CN113139935A - Slit-lamp picture quality monitoring system - Google Patents
Slit-lamp picture quality monitoring system Download PDFInfo
- Publication number
- CN113139935A CN113139935A CN202110340719.XA CN202110340719A CN113139935A CN 113139935 A CN113139935 A CN 113139935A CN 202110340719 A CN202110340719 A CN 202110340719A CN 113139935 A CN113139935 A CN 113139935A
- Authority
- CN
- China
- Prior art keywords
- picture
- diagnosis
- slit
- lamp
- module
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- A61B3/13—Ophthalmic microscopes
- A61B3/135—Slit-lamp microscopes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Multimedia (AREA)
- Surgery (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Biophysics (AREA)
- Ophthalmology & Optometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Eye Examination Apparatus (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a slit lamp picture quality monitoring system, which comprises: there are slit-lamp, first display screen, second display screen, megaphone, the printer of slit-lamp picture remote diagnosis system, wherein, slit-lamp picture remote diagnosis system includes: the system comprises a login module, a personal information management module, a picture quality monitoring module based on a ResNet50 construction model, a diagnosis list management module, a database and an uploading module. The invention solves the problem that diagnostic information is lost due to lower quality of partial slit lamp pictures when the slit lamp is shot, so that an ophthalmologist participating in telemedicine cannot make correct judgment, and has the advantages of greatly improving the diagnostic effect and being more humanized.
Description
Technical Field
The invention relates to the technical field of remote ophthalmologic medical systems, in particular to a slit lamp picture quality monitoring system.
Background
A slit-lamp microscope is an essential important instrument for ophthalmologic examination. The slit-lamp microscope consists of an illumination system and a binocular microscope, can not only enable superficial lesions to be observed clearly, but also adjust the focus and the width of a light source to be made into an optical section, so that the lesions of deep tissues can be also displayed clearly.
The slit lamp and the microscope are required to have enough light sources of the slit lamp with left and right swinging angles mechanically, so that slit edges of the slit lamp are required to be very flat, the slit is required to be clearly imaged on a vertical plane of a circle center swinging left and right, and the focus of the microscope is also required to be focused on the vertical plane of the circle center.
The slit illumination light source must have:
1. the width of the crack is adjustable within the range of 0 to 10 mm; 2. the length of the crack can be adjusted within the range of 1-10 mm (when the length and the width are 10mm, the light of the crack is actually a circular light spot); 3. the direction of the crack is adjustable; 4. the brightness of the light source is adjustable, and a background lighting light microscope with adjustable brightness is a stereo binocular structure and must be provided with: (1) clear imaging; (2) the focal length of the ocular can be adjusted to adapt to different eye diopters of an operator; (3) the distance between the two eyepieces can be adjusted to adapt to the mechanical structure of interpupillary distance of different operators.
Besides the function of left-right swinging, the three-dimensional adjustable moving worktable is also provided; the jaw frame device can fix the skull of a patient, and the jaw support on the jaw frame can be adjusted up and down to adapt to the skull length of different patients; the fixation lamp can avoid the involuntary rotation of the eyes of the patient.
The principle of the slit lamp is as follows: as the name implies, the light illuminates the eye through a slit. The light source is a narrow slit light source, so the light source is called as a 'smooth knife'. The 'optical knife' is irradiated on the eyes to form an optical section, so that the health condition of each part of the eyes can be observed. The principle is that the Tdahr phenomenon of the British physics of Medindall is utilized.
Slit-lamp anterior segment photography is indispensable as the most basic examination item of ophthalmology in telemedicine. However, due to the influence of misoperation of the photographer and poor patient matching, the quality of the photographed picture of a part of slit lamps is low, so that the diagnostic information is lost, and an ophthalmologist participating in remote medical treatment cannot make a correct judgment or requires a local hospital to shoot the examinee again. This may seriously reduce the efficiency of remote medical treatment, increase the risk of medical errors, and even possibly cause medical disputes. In addition, the accuracy of a subsequent artificial intelligence diagnosis and treatment system can be reduced by the low-quality images. Therefore, image quality monitoring of real-time slit-lamp eye anterior segment photography is very important.
At present, ophthalmology professionals are required to monitor the quality of slit lamp pictures, and the slit lamp pictures are time-consuming, labor-consuming and can not be implemented in township or community medical institutions lacking ophthalmology professionals, and the places are most in need of remote ophthalmology medical treatment.
Disclosure of Invention
The technical problem solved by the invention is as follows: when the slit lamp is shot, the quality of partial slit lamp pictures is low, so that the diagnostic information is lost, and an ophthalmologist participating in remote medical treatment cannot make correct judgment.
The technical scheme of the invention is as follows:
a slit-lamp picture quality monitoring system comprising:
a slit lamp used for taking pictures of eyes of patients, a slit lamp picture remote diagnosis system which can be accessed by a mobile terminal is arranged on the slit lamp,
a first display screen for displaying the diagnosis and treatment picture of the ophthalmology specialist participating in the telemedicine,
a second display screen for displaying the shooting effect of the slit-lamp photo,
a loudspeaker for prompting the picture collector to shoot the picture again after adjusting the posture of the patient,
a printer for printing the results of the diagnosis,
wherein, slit-lamp picture remote diagnosis system includes:
a login module for registering and logging in the slit-lamp picture remote diagnosis system,
a personal information management module for recording basic information of patients and ophthalmologists,
a picture quality monitoring module for being directed at slit lamp shooting picture quality carries out monitoring, and picture quality monitoring module includes: a trained picture quality recognition model submodule is established based on a ResNet50 deep learning algorithm, a voice prompt submodule which is used for outputting voice after low-quality picture problems are classified and corresponded,
a diagnosis management module for controlling the printer to print the diagnosis result,
a database for storing clear photographs, personal information, diagnostic procedures, diagnostic results and prompt voices,
and the uploading module is used for uploading the acquired clear photos and the personal information to the database.
Further, the construction training process of the picture quality monitoring model comprises the following steps:
s1: selecting 1.2 ten thousand high-quality and low-quality slit lamp pictures marked by an ophthalmology expert, homogenizing all picture pixel values to be between 0 and 1, and adjusting the size of the picture to be 224 multiplied by 224 pixels to be used as an image data set;
s2: constructing a slit lamp picture quality monitoring model by using a ResNet50 deep learning algorithm, and optimizing the slit lamp picture quality monitoring model by using a self-adaptive moment estimation optimizer;
s3: training a picture quality monitoring model by using an image data set;
s4: a plurality of models is used for 180 rounds of iterative training. In the training process, after each iterative training, a verification set is used for evaluating the verification loss, and the verification loss is used as a reference for model selection;
s5: if the verification loss does not improve for 60 consecutive rounds, the training process is stopped and the model with the minimum verification loss is used as the finally selected model.
Further, the initial learning rate of the adaptive moment estimation optimizer is 0.001, beta 1/0.9, beta2/0.999, and the fuzzy coefficient is 1e-7The learning rate is attenuated to 0, and the recognition rate of the model low-quality photos obtained by final training can reach more than 95%.
Further, the diagnostic management module includes: the diagnosis sheet filling sub-module is used for filling diagnosis opinions by an ophthalmologist according to the eye picture of the patient, and the diagnosis sheet generating sub-module is used for generating an electronic diagnosis sheet and calling a printer to output paper, so that the remote specialist can fill the diagnosis opinions after the diagnosis is finished.
Further, the personal information management module includes: the personal management module can supplement personal information of experts and patients in the diagnosis list in advance.
Preferably, the slit-lamp picture quality monitoring system further comprises: a first camera for taking a picture of a patient, a second camera for taking a picture of a remote ophthalmologist, the slit-lamp picture remote diagnosis system further comprising: the remote diagnosis module for the remote diagnosis and treatment of the ophthalmology experts and the patients enables the experts to conduct remote diagnosis with the patients through the camera.
Preferably, the remote diagnosis module comprises: the camera calling submodule is used for calling the camera, the face diagnosis video recording submodule is used for recording the diagnosis process, and the remote diagnosis module can record the remote face diagnosis process, so that the diagnosis process can be traced.
Preferably, the slit-lamp picture remote diagnosis system further comprises: the scheduling management module is used for managing the scheduling of the experts and can enable the patient to select corresponding time to carry out eye examination according to the scheduling condition of the experts.
Preferably, the shift scheduling management module comprises: the system comprises an online diagnosis management submodule for managing the online diagnosis working period of an expert and a diagnosis management submodule for managing the diagnosis working period of the expert, so that the expert can select a diagnosis mode and time according to personal conditions and is suitable for more different application scenes.
Further preferably, the slit-lamp picture remote diagnosis system further comprises: and the notification module is used for notifying the patient to check and receive the diagnosis list after the on-line diagnosis of the ophthalmology specialist is finished, and the patient can timely obtain the diagnosis result according to the notification submodule and effectively treat the eyes according to the diagnosis result.
The invention has the beneficial effects that:
1. according to the invention, an artificial intelligent slit lamp image quality monitoring system is constructed through a deep learning algorithm, the picture with unqualified quality is automatically identified, the picture acquisition personnel is prompted to shoot again in time, and misdiagnosis or missed diagnosis caused by the loss of diagnosis information due to the low-quality picture is avoided;
2. the invention enables the ophthalmologist to diagnose the patient in two modes of remote face diagnosis and on-line diagnosis, can be better suitable for the current situation that the township medical institution lacks the ophthalmologist, is convenient for the specialist to adjust the shift according to the personal condition on the one hand, and is convenient for the patient to select the diagnosis mode according to the personal state of illness on the other hand, thereby being more humanized.
Drawings
FIG. 1 is an overall structural view of embodiments 1 and 2;
FIG. 2 is an overall structural diagram of examples 1 and 2;
FIG. 3 is a flowchart of the operation of the slit-lamp picture remote diagnosis system according to the present invention;
FIG. 4 is a flow chart of the construction training of the picture quality monitoring model;
fig. 5 is an overall frame diagram of embodiments 3, 4, and 5.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two.
It should be understood that although the terms first, second, third, etc. may be used to describe … … in embodiments of the present invention, these … … should not be limited to these terms. These terms are used only to distinguish … …. For example, the first … … can also be referred to as the second … … and similarly the second … … can also be referred to as the first … … without departing from the scope of embodiments of the present invention.
Example 1
As shown in fig. 1 and fig. 2, a slit-lamp picture quality monitoring system includes:
a slit lamp used for taking pictures of eyes of patients, a slit lamp picture remote diagnosis system which can be accessed by other equipment is arranged on the slit lamp,
a first display screen for displaying the diagnosis and treatment picture of the ophthalmology specialist participating in the telemedicine,
a second display screen for displaying the shooting effect of the slit-lamp photo,
a loudspeaker for prompting the picture collector to shoot the picture again after adjusting the posture of the patient,
a printer for printing the results of the diagnosis,
the slit-lamp picture remote diagnosis system comprises:
a login module for registering and logging in the slit-lamp picture remote diagnosis system,
a personal information management module for recording basic information of a patient and an ophthalmologist, the personal information management module comprising: an expert management sub-module for managing the personal information of the expert, a patient management sub-module for managing the personal information of the patient,
a picture quality monitoring module for being directed at slit lamp shooting picture quality carries out monitoring, and picture quality monitoring module includes: a trained picture quality recognition model submodule is established based on a ResNet50 deep learning algorithm, a voice prompt submodule which is used for outputting voice after low-quality picture problems are classified and corresponded,
a diagnostic management module for controlling a printer to print diagnostic results, the diagnostic management module comprising: a diagnosis sheet filling sub-module used for an ophthalmologist to fill in diagnosis opinions according to the eye photos of the patient, a diagnosis sheet generating sub-module used for generating an electronic diagnosis sheet and calling a printer to output paper,
a database for storing clear photographs, personal information, diagnostic procedures, diagnostic results and prompt voices, the prompt voices being stored in the database in a byte stream,
and the uploading module is used for uploading the acquired clear photos and the personal information to the database.
The first display screen, the second display screen, the loudspeaker and the printer are electrically connected with the slit lamp.
As shown in fig. 4, the construction and training process of the picture quality monitoring model is as follows:
s1: selecting 1.2 ten thousand high-quality and low-quality slit lamp pictures marked by an ophthalmology expert, homogenizing all picture pixel values to be between 0 and 1, and adjusting the size of the picture to be 224 multiplied by 224 pixels to be used as an image data set;
s2: constructing a slit lamp picture quality monitoring model by using a ResNet50 deep learning algorithm, and optimizing the slit lamp picture quality monitoring model by using a self-adaptive moment estimation optimizer;
s3: training a picture quality monitoring model by using an image data set;
s4: performing 180 rounds of iterative training by using a plurality of models, and in the training process, after each iterative training, evaluating the verification loss by using a verification set, wherein the verification loss is used as a reference for model selection;
s5: if the verification loss does not improve for 60 consecutive rounds, the training process is stopped and the model with the minimum verification loss is used as the finally selected model.
Wherein the initial learning rate of the adaptive moment estimation optimizer is 0.001, beta 1/0.9 and beta2/0.999, and the fuzzy coefficient is 1e-7The learning rate decays to 0.
Example 2
The embodiment is an application scenario based on embodiment 1, and includes the following steps:
s1: a patient registers and logs in the slit lamp picture remote diagnosis system at a mobile terminal through a login module, and the information of the patient can be checked through personal information management;
s2: the picture collection personnel operates the slit lamp to shoot the eyes of the patient, after the shooting is finished, the picture quality identification model submodule carries out quality judgment analysis on the picture, when the shot picture is judged to be a low-quality picture, the shot picture with the unclear part selected out from the frame is displayed on the second display screen, meanwhile, the picture quality identification model submodule enables the reason causing the unclear picture to correspond to the corresponding prompt voice in the database and plays the prompt voice through the loudspeaker to prompt the picture collection personnel, and the process is shown in figure 3;
s3: after adjusting the slit lamp, the picture collector shoots a clear eye picture and uploads the picture to the database through the uploading module;
s4: an ophthalmologist logs in a slit lamp picture remote diagnosis system at a mobile terminal through a login module;
s5: the ophthalmologist checks the eye picture of the patient through the diagnosis sheet filling sub-module, fills the diagnosis sheet according to the condition of the patient, and uploads the diagnosis sheet to the database through the uploading module after filling;
s6: the patient generates a diagnosis list through the diagnosis list generation submodule and prints the diagnosis list through a printer.
Example 3
This example differs from example 1 in that:
as shown in fig. 5, the slit-lamp picture quality monitoring system further includes:
a first camera for taking a picture of the patient,
a second camera for taking a picture of a remote ophthalmologist,
the slit-lamp picture remote diagnosis system further comprises:
a remote diagnosis module for remote diagnosis and treatment of an ophthalmologist and a patient, the remote diagnosis module comprising: a camera calling submodule for calling the camera, a face diagnosis video recording submodule for recording the diagnosis process,
a management module of arranging a shift for managing expert's arrangement of shifts, the management module of arranging a shift includes: an on-line diagnosis management submodule for managing the expert on-line diagnosis working period, a face-examination management submodule for managing the expert face-examination working period,
and the notification module is used for notifying the patient to check and accept the diagnosis list after the on-line diagnosis of the ophthalmology specialist is finished.
Example 4
The embodiment is an application scenario based on embodiment 3, and includes the following steps:
s1: a patient registers and logs in the slit lamp picture remote diagnosis system at a mobile terminal through a login module, and the information of the patient can be checked through personal information management;
s2: the patient inquires about the scheduling condition of the expert through the scheduling management module, wherein the patient can check the online diagnosis time period of the ophthalmology expert through the online diagnosis management submodule (the patient can go to a hospital at any time, the ophthalmology expert directly diagnoses the patient through the clear eye picture in the online diagnosis time period), and can check the remote diagnosis time period of the ophthalmology expert through the diagnosis management submodule (the patient goes to the hospital in the remote diagnosis time period of the ophthalmology expert, and the ophthalmology expert can diagnose by checking the clear eye picture of the patient and combining the video inquiry mode);
s3: selecting an expert to diagnose on line by a patient according to personal conditions;
s4: the picture collection personnel operates the slit lamp to shoot the eyes of the patient, after the shooting is finished, the picture quality identification model submodule carries out quality judgment analysis on the picture, when the shot picture is judged to be a low-quality picture, the shot picture with the unclear part selected out from the frame is displayed on the second display screen, meanwhile, the picture quality identification model submodule enables the reason causing the unclear picture to correspond to the corresponding prompt voice in the database and plays the prompt voice through the loudspeaker to prompt the picture collection personnel, and the process is shown in figure 3;
s5: after adjusting the slit lamp, the picture collector shoots a clear eye picture and uploads the picture to the database through the uploading module;
s6: an ophthalmologist logs in a slit lamp picture remote diagnosis system at a mobile terminal through a login module;
s7: the ophthalmologist checks the eye picture of the patient through the diagnosis sheet filling sub-module, fills the diagnosis sheet according to the condition of the patient, and uploads the diagnosis sheet to the database through the uploading module after filling;
s8: the notification module notifies the patient to check the printed diagnosis list through a short message;
s9: the patient generates a diagnosis list through the diagnosis list generation submodule and prints the diagnosis list through a printer.
Example 5
The embodiment is an application scenario based on embodiment 3, and includes the following steps:
s1: a patient registers and logs in the slit lamp picture remote diagnosis system at a mobile terminal through a login module, and the information of the patient can be checked through personal information management;
s2: the patient inquires about the scheduling condition of the expert through the scheduling management module, wherein the patient can check the online diagnosis time period of the ophthalmology expert through the online diagnosis management submodule (the patient can go to a hospital at any time, the ophthalmology expert directly diagnoses the patient through the clear eye picture in the online diagnosis time period), and can check the remote diagnosis time period of the ophthalmology expert through the diagnosis management submodule (the patient goes to the hospital in the remote diagnosis time period of the ophthalmology expert, and the ophthalmology expert can diagnose by checking the clear eye picture of the patient and combining the video inquiry mode);
s3: the patient selects remote face-examination according to personal conditions, and goes to a hospital in the period of the remote face-examination of the ophthalmologist;
s4: the picture collection personnel operates the slit lamp to shoot the eyes of the patient, after the shooting is finished, the picture quality identification model submodule carries out quality judgment analysis on the picture, when the shot picture is judged to be a low-quality picture, the shot picture with the unclear part selected out from the frame is displayed on the second display screen, meanwhile, the picture quality identification model submodule enables the reason causing the unclear picture to correspond to the corresponding prompt voice in the database and plays the prompt voice through the loudspeaker to prompt the picture collection personnel, and the process is shown in figure 3;
s5: after adjusting the slit lamp, the picture collector shoots a clear eye picture and uploads the picture to the database through the uploading module;
s6: an ophthalmologist logs in a slit lamp picture remote diagnosis system at a PC (personal computer) end through a login module;
s7: the camera calling sub-module calls a first camera to shoot a patient, a second camera shoots a remote ophthalmology specialist, a first display screen displays a specialist picture, a second display screen displays a slit lamp shot picture, and the facial examination video recording sub-module records a remote facial examination process;
s8: the expert explains the slit lamp to take a picture for the patient through the video, and makes an inquiry about the eye condition of the patient, after the inquiry is finished, fills in a diagnosis list, and after the completion of the filling in, uploads the diagnosis list to the database through an uploading module;
s9: the expert generates a diagnosis list through the diagnosis list generation submodule and prints the diagnosis list through a printer;
s10: after the remote face examination is finished, the face examination video recording sub-module uploads the recorded video to the database through the uploading module.
Claims (9)
1. A slit-lamp picture quality monitoring system, comprising:
the slit lamp is used for taking an eye picture for a patient, the slit lamp is provided with a slit lamp picture remote diagnosis system which can be accessed through other equipment,
a first display screen for displaying the diagnosis and treatment picture of the ophthalmology specialist participating in the telemedicine,
a second display screen for displaying the shooting effect of the slit-lamp photo,
a loudspeaker for prompting the picture collector to shoot the picture again after adjusting the posture of the patient,
a printer for printing the results of the diagnosis,
wherein, the slit-lamp picture remote diagnosis system includes:
a login module for registering and logging in the slit-lamp picture remote diagnosis system,
a personal information management module for recording basic information of patients and ophthalmologists,
the picture quality monitoring module is used for monitoring the quality of pictures shot by the slit lamp and comprises: a trained picture quality recognition model submodule is established based on a ResNet50 deep learning algorithm, a voice prompt submodule which is used for outputting voice after low-quality picture problems are classified and corresponded,
a diagnosis management module for controlling the printer to print the diagnosis result,
a database for storing clear photographs, personal information, diagnostic procedures, diagnostic results and prompt voices,
and the uploading module is used for uploading the acquired clear photos and the personal information to the database.
2. The system of claim 1, wherein the picture quality monitoring model is constructed and trained by:
s1: selecting 1.2 ten thousand high-quality and low-quality slit lamp pictures marked by an ophthalmology expert, homogenizing all picture pixel values to be between 0 and 1, and adjusting the size of the picture to be 224 multiplied by 224 pixels to be used as an image data set;
s2: constructing a slit lamp picture quality monitoring model by using a ResNet50 deep learning algorithm, and optimizing the slit lamp picture quality monitoring model by using a self-adaptive moment estimation optimizer;
s3: training a picture quality monitoring model by using an image data set;
s4: performing 180 rounds of iterative training by using a plurality of models, and in the training process, after each iterative training, evaluating the verification loss by using a verification set, wherein the verification loss is used as a reference for model selection;
s5: if the verification loss does not improve for 60 consecutive rounds, the training process is stopped and the model with the minimum verification loss is used as the finally selected model.
3. The system of claim 2, wherein the adaptive moment estimation optimizer has an initial learning rate of 0.001, beta 1/0.9, beta2/0.999, and a fuzzy coefficient of 1e-7The learning rate decays to 0.
4. The system of claim 1, wherein said diagnostic management module comprises: a diagnosis sheet filling sub-module used for an ophthalmologist to fill in diagnosis opinions according to the eye photos of the patient, and a diagnosis sheet generating sub-module used for generating an electronic diagnosis sheet and calling paper output of a printer.
5. A system as claimed in claim 1, wherein said personal information management module comprises: the expert management submodule is used for managing the personal information of the expert, and the patient management submodule is used for managing the personal information of the patient.
6. The system of claim 1, wherein the slit-lamp picture quality monitoring system further comprises: a first camera for taking a picture of a patient, a second camera for taking a picture of a remote ophthalmologist, the slit-lamp picture remote diagnosis system further comprising: a remote diagnosis module for remote diagnosis and treatment of ophthalmologists and patients.
7. A system according to claim 6, wherein the remote diagnostic module comprises: a camera calling submodule for calling the camera and a face diagnosis video recording submodule for recording the diagnosis process.
8. The system of claim 1, wherein the slit-lamp picture remote diagnosis system further comprises: and the scheduling management module is used for managing expert scheduling.
9. The system of claim 8, wherein the shift management module comprises: the on-line diagnosis management submodule is used for managing the expert on-line diagnosis working period, and the on-line diagnosis management submodule is used for managing the expert on-line diagnosis working period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110340719.XA CN113139935A (en) | 2021-03-30 | 2021-03-30 | Slit-lamp picture quality monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110340719.XA CN113139935A (en) | 2021-03-30 | 2021-03-30 | Slit-lamp picture quality monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113139935A true CN113139935A (en) | 2021-07-20 |
Family
ID=76811723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110340719.XA Pending CN113139935A (en) | 2021-03-30 | 2021-03-30 | Slit-lamp picture quality monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113139935A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114595747A (en) * | 2022-02-21 | 2022-06-07 | 宁波市眼科医院 | Intelligent identification system for malignant tumors of eyelids based on photos |
| CN114595747B (en) * | 2022-02-21 | 2024-05-14 | 宁波市眼科医院 | Eyelid malignancy intelligent recognition system based on photo |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204698510U (en) * | 2015-06-02 | 2015-10-14 | 福州大学 | The diabetic retinopathy optical fundus examination photographic means that picture quality ensures |
| CN109273072A (en) * | 2018-08-23 | 2019-01-25 | 北京极视互联科技有限公司 | A kind of medical method of tele-medicine |
| CN110232719A (en) * | 2019-06-21 | 2019-09-13 | 腾讯科技（深圳）有限公司 | A kind of classification method of medical image, model training method and server |
| CN110870759A (en) * | 2018-08-31 | 2020-03-10 | 福州依影健康科技有限公司 | Quality control method and system for remote fundus screening and storage device |
| CN111161257A (en) * | 2019-12-31 | 2020-05-15 | 中山大学中山眼科中心 | Wide-area fundus image quality control method and artificial intelligence system |
| CN112381821A (en) * | 2020-12-08 | 2021-02-19 | 北京青燕祥云科技有限公司 | Intelligent handheld fundus camera and image analysis method |
-
2021
- 2021-03-30 CN CN202110340719.XA patent/CN113139935A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204698510U (en) * | 2015-06-02 | 2015-10-14 | 福州大学 | The diabetic retinopathy optical fundus examination photographic means that picture quality ensures |
| CN109273072A (en) * | 2018-08-23 | 2019-01-25 | 北京极视互联科技有限公司 | A kind of medical method of tele-medicine |
| CN110870759A (en) * | 2018-08-31 | 2020-03-10 | 福州依影健康科技有限公司 | Quality control method and system for remote fundus screening and storage device |
| CN110232719A (en) * | 2019-06-21 | 2019-09-13 | 腾讯科技（深圳）有限公司 | A kind of classification method of medical image, model training method and server |
| CN111161257A (en) * | 2019-12-31 | 2020-05-15 | 中山大学中山眼科中心 | Wide-area fundus image quality control method and artificial intelligence system |
| CN112381821A (en) * | 2020-12-08 | 2021-02-19 | 北京青燕祥云科技有限公司 | Intelligent handheld fundus camera and image analysis method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114595747A (en) * | 2022-02-21 | 2022-06-07 | 宁波市眼科医院 | Intelligent identification system for malignant tumors of eyelids based on photos |
| CN114595747B (en) * | 2022-02-21 | 2024-05-14 | 宁波市眼科医院 | Eyelid malignancy intelligent recognition system based on photo |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11766173B2 (en) | Device and method for capturing, analyzing, and sending still and video images of the fundus during examination using an ophthalmoscope | |
| US20210290056A1 (en) | Systems and methods for capturing, annotating and sharing ophthalmic images obtained using a hand held computer | |
| US9211064B2 (en) | Fundus imaging system | |
| EP1349488B1 (en) | System and method for eye screening | |
| ES2668118T3 (en) | Digital slit lamp microscope system | |
| CN110428410B (en) | Fundus medical image processing method, device, equipment and storage medium | |
| US20110299036A1 (en) | Portable digital direct ophthalmoscope | |
| KR101998595B1 (en) | Method and Apparatus for jaundice diagnosis based on an image | |
| CN114207736A (en) | Information processing apparatus, information processing method, information processing system, and program | |
| JP2010142428A (en) | Photographing apparatus, photographing method, program and recording medium | |
| CN108836259B (en) | Self-photographing type shared fundus photographing device | |
| US20220076417A1 (en) | Vision screening systems and methods | |
| WO2021162124A1 (en) | Diagnosis assisting device, and diagnosis assisting system and program | |
| CN108885244A (en) | A kind of magnetic resonance multi-parameter subject monitoring method and monitoring system | |
| CN113139935A (en) | Slit-lamp picture quality monitoring system | |
| JP2015091564A (en) | Imaging apparatus and imaging method, program, recording medium | |
| JP2021194339A (en) | Slit lamp microscope | |
| KR100368522B1 (en) | Gene diagnostic system using camera for iris | |
| CN113744254A (en) | Fundus image analysis method and system, storage medium and computer equipment | |
| US20230337912A1 (en) | System, device and method for portable, connected and intelligent eye imaging | |
| CN113456095A (en) | Remote intelligent inspection system for radiology department | |
| CN111260635A (en) | Full-automatic fundus photo acquisition, eye disease identification and personalized management system with embedded lightweight artificial neural network | |
| CN105167744A (en) | Embedded self-networking information acquisition system and embedded self-networking information acquisition method based on machine vision | |
| JP7345610B2 (en) | slit lamp microscope | |
| Baker et al. | A Review of Smartphone Adapters Capable of Imaging the Anterior Segment in Ophthalmology |
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 |