wherein the spliced information blocks are the diagnosis information in the picture format.
The format conversion module is used for converting the doctor seeing information from a picture format into a text format and sending the converted doctor seeing information to the doctor end and the auxiliary diagnosis module, and the doctor end is used for displaying the doctor seeing information.
The doctor end is further used for obtaining auxiliary diagnosis signals and sending the patient information and the auxiliary diagnosis signals to the background server, and the information auxiliary diagnosis module is further used for screening out bottom pictures from the database according to the patient information after receiving the auxiliary diagnosis signals, superposing the bottom pictures on the video pictures of the information to be diagnosed and sending the bottom pictures to the doctor end for displaying.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.

Claims (6)

  1. An AI-CPU system platform, comprising a background server, characterized in that: the background server comprises an area identification module, an area judgment module, an area marking module, a case generation module, a format conversion module, an information division module, a contact establishment module, an information storage module and a database;
    the area identification module is used for acquiring the image picture, identifying a suspicious area in the image picture and generating a matching value when identifying the suspicious area in the image picture; the region judgment module is used for acquiring the detection type, acquiring a matching threshold value according to the detection type, and taking the suspicious region as a focus region when the matching value is greater than the matching threshold value; the detection types comprise physical examination and special examination; the region marking module is used for generating a bottom picture according to the judged image picture and marking a marking region with the same position as the focus region in the bottom picture;
    the medical record generating module is used for acquiring patient information and generating treatment information according to the patient information and the image picture, the format converting module is used for converting the treatment information in the text format into a required picture format, the information dividing module is used for dividing the treatment information in the picture format into a plurality of information blocks, and the establishing connection module is used for establishing connection among the information blocks; the information storage module is used for storing the information blocks in a database;
    the background server stores all information templates, association algorithms and association rules, the information dividing module is used for acquiring any information template and dividing the information of the doctor seeing visit into a plurality of information blocks according to the information template, the association establishing module is used for generating a unique association value of each information block according to the association algorithms and establishing association among the information blocks according to the association values and the association rules;
    the association rule generates the same number of mark labels according to the number of the information blocks, and randomly marks the areas corresponding to the information blocks on the information template according to the mark labels; the association rule is to acquire the association value of the information block corresponding to the specified mark label, and take the association value as the file header of the information block corresponding to the next mark label according to the sequence of the mark labels, and take the association value of the information block corresponding to the tail mark label as the file header of the information template.
  2. 2. The AI-CPU system platform of claim 1, wherein: the background server stores a focus information data model and is used for identifying suspicious regions in the image picture according to the focus information data model.
  3. 3. The AI-CPU system platform of claim 1, wherein: the background server is used for establishing the same coordinate system in the image picture and the bottom picture, acquiring a coordinate set of a focus area in the image picture according to the coordinate system, and marking a marking area in the bottom picture according to the coordinate set.
  4. 4. The AI-CPU system platform of claim 1, wherein: the format conversion module is also used for converting the picture format into the text format.
  5. 5. The AI-CPU system platform of claim 1, wherein: the association algorithm is a hash algorithm, and the connection establishing module is used for generating a hash value of the information block as an association value according to the hash algorithm.
  6. 6. The AI-CPU system platform of claim 5 wherein: the background server is used for screening all the information blocks and the information template according to the patient information, generating splicing labels according to the number of the information blocks, sequentially marking the information blocks according to the screening sequence, and sequentially splicing all the information blocks into the information template according to the splicing labels and the marking labels.
CN201910467880.6A 2019-05-31 2019-05-31 AI-CPU system platform Active CN110197722B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910467880.6A CN110197722B (en) 2019-05-31 2019-05-31 AI-CPU system platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910467880.6A CN110197722B (en) 2019-05-31 2019-05-31 AI-CPU system platform

Publications (2)

Publication Number Publication Date
CN110197722A CN110197722A (en) 2019-09-03
CN110197722B true CN110197722B (en) 2022-06-07

Family

ID=67753496

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910467880.6A Active CN110197722B (en) 2019-05-31 2019-05-31 AI-CPU system platform

Country Status (1)

Country Link
CN (1) CN110197722B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111175958A (en) * 2019-12-31 2020-05-19 杭州迪英加科技有限公司 Remote consultation method and system for pathological section under microscope
CN111816281B (en) * 2020-06-23 2024-05-14 无锡祥生医疗科技股份有限公司 Ultrasonic image inquiry device

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105039523A (en) * 2008-11-17 2015-11-11 威拉赛特公司 Methods and compositions of molecular profiling for disease diagnostics
CN103685162A (en) * 2012-09-05 2014-03-26 ***通信集团公司 File storing and sharing method
CN103118089A (en) * 2013-01-22 2013-05-22 华中科技大学 Safe storage method based on a plurality of cloud storage systems and system thereof
CN104657928B (en) * 2015-02-14 2016-04-06 张晓� A kind of medical coordination system
CN106372390B (en) * 2016-08-25 2019-04-02 汤一平 A kind of self-service healthy cloud service system of prevention lung cancer based on depth convolutional neural networks
CN108573490B (en) * 2018-04-25 2020-06-05 王成彦 Intelligent film reading system for tumor image data
CN108985345B (en) * 2018-06-25 2020-09-18 安徽倍泰光电科技有限公司 Detection apparatus based on lung medical image fusion classification
CN108695001A (en) * 2018-07-16 2018-10-23 武汉大学人民医院（湖北省人民医院） A kind of cancer lesion horizon prediction auxiliary system and method based on deep learning

Also Published As

Publication number Publication date
CN110197722A (en) 2019-09-03

Similar Documents

Publication Publication Date Title
US10810735B2 (en) Method and apparatus for analyzing medical image
WO2019103440A1 (en) Method for supporting reading of medical image of subject and device using same
WO2021021329A1 (en) System and method for interpretation of multiple medical images using deep learning
CN111161848B (en) Focus marking method and device for CT image and storage medium
US20220301159A1 (en) Artificial intelligence-based colonoscopic image diagnosis assisting system and method
KR102078876B1 (en) Method and system for detecting pneumothorax
CN111696083A (en) Image processing method and device, electronic equipment and storage medium
US10832410B2 (en) Computer system, method, and program for diagnosing subject
CN110197722B (en) AI-CPU system platform
US20220277445A1 (en) Artificial intelligence-based gastroscopic image diagnosis assisting system and method
CN111401102A (en) Deep learning model training method and device, electronic equipment and storage medium
CN113298773A (en) Heart view identification and left ventricle detection device and system based on deep learning
CN110110750B (en) Original picture classification method and device
CN112862752A (en) Image processing display method, system electronic equipment and storage medium
CN116825266A (en) Diagnosis report auxiliary generation system based on medical image big data
CN115661037A (en) Capsule endoscope auxiliary detection method, device, system, equipment and medium
CN113256625A (en) Electronic equipment and recognition device
CN114283114A (en) Image processing method, device, equipment and storage medium
KR102136107B1 (en) Apparatus and method for alignment of bone suppressed chest x-ray image
KR20210054140A (en) Medical image diagnosis assistance apparatus and method using a plurality of medical image diagnosis algorithm for endoscope images
CN112750537A (en) Remote medical guide system
CN114332844B (en) Intelligent classification application method, device, equipment and storage medium of medical image
EP4266255A1 (en) Method and system for generating label of medical image
KR102564443B1 (en) Gastroscopy system with improved reliability of gastroscopy using deep learning
CN113706449B (en) Pathological image-based cell analysis method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant