CN115036008A - Ophthalmology screening diagnosis and treatment system based on artificial intelligence - Google Patents

Ophthalmology screening diagnosis and treatment system based on artificial intelligence Download PDF

Info

Publication number
CN115036008A
CN115036008A CN202210722238.XA CN202210722238A CN115036008A CN 115036008 A CN115036008 A CN 115036008A CN 202210722238 A CN202210722238 A CN 202210722238A CN 115036008 A CN115036008 A CN 115036008A
Authority
CN
China
Prior art keywords
information
picture
cloud server
processor
screening
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.)
Withdrawn
Application number
CN202210722238.XA
Other languages
Chinese (zh)
Inventor
赵永吉
游志鹏
胡寒英
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.)
Affiliated Eye Hospital Of Nanchang University
Original Assignee
Affiliated Eye Hospital Of Nanchang University
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 Affiliated Eye Hospital Of Nanchang University filed Critical Affiliated Eye Hospital Of Nanchang University
Priority to CN202210722238.XA priority Critical patent/CN115036008A/en
Publication of CN115036008A publication Critical patent/CN115036008A/en
Withdrawn legal-status Critical Current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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • 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
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30041—Eye; Retina; Ophthalmic

Landscapes

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

Abstract

The invention discloses an artificial intelligence-based ophthalmic screening diagnosis and treatment system in the field of ophthalmic examination, which comprises a dynamic capture system for capturing eyeball rotation states, a camera for controlling photographing by using the dynamic capture system, an ultrasonic probe for scanning images and a processor for processing and judging data, wherein the processor is in signal connection with a cloud server for storing data. Utilize the camera to catch the movement of eyeball among this technical scheme and shoot to replace traditional ophthalmology inspection process doctor and utilize the detection of inspection flashlight to each direction of patient's crystalline lens, the shooting of photo provides the picture reference basis for the on-line consultation simultaneously.

Description

Ophthalmology screening diagnosis and treatment system based on artificial intelligence
Technical Field
The invention belongs to the field of ophthalmic examination, and particularly relates to an ophthalmic screening diagnosis and treatment system based on artificial intelligence.
Background
Accurate examination and diagnosis in ophthalmic diseases are a prerequisite and guarantee for correct and effective treatment, and common ophthalmic diseases such as keratitis, glaucoma, retinopathy, myopia and the like all need to be accurately diagnosed and examined, and after the condition of the disease is confirmed, reasonable treatment is carried out.
However, at the time of the application of the present invention, it is necessary to reduce unnecessary contact between doctors and patients as much as possible, when a patient is treated by an ophthalmic diagnosis and treatment in the prior art, since different patients have different ophthalmic diseases, when a clinician performs an ophthalmic disease examination, the clinician observes the lens or the blood vessel of the eye of the patient at multiple angles by using an examination lamp, thereby causing close contact, but for the disease detection, the rehabilitation method for each ophthalmic disease is different, and if no detailed consultation is performed, the difference of the treatment effect is obvious, which affects the health of the patient, so a system capable of providing an accurate consultation result on the premise that the clinician does not closely contact the patient is urgently provided in the market.
Disclosure of Invention
In order to solve the above problems, an object of the present invention is to provide an artificial intelligence-based ophthalmic screening medical system that provides accurate consultation results without a doctor coming into close contact with a patient.
In order to achieve the purpose, the technical scheme of the invention is as follows: an ophthalmic screening diagnosis and treatment system based on artificial intelligence comprises a dynamic capture system for capturing eyeball rotation states, a camera for controlling photographing by using the dynamic capture system, an ultrasonic probe for scanning images and a processor for processing and judging data, wherein the processor is in signal connection with a cloud server for storing data;
when the camera shoots, the position of the through hole in a natural state is marked as a central point, then the camera adjusts the brightness of the picture according to the distance from the eyeball to the central point, the picture is brightest when the eyeball is farthest away from the central point, and the whole picture is dark when the eyeball is closest to the central point;
the processor is provided with a signal receiving end and a signal transmission end, the signal receiving end respectively receives information shot by the camera, image information of the ultrasonic probe and return information of the cloud server, the signal transmission end is used for transmitting the information shot by the camera and the image information of the ultrasonic probe to the cloud server, a picture brightness screening function is arranged in the cloud server, pictures with brightness lower than a preset value are eliminated as useless pictures, the cloud server compares the pictures meeting brightness screening to match similar cases and returns the similar cases to the processor, and diagnosis is completed
Further, the signals compared by the processor include picture signals and text signals, and the processing of the picture signals includes:
selecting photos, screening according to the brightness of the photos, and removing the photos with the brightness lower than a preset value;
vectorizing the photos, namely vectorizing the shot photos and the photos returned by the cloud server;
step three, establishing a coordinate axis, marking the position of the through hole in a natural state as a central point, wherein the width of the crystalline lens is a Y axis, the length of the crystalline lens is an x axis, and the height of the crystalline lens is a z axis;
and step four, checking the picture, comparing the actually shot picture with the picture of the cloud server, wherein the comparison comprises vector comparison and color comparison, finding a vector picture with similar foreign body coordinates in the picture, and then comprehensively determining a plurality of cases to display by finding a picture with similar lens color.
The patient diagnosis system further comprises a storage module and a reading module, wherein the storage module is used for storing case information of each diagnosis of the patient and matched disease types, and the reading module is used for sending the information in the storage module to a specified storage medium.
The system further comprises a voice input device, the voice input device is used for inputting information of symptoms of the patient and transmitting the information to the processor, and the processor performs secondary screening according to the returned cloud server data and the symptom information.
Further, the system also comprises an output device, wherein the output device comprises a display screen used for displaying information after case matching.
Further, the comparison of the text signals comprises the steps of converting information input by the voice input device of the patient into text information, comparing the text information with case text information in the cloud server at the moment, and sorting the cases after the case collation picture with the most synonyms and the highest contact ratio is found again.
After the scheme is adopted, the following beneficial effects are realized: 1. according to the technical scheme, the camera is used for capturing the movement of the eyeballs to shoot, so that a traditional ophthalmology examination process is replaced, a doctor uses the examination flashlight to detect all directions of crystalline lenses of patients, and meanwhile, the shooting of pictures provides a picture reference basis for on-line consultation.
2. According to the technical scheme, all directions of the crystalline lens need to be detected, and in order to avoid missing data at a certain position in the capturing process of the camera, the camera is used for taking pictures in a contact mode, and useless pictures are removed through the brightness of the pictures.
3. According to the technical scheme, the artificial influence is reduced, the third-party interface data is utilized for comparison and sorting, the artificial consultation time is reduced, and the consultation efficiency is improved.
4. The screening process of the technology has three sections, wherein the first section is used for screening and removing useless information according to light, the second section is used for matching corresponding cases according to a coordinate system and colors, and the third section is used for screening cases, so that similar but irrelevant cases are removed according to character information to improve the accuracy.
Drawings
FIG. 1 is a schematic diagram of an embodiment of the present invention.
Detailed Description
The following is further detailed by way of specific embodiments:
the embodiment is basically as shown in the attached figure 1: an artificial intelligence-based ophthalmic screening diagnosis and treatment system comprises a dynamic capture system for capturing eyeball rotation states, a camera for controlling photographing by using the dynamic capture system, an ultrasonic probe for scanning images and a processor for processing and judging data, wherein the processor is in signal connection with a cloud server for storing data;
when the camera shoots, the position of the through hole in a natural state is marked as a central point, then the camera adjusts the brightness of the picture according to the distance from the eyeball to the central point, the picture is brightest when the eyeball is farthest away from the central point, and the whole picture is dark when the eyeball is closest to the central point;
the processor is provided with a signal receiving end and a signal transmission end, the signal receiving end receives information shot by the camera, image information of the ultrasonic probe and return information of the cloud server respectively, the signal transmission end is used for transmitting the information shot by the camera and the image information of the ultrasonic probe to the cloud server, a picture brightness screening function is arranged in the cloud server, pictures with brightness lower than a preset value are eliminated as useless pictures, and the cloud server compares the pictures meeting brightness screening to match similar cases and returns the similar cases to the processor to finish diagnosis.
The camera is used for capturing the movement of eyeballs to take a picture, so that the traditional ophthalmology examination process is replaced, a doctor uses an examination flashlight to detect all directions of crystalline lenses of a patient, and meanwhile, the picture taking provides a picture reference basis for on-line consultation. Because all directions of the crystalline lens need to be detected, in order to avoid missing data at a certain position in the capturing process of the camera, the camera is used for taking pictures in a contact mode, and useless pictures are removed through the brightness of the pictures.
The medical diagnosis system further comprises a storage module and a reading module, wherein the storage module is used for storing the case information of each diagnosis of the patient and the matched disease type, the reading module is used for sending the information in the storage module to a specified storage medium, the medical diagnosis system further comprises a voice input device, the voice input device is used for inputting the information of the disease of the patient and transmitting the information to the processor, and the processor performs secondary screening according to the returned cloud server data and the disease information.
The signal compared by the processor comprises a picture signal and a character signal, and the processing step of the picture signal comprises the following steps:
selecting photos, screening according to the brightness of the photos, and removing the photos with the brightness lower than a preset value;
vectorizing the photos, namely vectorizing the shot photos and the photos returned by the cloud server;
step three, establishing a coordinate axis, marking the position of the through hole in a natural state as a central point, wherein the width of the crystalline lens is an axis Y, the length of the crystalline lens is an axis x, and the height of the crystalline lens is an axis z;
and step four, checking the pictures, comparing the actually shot pictures with the pictures of the cloud server, wherein the comparison comprises vector comparison and color comparison, finding vector pictures with similar foreign body coordinates in the pictures, and then comprehensively determining a plurality of cases to display by finding the pictures with similar lens colors.
This technical scheme still includes output device, and output device is including the display screen that is used for the case to match the back display information, and the contrast of text signal is including turning into text information with the information that patient's voice input device types, compares text information and the case text information in the high in the clouds server this moment, finds that the most and case that the coincidence degree is the highest of synonym is sorted once more to the case after the picture proofreading.
The screening process of the technology has three sections, wherein the first section is used for screening and removing useless information according to light, the second section is used for matching corresponding cases according to a coordinate system and colors, and the third section is used for screening cases, so that similar but irrelevant cases are removed according to character information to improve the accuracy.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
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. The utility model provides an ophthalmology screening system of diagnosing based on artificial intelligence which characterized in that: the system comprises a dynamic capture system for capturing the rotation state of eyeballs, a camera for controlling photographing by using the dynamic capture system, an ultrasonic probe for scanning images and a processor for processing and judging data, wherein the processor is in signal connection with a cloud server for storing data;
when the camera shoots, the position of the through hole in a natural state is marked as a central point, then the camera adjusts the brightness of the picture according to the distance from the eyeball to the central point, the picture is brightest when the eyeball is farthest away from the central point, and the whole picture is dark when the eyeball is closest to the central point;
the processor is provided with a signal receiving end and a signal transmission end, the signal receiving end receives information shot by the camera, image information of the ultrasonic probe and return information of the cloud server respectively, the signal transmission end is used for transmitting the information shot by the camera and the image information of the ultrasonic probe to the cloud server, a picture brightness screening function is arranged in the cloud server, pictures with brightness lower than a preset value are removed as useless pictures, and the cloud server compares the pictures meeting brightness screening and returns matched similar cases to the processor to finish diagnosis.
2. The artificial intelligence based ophthalmic screening medical system of claim 1, wherein: the signal compared by the processor comprises a picture signal and a character signal, and the processing step of the picture signal comprises the following steps:
selecting photos, screening according to the brightness of the photos, and removing the photos with the brightness lower than a preset value;
vectorizing the photos, namely vectorizing the shot photos and the photos returned by the cloud server;
step three, establishing a coordinate axis, marking the position of the through hole in a natural state as a central point, wherein the width of the crystalline lens is a Y axis, the length of the crystalline lens is an x axis, and the height of the crystalline lens is a z axis;
and step four, checking the picture, comparing the actually shot picture with the picture of the cloud server, wherein the comparison comprises vector comparison and color comparison, finding a vector picture with similar foreign body coordinates in the picture, and then comprehensively determining a plurality of cases to display by finding a picture with similar lens color.
3. The artificial intelligence-based ophthalmic screening medical system of claim 2, wherein: the patient diagnosis system further comprises a storage module and a reading module, wherein the storage module is used for storing case information of each diagnosis of the patient and the matched disease type, and the reading module is used for sending the information in the storage module to a specified storage medium.
4. The artificial intelligence-based ophthalmic screening medical system of claim 2, wherein: the system also comprises a voice input device, wherein the voice input device is used for inputting the information of the symptoms of the patient and transmitting the information to the processor, and the processor performs secondary screening according to the returned cloud server data and the symptom information.
5. The artificial intelligence based ophthalmic screening medical system of claim 1, wherein: the medical record matching system further comprises an output device, wherein the output device comprises a display screen used for displaying information after case matching.
6. The artificial intelligence based ophthalmic screening medical system of claim 4, wherein: the comparison of the text signals comprises the steps of converting information input by the voice input device of the patient into text information, comparing the text information with case text information in the cloud server at the moment, and sorting the cases after the case is corrected by finding the case with the most synonyms and the highest contact ratio.
CN202210722238.XA 2022-06-24 2022-06-24 Ophthalmology screening diagnosis and treatment system based on artificial intelligence Withdrawn CN115036008A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210722238.XA CN115036008A (en) 2022-06-24 2022-06-24 Ophthalmology screening diagnosis and treatment system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210722238.XA CN115036008A (en) 2022-06-24 2022-06-24 Ophthalmology screening diagnosis and treatment system based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN115036008A true CN115036008A (en) 2022-09-09

Family

ID=83127530

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210722238.XA Withdrawn CN115036008A (en) 2022-06-24 2022-06-24 Ophthalmology screening diagnosis and treatment system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN115036008A (en)

Similar Documents

Publication Publication Date Title
WO2020259209A1 (en) Fundus image recognition method, apparatus and device, and storage medium
WO2021135557A1 (en) Artificial intelligence multi-mode imaging analysis apparatus
CN100511266C (en) Organism eye determining method and organism eye determining device
CN1486156A (en) System and method for eye screening
WO2020098038A1 (en) Pupil tracking image processing method
CN111986211A (en) Deep learning-based ophthalmic ultrasonic automatic screening method and system
CN114937024A (en) Image evaluation method and device and computer equipment
WO2020211174A1 (en) Machine vision-based method for processing eccentric photorefraction image
CN108009534A (en) Biopsy method based on pupil gray scale
CN117237711A (en) Bimodal fundus image classification method based on countermeasure learning
CN115359548B (en) Handheld intelligent pupil detection device and detection method
CN115036008A (en) Ophthalmology screening diagnosis and treatment system based on artificial intelligence
CN115456974A (en) Strabismus detection system, method, equipment and medium based on face key points
EP3695775B1 (en) Smartphone-based handheld optical device and method for capturing non-mydriatic retinal images
WO2021139446A1 (en) Anti-vascular endothelial growth factor (vegf) curative effect prediction apparatus and method
CN113744254A (en) Fundus image analysis method and system, storage medium and computer equipment
CN111539940A (en) Ultra-wide angle fundus image generation method and device
KR102473744B1 (en) A method of diagnosing strabismus through the analysis of eyeball image from cover and uncovered test
Hakeem et al. Inception V3 and CNN Approach to Classify Diabetic Retinopathy Disease
WO2020181267A1 (en) Diagnostic tool for eye disease detection
Sitienei Applying Artificial Intelligence and Mobile Technologies to Enable Practical Screening for Diabetic Retinopathy
Jahan et al. Detecting anomalies in human eyes using structural similarity index measurement
Khan et al. A Discriminative Colour-to-Grayscale Representation for Retinal Vessel Segmentation
Hacisoftaoglu Deep Learning Frameworks for Diabetic Retinopathy Detection Using Smartphone-Based Retinal Imaging Systems
Abay et al. Quality assessment of Low-cost retinal Videos for Glaucoma screening

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20220909