CN116453692A - Ophthalmology disease risk assessment screening system - Google Patents
Ophthalmology disease risk assessment screening system Download PDFInfo
- Publication number
- CN116453692A CN116453692A CN202310247964.5A CN202310247964A CN116453692A CN 116453692 A CN116453692 A CN 116453692A CN 202310247964 A CN202310247964 A CN 202310247964A CN 116453692 A CN116453692 A CN 116453692A
- Authority
- CN
- China
- Prior art keywords
- fundus
- module
- image
- key
- 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.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 75
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 75
- 238000012216 screening Methods 0.000 title claims abstract description 66
- 238000012502 risk assessment Methods 0.000 title claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 70
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 13
- 230000006806 disease prevention Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 206010025482 malaise Diseases 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 9
- 210000001508 eye Anatomy 0.000 description 4
- 208000030533 eye disease Diseases 0.000 description 4
- 230000003902 lesion Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 208000031226 Hyperlipidaemia Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 210000000795 conjunctiva Anatomy 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 210000004561 lacrimal apparatus Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/12—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for looking at the eye fundus, e.g. ophthalmoscopes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/14—Arrangements specially adapted for eye photography
-
- 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
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
-
- 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
- G06T2207/30168—Image quality inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Ophthalmology & Optometry (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The utility model discloses an ophthalmology sickness risk assessment screening system in the technical field of risk assessment screening systems, which comprises a video acquisition module, a video acquisition module and a control module, wherein the video acquisition module is used for acquiring pre-assessed fundus video information; the video processing module is used for extracting a plurality of key fundus images in fundus video information; the image feature recognition module is used for comparing the numbered key fundus images with the reference fundus images respectively; an image feature processing module: the method comprises the steps of performing different operations according to a distinguishing place identified by a convolutional neural network, and outputting an evaluation fundus image; the primary evaluation screening module is used for outputting an ophthalmic disease risk result and accuracy thereof; and the secondary evaluation screening module is used for reevaluating the ophthalmic disease risk results with low accuracy. According to the utility model, the fundus image suitable for evaluation and screening is extracted by carrying out video acquisition on the fundus, so that the interference of inaccurate fundus image acquisition on the evaluation and screening result is reduced, and the accuracy of the evaluation and screening is improved.
Description
Technical Field
The utility model belongs to the technical field of risk assessment screening systems, and particularly relates to an ophthalmologic disease risk assessment screening system.
Background
Ophthalmic examinations are general examinations of the eye, including eye appendages and anterior segment examinations. Eye attachment examinations include examinations of the eyelid, conjunctiva, lacrimal apparatus, eyeball position, and orbit. The ophthalmic examination can evaluate and screen the risks of the ophthalmic diseases, and can evaluate and screen the risks of the diseases such as diabetes, hypertension, hyperlipidemia, cerebral apoplexy and the like based on the ophthalmic examination, thereby having positive effects on the physical health of people. However, the traditional ophthalmic examination, evaluation and screening mostly adopts a mode of manually evaluating and screening by doctors, the efficiency of the mode is limited, and the problem of inaccurate evaluation and screening is inevitably caused after the evaluation and screening doctors work for a long time.
To conclude the above problems, chinese patent, bulletin number: CN210167123U discloses a screening system for fundus image lesions, comprising: a storage module deployed in a cloud server; an acquisition module for acquiring more than two fundus images from different eyes of the same person and uploading the fundus images to a storage module; the input module is used for inputting the information of the checked person corresponding to the fundus image, correlating with the fundus image and uploading the information of the checked person to the storage module; and the screening module is used for extracting fundus images and examinee information from the storage module and automatically judging whether the related fundus images have lesions by using a deep learning method based on an artificial neural network so as to generate a screening result. According to the utility model, the deep learning method based on the artificial neural network can be used for assisting a doctor in judging the lesion recognition of the fundus image, so that the screening efficiency of the fundus image lesion can be effectively improved.
The technical scheme of the patent effectively solves the problem of low ophthalmology disease risk assessment screening efficiency, but fundus information adopts an image acquisition mode, and the fundus image is identified, so that the ophthalmology disease risk is assessed and screened; the fundus image acquisition process is easy to be interfered by external environment or the interference of a patient, so that the fundus image acquisition is inaccurate, and the problem of inaccurate evaluation and screening of ophthalmology disease risks is caused.
Disclosure of Invention
The utility model aims to provide an ophthalmologic disease risk assessment screening system which can acquire accurate fundus image information so as to reduce the influence of fundus images on the assessment screening of ophthalmologic disease risks.
In order to achieve the above object, the technical scheme of the present utility model is as follows:
an ophthalmology disease risk assessment screening system comprises a video acquisition module, a video processing module, an image feature recognition module, an image feature processing module, a primary assessment screening module and a secondary assessment screening module;
the video acquisition module is used for acquiring pre-estimated fundus video information;
the video processing module is used for randomly extracting a plurality of key fundus images in fundus video information and numbering the key fundus images (fundus image 1, fundus image 2, fundus image 3 … … fundus image n);
the image characteristic recognition module comprises a memory and a convolutional neural network after training, wherein the memory is used for storing reference preset fundus images, and the convolutional neural network is used for comparing the numbered key fundus images with the reference fundus images respectively and recognizing the areas of each numbered key fundus image and the reference fundus images;
the image feature processing module is used for carrying out definition evaluation on the key fundus image extracted by the video processing module by adopting a Tenengarad gradient method, judging whether a distinguishing position result output by the image feature recognition module is effective or not based on a definition evaluation result, carrying out video acquisition again if the definition evaluation result does not reach the standard, marking the distinguishing position if the definition evaluation result reaches the standard, and outputting and evaluating the fundus image after the operation;
the primary evaluation screening module is used for outputting a primary ophthalmology disease risk result according to the evaluation fundus image and outputting the accuracy of the primary ophthalmology disease risk result;
and the secondary evaluation screening module is used for manually evaluating and screening the ophthalmic diseased risk results with the accuracy lower than the threshold value and outputting secondary ophthalmic diseased risk results.
The technical principle of the scheme is as follows:
firstly, acquiring pre-estimated fundus video information through a video acquisition module; the method comprises the steps of extracting clear key fundus images in fundus videos through a video processing module, and numbering the key fundus images; sequentially comparing the numbered key fundus images with reference fundus images in a memory through a convolutional neural network, and identifying the areas of each key fundus image and the reference fundus images; re-performing fundus video acquisition on the key fundus images with the definition not reaching the standard through an image feature processing module, marking the distinguishing positions of the key fundus images with the definition reaching the standard, marking the distinguishing positions, and outputting and evaluating fundus images; outputting an ophthalmic diseased risk result and the accuracy of the ophthalmic diseased risk result according to the evaluation fundus image through a second convolutional neural network; and finally, manually reevaluating the ophthalmic diseased risk result with the accuracy lower than the threshold value through a secondary evaluation screening module, and outputting the ophthalmic diseased risk result.
The adoption of the scheme has the following beneficial effects:
1. compared with the prior art, the technical scheme has the advantages that the video acquisition is carried out on the fundus, the images suitable for evaluation screening are extracted from the video to evaluate and screen the eye diseases, and the interference of inaccurate fundus image acquisition on evaluation screening results in the evaluation and screening process of the eye diseases is reduced;
2. according to the technical scheme, a plurality of key fundus images are extracted from fundus video information, the definition evaluation is carried out on the key fundus images, and fundus images with the definition reaching the standard are used for evaluation screening, so that the accuracy of ophthalmology sickness evaluation screening is further improved;
3. according to the technical scheme, the ophthalmic disease risk result with low evaluation and screening accuracy of the second convolutional neural network is manually reevaluated and screened, and the accuracy of the ophthalmic disease evaluation and screening is improved while the labor cost is reduced by adopting a man-machine combination mode.
Further, the system also comprises a report generation module, wherein the report generation module is used for evaluating a primary ophthalmologic disease risk result or a secondary ophthalmologic disease risk result and outputting an ophthalmologic disease risk report.
The beneficial effects are that: the report generation module evaluates the primary ophthalmology disease risk result or the secondary ophthalmology disease risk result, so that a patient can intuitively know the basic ophthalmology disease risk condition, and then the ophthalmology disease risk detail condition is known through the ophthalmology disease risk report.
Further, the video acquisition module is a fundus camera.
The beneficial effects are that: the fundus camera acquires the fundus video, so that clearer video information of the fundus can be acquired.
Further, the key fundus image is extracted by an inter-frame difference method, and a plurality of images with larger image differences of the key frames are extracted as the key fundus image and numbered.
The beneficial effects are that: the method has the advantages that the inter-frame difference technology is adopted to extract the images of the key frames, the key frames are one frame of each key action of the video object, so that more different and effective key fundus images can be extracted, more areas can be compared later, and the accuracy of the subsequent ophthalmology disease assessment risk is improved.
Further, the reference fundus image is composed of a plurality of fundus images without risk of suffering from a disease.
The beneficial effects are that: the key fundus image can be compared with more different fundus images without the risk of suffering from the eye diseases, so that the contrast of the key fundus image is increased, and the interference of the reference fundus image on the result of the risk of suffering from the eye diseases is reduced.
Further, the fundus image is evaluated as the most clear and easily identifiable key fundus image at the distinguishing point.
The beneficial effects are that: the key fundus image with the clearest and easiest distinguishing part is used as the evaluation fundus image for evaluation screening, which is beneficial to the more accurate evaluation screening of the follow-up primary evaluation screening module and the secondary evaluation screening module.
Further, based on the definition evaluation results of the key fundus images, a mapping relation is formed between the accuracy of each definition evaluation result and the accuracy of the ophthalmic disease risk result, and the higher the definition evaluation result is, the higher the accuracy corresponding to the definition evaluation result is.
The beneficial effects are that: the higher the definition of the key fundus image at the area is, the more favorable the evaluation and screening are, the higher the accuracy of the ophthalmologic disease risk result is, the more favorable the evaluation and screening are, and the higher the accuracy of the ophthalmologic disease risk result is.
Further, ophthalmic disease risk reports include ophthalmic disease risk levels, ophthalmic disease conditions, and ophthalmic disease prevention regimens.
The beneficial effects are that: the ophthalmologic disease risk level can be expressed by a level, a score or a color, so that a patient can intuitively know the ophthalmologic disease condition; the ophthalmologic disease condition is convenient for the patient to know the ophthalmologic disease condition in detail after intuitively knowing the basic ophthalmologic disease condition; the ophthalmologic disease prevention scheme is convenient for patients to take countermeasures in time to reduce the occurrence probability of diseases.
Drawings
FIG. 1 is a flow chart of an embodiment of an ophthalmic disease risk assessment screening system of the present utility model;
FIG. 2 is a schematic diagram of an embodiment of an ophthalmic disease risk assessment screening system of the present utility model.
Detailed Description
The following is a further detailed description of the embodiments:
reference numerals in the drawings of the specification include: the system comprises a video acquisition module 1, a video processing module 2, an image feature recognition module 3, an image feature processing module 4, a primary evaluation screening module 5, a secondary evaluation screening module 6, a report generation module 7, a fundus camera 101, a memory 201, a convolutional neural network 202 and a human being 601.
An example is substantially as shown in figures 1 and 2: an ophthalmology disease risk assessment screening system comprises a video acquisition module 1, a video processing module 2, an image feature recognition module 3, an image feature processing module 4, a primary assessment screening module 5, a secondary assessment screening module 6 and a report generation module 7.
The video acquisition module 1 is a fundus camera 101 and is used for acquiring pre-estimated fundus video information.
The video processing module 2 is used for extracting images of three key frames in fundus video information through an inter-frame difference method, taking the images as key fundus images and numbering the key fundus images.
The image feature recognition module 3 comprises a memory 201 and a convolutional neural network 202 after training is completed, wherein the memory 201 is used for storing preset reference fundus images, and the reference fundus images consist of a plurality of fundus images without risk of illness; the convolutional neural network 202 is used for comparing the numbered key fundus images with the reference fundus image respectively, and identifying the difference between each numbered key fundus image and the reference fundus image.
The image feature processing module 4 is configured to perform sharpness evaluation on the key fundus image extracted by the video processing module 2 by using a teningrad gradient method, determine whether the difference result output by the image feature recognition module is valid based on the sharpness evaluation result, re-perform video acquisition if the sharpness evaluation result does not reach the standard, and perform circling marking on the difference if the sharpness evaluation result reaches the standard, and output the evaluation fundus image after the above operations.
The primary evaluation screening module 5 is used for outputting an ophthalmologic disease risk result according to the difference of the evaluation fundus image marked by the circling of the image feature processing module 4; and based on the definition evaluation results of the key fundus images, forming a mapping relation between the accuracy of each definition evaluation result and the accuracy of the ophthalmic disease risk result, so that the definition evaluation results and the accuracy of the ophthalmic disease risk result are in one-to-one correspondence, the higher the definition evaluation results are, the higher the corresponding accuracy is, and the accuracy is quantified in a percentage manner.
And the secondary evaluation screening module 6 is used for manually carrying out 601 evaluation screening on the ophthalmic disease risk results with the accuracy lower than 80 percent and re-outputting the ophthalmic disease risk results.
The report generation module 7 is used for evaluating the ophthalmic disease risk result and outputting an ophthalmic disease risk report, wherein the ophthalmic disease risk report comprises the ophthalmic disease risk grade, the ophthalmic disease condition and the ophthalmic disease prevention scheme.
The specific implementation process is as follows:
s1, fundus video acquisition, wherein the video acquisition module 1, namely the fundus camera 101, is used for acquiring pre-estimated fundus video information, and the length of the video is five seconds according to requirements.
S2, extracting key fundus images, namely extracting images of three key frames in fundus video information through an interframe difference method, wherein the three key frames have larger differences in fundus image content, and taking the three key frames as key fundus images and numbering the key fundus images as a fundus image (1), a fundus image (2) and a fundus image (3).
S3, feature identification, namely comparing the fundus image (1), the fundus image (2) and the fundus image (3) with a reference fundus image in the memory 201 sequentially through the convolutional neural network 202, and respectively identifying the fundus image (1), the fundus image (2) and the fundus image (3) from the reference fundus image.
S4, feature processing, namely marking the distinguishing part of the key fundus image with the qualified definition evaluation result in a circling way based on the definition evaluation result, and if the definition evaluation result does not reach the standard, re-performing fundus video acquisition, extracting the key fundus image and feature recognition steps.
S5, primarily evaluating, namely evaluating the fundus image through the convolutional neural network after training is completed, outputting a primary ophthalmology disease risk result, and outputting the accuracy of the primary ophthalmology disease risk result, and if the accuracy is less than 80%, performing S6, otherwise, directly performing S7.
S6, performing secondary evaluation, namely evaluating fundus images with accuracy less than 80% through manual work 601, and outputting a secondary ophthalmology disease risk result.
And S7, outputting a report, namely evaluating a primary ophthalmologic disease risk result or a secondary ophthalmologic disease risk result through the report generation module 7, and outputting an ophthalmologic disease risk report.
The foregoing is merely exemplary of the present utility model and the specific structures and/or characteristics of the present utility model that are well known in the art have not been described in detail herein. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present utility model, and these should also be considered as the scope of the present utility model, which does not affect the effect of the implementation of the present utility model and the utility of the patent. The protection scope of the present application shall be subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (8)
1. The ophthalmologic disease risk assessment screening system is characterized by comprising a video acquisition module, a video processing module, an image feature recognition module, an image feature processing module, a primary assessment screening module and a secondary assessment screening module;
the video acquisition module is used for acquiring pre-estimated fundus video information;
the video processing module is used for randomly extracting a plurality of key fundus images in fundus video information and numbering the key fundus images (fundus image 1, fundus image 2, fundus image 3 … … fundus image n);
the image characteristic recognition module comprises a memory and a convolutional neural network after training, wherein the memory is used for storing reference preset fundus images, and the convolutional neural network is used for comparing the numbered key fundus images with the reference fundus images respectively and recognizing the areas of each numbered key fundus image and the reference fundus images;
the image feature processing module is used for carrying out definition evaluation on the key fundus image extracted by the video processing module by adopting a Tenengarad gradient method, judging whether a distinguishing position result output by the image feature recognition module is effective or not based on a definition evaluation result, carrying out video acquisition again if the definition evaluation result does not reach the standard, marking the distinguishing position if the definition evaluation result reaches the standard, and outputting and evaluating the fundus image after the operation;
the primary evaluation screening module is used for outputting a primary ophthalmology disease risk result according to the evaluation fundus image and outputting the accuracy of the primary ophthalmology disease risk result;
and the secondary evaluation screening module is used for manually evaluating and screening the ophthalmic diseased risk results with the accuracy lower than the threshold value and outputting secondary ophthalmic diseased risk results.
2. The ophthalmic risk of developing disease assessment screening system of claim 1, wherein: the system also comprises a report generation module, wherein the report generation module is used for evaluating a primary ophthalmologic disease risk result or a secondary ophthalmologic disease risk result and outputting an ophthalmologic disease risk report.
3. The ophthalmic risk of developing disease assessment screening system of claim 2, wherein: the video acquisition module is a fundus camera.
4. The ophthalmic risk of developing disease assessment screening system of claim 3, wherein: the key fundus image is extracted by an interframe difference method, and a plurality of images with larger image differences are extracted as the key fundus image and numbered.
5. The ophthalmic disease risk assessment screening system of claim 4, wherein: the reference fundus image is composed of a plurality of fundus images without risk of illness.
6. The ophthalmic disease risk assessment screening system of claim 5, wherein: the evaluation fundus image is the key fundus image with the best definition evaluation result.
7. The ophthalmic disease risk assessment screening system of claim 6, wherein: and forming a mapping relation between the accuracy of each definition evaluation result and the accuracy of the ophthalmic disease risk result based on the definition evaluation result of the key fundus image, wherein the higher the definition evaluation result is, the higher the accuracy corresponding to the definition evaluation result is.
8. The ophthalmic disease risk assessment screening system of claim 7, wherein: the ophthalmic disease risk report includes ophthalmic disease risk level, ophthalmic disease condition, and ophthalmic disease prevention regimen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310247964.5A CN116453692A (en) | 2023-03-15 | 2023-03-15 | Ophthalmology disease risk assessment screening system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310247964.5A CN116453692A (en) | 2023-03-15 | 2023-03-15 | Ophthalmology disease risk assessment screening system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116453692A true CN116453692A (en) | 2023-07-18 |
Family
ID=87119221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310247964.5A Pending CN116453692A (en) | 2023-03-15 | 2023-03-15 | Ophthalmology disease risk assessment screening system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116453692A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095450A (en) * | 2023-10-20 | 2023-11-21 | 武汉大学人民医院（湖北省人民医院） | Eye dryness evaluation system based on images |
-
2023
- 2023-03-15 CN CN202310247964.5A patent/CN116453692A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095450A (en) * | 2023-10-20 | 2023-11-21 | 武汉大学人民医院（湖北省人民医院） | Eye dryness evaluation system based on images |
| CN117095450B (en) * | 2023-10-20 | 2024-01-09 | 武汉大学人民医院（湖北省人民医院） | Eye dryness evaluation system based on images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180235458A1 (en) | System and device for preliminary diagnosis of ocular diseases | |
| CN111310851A (en) | Artificial intelligence ultrasonic auxiliary system and application thereof | |
| CN111986211A (en) | Deep learning-based ophthalmic ultrasonic automatic screening method and system | |
| TWI719587B (en) | Pre-processing method and storage device for quantitative analysis of fundus image | |
| CN108416772A (en) | A kind of strabismus detection method based on concatenated convolutional neural network | |
| CN111785363A (en) | AI-guidance-based chronic disease auxiliary diagnosis system | |
| CN112233087A (en) | Artificial intelligence-based ophthalmic ultrasonic disease diagnosis method and system | |
| CN112950737B (en) | Fundus fluorescence contrast image generation method based on deep learning | |
| CN114694236B (en) | Eyeball motion segmentation positioning method based on cyclic residual convolution neural network | |
| TWI746287B (en) | Data storage system and data storage method | |
| CN116453692A (en) | Ophthalmology disease risk assessment screening system | |
| CN112446860B (en) | Automatic screening method for diabetic macular edema based on transfer learning | |
| CN112419248A (en) | Ear sclerosis focus detection and diagnosis system based on small target detection neural network | |
| CN112950577B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN110096978A (en) | The method of eccentricity cycles image procossing based on machine vision | |
| KR20110019992A (en) | Diagnosing system and method using iridology | |
| CN112102234B (en) | Ear sclerosis focus detection and diagnosis system based on target detection neural network | |
| CN102283634A (en) | Method and system for testing eye ground image based on image identification | |
| KR102208508B1 (en) | Systems and methods for performing complex ophthalmic tratment | |
| CN111588345A (en) | Eye disease detection method, AR glasses and readable storage medium | |
| CN113558564B (en) | Data processing system based on simple high myopia database construction | |
| CN114240934B (en) | Image data analysis method and system based on acromegaly | |
| CN113744254B (en) | Fundus image analysis method, fundus image analysis system, storage medium and computer equipment | |
| CN112991289B (en) | Processing method and device for standard section of image | |
| CN111259743B (en) | Training method and system for myopia image deep learning recognition model |
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 |