CN115565660A - Medical image data sharing management system based on feature recognition - Google Patents

Medical image data sharing management system based on feature recognition Download PDF

Info

Publication number
CN115565660A
CN115565660A CN202211175280.0A CN202211175280A CN115565660A CN 115565660 A CN115565660 A CN 115565660A CN 202211175280 A CN202211175280 A CN 202211175280A CN 115565660 A CN115565660 A CN 115565660A
Authority
CN
China
Prior art keywords
target
medical image
patient
diagnosis
medical
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.)
Pending
Application number
CN202211175280.0A
Other languages
Chinese (zh)
Inventor
王云
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.)
Hubei Wisteria Beauty Management Co ltd
Original Assignee
Hubei Wisteria Beauty Management 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 Hubei Wisteria Beauty Management Co ltd filed Critical Hubei Wisteria Beauty Management Co ltd
Priority to CN202211175280.0A priority Critical patent/CN115565660A/en
Publication of CN115565660A publication Critical patent/CN115565660A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • 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
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • 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
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • 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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
    • 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

Abstract

The invention relates to the technical field of medical image data sharing management, and particularly discloses a medical image data sharing management system based on feature recognition.

Description

Medical image data sharing management system based on feature recognition
Technical Field
The invention belongs to the technical field of medical image data sharing management, and particularly relates to a medical image data sharing management system based on feature recognition.
Background
With the increasing of the living pressure of people at present, various health problems of human bodies begin to be gradually shown, so that the patients inevitably need to go to hospitals for medical treatment, in the process of medical treatment, medical images are an indispensable health treatment means, and meanwhile, the medical images are widely popularized and applied by the hospitals due to the characteristics and advantages of being capable of obtaining internal tissue images of the human bodies in a non-invasive mode.
Nowadays, there are some drawbacks to the management of medical image data, which are embodied in the following aspects: (1) At present to the management of medical image data, more still rely on the patient to carry a plurality of medical image one-tenth pieces of self when carrying out the doctor's diagnosis, intelligent level is relatively poor, therefore has great limitation, and the patient inevitably appears losing or forgets to carry the situation that the medical image becomes one-tenth pieces, not only can't provide the diagnosis and treatment foundation of reliability for the doctor, still influenced patient's self doctor's diagnosis and treatment progress to a great extent, and then the healthy of harm patient.
(2) The prior art lacks in carrying out the pertinence analysis to diagnosis hospital and diagnostician in patient's diagnosis early stage of seeking medical advice, and pertinence analysis level is lower, and lacks the systematicness, can't select adaptation diagnosis hospital and adaptation diagnostician according to patient's actual state of an illness, and then leads to can't providing the reliability reference for patient's treatment of seeking medical advice, has influenced patient's the level of diagnosing and treating of seeking medical advice to a great extent.
Disclosure of Invention
In order to overcome the disadvantages in the background art, embodiments of the present invention provide a medical image data sharing management system based on feature recognition, which can effectively solve the problems related to the background art.
The purpose of the invention can be realized by the following technical scheme: a medical image data sharing management system based on feature recognition comprises: the system comprises a medical image database, a target patient basic parameter acquisition module, a target patient basic parameter analysis module, a target diagnosis hospital analysis module, a diagnostician matching analysis module, a target patient medical image acquisition and analysis module and a medical image data sharing module.
The medical image database is used for storing medical image treatment data of each patient corresponding to each disease condition name at each body part of each diagnosis hospital and storing the times of the medical patients belonging to each medical department of each diagnosis hospital.
The target patient basic parameter acquisition module is used for acquiring basic parameters of a target patient.
The target patient basic parameter analysis module is used for analyzing basic parameters of a target patient, and then matching and screening out each target diagnosis hospital.
The target diagnosis hospital analysis module is used for analyzing each target diagnosis hospital and further screening out adaptive diagnosis hospitals.
The diagnostician matching analysis module is used for performing matching analysis on each diagnostician so as to screen out adaptive diagnosticians.
The target patient medical image acquisition and analysis module is used for acquiring and analyzing the target patient medical image.
The medical image data sharing module is used for sharing medical image treatment data.
Preferably, the acquisition of basic parameters of the target patient is performed, wherein the basic parameters include: name, age, sex, height, weight, the affected part and the name of the disease.
As a preferred scheme, the analyzing of the basic parameters of the target patient includes the following specific analyzing processes: recording the current diseased body part of the target patient as a target treatment body part, further extracting the name of the target treatment body part, recording the disease condition name of the target patient as a target treatment disease condition name, and further extracting each medical image treatment data of the target patient corresponding to the target treatment disease condition at the target treatment body part of each diagnosis hospital.
And according to the name of the target treatment body part and the name of the target treatment illness state, matching the medical image treatment data, which are stored in the medical image database and correspond to the name of the illness state, of each patient at each body part to which each diagnosis hospital belongs, and further acquiring the medical image treatment data, which correspond to the name of the target treatment illness state, of each patient at each target treatment body part to which each diagnosis hospital belongs.
According to the medical image treatment data of each patient corresponding to the target treatment disease name at the target treatment body part of each diagnosis hospital, extracting the basic information corresponding to each patient from the medical image treatment data, wherein the basic information comprises: name, sex, age, height and weight.
And matching the sex of the target patient with the sex of each patient, further screening out each patient corresponding to the sex of the target patient, and recording the patient as each reference fitting patient.
The age, the height and the weight of the target patient are respectively compared with the age, the height and the weight of each reference adaptive patient, and the physical condition matching index of the target patient and each reference adaptive patient is calculated, wherein the calculation formula is as follows:
Figure BDA0003864034260000041
in which α is ST i Is expressed as a physical condition matching index, NL, of the target patient to the i-th reference fitting patient 0 、SG 0 And TZ 0 Expressed as age, height and weight, nl, respectively, of the target patient i 、sg i And tz i Respectively expressed as age, height and weight, delta, of the ith reference fitting patient 1 、δ 2 And delta 3 Expressed as matching correction factors for preset age, height and weight, respectively, i is expressed as the number of each reference fitting patient, i =1,2.
As a preferred scheme, each target diagnosis hospital is screened out in a matching way, and the specific screening process is as follows: and comparing the target patient with the set matching index threshold value of the fitting physical condition according to the physical condition matching indexes of the target patient and the reference fitting patients, and if the physical condition matching indexes of the target patient and a certain reference fitting patient are within the range of the matching index threshold value of the fitting physical condition, marking the reference fitting patient as the target reference fitting patient, and counting the target reference fitting patients.
And extracting the name of each target reference fitting patient, screening each diagnosis hospital of each target reference fitting patient, and marking the diagnosis hospitals as each target diagnosis hospital.
As a preferred scheme, the analysis of each target diagnosis hospital comprises the following specific processes: and extracting the corresponding name of each target diagnosis hospital, further matching the name with the number of medical patients belonging to each medical department of each diagnosis hospital stored in the medical image database, and extracting the number of medical patients belonging to each medical department of each target diagnosis hospital.
And matching the name of the target treatment body part and the name of the target treatment illness state of the target patient with medical departments corresponding to various illness state names of various set body parts to obtain the medical department corresponding to the target patient, and marking the medical department as the target medical department.
Extracting the number of medical patients belonging to the target medical department of each target diagnosis hospital, and further calculating the matching index of each target diagnosis hospital, wherein the calculation formula is as follows:
Figure BDA0003864034260000051
wherein epsilon RC j Expressed as the matching index, η, of the jth target diagnostic hospital j The number of medical patients to which the target medical department of the jth target diagnosis hospital belongs is represented, e is represented by a natural constant, j is represented by the number of each target diagnosis hospital, and j =1,2.
Based on the times of the medical patients belonging to the target medical departments of the target diagnosis hospitals, extracting treatment parameters of the medical patients, wherein the treatment parameters comprise treatment duration, treatment cost and medical image quantity, further obtaining average treatment duration, average treatment cost and average medical image quantity of the medical patients belonging to the target medical departments of the target diagnosis hospitals, calculating medical matching indexes of the target diagnosis hospitals according to the average treatment duration, average treatment cost and average medical image quantity, and recording the medical matching indexes as mu YL j In which μ YL j Is expressed as the jthMedical matching index of the target diagnostic hospital.
Based on the matching index of each target diagnosis hospital and the medical matching index of each target diagnosis hospital, the comprehensive adaptation index of each target diagnosis hospital is further calculated comprehensively, and the calculation formula is as follows:
Figure BDA0003864034260000052
wherein
Figure BDA0003864034260000053
Expressed as the composite fit index for the jth target diagnostic hospital.
As a preferred scheme, the screening is adapted to a diagnosis hospital, and the specific screening process comprises the following steps: and based on the comprehensive adaptation indexes of the target diagnosis hospitals, sequencing the comprehensive adaptation indexes of the target diagnosis hospitals from large to small, extracting the target diagnosis hospital with the first ranking of the comprehensive adaptation indexes, and recording the target diagnosis hospital as the adaptation diagnosis hospital.
As a preferred scheme, the matching analysis for each diagnostician is performed in the following specific process: extracting each diagnostician corresponding to a target medical department to which the adaptive diagnosis hospital belongs, and further extracting the practitioner parameters of each diagnostician, wherein the practitioner parameters comprise: calculating the adaptation indexes corresponding to the diagnosticians according to the working duration, the job title grades and the diagnosis times, wherein the calculation formula is as follows:
Figure BDA0003864034260000061
where σ is YS p Expressed as the fit index, Δ SC, for the pth diagnostician p 、ΔDJ p And Δ RC p Respectively expressed as the working duration, the job title grade and the number of diagnosticians of the p-th diagnostician, p is the number of each diagnostician, p =1,2 1 、Φ 2 And phi 3 And the adaptive weight factors are respectively expressed as preset adaptation time length, job title grade and diagnosis person number of the diagnostician.
As a preferred scheme, the acquisition and analysis of the medical image of the target patient comprises the following specific processes: based on the medical image treatment data of the target treatment body part corresponding to the target treatment disease name of each target reference adaptive patient in each diagnosis hospital, extracting each medical image of the target treatment body part corresponding to the target treatment disease name of each target reference adaptive patient in each diagnosis hospital, and recording the medical image as each reference medical image.
And acquiring a medical image of the target treatment body part of the target patient, further acquiring the medical image of the target treatment body part of the target patient, and recording the medical image as a target diagnosis medical image.
The detection points of each reference medical image are distributed in a systematic sampling point distribution mode, each detection point corresponding to each reference medical image is obtained, the gray value of each detection point corresponding to each reference medical image is further extracted, similarly, the gray value of each detection point corresponding to the target diagnosis medical image is extracted, the gray similarity index corresponding to the target diagnosis medical image and each reference medical image is calculated, and the calculation formula is as follows:
Figure BDA0003864034260000071
wherein ω is HD f Expressed as a gray scale similarity index corresponding to the target diagnostic medical image and the f-th reference medical image,
Figure BDA0003864034260000073
expressed as a preset gray scale tolerance value, beta r f Expressed as the gray value phi of the r-th detection point corresponding to the f-th reference medical image r Is expressed as a gray value to which the r-th detection point corresponding to the target diagnostic medical image belongs, f is expressed as the number of each reference medical image, f =1,2,. Multidot.g., g, r is expressed as the number of each detection point, r =1,2,. Multidot.t, t, t is expressed as the number of detection points, theta is expressed as the number of detection points 0 And is expressed as a preset gray scale correction factor corresponding to the medical image.
Based on each reference medical image, further extracting the outline of the human body part to which each reference medical image belongs, and extracting the outline area of the human body part to which each reference medical image belongs, and in the same way,extracting the outline of the human body part to which the target diagnosis medical image belongs, further performing coincidence comparison on the outline of the human body part to which the target diagnosis medical image belongs and the outline of the human body part to which each reference medical image belongs, extracting the area of the coincided outlines of the human body parts, and accordingly calculating the outline similarity index of the human body parts corresponding to the target diagnosis medical image and each reference medical image, wherein the calculation formula is as follows:
Figure BDA0003864034260000072
in which ξ MJ f Is expressed as the contour similarity index of the body part corresponding to the target diagnosis medical image and the f-th reference medical image, S Heavy load f Expressed as the area of the outline of the coincidence of the target diagnostic medical image and the part of the human body to which the f-th reference medical image belongs, S min Is expressed as the minimum overlapping area of the preset similar outline.
Based on the gray level similarity index corresponding to the target diagnosis medical image and each reference medical image and the outline similarity index of the human body part corresponding to the target diagnosis medical image and each reference medical image, further calculating the comprehensive similarity index corresponding to the target diagnosis medical image and each reference medical image, wherein the calculation formula is as follows:
Figure BDA0003864034260000081
wherein psi f Expressed as a composite similarity index corresponding to the target diagnostic medical image and the f-th reference medical image, a 1 And a 2 Respectively expressed as the ratio of the preset gray scale of the medical image to the corresponding similar weight of the outline of the human body part.
As a preferred scheme, the sharing of the medical image treatment data comprises the following specific processes: and based on the comprehensive similarity indexes corresponding to the target diagnosis medical image and the reference medical images, further extracting the reference medical image corresponding to the maximum value of the comprehensive similarity indexes, extracting the target reference adaptive patient to which the reference medical image belongs, further extracting the medical image treatment data of the target reference adaptive patient to which the reference medical image belongs, and sharing the medical image treatment data to an adaptive diagnosis doctor.
And sharing the medical image treatment data of the target patient corresponding to the target treatment illness state at the target treatment body part of each diagnosis hospital to the adaptive diagnostician.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects: (1) The medical image data sharing management system based on feature recognition can store the medical image treatment data of the target patient in each diagnosis hospital, further can share the medical image treatment data to a diagnostician when the target patient is subjected to medical diagnosis, effectively overcomes the defect that the patient is dependent on carrying a plurality of medical images to form a film when the patient is subjected to medical diagnosis, improves the intelligent level, avoids the condition that the patient loses or forgets to carry the medical image to form a film, can provide reliable diagnosis and treatment basis for the doctor, improves the diagnosis and treatment progress of the patient to a greater extent, and further effectively ensures the physical health of the patient.
(2) According to the invention, the adaptive diagnosis hospitals are matched and screened out by collecting and analyzing the basic parameters of the target patient, and the adaptive diagnosis doctors are screened out by matching and analyzing each diagnosis doctor, so that the defect that the prior art lacks the limitation of performing targeted analysis on the diagnosis hospitals and the diagnosis doctors in the early stage of the patient hospitalization diagnosis is overcome, the targeted analysis level is higher, the system is provided, the adaptive diagnosis hospitals and the adaptive diagnosis doctors can be screened out according to the actual state of illness of the patient, the reliability reference basis can be provided for the hospitalization treatment of the patient, and the hospitalization diagnosis level of the patient is improved to a greater extent.
(3) The invention also obtains each target reference adaptive patient by screening through evaluating the body condition matching indexes of the target patient and each reference adaptive patient, extracts each reference medical image corresponding to each target reference adaptive patient according to the target treatment body part and the target treatment state name of the target patient, extracts the comprehensive similarity index corresponding to the target diagnosis medical image and each reference medical image, extracts the medical image treatment data of the target reference adaptive patient to which the reference medical image corresponding to the maximum value of the comprehensive similarity index belongs, shares the medical image treatment data to the adaptive diagnostician, can provide a reliable diagnosis reference for the adaptive diagnostician, and can further achieve a higher diagnosis and treatment level of the target patient by combining with the adaptive diagnostician, greatly improves the body guarantee of the target patient, and is beneficial to relieving the diagnosis pressure of the diagnostician.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a schematic diagram of the system structure connection of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, the present invention provides a medical image data sharing management system based on feature recognition, including: the system comprises a medical image database, a target patient basic parameter acquisition module, a target patient basic parameter analysis module, a target diagnosis hospital analysis module, a diagnostician matching analysis module, a target patient medical image acquisition and analysis module and a medical image data sharing module.
The system comprises a target patient basic parameter acquisition module, a target patient basic parameter analysis module, a target diagnosis hospital analysis module, a diagnostician matching analysis module, a medical image data sharing module, a medical image database, a target patient medical image acquisition and analysis module and a medical image data sharing module, wherein the target patient basic parameter acquisition module is connected with the target patient basic parameter analysis module, the target patient basic parameter analysis module is connected with the target diagnosis hospital analysis module, the diagnostician matching analysis module is connected with the medical image data sharing module, the medical image database is respectively connected with the target patient basic parameter analysis module and the target diagnosis hospital analysis module, and the target patient medical image acquisition and analysis module is respectively connected with the target patient basic parameter analysis module and the medical image data sharing module.
The medical image database is used for storing medical image treatment data of each patient corresponding to each disease condition name at each body part of each diagnosis hospital and storing the number of medical patients belonging to each medical department of each diagnosis hospital.
The target patient basic parameter acquisition module is used for acquiring basic parameters of a target patient.
Specifically, the acquisition of basic parameters of a target patient is performed, wherein the basic parameters include: name, age, sex, height, weight, the affected part and the name of the disease condition.
Illustratively, the disease condition name is: fracture, headache, abdominal pain, etc.
The target patient basic parameter analysis module is used for analyzing basic parameters of a target patient, and then matching and screening out each target diagnosis hospital.
Specifically, the analysis of the basic parameters of the target patient includes the following specific analysis processes: recording the current diseased body part of the target patient as a target treatment body part, further extracting the name of the target treatment body part, recording the disease condition name of the target patient as a target treatment disease condition name, and further extracting each medical image treatment data of the target patient corresponding to the target treatment disease condition at the target treatment body part of each diagnosis hospital.
And according to the name of the target treatment body part and the name of the target treatment illness state, matching the name of the target treatment illness state with each medical image treatment data of each illness state name corresponding to each body part of each patient belonging to each diagnosis hospital stored in the medical image database, and further acquiring each medical image treatment data of each patient corresponding to the target treatment illness state name of each target treatment body part of each diagnosis hospital.
According to the medical image treatment data of each patient corresponding to the target treatment disease name at the target treatment body part of each diagnosis hospital, extracting the basic information corresponding to each patient from the medical image treatment data, wherein the basic information comprises: name, gender, age, height and weight.
It should be noted that the medical image treatment data includes the medical image and the electronic medical record of each patient, and the electronic medical record includes basic information such as name, sex, age, height, weight, and the like.
And matching the sex of the target patient with the sex of each patient, further screening out each patient corresponding to the sex of the target patient, and recording the patient as each reference fitting patient.
The age, the height and the weight of the target patient are respectively compared with the age, the height and the weight of each reference adaptive patient, and the physical condition matching index of the target patient and each reference adaptive patient is calculated, wherein the calculation formula is as follows:
Figure BDA0003864034260000121
in which α is ST i Expressed as the condition match index, NL, of the target patient to the ith reference fitting patient 0 、SG 0 And TZ 0 Expressed as age, height and weight, nl, respectively, of the target patient i 、sg i And tz i Respectively expressed as age, height and weight, delta, of the ith reference fitting patient 1 、δ 2 And delta 3 Expressed as matching correction factors for preset age, height and weight, respectively, i is expressed as the number of each reference fitting patient, i =1,2.
Further, each target diagnosis hospital is screened out in the matching way, and the specific screening process is as follows: and comparing the target patient with the set matching index threshold value of the fitting physical condition according to the physical condition matching indexes of the target patient and the reference fitting patients, and if the physical condition matching indexes of the target patient and a certain reference fitting patient are within the range of the matching index threshold value of the fitting physical condition, marking the reference fitting patient as the target reference fitting patient, and counting the target reference fitting patients.
And extracting the name of each target reference fitting patient, extracting the medical image treatment data of each target reference fitting patient corresponding to the name of the target treatment illness state at the target treatment body part of each diagnosis hospital, acquiring each diagnosis hospital of each target reference fitting patient, and marking the diagnosis hospitals as each target diagnosis hospital.
The target diagnosis hospital analysis module is used for analyzing each target diagnosis hospital and further screening out adaptive diagnosis hospitals.
Specifically, the analysis of each target diagnosis hospital comprises the following specific processes: and extracting the corresponding name of each target diagnosis hospital, further matching the name with the medical patient number of each medical department of each diagnosis hospital stored in the medical image database, and extracting the medical patient number of each medical department of each target diagnosis hospital.
And matching the name of the target treatment body part of the target patient and the name of the target treatment illness state with medical departments corresponding to various illness state names of various set body parts to obtain the medical department corresponding to the target patient, and recording the medical department as the target medical department.
For example, the name of the target treatment body part of the target patient and the name of the target treatment disease are matched with medical departments corresponding to various disease names of the various set body parts, and if the name of the target treatment body part of the target patient is the calf and the name of the disease is fracture, the medical department corresponding to the target patient is an orthopedics department.
Extracting the number of medical patients to which the target medical departments of the target diagnosis hospitals belong, and further calculating the matching index of the target diagnosis hospitals, wherein the calculation formula is as follows:
Figure BDA0003864034260000131
wherein epsilon RC j Expressed as the matching index, η, of the jth target diagnostic hospital j The number of medical patients to which the target medical department of the jth target diagnosis hospital belongs is represented, e is represented by a natural constant, j is represented by the number of each target diagnosis hospital, and j =1,2.
Target medical department medical doctor based on each target diagnosis hospitalThe patient treatment times are further extracted, the treatment parameters of the medical patients are further extracted, the treatment parameters comprise treatment duration, treatment cost and medical image quantity, the average treatment duration, the average treatment cost and the average medical image quantity of the medical patients belonging to the target medical departments of the target diagnosis hospitals are further obtained, the medical matching index of the target diagnosis hospitals is calculated according to the average treatment duration, the average treatment cost and the average medical image quantity, and the medical matching index is recorded as mu YL j In which μ YL j Expressed as the medical match index for the jth target diagnostic hospital.
It should be noted that the medical matching index calculation formula of each target diagnosis hospital is as follows:
Figure BDA0003864034260000141
in which μ YL j Medical matching index expressed as jth target diagnosis hospital, where T j m 、M j m And S j m Respectively expressed as the treatment duration, treatment cost and the number of medical images of the mth medical patient to which the target medical department of the jth target diagnosis hospital belongs 1 j 、τ 2 j And τ 3 j Respectively expressed as the average treatment time, the average treatment cost and the average medical image number of the medical patients belonging to the target medical department of the jth target diagnosis hospital, wherein m is the number of each medical patient, m =1,2, · v, v is the number of the medical patients, and χ 1 、χ 2 Hexix- 3 Respectively expressed as the matching weight ratio corresponding to the preset treatment duration, treatment cost and medical image quantity.
It should be noted that, the specific extraction of the treatment parameters of each medical patient is a discharge list and a medical expense detailed list of each patient in the hospital system background.
Based on the matching index of each target diagnosis hospital and the medical matching index of each target diagnosis hospital, the comprehensive adaptation index of each target diagnosis hospital is further calculated comprehensively, and the calculation formula is as follows:
Figure BDA0003864034260000151
wherein
Figure BDA0003864034260000152
Expressed as the composite fit index for the jth target diagnostic hospital.
Further, the screening adaptive diagnosis hospital has the specific screening process that: and based on the comprehensive adaptation indexes of the target diagnosis hospitals, sequencing the comprehensive adaptation indexes of the target diagnosis hospitals from large to small, extracting the target diagnosis hospital with the first ranking of the comprehensive adaptation indexes, and recording the target diagnosis hospital as the adaptation diagnosis hospital.
The diagnostician matching analysis module is used for performing matching analysis on each diagnostician so as to screen out adaptive diagnosticians.
Specifically, the matching analysis is performed for each diagnostician, and the specific process is as follows: extracting each diagnostician corresponding to a target medical department to which the adaptive diagnosis hospital belongs, and further extracting the practitioner parameters of each diagnostician, wherein the practitioner parameters comprise: calculating the adaptation indexes corresponding to the diagnosticians according to the working duration, the job title grades and the diagnosis times, wherein the calculation formula is as follows:
Figure BDA0003864034260000153
where σ is YS p Expressed as the fit index, Δ SC, for the pth diagnostician p 、ΔDJ p And Δ RC p Respectively expressed as the working duration, the job title grade and the number of diagnosticians of the p-th diagnostician, p is the number of each diagnostician, p =1,2 1 、Φ 2 And phi 3 And the adaptive weight factors are respectively expressed as the preset adaptation weight factors corresponding to the working duration, the job title grade and the number of diagnosticians of the diagnostician.
It should be noted that, the extracted working parameters of each diagnostician are specifically extracted from a system background of a medical department where each diagnostician is located, and meanwhile, the job title grades include positive high, secondary high, intermediate level and primary level, and the corresponding specific grade values are: four, three, two and one.
It should be noted that, the screening of the adaptive diagnostician specifically includes the following steps: and based on the adaptation indexes corresponding to the diagnosticians, sequencing the adaptation indexes corresponding to the diagnosticians in sequence from large to small to obtain the arrangement sequence of the adaptation indexes corresponding to the diagnosticians, extracting the diagnostician to which the adaptation index with the first rank belongs, and recording the diagnostician as the adaptation diagnostician.
In a specific embodiment, through carrying out acquisition and analysis to the basic parameter of target patient according to, and then the matching is selected and is diagnosed the hospital, and carry out matching analysis to each diagnostician, and then select adaptation diagnostician, it lacks the limitation of carrying out the pertinence analysis to diagnostician and diagnostician in the earlier stage to have remedied the diagnosis at the patient, pertinence analysis level is higher, and has systematicness, can select adaptation diagnostician and adaptation diagnostician according to patient's actual state of an illness, and then can provide the reliability reference basis for patient's treatment of seeking medical advice, patient's the level of treating of seeking medical advice has been promoted to a great extent.
The target patient medical image acquisition and analysis module is used for acquiring and analyzing the target patient medical image.
Specifically, the acquisition and analysis of the medical image of the target patient includes the following specific processes: based on the medical image treatment data of the target treatment body part corresponding to the target treatment disease name of each target reference adaptive patient in each diagnosis hospital, extracting each medical image of the target treatment body part corresponding to the target treatment disease name of each target reference adaptive patient in each diagnosis hospital, and recording the medical image as each reference medical image.
And acquiring a medical image of the target treatment body part of the target patient, further acquiring the medical image to which the target treatment body part of the target patient belongs, and recording the medical image as a target diagnosis medical image.
Arranging detection points of each reference medical image in a systematic sampling point arrangement mode to obtain each detection point corresponding to each reference medical image, and further extracting each detection point corresponding to each reference medical imageSimilarly, the gray value to which each detection point corresponding to the target diagnostic medical image belongs is extracted, and the gray similarity index corresponding to the target diagnostic medical image and each reference medical image is calculated, wherein the calculation formula is as follows:
Figure BDA0003864034260000171
wherein omega HD f Expressed as a gray scale similarity index corresponding to the target diagnostic medical image and the f-th reference medical image,
Figure BDA0003864034260000172
expressed as a preset gray scale tolerance value, beta r f Expressed as the gray value phi of the r-th detection point corresponding to the f-th reference medical image r Representing the gray value of the r-th detection point corresponding to the target diagnosis medical image, f representing the number of each reference medical image, f =1,2,. The.. G, r representing the number of each detection point, r =1,2,. The.. T, t representing the number of detection points, theta 0 And is expressed as a preset gray scale correction factor corresponding to the medical image.
It should be noted that the specific process of performing detection point layout in the systematic sampling point layout manner includes: dividing the reference medical image into grids with equal size at distance intervals of 40mm and 40mm, and taking the intersection point and the central point of each grid line as a detection point.
In an embodiment of the present invention, the medical image includes: CT, X-ray, and nuclear magnetic resonance, etc., all of which have the common image characteristic of being grayscale images.
Based on each reference medical image, extracting the outline contour of the human body part to which each reference medical image belongs from the reference medical images, extracting the outline contour area of the human body part to which each reference medical image belongs, similarly, extracting the outline contour of the human body part to which the target diagnosis medical image belongs, further performing superposition comparison on the outline contour of the human body part to which the target diagnosis medical image belongs and the outline contour of the human body part to which each reference medical image belongs, extracting the overlapped outline contour areas of the human body parts, and calculating the outer parts of the human body parts corresponding to the target diagnosis medical image and each reference medical image according to the superposed outline contour areas of the human body partsThe shape and contour similarity index is calculated by the following formula:
Figure BDA0003864034260000181
in which ξ MJ f Is expressed as the contour similarity index of the body part corresponding to the target diagnosis medical image and the f-th reference medical image, S Heavy load f Is expressed as the area of the outline of the coincidence of the target diagnostic medical image and the part of the human body to which the f-th reference medical image belongs, S min Is expressed as the minimum overlapping area of the preset similar outline.
Based on the gray level similarity index corresponding to the target diagnosis medical image and each reference medical image and the outline similarity index of the human body part corresponding to the target diagnosis medical image and each reference medical image, further calculating the comprehensive similarity index corresponding to the target diagnosis medical image and each reference medical image, wherein the calculation formula is as follows:
Figure BDA0003864034260000182
wherein psi f Expressed as a composite similarity index corresponding to the target diagnostic medical image and the f-th reference medical image, a 1 And a 2 Respectively expressed as the corresponding similar weight ratio of the gray scale of the preset medical image and the outline of the human body part.
The medical image data sharing module is used for sharing medical image treatment data.
Specifically, the sharing of medical image treatment data includes the following specific processes: and based on the comprehensive similarity indexes corresponding to the target diagnosis medical image and the reference medical images, further extracting the reference medical image corresponding to the maximum value of the comprehensive similarity indexes, extracting the target reference adaptive patient to which the reference medical image belongs, further extracting the medical image treatment data of the target reference adaptive patient to which the reference medical image belongs, and sharing the medical image treatment data to an adaptive diagnostician.
And sharing the medical image treatment data of the target patient corresponding to the target treatment illness state of the target treatment body part of each diagnosis hospital to the adaptive diagnostician.
It should be noted that, the above sharing the medical image treatment data to the adaptive diagnostician includes the following specific sharing processes: and sharing the medical image treatment data to a PC receiving end of an adaptive diagnostician through transmission.
In a specific embodiment, the matching indexes of the body conditions of the target patient and the reference adaptive patients are evaluated, the target reference adaptive patients are obtained through screening, the reference medical images corresponding to the target reference adaptive patients are extracted according to the target treatment body part and the target treatment disease name of the target patient, the comprehensive similarity indexes corresponding to the target diagnosis medical images and the reference medical images are evaluated, the medical image treatment data of the target reference adaptive patients corresponding to the reference medical images corresponding to the maximum value of the comprehensive similarity indexes are extracted and shared to the adaptive diagnostician, a reliable diagnosis reference basis can be provided for the adaptive diagnostician, and the higher diagnosis and treatment level of the target patient can be further achieved through combination with the adaptive diagnostician, the body guarantee of the target patient is greatly improved, and the diagnosis pressure of the diagnostician is relieved.
In the embodiment of the invention, by providing the medical image data sharing management system based on the feature recognition, the medical image treatment data of the target patient in each diagnosis hospital can be stored, and then the medical image treatment data can be shared to the diagnostician when the target patient is subjected to medical diagnosis, so that the defect that the patient carries a plurality of medical images to form a film when the patient is subjected to medical diagnosis is effectively overcome, the intelligent level is improved, the condition that the patient loses or forgets to carry the medical images to form a film is avoided, not only can a reliable diagnosis and treatment basis be provided for the doctor, but also the medical diagnosis and treatment progress of the patient is improved to a greater extent, and the physical health of the patient is effectively guaranteed.
The foregoing is merely illustrative and explanatory of the present invention and various modifications, additions or substitutions may be made to the specific embodiments described by those skilled in the art without departing from the scope of the invention as defined in the accompanying claims.

Claims (9)

1. A medical image data sharing management system based on feature recognition is characterized by comprising: the system comprises a medical image database, a target patient basic parameter acquisition module, a target patient basic parameter analysis module, a target diagnosis hospital analysis module, a diagnostician matching analysis module, a target patient medical image acquisition and analysis module and a medical image data sharing module;
the medical image database is used for storing medical image treatment data of each patient corresponding to each disease condition name at each body part of each diagnosis hospital and storing the number of medical patients belonging to each medical department of each diagnosis hospital;
the target patient basic parameter acquisition module is used for acquiring basic parameters of a target patient;
the target patient basic parameter analysis module is used for analyzing basic parameters of a target patient so as to match and screen out each target diagnosis hospital;
the target diagnosis hospital analysis module is used for analyzing each target diagnosis hospital so as to screen out the adaptive diagnosis hospital;
the diagnostician matching analysis module is used for performing matching analysis on each diagnostician so as to screen out a suitable diagnostician;
the target patient medical image acquisition and analysis module is used for acquiring and analyzing a target patient medical image;
the medical image data sharing module is used for sharing medical image treatment data.
2. The medical image data sharing management system based on feature recognition as claimed in claim 1, wherein: the acquisition of basic parameters of a target patient is carried out, wherein the basic parameters comprise: name, age, sex, height, weight, the affected part and the name of the disease condition.
3. The medical image data sharing management system based on feature recognition as claimed in claim 2, wherein: the basic parameters of the target patient are analyzed, and the specific analysis process comprises the following steps:
recording the body part of the target patient with the disease as a target treatment body part, further extracting the name of the target treatment body part, recording the disease name of the target patient as a target treatment disease name, and further extracting each medical image treatment data of the target patient corresponding to the target treatment disease at the target treatment body part of each diagnosis hospital;
according to the name of the target treatment body part and the name of the target treatment illness state, matching the name of the target treatment illness state with each medical image treatment data of each illness state name corresponding to each body part of each patient belonging to each diagnosis hospital stored in a medical image database, and further acquiring each medical image treatment data of each patient corresponding to the target treatment illness state name of each target treatment body part of each diagnosis hospital;
according to the medical image treatment data of each patient corresponding to the target treatment disease name at the target treatment body part of each diagnosis hospital, extracting the basic information corresponding to each patient from the medical image treatment data, wherein the basic information comprises: name, sex, age, height and weight;
matching the sex of the target patient with the sex of each patient, further screening out each patient corresponding to the sex of the target patient, and recording the patient as each reference fitting patient;
the age, the height and the weight of the target patient are respectively compared with the age, the height and the weight of each reference adaptive patient, and the physical condition matching index of the target patient and each reference adaptive patient is calculated, wherein the calculation formula is as follows:
Figure FDA0003864034250000021
Figure FDA0003864034250000031
wherein alpha is ST i Is expressed as a physical condition matching index, NL, of the target patient to the i-th reference fitting patient 0 、SG 0 And TZ 0 Expressed as age, height and weight, nl, respectively, of the target patient i 、sg i And tz i Respectively expressed as age, height and weight, delta, of the ith reference fitting patient 1 、δ 2 And delta 3 Expressed as matching correction factors for preset age, height and weight, respectively, i is expressed as the number of each reference fitting patient, i =1,2.
4. The medical image data sharing management system based on feature recognition as claimed in claim 3, wherein: the matching screening of each target diagnosis hospital comprises the following specific screening processes:
according to the body condition matching indexes of the target patient and each reference adaptive patient, comparing the target patient with a set adaptive body condition matching index threshold, if the body condition matching indexes of the target patient and a certain reference adaptive patient are in the range of the adaptive body condition matching index threshold, marking the reference adaptive patient as a target reference adaptive patient, and further counting each target reference adaptive patient;
and extracting the name of each target reference adaptive patient, screening each diagnosis hospital of each target reference adaptive patient, and marking the diagnosis hospitals as each target diagnosis hospital.
5. The medical image data sharing management system based on feature recognition as claimed in claim 1, wherein: the specific process of analyzing each target diagnosis hospital is as follows:
extracting the corresponding name of each target diagnosis hospital, further matching the name with the number of medical patients belonging to each medical department of each diagnosis hospital stored in the medical image database, and extracting the number of medical patients belonging to each medical department of each target diagnosis hospital;
matching the name of the target treatment body part of the target patient and the name of the target treatment illness state with medical departments corresponding to various illness state names of various set body parts to obtain the medical department corresponding to the target patient, and marking the medical department as the target medical department;
extracting the number of medical patients to which the target medical departments of the target diagnosis hospitals belong, and further calculating the matching index of the target diagnosis hospitals, wherein the calculation formula is as follows:
Figure FDA0003864034250000041
wherein epsilon RC j Expressed as the matching index, η, of the jth target diagnostic hospital j The number of medical patients belonging to a target medical department of the jth target diagnosis hospital is represented, e is represented as a natural constant, j is represented as the number of each target diagnosis hospital, and j =1,2.
Based on the times of the medical patients belonging to the target medical departments of the target diagnosis hospitals, extracting treatment parameters of the medical patients, wherein the treatment parameters comprise treatment duration, treatment cost and medical image quantity, further obtaining average treatment duration, average treatment cost and average medical image quantity of the medical patients belonging to the target medical departments of the target diagnosis hospitals, calculating medical matching indexes of the target diagnosis hospitals according to the average treatment duration, average treatment cost and average medical image quantity, and recording the medical matching indexes as mu YL j In which μ YL j A medical match index expressed as the jth target diagnostic hospital;
based on the matching index of each target diagnosis hospital and the medical matching index of each target diagnosis hospital, the comprehensive adaptation index of each target diagnosis hospital is further calculated comprehensively, and the calculation formula is as follows:
Figure FDA0003864034250000042
wherein
Figure FDA0003864034250000043
Expressed as the composite fit index for the jth target diagnostic hospital.
6. The medical image data sharing management system based on feature recognition as claimed in claim 5, wherein: the screening adaptive diagnosis hospital has the specific screening process that:
and based on the comprehensive adaptation indexes of the target diagnosis hospitals, sequencing the comprehensive adaptation indexes of the target diagnosis hospitals from large to small, extracting the target diagnosis hospital with the first ranking of the comprehensive adaptation indexes, and recording the target diagnosis hospital as the adaptation diagnosis hospital.
7. The medical image data sharing management system based on feature recognition as claimed in claim 6, wherein: the specific process of performing matching analysis on each diagnostician is as follows:
extracting each diagnostician corresponding to a target medical department to which the adaptive diagnosis hospital belongs, and further extracting the practitioner parameters of each diagnostician, wherein the practitioner parameters comprise: calculating the adaptation indexes corresponding to the diagnosticians according to the working duration, the job title grades and the diagnosis times, wherein the calculation formula is as follows:
Figure FDA0003864034250000051
Figure FDA0003864034250000052
wherein sigma YS p Expressed as the fit index, Δ SC, corresponding to the p-th diagnostician p 、ΔDJ p And Δ RC p Respectively expressed as the working duration, the job title grade and the number of diagnosticians of the p-th diagnostician, p is the number of each diagnostician, p =1,2 1 、Φ 2 And phi 3 And the adaptive weight factors are respectively expressed as preset adaptation time length, job title grade and diagnosis person number of the diagnostician.
8. The medical image data sharing management system based on feature recognition as claimed in claim 1, wherein: the method for acquiring and analyzing the medical image of the target patient comprises the following specific processes:
based on the medical image treatment data of each target reference adaptive patient corresponding to the target treatment disease name at the target treatment body part of each diagnosis hospital, extracting each medical image of each target reference adaptive patient corresponding to the target treatment disease name at the target treatment body part of each diagnosis hospital, and recording the medical image as each reference medical image;
acquiring a medical image of a target treatment body part of a target patient, further acquiring a medical image of the target treatment body part of the target patient, and recording the medical image as a target diagnosis medical image;
the detection points of each reference medical image are distributed in a systematic sampling point distribution mode, each detection point corresponding to each reference medical image is obtained, the gray value of each detection point corresponding to each reference medical image is further extracted, similarly, the gray value of each detection point corresponding to the target diagnosis medical image is extracted, the gray similarity index corresponding to the target diagnosis medical image and each reference medical image is calculated, and the calculation formula is as follows:
Figure FDA0003864034250000061
wherein ω is HD f Expressed as a gray scale similarity index corresponding to the target diagnostic medical image and the f-th reference medical image,
Figure FDA0003864034250000062
expressed as a preset gray scale tolerance value, beta r f Expressed as the gray value phi of the r-th detection point corresponding to the f-th reference medical image r Representing the gray value of the r-th detection point corresponding to the target diagnosis medical image, f representing the number of each reference medical image, f =1,2,. The.. G, r representing the number of each detection point, r =1,2,. The.. T, t representing the number of detection points, theta 0 "represents a gray scale correction factor corresponding to the preset medical image;
based on each reference medical image, extracting the outline of the human body part to which each reference medical image belongs and extracting the outline area of the human body part to which each reference medical image belongs, and similarly, extracting the outline of the human body part to which the target diagnosis medical image belongs, and further combining the outline of the human body part to which the target diagnosis medical image belongs and the outline of the human body part to which each reference medical image belongsThe outline of the human body part is overlapped and compared, the overlapped outline area of the human body part is extracted, and the outline similarity index of the human body part corresponding to the target diagnosis medical image and each reference medical image is calculated according to the formula:
Figure FDA0003864034250000071
in which ξ MJ f Is expressed as the contour similarity index of the body part corresponding to the target diagnosis medical image and the f-th reference medical image, S Heavy load f Is expressed as the area of the outline of the coincidence of the target diagnostic medical image and the part of the human body to which the f-th reference medical image belongs, S min Representing the minimum overlapping area of the preset similar outline profile;
based on the gray level similarity index corresponding to the target diagnosis medical image and each reference medical image and the outline similarity index of the human body part corresponding to the target diagnosis medical image and each reference medical image, further calculating the comprehensive similarity index corresponding to the target diagnosis medical image and each reference medical image, wherein the calculation formula is as follows:
Figure FDA0003864034250000072
wherein psi f Expressed as a composite similarity index corresponding to the target diagnostic medical image and the f-th reference medical image, a 1 And a 2 Respectively expressed as the corresponding similar weight ratio of the gray scale of the preset medical image and the outline of the human body part.
9. The medical image data sharing management system based on feature recognition as claimed in claim 1, wherein: the medical image treatment data is shared, and the specific process comprises the following steps:
based on the comprehensive similarity indexes corresponding to the target diagnosis medical image and the reference medical images, further extracting the reference medical image corresponding to the maximum value of the comprehensive similarity indexes, extracting a target reference adaptive patient to which the reference medical image belongs, further extracting medical image treatment data of the target reference adaptive patient to which the reference medical image belongs, and sharing the medical image treatment data to an adaptive diagnosis doctor;
and sharing the medical image treatment data of the target patient corresponding to the target treatment illness state at the target treatment body part of each diagnosis hospital to the adaptive diagnostician.
CN202211175280.0A 2022-09-26 2022-09-26 Medical image data sharing management system based on feature recognition Pending CN115565660A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211175280.0A CN115565660A (en) 2022-09-26 2022-09-26 Medical image data sharing management system based on feature recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211175280.0A CN115565660A (en) 2022-09-26 2022-09-26 Medical image data sharing management system based on feature recognition

Publications (1)

Publication Number Publication Date
CN115565660A true CN115565660A (en) 2023-01-03

Family

ID=84743674

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211175280.0A Pending CN115565660A (en) 2022-09-26 2022-09-26 Medical image data sharing management system based on feature recognition

Country Status (1)

Country Link
CN (1) CN115565660A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116313025A (en) * 2023-03-14 2023-06-23 上海光声制药有限公司 Intelligent management system for operation data of laser photodynamic therapeutic instrument
CN117312963A (en) * 2023-11-29 2023-12-29 山东企联信息技术股份有限公司 Intelligent classification method, system and storage medium for acquired information data

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116313025A (en) * 2023-03-14 2023-06-23 上海光声制药有限公司 Intelligent management system for operation data of laser photodynamic therapeutic instrument
CN116313025B (en) * 2023-03-14 2023-12-12 上海光声制药有限公司 Intelligent management system for operation data of laser photodynamic therapeutic instrument
CN117312963A (en) * 2023-11-29 2023-12-29 山东企联信息技术股份有限公司 Intelligent classification method, system and storage medium for acquired information data
CN117312963B (en) * 2023-11-29 2024-03-12 山东企联信息技术股份有限公司 Intelligent classification method, system and storage medium for acquired information data

Similar Documents

Publication Publication Date Title
CN115565660A (en) Medical image data sharing management system based on feature recognition
US10854339B2 (en) Systems and methods for associating medical images with a patient
US20200315518A1 (en) Apparatus for processing data for predicting dementia through machine learning, method thereof, and recording medium storing the same
CN108389626A (en) Cerebral apoplexy screening method based on artificial intelligence and system
KR20190132290A (en) Method, server and program of learning a patient diagnosis
CN110025312B (en) Method and system for predicting curative effect of herpetic neuralgia based on structural magnetic resonance
Salem et al. A case based expert system for supporting diagnosis of heart diseases
CN115714022A (en) Neonatal jaundice health management system based on artificial intelligence
CN112562860A (en) Training method and device of classification model and coronary heart disease auxiliary screening method and device
US8331635B2 (en) Cartesian human morpho-informatic system
CN116386795A (en) Obstetrical rehabilitation data management method and system
CN115862819A (en) Medical image management method based on image processing
CN114220543B (en) Body and mind pain index evaluation method and system for tumor patient
CN111329467A (en) Heart disease auxiliary detection method based on artificial intelligence
CN116631558B (en) Construction method of medical detection project based on Internet
CN116864104A (en) Chronic thromboembolic pulmonary artery high-pressure risk classification system based on artificial intelligence
Tung et al. Multi-lead ECG classification via an information-based attention convolutional neural network
CN111276218A (en) Accurate diagnosis and treatment system, equipment and method
Diab et al. An unsupervised classification method of uterine electromyography signals: Classification for detection of preterm deliveries
CN113434692A (en) Method, system and equipment for constructing graph neural network model and recommending diagnosis and treatment scheme
CN113077893A (en) Intelligent assistive device adaptive decision making system and method
TW202143248A (en) System and method of biomedical data prediction risk including a data collection unit, a data processing unit and a judgment unit
CN111951219A (en) Thyroid eye disease screening method, system and equipment based on orbit CT image
CN115482914B (en) Medical image data processing method, device and storage medium
CN112336310B (en) FCBF and SVM fusion-based heart disease diagnosis system

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