CN118507037B - Rapid dry eye detection method and device and electronic equipment - Google Patents
Rapid dry eye detection method and device and electronic equipment Download PDFInfo
- Publication number
- CN118507037B CN118507037B CN202410962437.7A CN202410962437A CN118507037B CN 118507037 B CN118507037 B CN 118507037B CN 202410962437 A CN202410962437 A CN 202410962437A CN 118507037 B CN118507037 B CN 118507037B
- Authority
- CN
- China
- Prior art keywords
- dry eye
- eye detection
- image
- user
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 171
- 208000003556 Dry Eye Syndromes Diseases 0.000 title claims abstract description 168
- 206010013774 Dry eye Diseases 0.000 title claims abstract description 168
- 238000004458 analytical method Methods 0.000 claims abstract description 69
- 238000012545 processing Methods 0.000 claims abstract description 67
- 238000007689 inspection Methods 0.000 claims abstract description 58
- 230000006870 function Effects 0.000 claims description 100
- 238000000034 method Methods 0.000 claims description 48
- 238000003384 imaging method Methods 0.000 claims description 28
- 238000005286 illumination Methods 0.000 claims description 24
- 239000003550 marker Substances 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 15
- 238000012634 optical imaging Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 12
- 210000000744 eyelid Anatomy 0.000 description 20
- 238000005259 measurement Methods 0.000 description 19
- 150000002632 lipids Chemical class 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 201000005111 ocular hyperemia Diseases 0.000 description 8
- 238000000605 extraction Methods 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 7
- 210000004175 meibomian gland Anatomy 0.000 description 6
- 230000004397 blinking Effects 0.000 description 5
- 210000003786 sclera Anatomy 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 210000004907 gland Anatomy 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 210000000795 conjunctiva Anatomy 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000002073 fluorescence micrograph Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011206 morphological examination Methods 0.000 description 1
- 230000028327 secretion Effects 0.000 description 1
- 208000024891 symptom Diseases 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
-
- 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
- A61B3/0016—Operational features thereof
- A61B3/0025—Operational features thereof characterised by electronic signal processing, e.g. eye models
-
- 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
- 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
- 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
- G06T2207/30—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)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Ophthalmology & Optometry (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Signal Processing (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Eye Examination Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a rapid dry eye detection method, a rapid dry eye detection device and electronic equipment, which relate to the technical field of medical detection and comprise the following steps: acquiring dry eye index selection information sent by a user side, wherein the index selection information comprises: the user side selects a target inspection item set from the preset inspection item sets; grouping the dry eye index selection information through a preset index analysis model, combining the index selection information meeting the same combining condition into the same function item, and determining a target function item set; and respectively acquiring user dry eye detection videos or user dry eye detection images corresponding to each target function item, and performing image data processing on the user dry eye detection videos or the user dry eye detection images by utilizing a data processing model corresponding to each inspection item in the target function items to determine a dry eye detection result. The invention can remarkably improve the accuracy and the detection efficiency of dry eye detection.
Description
Technical Field
The invention relates to the technical field of medical detection, in particular to a rapid dry eye detection method, a rapid dry eye detection device and electronic equipment.
Background
The traditional dry eye detection method comprises a smearing test, tear analysis, ocular surface morphological examination and the like, has certain limitation, mainly depends on the experience of doctors and is complex to operate, and at present, related technologies propose that the dry eye detection can be carried out based on optics, computer vision and artificial intelligence.
However, when the above scheme evaluates different dry eye indexes, the device needs to be adjusted repeatedly for a plurality of times to obtain good image data, the operation is complex, the detection efficiency is low, and inaccuracy of the image data can lead to larger deviation of analysis results, thereby affecting the accuracy of dry eye index evaluation, in addition, since the above scheme only can analyze a single index when shooting data each time, when a plurality of indexes need to be evaluated, shooting and analysis are needed for a plurality of times, and each shooting and analysis need to be matched with a patient again, so that doctors also need to wait and check analysis results after each shooting and carry out next shooting after confirming no errors, thereby increasing the detection time and reducing the dry eye detection efficiency.
Disclosure of Invention
In view of the above, the present invention aims to provide a method and an apparatus for rapid dry eye detection, and an electronic device, which can significantly improve the accuracy and efficiency of dry eye detection.
In a first aspect, an embodiment of the present invention provides a method for rapid dry eye detection, the method including: acquiring dry eye index selection information sent by a user side, wherein the index selection information comprises: the user side selects a target inspection item set from the preset inspection item sets; grouping the dry eye index selection information through a preset index analysis model, combining the index selection information meeting the same combining condition into the same function item, and determining a target function item set; and respectively acquiring user dry eye detection videos or user dry eye detection images corresponding to each target function item, and performing image data processing on the user dry eye detection videos or the user dry eye detection images by utilizing a data processing model corresponding to each inspection item in the target function items to determine a dry eye detection result.
In one embodiment, the step of grouping dry eye index selection information by a preset index analysis model, merging index selection information satisfying the same merging condition into the same function item, and determining a target function item set includes: when the left and right eye examination items of the examination item are the same, and the user side examination operation required when measuring the examination item is the same, determining the examination item as the target function item set, wherein the user side examination operation includes: blink and non-blink, target function item sets include: single index function items and multi-index function items.
In one embodiment, before the step of acquiring the user dry eye detection video or the user dry eye detection image corresponding to each target function item, respectively, the method includes: acquiring index analysis marker information corresponding to each inspection item in the same target function item, and measuring object distance information and object distance change information corresponding to an optical imaging unit when each inspection item is performed, wherein the index analysis marker information is used for determining a detection position of dry eye detection, and the optical imaging unit comprises: illumination subassembly, imaging module and control panel, illumination subassembly includes: an illumination source, a backlight plate and a placido cone, the imaging assembly comprising: the control panel is used for controlling the position of the zoom lens group; the illumination assembly is used for illuminating the eye surface of the patient, and the imaging assembly is used for imaging the eye surface of the patient; and changing the position of the zoom lens group based on the object distance change information, analyzing marker information according to indexes, and adjusting the positions of the light source of the illumination component and the zoom lens group so as to realize clear imaging on indexes corresponding to various inspection items when acquiring user dry eye detection videos or user dry eye detection images corresponding to various target function items, and simultaneously analyzing a plurality of indexes in one shooting process.
In one embodiment, after the step of acquiring the user dry eye detection video or the user dry eye detection image corresponding to each target function item, respectively, the method includes: when the target function item is a single-index function item, performing image data processing on a user dry eye detection image corresponding to the single-index function item, and determining a dry eye detection result; when the target function item is a multi-index function item, gray analysis processing is carried out on the dry eye detection video of the user according to the image category to be input corresponding to each inspection item in the target function item, a target image is determined, image data processing is carried out on the target image, and a dry eye detection result is determined.
In one embodiment, according to the image category to be input corresponding to each inspection item in the target function item, gray analysis processing is performed on the dry eye detection video of the user, and the step of determining the target image includes: receiving original images in a dry eye detection video of a user frame by frame, and determining continuous frame sequence images; converting the continuous frame sequence images into gray images, and calculating the gray value of each frame image and the average gray value of the gray image at the current moment in real time; and carrying out gray analysis processing on the gray image according to the gray value, the average gray value and the type of the image to be input, and determining the target image.
In one embodiment, the step of performing gray analysis processing on the gray image according to the gray value, the average gray value and the image category to be input to determine the target image includes: when the type of the image to be input is a blink frame image, comparing the gray value of the current frame image with the average gray value; if the difference value between the gray value and the average gray value is smaller than the preset threshold value, updating the average gray value by using the gray value, and determining the updated average gray value; and if the difference value between the gray level value and the average gray level value is not smaller than the preset threshold value, determining the current frame image as a blink frame image.
In one embodiment, the step of performing gray analysis processing on the gray image according to the gray value, the average gray value and the image category to be input to determine the target image further includes: when the type of the image to be input is open eye frame image, acquiring discontinuous two frames of blink frame images; and determining an eye-open frame image according to the blink frame image, and determining an intermediate frame image of the two-frame blink frame image as a single-frame eye-open frame image.
In a second aspect, an embodiment of the present invention further provides a rapid dry eye detection apparatus, including: the information acquisition module acquires dry eye index selection information sent by a user side, wherein the index selection information comprises: the user side selects a target inspection item set from the preset inspection item sets; the index grouping module is used for grouping the index selection information through a preset index analysis model, combining dry eye index selection information meeting the same combining condition into the same function item, and determining a target function item set; and the dry eye detection module is used for respectively acquiring user dry eye detection videos or user dry eye detection images corresponding to each target function item, performing image data processing on the user dry eye detection videos or the user dry eye detection images by utilizing a data processing model corresponding to each inspection item in the target function items, and determining a dry eye detection result.
In a third aspect, embodiments of the present invention also provide an electronic device comprising a processor and a memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement the method of any one of the first aspects.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions that, when invoked and executed by a processor, cause the processor to implement the method of any one of the first aspects.
The embodiment of the invention has the following beneficial effects:
According to the rapid dry eye detection method, the rapid dry eye detection device and the electronic equipment, accuracy and detection efficiency of dry eye detection can be remarkably improved, after dry eye index selection information sent by a user side is obtained, grouping processing is conducted on the dry eye index selection information through a preset index analysis model, index selection information meeting the same combination condition is combined into the same function item, a target function item set is determined, finally user dry eye detection videos or user dry eye detection images corresponding to all target function items are respectively obtained, image data processing is conducted on the user dry eye detection videos or the user dry eye detection images through a data processing model corresponding to all detection items in the target function items, and dry eye detection results are determined.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for detecting fast dry eye according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a target inspection item according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a target function item according to an embodiment of the present invention;
Fig. 4 is a schematic flow chart of a method for detecting fast dry eye according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a rapid dry eye detection device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described in conjunction with the embodiments, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
At present, the dry eye detection technology has been remarkably developed, and the traditional dry eye detection method comprises smearing tests, tear analysis, ocular surface morphology examination and the like, but the methods have certain limitations, such as complex operation, reliance on doctor experience and the like, and the latest development comprises dry eye detection technology based on optics, computer vision and artificial intelligence, which can more accurately evaluate indexes of tear secretion quantity, tear film stability, ocular surface morphology, ocular surface wettability and the like of a patient, thereby improving the accuracy and efficiency of diagnosis.
However, when different dry eye indexes are evaluated, the conventional dry eye imaging system needs to be repeatedly adjusted for multiple times to obtain good image data, the operation is complex, the detection efficiency is low, the inaccuracy of the image data can lead to larger deviation of analysis results and influence the evaluation of the dry eye indexes, in addition, the conventional dry eye detector only can analyze single indexes when the evaluation of multiple indexes is needed, a doctor needs to perform multiple times of shooting and analysis, possibly needs to wait and check the analysis results after each shooting, and performs the next shooting after confirming no errors, so that the detection time is increased, and the detection efficiency is reduced.
Because patients need to be matched again in each shooting, the detection difficulty can be increased, and particularly for some special groups, for example, the eyes of dry eye patients can have uncomfortable feeling or pain and other symptoms due to multiple shooting, in addition, part of detection projects can not blink when shooting is required, or the patients can have rest or relax due to the uncomfortable eye requirements, the eye surface state of the next shooting can be influenced, the difference exists among the data of multiple shooting, and the diagnosis accuracy is reduced.
Referring to a flow chart of a method for detecting rapid dry eye shown in fig. 1, the method mainly includes the following steps S102 to S106:
Step S102, acquiring dry eye index selection information sent by a user side, wherein the index selection information comprises: in one embodiment, referring to a schematic diagram of a target inspection item shown in fig. 2, the target inspection item set selected by the user side from the preset inspection item set includes: tear river height measurement, non-invasive tear film rupture time measurement, lipid layer measurement, eye red analysis, incomplete blink analysis, eyelid margin shooting, meibomian gland upper/lower eyelid analysis and fluorescence image shooting, and a user side can autonomously select a target examination item and submit a detection flow.
Step S104, grouping processing is performed on dry eye index selection information through a preset index analysis model, index selection information meeting the same combination condition is combined into the same function item, and a target function item set is determined, in one embodiment, when left and right eye examination items of the examination items are the same, and user side examination operations required when the examination items are measured are the same, the examination items are determined as the target function item set, wherein the user side examination operations include: blink and non-blink, target function item sets include: the single index functional item and the multi-index functional item, specifically, referring to a schematic diagram of one target functional item shown in fig. 3, the eyelid margin shooting, the meibomian gland upper/lower eyelid analysis and the fluorescent image shooting are single index functional items, wherein the single index functional item only comprises one index to be detected, that is, the three detection items cannot be combined and can only be detected independently, the tear level measurement and the non-invasive tear film rupture time measurement are in the same multi-index functional item, the lipid layer measurement, the eye red analysis and the incomplete blink analysis are in the same multi-index functional item, and the same multi-index functional item can share one shot data, that is, a plurality of indexes can be analyzed only by shooting once.
Step S106, respectively acquiring user dry eye detection videos or user dry eye detection images corresponding to each target function item, and performing image data processing on the user dry eye detection videos or the user dry eye detection images by utilizing a data processing model corresponding to each inspection item in the target function items to determine dry eye detection results, wherein in one embodiment, the tear height measurement requires image data processing on the user dry eye detection videos through a tear segmentation model; the non-invasive tear film rupture time measurement requires image data processing of a user dry eye detection video through a placido ring rupture area extraction model; the lipid layer measurement requires image data processing of a user dry eye detection video through a ring body region extraction model; the eye red analysis needs to process image data of a user dry eye detection video through a scleral region segmentation model; the incomplete blink analysis needs to process image data of a user dry eye detection video through a blink frame extraction model and a eyelid margin area segmentation model; the analysis of the upper eyelid/lower eyelid of the meibomian gland requires image data processing of the dry eye detection image of the user through a palpebral conjunctiva segmentation model; the eyelid margin shooting and the fluorescence image shooting can be directly obtained without a data processing model.
According to the rapid dry eye detection method, the rapid dry eye detection device and the electronic equipment provided by the embodiment of the invention, the optical imaging unit can be adjusted, so that the optical parameters of the same group of light sources, lenses, cameras and the like can be adapted to a plurality of data processing units, and when a plurality of indexes are evaluated, the positions of the zoom lens group are changed based on the change of the object distance of the optical imaging unit, so that clear imaging is realized for different indexes, and a plurality of indexes are simultaneously analyzed by shooting once.
In addition, when a plurality of indexes are evaluated, the difference of objects is analyzed based on each index, the positions of the light source of the lighting component and the zoom lens group are changed, clear imaging is realized on different indexes, one shooting is realized, the plurality of indexes are simultaneously analyzed, the shooting and displaying flow is optimized, the selected modes during shooting can be automatically grouped according to whether one shooting data can be shared, and the plurality of indexes can be analyzed only by shooting once in the same group.
And automatically extracting single-frame images meeting the standard from one section of shot video data, carrying out video processing and picture processing in parallel according to different functional requirements to obtain respective processing results, and simultaneously merging operations which can be merged in different inspection items, thereby avoiding repeated processing, reducing processing time consumption, and when the results are displayed, enabling all groups to be sequentially displayed with analysis results after shooting is finished, and further obviously improving the accuracy and the detection efficiency of dry eye detection.
Referring to a specific flow chart of a method for detecting rapid dry eye shown in fig. 4, the embodiment of the present invention further provides an embodiment of rapid dry eye detection, specifically referring to the following (1) to (4):
(1) Acquiring index analysis marker information corresponding to each inspection item in the same target function item, measuring object distance information and object distance change information corresponding to an optical imaging unit when each inspection item is performed, changing the position of a zoom lens group based on the object distance change information, and adjusting the positions of a light source of an illumination component and the zoom lens group according to the index analysis marker information so as to realize clear imaging of indexes corresponding to each inspection item when a user dry eye detection video or a user dry eye detection image corresponding to each target function item is acquired, and simultaneously analyzing a plurality of indexes in one shooting process, wherein the index analysis marker information is used for determining the detection position of dry eye detection, and the optical imaging unit comprises: illumination subassembly, imaging module and control panel, illumination subassembly includes: an illumination source, a backlight plate and a placido cone, the imaging assembly comprising: the control panel is used for controlling the position of the zoom lens group; the illumination component is used for illuminating the eye surface of a patient, the imaging component is used for imaging the eye surface of the patient, the same group can be shot once through the adjustment, and a plurality of indexes can be analyzed, so that the detection efficiency is improved, the shooting times are reduced, the patient does not need to be matched with the shooting for many times, the detection process can be completed more quickly, the plurality of indexes are analyzed through the same group of data, the difference in the data acquisition and processing processes is reduced, and the accuracy of the detection result is improved.
(2) When the target function item is a single-index function item, performing image data processing on a user dry eye detection image corresponding to the single-index function item, and determining a dry eye detection result, in one embodiment, the single-index function item includes: the method comprises the steps of eyelid margin shooting, meibomian gland upper/lower eyelid analysis and fluorescent image shooting, wherein the eyelid margin shooting and the fluorescent image shooting do not need to be processed by a data processing unit, upper eyelid images and lower eyelid images need to be acquired during the analysis of the meibomian gland upper/lower eyelid, upper eyelid conjunctiva areas and lower eyelid areas are separated by an eyelid conjunctiva separation module, gland characteristic enhancement and gland separation are carried out on the images by a gland area extraction module to obtain gland areas, and finally the loss ratio result of the meibomian glands is calculated.
(3) When the target function item is a multi-index function item, according to the category of the image to be input corresponding to each inspection item in the target function item, gray analysis processing is performed on the dry eye detection video of the user, and the step of determining the target image includes the following steps (a) to (C):
(A) Receiving original images in a dry eye detection video of a user frame by frame, determining a continuous frame sequence image, converting the continuous frame sequence image into a gray image, calculating the gray value of each frame image and the average gray value of the gray image at the current moment in real time, wherein the average gray value refers to the gray average value of the received images, namely, receiving each frame image data frame by frame, converting the original images into the gray image, calculating the gray value of the current frame image, comparing the gray average value of the received images with the gray value of the current frame image in the process of continuously receiving each frame image, merging the gray value of the current frame with the gray value of the received images if the gray average value of the current frame is less than 10, calculating and updating the gray average value, otherwise marking the current frame image as a blink frame image, continuously receiving the next frame image, determining the images within the range of the two frames of blink frame images as open eye frame images, and taking one frame with the frame sequence number in the middle of the two frames as a single-frame eye frame image, wherein the single-eye image is used for measuring the eye height and the eye height of a red frame image.
(B) According to the gray value, the average gray value and the class of the image to be input, gray analysis processing is carried out on the gray image, a target image is determined, and when the class of the image to be input is a blink frame image, the gray value of the current frame image is compared with the average gray value: if the difference between the gray value and the average gray value is smaller than the preset threshold, the average gray value is updated by the gray value, the updated average gray value is determined, if the difference between the gray value and the average gray value is not smaller than the preset threshold, the current frame image is determined to be a blink frame image, in one embodiment, if the gray value of the current frame is gv, the number of the current frame is n, and the calculated gray average value is mgv, the update calculation mode of the gray average value can be expressed as the following formula:
(C) When the type of the image to be input is open eye frame image, acquiring discontinuous two frames of blink frame images, determining open eye frame images according to the blink frame images, and determining the middle frame image of the two frames of blink frame images as a single frame open eye frame image.
(4) When the target function item is a multi-index function item, image data processing is carried out aiming at the target image, a dry eye detection result is determined, specifically, when the multi-index function item measurement of tear-river height measurement and non-invasive tear film rupture time measurement is carried out, calculation of the non-invasive tear film rupture time is carried out, blink detection is firstly carried out twice, then the Placido ring change condition of each frame of image is analyzed frame by frame through a Placido ring rupture area extraction module, when a subject carries out blink for the third time or shooting video is finished, the time and area result of the Placido ring rupture in an effective frame sequence are returned, wherein in order to ensure the high efficiency of data processing, each shot frame is sent to a data processing unit for processing, a continuous frame sequence to be analyzed is firstly obtained through blink detection, then the Placido ring rupture judgment is carried out on each image, and finally the position and the time result of the Placido ring rupture are returned.
In addition, for calculation of the tear height measurement, firstly inputting an image into a pre-trained tear segmentation model to extract a tear region, then selecting three pairs of coordinate points at the top and the bottom of three positions of the tear by a tear measurement module according to a specified width position, taking the average value of the tear heights of the three positions as a tear measurement result, namely, selecting three height measurement points from the middle part of the tear region and a certain distance from the left to the right, and calculating the distance from the upper edge to the lower edge of the three measurement points to obtain the tear height result.
In another embodiment, when multi-index functional item measurement of lipid layer measurement, eye red analysis and incomplete blink analysis is performed, firstly, normal open eye frames and all blink frames are distinguished through a blink detection module, the normal open eye frames are used for calculation of lipid layer analysis, the blink frames are used for calculation of incomplete blink analysis, for calculation of lipid layers, the lower half area of Placido rings is extracted from screened normal open eye frame images through a ring body area extraction module, then the lipid layer thickness of each frame is calculated through a lipid layer color calculation module according to the mapping relation between lipid layer colors and thickness, specifically, the lower half area of Placido rings of each image is extracted, the color of each pixel on each Placido ring of the area is calculated, and then the thickness result of the lipid layer is converted according to the mapping relation between the lipid layer colors and the thickness.
In addition, for calculation of incomplete blinking, all blinking frames are sent to a blinking frame extraction module to obtain a frame with the maximum eyelid closure degree in each blinking process, a region surrounded by eyes of the frame from an upper eyelid to a lower eyelid is segmented by a eyelid gap region segmentation module, and the non-closure height of the eyelid gap region of the frame is calculated, so that a judgment result of incomplete blinking is obtained.
And for eye red analysis calculation, sending the extracted single-frame open eye frames into a sclera region segmentation module to segment a left sclera region and a right sclera region of a subject, extracting pixel areas of all red regions of the sclera region in an eye red color calculation module, and dividing the pixel areas by the total area of the sclera region to obtain an eye red occupation ratio, namely an eye red analysis result.
(4) And optimizing the analysis result display flow, and displaying the analysis results in sequence after all the grouping shooting ends, so that the detection process is more convenient, users do not need to wait too long time between shooting of different grouping, and the user experience is improved.
In summary, the invention can realize the function of adapting the same optical structure to a plurality of data processing units by adjusting the positions of the illumination light source and the zoom lens group in the optical imaging unit, so that the data shot at a time can be used for acquiring a plurality of indexes, the selected modes can be automatically grouped during shooting, the plurality of indexes can be analyzed by the same group only by shooting once, thereby improving the detection efficiency, reducing the shooting times, further enabling a patient not to need to coordinate shooting for a plurality of times, completing the detection process more quickly, analyzing the plurality of indexes by the same group of data, reducing the difference in the data acquisition and processing processes, and improving the accuracy of the detection result.
In addition, the invention optimizes the analysis result display flow of the man-machine interaction unit, and sequentially displays the analysis results after all the items are shot, so that the detection process is more convenient, users do not need to wait too long time between different groups of shooting, and the user experience is improved.
For the rapid dry eye detection method provided in the foregoing embodiment, an embodiment of the present invention provides a rapid dry eye detection device, referring to a schematic structural diagram of a rapid dry eye detection device shown in fig. 5, the device includes the following parts:
the information obtaining module 502 obtains dry eye index selection information sent by the user side, where the index selection information includes: the user side selects a target inspection item set from the preset inspection item sets;
the index grouping module 504 performs grouping processing on the index selection information through a preset index analysis model, merges dry eye index selection information meeting the same merging condition into the same function item, and determines a target function item set;
The dry eye detection module 506 acquires a user dry eye detection video or a user dry eye detection image corresponding to each target function item, and performs image data processing on the user dry eye detection video or the user dry eye detection image by using a data processing model corresponding to each inspection item in the target function items, thereby determining a dry eye detection result.
The rapid dry eye detection device provided by the embodiment of the application can remarkably improve the accuracy and the detection efficiency of dry eye detection.
In one embodiment, when performing the step of grouping the dry eye index selection information by the preset index analysis model, and merging the index selection information satisfying the same merging condition into the same function item, the index grouping module 504 is further configured to: when the left and right eye examination items of the examination item are the same, and the user side examination operation required when measuring the examination item is the same, determining the examination item as the target function item set, wherein the user side examination operation includes: blink and non-blink, target function item sets include: single index function items and multi-index function items.
In one embodiment, before performing the step of acquiring the user dry eye detection video or the user dry eye detection image corresponding to each target function item, the dry eye detection module 506 is further configured to: acquiring index analysis marker information corresponding to each inspection item in the same target function item, and measuring object distance information and object distance change information corresponding to an optical imaging unit when each inspection item is performed, wherein the index analysis marker information is used for determining a detection position of dry eye detection, and the optical imaging unit comprises: illumination subassembly, imaging module and control panel, illumination subassembly includes: an illumination source, a backlight plate and a placido cone, the imaging assembly comprising: the control panel is used for controlling the position of the zoom lens group; the illumination assembly is used for illuminating the eye surface of the patient, and the imaging assembly is used for imaging the eye surface of the patient; and changing the position of the zoom lens group based on the object distance change information, analyzing marker information according to indexes, and adjusting the positions of the light source of the illumination component and the zoom lens group so as to realize clear imaging on indexes corresponding to various inspection items when acquiring user dry eye detection videos or user dry eye detection images corresponding to various target function items, and simultaneously analyzing a plurality of indexes in one shooting process.
In one embodiment, after performing the step of acquiring the user dry eye detection video or the user dry eye detection image corresponding to each target function item, the dry eye detection module 506 is further configured to: when the target function item is a single-index function item, performing image data processing on a user dry eye detection image corresponding to the single-index function item, and determining a dry eye detection result; when the target function item is a multi-index function item, gray analysis processing is carried out on the dry eye detection video of the user according to the image category to be input corresponding to each inspection item in the target function item, a target image is determined, image data processing is carried out on the target image, and a dry eye detection result is determined.
In one embodiment, when performing the step of performing gray-scale analysis processing on the dry eye detection video of the user according to the image category to be input corresponding to each inspection item in the target function item, and determining the target image, the dry eye detection module 506 is further configured to: receiving original images in a dry eye detection video of a user frame by frame, and determining continuous frame sequence images; converting the continuous frame sequence images into gray images, and calculating the gray value of each frame image and the average gray value of the gray image at the current moment in real time; and carrying out gray analysis processing on the gray image according to the gray value, the average gray value and the type of the image to be input, and determining the target image.
In one embodiment, when performing the step of performing gray-scale analysis processing on the gray-scale image according to the gray-scale value, the average gray-scale value and the image category to be input, the dry eye detection module 506 is further configured to: when the type of the image to be input is a blink frame image, comparing the gray value of the current frame image with the average gray value; if the difference value between the gray value and the average gray value is smaller than the preset threshold value, updating the average gray value by using the gray value, and determining the updated average gray value; and if the difference value between the gray level value and the average gray level value is not smaller than the preset threshold value, determining the current frame image as a blink frame image.
In one embodiment, when performing the step of performing gray-scale analysis processing on the gray-scale image according to the gray-scale value, the average gray-scale value and the image category to be input, the dry eye detection module 506 is further configured to: when the type of the image to be input is open eye frame image, acquiring discontinuous two frames of blink frame images; and determining an eye-open frame image according to the blink frame image, and determining an intermediate frame image of the two-frame blink frame image as a single-frame eye-open frame image.
The device provided by the embodiment of the present invention has the same implementation principle and technical effects as those of the foregoing method embodiment, and for the sake of brevity, reference may be made to the corresponding content in the foregoing method embodiment where the device embodiment is not mentioned.
The embodiment of the invention provides electronic equipment, which comprises a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the embodiments described above.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 100 includes: a processor 60, a memory 61, a bus 62 and a communication interface 63, the processor 60, the communication interface 63 and the memory 61 being connected by the bus 62; the processor 60 is arranged to execute executable modules, such as computer programs, stored in the memory 61.
The memory 61 may include a high-speed random access memory (RAM, random Access Memory) and may further include a non-volatile memory (non-volatilememory), such as at least one disk memory. The communication connection between the system network element and at least one other network element is achieved via at least one communication interface 63 (which may be wired or wireless), and may use the internet, a wide area network, a local network, a metropolitan area network, etc.
Bus 62 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 6, but not only one bus or type of bus.
The memory 61 is configured to store a program, and the processor 60 executes the program after receiving an execution instruction, and the method executed by the apparatus for flow defining disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 60 or implemented by the processor 60.
The processor 60 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in the processor 60. The processor 60 may be a general-purpose processor, including a Central Processing Unit (CPU), a network processor (NetworkProcessor NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 61 and the processor 60 reads the information in the memory 61 and in combination with its hardware performs the steps of the method described above.
The computer program product of the readable storage medium provided by the embodiment of the present invention includes a computer readable storage medium storing a program code, where the program code includes instructions for executing the method described in the foregoing method embodiment, and the specific implementation may refer to the foregoing method embodiment and will not be described herein.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method of rapid dry eye detection, the method comprising:
acquiring dry eye index selection information sent by a user side, wherein the index selection information comprises: the user side selects a target inspection item set from the preset inspection item sets;
grouping processing is performed on the dry eye index selection information through a preset index analysis model, the index selection information meeting the same combination condition is combined into the same function item, and a target function item set is determined, wherein when left and right eye inspection items of the inspection items are the same, and user side inspection operations required for measuring the inspection items are the same, the inspection items are determined to be the target function item set, and the user side inspection operations comprise: blink and non-blink, the set of target function items comprising: single index function items and multi-index function items;
Acquiring user dry eye detection videos or user dry eye detection images corresponding to each target function item respectively, and performing image data processing on the user dry eye detection videos or the user dry eye detection images by utilizing a data processing model corresponding to each inspection item in the target function items to determine dry eye detection results;
Before the step of acquiring a user dry eye detection video or a user dry eye detection image corresponding to each target function item, acquiring index analysis marker information corresponding to each inspection item and object distance information and object distance change information corresponding to an optical imaging unit when each inspection item in the same target function item is measured, wherein the index analysis marker information is used for determining a detection position of dry eye detection, and the optical imaging unit comprises: an illumination assembly, an imaging assembly, and a control board, the illumination assembly comprising: an illumination source, a backlight plate and a placido cone, the imaging assembly comprising: the control panel is used for controlling the position of the zoom lens group; the illumination assembly is used for illuminating the eye surface of the patient, and the imaging assembly is used for imaging the eye surface of the patient; and changing the position of the zoom lens group based on the object distance change information, analyzing marker information according to the indexes, and adjusting the light source of the lighting component and the position of the zoom lens group so as to realize clear imaging on the indexes corresponding to each inspection item when acquiring the user dry eye detection video or the user dry eye detection image corresponding to each target function item, and simultaneously analyzing a plurality of indexes in one shooting process.
2. The quick dry eye detection method according to claim 1, characterized by comprising, after the step of acquiring the user dry eye detection video or the user dry eye detection image corresponding to each target function item, respectively:
When the target function item is a single-index function item, performing image data processing on the user dry eye detection image corresponding to the single-index function item, and determining a dry eye detection result;
When the target function item is a multi-index function item, gray analysis processing is carried out on the dry eye detection video of the user according to the image category to be input corresponding to each inspection item in the target function item, a target image is determined, image data processing is carried out on the target image, and a dry eye detection result is determined.
3. The method according to claim 2, wherein the step of performing gray level analysis processing on the user dry eye detection video according to the category of the image to be input corresponding to each inspection item in the target function items, and determining the target image includes:
Receiving original images in the user dry eye detection video frame by frame, and determining continuous frame sequence images;
Converting the continuous frame sequence images into gray images, and calculating the gray value of each frame image and the average gray value of the gray images at the current moment in real time;
and carrying out gray analysis processing on the gray level image according to the gray level value, the average gray level value and the image category to be input, and determining the target image.
4. The method according to claim 3, wherein the step of performing gray analysis processing on the gray image according to the gray value, the average gray value, and the category of the image to be input to determine the target image comprises:
When the image category to be input is a blink frame image, comparing the gray value of the current frame image with the average gray value;
If the difference value between the gray value and the average gray value is smaller than a preset threshold value, updating the average gray value by using the gray value, and determining the updated average gray value;
and if the difference value between the gray value and the average gray value is not smaller than a preset threshold value, determining the current frame image as a blink frame image.
5. The method according to claim 3, wherein the step of performing gray analysis processing on the gray image according to the gray value, the average gray value, and the category of the image to be input to determine the target image further comprises:
when the image category to be input is open eye frame images, acquiring discontinuous two-frame blink frame images;
And determining the open eye frame image according to the blink frame image, and determining the middle frame image of the blink frame images as a single open eye frame image.
6. A rapid dry eye detection device, the device comprising:
the information acquisition module acquires dry eye index selection information sent by a user side, wherein the index selection information comprises: the user side selects a target inspection item set from the preset inspection item sets;
The index grouping module performs grouping processing on the index selection information through a preset index analysis model, merges the dry eye index selection information meeting the same merging condition into the same function item, and determines a target function item set, wherein when left and right eye inspection items of the inspection items are the same, and user side inspection operations required when the inspection items are measured are the same, the inspection items are determined to be the target function item set, and the user side inspection operations comprise: blink and non-blink, the set of target function items comprising: single index function items and multi-index function items;
The dry eye detection module is used for respectively acquiring user dry eye detection videos or user dry eye detection images corresponding to each target function item, performing image data processing on the user dry eye detection videos or the user dry eye detection images by utilizing a data processing model corresponding to each inspection item in the target function items, and determining a dry eye detection result;
Before the step of acquiring a user dry eye detection video or a user dry eye detection image corresponding to each target function item, acquiring index analysis marker information corresponding to each inspection item and object distance information and object distance change information corresponding to an optical imaging unit when each inspection item in the same target function item is measured, wherein the index analysis marker information is used for determining a detection position of dry eye detection, and the optical imaging unit comprises: an illumination assembly, an imaging assembly, and a control board, the illumination assembly comprising: an illumination source, a backlight plate and a placido cone, the imaging assembly comprising: the control panel is used for controlling the position of the zoom lens group; the illumination assembly is used for illuminating the eye surface of the patient, and the imaging assembly is used for imaging the eye surface of the patient; and changing the position of the zoom lens group based on the object distance change information, analyzing marker information according to the indexes, and adjusting the light source of the lighting component and the position of the zoom lens group so as to realize clear imaging on the indexes corresponding to each inspection item when acquiring the user dry eye detection video or the user dry eye detection image corresponding to each target function item, and simultaneously analyzing a plurality of indexes in one shooting process.
7. An electronic device comprising a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the method of any one of claims 1 to 5.
8. A computer readable storage medium storing computer executable instructions which, when invoked and executed by a processor, cause the processor to implement the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410962437.7A CN118507037B (en) | 2024-07-18 | 2024-07-18 | Rapid dry eye detection method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410962437.7A CN118507037B (en) | 2024-07-18 | 2024-07-18 | Rapid dry eye detection method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118507037A CN118507037A (en) | 2024-08-16 |
| CN118507037B true CN118507037B (en) | 2024-10-22 |
Family
ID=92229655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410962437.7A Active CN118507037B (en) | 2024-07-18 | 2024-07-18 | Rapid dry eye detection method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118507037B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110367926A (en) * | 2019-07-22 | 2019-10-25 | 天津市索维电子技术有限公司 | A kind of xerophthalmia check device and method applied to self-medicine |
| CN111062443A (en) * | 2019-12-20 | 2020-04-24 | 浙江大学 | Tear film rupture time detecting system based on deep learning |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855476A (en) * | 2011-06-27 | 2013-01-02 | 王晓鹏 | Self-adaptive binocular iris synchronous collection system of single image sensor |
| US20220313077A1 (en) * | 2021-04-01 | 2022-10-06 | CorneaCare Inc. | Method of and system for automated machine-assisted detection of ocular disease conditions in human eyes captured using visible illumination light sources and digital camera systems |
| CN114005171B (en) * | 2021-10-25 | 2024-12-10 | 中山大学中山眼科中心 | Method and system for identifying target areas in video images based on ocular surface staining |
| CN114343563B (en) * | 2021-12-31 | 2024-10-01 | 温州医科大学附属眼视光医院 | Method, device and system for assisting dry eye diagnosis and typing through multi-mode fusion |
| CN114820537B (en) * | 2022-05-06 | 2025-04-04 | 上海美沃精密仪器股份有限公司 | A dry eye FBUT detection method, system and storage medium based on deep learning |
| CN117315629A (en) * | 2022-06-20 | 2023-12-29 | 哈曼国际工业有限公司 | Blink detection method and system |
| CN115177206A (en) * | 2022-07-12 | 2022-10-14 | 中国科学院苏州生物医学工程技术研究所 | Xerophthalmia detection method and device and storage medium |
| CN116864105A (en) * | 2023-06-30 | 2023-10-10 | 平安科技（深圳）有限公司 | Dry eye risk prediction method, device, equipment and medium based on artificial intelligence |
-
2024
- 2024-07-18 CN CN202410962437.7A patent/CN118507037B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110367926A (en) * | 2019-07-22 | 2019-10-25 | 天津市索维电子技术有限公司 | A kind of xerophthalmia check device and method applied to self-medicine |
| CN111062443A (en) * | 2019-12-20 | 2020-04-24 | 浙江大学 | Tear film rupture time detecting system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118507037A (en) | 2024-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102724424B1 (en) | Digital therapeutic corrective glasses | |
| WO2020199593A1 (en) | Image segmentation model training method and apparatus, image segmentation method and apparatus, and device and medium | |
| AU2012328140B2 (en) | System and method for identifying eye conditions | |
| CA2533068C (en) | Method and apparatus for online contact lens evaluation | |
| CN105310646B (en) | The human health status being imaged based on white of the eye without shadow is in body analysis system | |
| CN104102899B (en) | Retinal vessel recognition methods and device | |
| US12232811B2 (en) | Computer-implemented method and system for interactively measuring ocular refractive errors, addition and power of reading glasses | |
| CN108427503A (en) | Human eye method for tracing and human eye follow-up mechanism | |
| JPH11136498A (en) | Computer program matter for red eye detection | |
| CN110377385A (en) | A kind of screen display method, device and terminal device | |
| CN106265006A (en) | The antidote of a kind of dominant eye and mobile terminal | |
| CN110930446A (en) | Pre-processing method and storage device for quantitative analysis of fundus image | |
| CN112837805A (en) | Extraction method of eyelid topological morphological features based on deep learning | |
| WO2020232855A1 (en) | Method and apparatus for adjusting screen display on the basis of subtle expression | |
| JP2016530000A (en) | System and method for measuring facial features | |
| US20230346276A1 (en) | System and method for detecting a health condition using eye images | |
| KR102380560B1 (en) | Corneal Ulcer Region Detection Apparatus Using Image Processing and Method Thereof | |
| TW202303469A (en) | Image segmentation method and electronic device, recording medium and computer program product using the same | |
| CN118196218B (en) | Fundus image processing method, device and equipment | |
| CN118507037B (en) | Rapid dry eye detection method and device and electronic equipment | |
| CN103955941B (en) | A kind of specularmicroscope and the method for analysis | |
| WO2024120179A1 (en) | Glasses diopter identification method and apparatus, electronic device and storage medium | |
| CN113850772B (en) | Glaucoma screening method, system, device and storage medium based on AS-OCT video | |
| KR20200102034A (en) | Apparatus and method for cell counting | |
| CN112734701A (en) | Fundus focus detection method, fundus focus detection device and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |