CN111481165A - Full-automatic intelligent fundus disease diagnosis system - Google Patents
Full-automatic intelligent fundus disease diagnosis system Download PDFInfo
- Publication number
- CN111481165A CN111481165A CN201910081646.XA CN201910081646A CN111481165A CN 111481165 A CN111481165 A CN 111481165A CN 201910081646 A CN201910081646 A CN 201910081646A CN 111481165 A CN111481165 A CN 111481165A
- Authority
- CN
- China
- Prior art keywords
- fundus
- user
- unit
- camera
- automatic
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 60
- 201000010099 disease Diseases 0.000 title claims abstract description 35
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 35
- 210000001061 forehead Anatomy 0.000 claims abstract description 23
- 230000003287 optical effect Effects 0.000 claims abstract description 15
- 230000004913 activation Effects 0.000 claims description 24
- 210000003128 head Anatomy 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 15
- 230000001960 triggered effect Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 abstract description 5
- 210000001508 eye Anatomy 0.000 description 28
- 206010012689 Diabetic retinopathy Diseases 0.000 description 10
- 238000012216 screening Methods 0.000 description 10
- 210000001747 pupil Anatomy 0.000 description 8
- 206010012601 diabetes mellitus Diseases 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 7
- 238000012550 audit Methods 0.000 description 6
- 238000000034 method Methods 0.000 description 6
- 230000036541 health Effects 0.000 description 4
- 210000004373 mandible Anatomy 0.000 description 4
- 201000004569 Blindness Diseases 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 208000030533 eye disease Diseases 0.000 description 2
- 210000002189 macula lutea Anatomy 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000002207 retinal effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 206010025421 Macule Diseases 0.000 description 1
- 208000031662 Noncommunicable disease Diseases 0.000 description 1
- 208000017442 Retinal disease Diseases 0.000 description 1
- 206010038923 Retinopathy Diseases 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 208000037821 progressive disease Diseases 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000004393 visual impairment Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/12—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for looking at the eye fundus, e.g. ophthalmoscopes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/14—Arrangements specially adapted for eye photography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Ophthalmology & Optometry (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention provides a full-automatic intelligent fundus disease diagnosis system. Specifically, the present invention provides a diagnostic system comprising: (a) a fully automatic fundus camera (2) comprising: a photographing control unit, a base (25), and a camera body (21) having an optical head (24) provided on the base, a mandibular rest (23), and a forehead rail support; (b) the full-automatic intelligent fundus disease diagnosis system provided by the invention has the functions of fundus image acquisition, disease diagnosis, report issuing, medical treatment or further referral suggestion and the like. The diagnosis system of the invention can greatly save medical resources and is suitable for medical institutions of all levels including basic medical institutions.
Description
Technical Field
The invention belongs to the field of medical treatment, and particularly relates to a full-automatic intelligent fundus disease diagnosis system.
Background
Diabetes is one of the most important chronic non-infectious diseases that currently threaten human health worldwide. According to statistics of the international diabetes union in 2014, the number of people with diabetes worldwide has reached 3.82 hundred million, and Diabetic Retinopathy (DR) is one of seven key managed eye diseases confirmed by the world health organization, is a chronic progressive disease which seriously affects vision and even causes blindness due to retinal microvascular damage, and is the most common eye complication and the most main cause of blindness of diabetic patients.
Retinopathy caused by diabetes mellitus is completely preventable and alleviated. Regular ocular (retinal) examination of diabetics allows 90% of patients to effectively prevent severe vision loss. Community screening and community prevention are key in overall prevention and treatment of DR.
China faces a plurality of difficulties in early screening intervention of DR. On the one hand, China is diverse in ophthalmologic resources and eye protection service capabilities in hospitals and community health service centers at all levels. Few outpatients of community ophthalmology specialty are needed, eye disease screening equipment is backward, and necessary automatic screening equipment which is simple and easy to operate is lacked. Compared with the countries such as the United kingdom, Australia, the United states and the like, residents can carry out prescription and ophthalmic examination service of diabetics in communities, and the ophthalmic equipment of the communities in China is particularly insufficient. The lack of automated equipment has also resulted in many primary eye care programs not being able to be deployed on a large scale. Meanwhile, the traditional diagnosis method in the medical science at home and abroad is greatly influenced by subjective factors, and the correctness of the diagnosis result is closely related to the medical level of a doctor. Although China has a certain number of doctors and specialists on the whole, compared with specialized hospitals, particularly hospitals in medium, small and remote areas and community health service centers, the number of specialists is small, so that the DR misdiagnosis rate is high, and the patients and families are subjected to endless pain and regret; on the other hand, ophthalmologists in third-class hospitals or special hospitals are in overload work state for a long time. Due to the unreasonable distribution of medical resources, patients can go to a third-level hospital to see a doctor no matter whether the patients are big or small.
In view of the above, there is an urgent need in the art to develop a fully automatic intelligent fundus disease diagnosis system that facilitates self-help fundus screening by users (especially DR patients, diabetic patients, or other susceptible objects).
Disclosure of Invention
The invention aims to provide a full-automatic intelligent fundus disease diagnosis system which is convenient for self-help fundus screening of users (especially DR patients, diabetes patients or other susceptible objects).
In a first aspect of the present invention, there is provided a fully automatic intelligent fundus disease diagnosis system, comprising:
(a) a fully automatic fundus camera (2) comprising: a photographing control unit, a base (25), and a camera body (21) having an optical head (24) provided on the base, a mandibular rest (23), and a forehead rail support; the full-automatic fundus camera is used for photographing the fundus of the user under the control of the photographing control unit so as to acquire a fundus image of the user;
(b) the starting unit is in signal connection with the photographing control unit and is used for starting an automatic photographing program of the full-automatic fundus camera to acquire a fundus image of a user; wherein the activation unit is arranged to be controlled by the user and/or arranged to be activated automatically when the user is in position; and
(c) an analysis diagnosis unit for analyzing a fundus image of the user acquired by the fully automatic fundus camera and performing diagnosis of a fundus disease.
In another preferred example, the diagnostic system further includes:
(d) a control subsystem in signal connection with the fully automatic fundus camera and the analytical diagnostic unit.
In another preferred embodiment, the starting unit is selected from the group consisting of: a user self-controlled start-up unit, a seated self-started start-up unit, or a combination thereof.
In another preferred embodiment, the user-controlled activation unit comprises an activation switch for the user to press.
In another preferred embodiment, the self-priming in-place starting unit comprises: the automatic photographing device comprises a positioning detector for detecting whether the head of a user is positioned or not and a starting control unit in signal connection with the positioning detector, wherein the starting control unit is provided with a timer, the timer counts the time after positioning, which is recorded as t1, and when t1 is greater than or equal to the preset positioning time t0 (namely t1 is greater than or equal to t0), the starting control unit sends a starting signal to start an automatic photographing program of the full-automatic fundus camera.
In another preferred embodiment, t0 is 2-10 seconds, preferably 3-10 seconds, more preferably 4-8 seconds.
In another preferred example, the timer starts timing after detecting that the head of the user is in place and continues timing with the head kept in place; if the in-position detector detects a deviation or departure of the user's head, the timer terminates the timing and returns the timing to 0.
In another preferred embodiment, the forehead rail support includes a forehead rail (22), and a first support bar (26a) and a second support bar (26 b).
In another preferred embodiment, the activating unit is manually triggered or automatically triggered.
In another preferred example, the activation unit is of the manual trigger type and comprises a manual trigger switch (27) for the user to activate the fundus camera by himself;
the manual trigger switch is arranged on a base of the full-automatic fundus camera; or independently provided in the periphery of the fully automatic fundus camera.
In another preferred embodiment, the manually-triggered starting unit is a key switch.
In another preferred embodiment, the activation unit is the auto-trigger type, and the auto-trigger type activation unit includes a seating detector for detecting whether the head of the user is seated (the auto-trigger type activation unit is used for automatically turning on the fully automatic fundus camera when the user is seated).
In another preferred embodiment, the in-position detector includes: a second sensor (262) disposed on the forehead rail (22).
In another preferred embodiment, the in-position detector further includes: and a third sensor (261) provided to the first support rod (26a) and the second support rod (26 b).
In another preferred example, the in-position detector includes a second sensor (262) and a third sensor (261).
In another preferred embodiment, the second sensor is a pressure sensor (for detecting whether the user is holding the forehead against the forehead rail).
In another preferred example, the third sensor is a distance sensor.
In another preferred example, the third sensors are respectively arranged at corresponding positions (or symmetrical positions) of the first supporting rod (26a) and the second supporting rod (26 b).
In another preferred example, the third sensor provided on the first support rod (26a) and the third sensor provided on the second support rod (26b) are symmetrically disposed.
In another preferred example, the third sensor located on the first support rod (26a) and the third sensor located on the second support rod (26b) are located at the same horizontal position.
In another preferred example, the control subsystem further comprises an interactive interface.
In another preferred embodiment, said activation unit is independent of or integrated with the fully automatic fundus camera.
In another preferred example, the full-automatic fundus camera further comprises an iris recognition module, and the iris recognition module is in signal connection with the photographing control unit.
In another preferred example, the camera body (21) is provided with a first moving mechanism that allows the camera body (21) to move in a horizontal direction (X-axis and Y-axis) and a vertical direction (Z-axis direction) with respect to the base.
In another preferred example, the lower jaw support (23) is provided with a second moving mechanism that moves the lower jaw support (23) in the vertical direction (Z-axis direction).
In another preferred embodiment, the diagnostic system further comprises:
(e) the voice prompt unit is used for sending out preset voice for prompting a user; preferably, the voice prompt unit is in signal connection with the control subsystem.
In another preferred embodiment, the diagnostic system further comprises:
(f-1) an identification unit; and
and (f-2) a user information subsystem.
In another preferred embodiment, the user identity recognition unit comprises a fingerprint recognition module, a face recognition module, an iris recognition module and/or an identity document card reading module.
In another preferred embodiment, the diagnostic system further comprises:
(g) the image auditing unit is used for auditing whether the image acquired by the full-automatic fundus camera meets a preset image standard or not; preferably, the image auditing unit is in signal connection with the control subsystem.
In another preferred embodiment, the diagnostic system further comprises:
(h) and the result output unit is in signal connection with the control subsystem.
In another preferred example, the diagnosis result output unit is an intelligent terminal, a printer, and/or an interface capable of connecting with an external storage device.
In another preferred example, the fully automatic fundus camera further comprises a flash and/or a photosensitive element.
In another preferred example, the photographic control unit includes:
(i) the pupil searching and calibrating module is used for enabling the optical head to move to a pupil position and calibrate;
(ii) the automatic focusing module is used for searching a shooting center and focusing on the shooting center; and
(iii) and the brightness adjusting module is used for adjusting the brightness during shooting.
In another preferred example, the lower jaw support (23) of the full-automatic fundus camera is further provided with a first sensor which is a pressure sensor and is in signal connection with a camera control unit.
It is to be understood that within the scope of the present invention, the above-described features of the present invention and those specifically described below (e.g., in the examples) may be combined with each other to form new or preferred embodiments. Not to be reiterated herein, but to the extent of space.
Drawings
Fig. 1 is a schematic diagram of one embodiment of the fully automatic intelligent fundus disease diagnosis system with a manually triggered start unit of the present invention.
Fig. 2 is a schematic diagram of another embodiment of the fully automatic intelligent fundus disease diagnosis system with a manually triggered start unit according to the present invention.
Fig. 3 is a schematic diagram of an embodiment of the fully automatic intelligent fundus disease diagnosis system with an auto-triggered start unit according to the present invention.
Fig. 4 shows the connection relationship of the parts of the fundus disease diagnosis system in one embodiment of the present invention.
Fig. 5 shows the connection relationship of the parts of the fundus disease diagnosis system in another embodiment of the present invention.
Fig. 6 shows a flow of acquiring a fundus image in one embodiment of the present invention.
In the figure, the respective designations are as follows:
2 is a full-automatic fundus camera;
21 is a camera body, 22 is a forehead crosspiece, 23 is a mandible support, 24 is an optical head, 25 is a base, 26a is a first supporting rod, 26b is a second supporting rod, and 27 is a manual trigger switch;
Detailed Description
The present inventors have conducted extensive and intensive studies. In order to solve the problems of unbalanced treatment resources, few primary doctors and the like, a fully-automatic fundus camera is integrated by a user self-control starting unit and/or a positioning self-starting unit through structural optimization, so that the fully-automatic fundus camera is effectively integrated with a starting unit, an analysis and diagnosis unit and a voice prompt unit which do not need to be operated by doctors, self-help fundus image acquisition is realized, a user can perform primary diagnosis or screening of fundus diseases by the diagnosis system, and medical resources are greatly saved. The present invention has been completed based on this finding.
Term(s) for
As used herein, the term "signal connection" refers to the transfer of data, instructions, etc. between 2 units or modules or systems, either by wire or wirelessly.
As used herein, "fully automatic smart fundus camera," "fully automatic fundus camera," or "fundus camera" may be used interchangeably to a fully automatic fundus camera for acquiring images of the fundus of a user.
As used herein, the term "eye position" refers to the position of an eyeball in an ophthalmic examination.
Full-automatic intelligent fundus disease diagnosis system
As shown in fig. 1, fig. 2, fig. 3, fig. 4, and fig. 5, the present invention provides a fully automatic fundus disease diagnosis system including:
(a) fully automatic fundus camera (2) comprising: a photographing control unit, a base (25), and a camera body (21) having an optical head (24), a mandibular rest (23), and a forehead rail support, which are provided on the base; and the fully automatic fundus camera is used to acquire (preferably, the fully automatic fundus camera is used to automatically switch left and right eye photographing, automatically find pupils and calibrate, automatically focus, and automatically photograph and output a fundus image of the user, thereby acquiring a fundus image) a fundus image of the user under the control of the photographing control unit.
In one embodiment, the camera body (21) further comprises an iris recognition module in signal connection with the camera control unit for acquiring eye position information of the user. Preferably, the iris recognition module is further in signal connection with the control subsystem and is used for acquiring iris information.
In one embodiment, the camera body (21) is provided with a first moving mechanism that allows the camera body (21) to move in a horizontal direction (X-axis and Y-axis) and a vertical direction (Z-axis direction) with respect to the base; and/or the lower jaw support (23) is provided with a second moving mechanism which enables the lower jaw support (23) to move in the vertical direction (Z-axis direction); the first moving mechanism and/or the second moving mechanism are/is used for adjusting the relative position of the optical head of the camera body and the eyes of the user according to the eye position information obtained by the iris recognition module under the control of the photographing control unit, so that the eyes of the user are basically positioned right in front of the optical head, and the subsequent pupil finding and calibration are facilitated.
In a particular embodiment, the fully automatic fundus camera further comprises a flash and/or a photosensitive element.
Wherein the photographing control unit includes: (i) the pupil searching and calibrating module is used for moving the optical head to a pupil position (for example, the camera body is moved back and forth and left and right through the first moving mechanism) and calibrating; (ii) an auto-focus module for finding a photographing center (preferably, the photographing center is a macula or a video disc) and focusing on the photographing center; and (iii) a brightness adjusting module for adjusting the brightness during shooting (such as adjusting the brightness of the flash lamp according to the sensing of the conductive ambient light intensity by the photosensitive element).
In another preferred example, the lower jaw support (23) of the full-automatic fundus camera is further provided with a first sensor which is a pressure sensor and is in signal connection with the photographic control unit, and the first sensor is used for confirming whether a user places a lower jaw on the lower jaw support.
(b) The starting unit is in signal connection with the photographing control unit and is used for starting the full-automatic fundus camera to acquire a fundus image of a user;
(c) an analysis diagnosis unit for analyzing a fundus image of the user acquired by the fully automatic fundus camera and performing diagnosis of a fundus disease, for example, whether the user has a fundus disease and/or the progress of the user's fundus disease, and specifically, the unit analyzes the fundus image and performs diagnosis of the fundus disease by means of an artificial intelligence fundus disease diagnosis software, which may employ a commercially available or autonomously developed diagnosis software, for example, a diagnosis software based on big data and applied with a deep learning neural convolution network technique.
In one embodiment, as shown in fig. 4, the analysis and diagnosis unit is locally provided, and the obtained fundus image is directly analyzed in the locally provided analysis and diagnosis unit and the result is directly output.
In another embodiment, as shown in fig. 5, the analysis and diagnosis unit is provided in a cloud server (including a DR analysis and diagnosis center), and the obtained fundus image is transmitted to the cloud via the control subsystem and analyzed.
(d) The control subsystem is in signal connection with the full-automatic fundus camera, the analysis and diagnosis unit and the voice prompt unit; preferably, the control subsystem further comprises an interactive interface for user selection (for example, the user may select a way of viewing the diagnosis result on the interactive interface, such as obtaining a paper report or sending the paper report to the user's smart terminal);
in a specific embodiment, the control subsystem further records the number of times of the image auditing unit failing to audit, and compares the recorded number of times with a preset maximum number of attempts (generally, the preset maximum number of attempts is 2-5 times, preferably, 3 times); preferably, the control subsystem is further configured to control the voice prompt unit to issue a voice prompt corresponding to the audit result according to the audit result (pass or fail) of the image audit unit (if the audit is passed, the voice prompt unit informs the user that the fundus image acquisition is completed, and waits for a fundus disease diagnosis result); if the number of times of non-passing of the audit is less than or equal to the preset maximum trial number, the control subsystem controls the voice prompt unit to inform the user that the fundus image needs to be shot again; if the number of times of non-passing examination is larger than the preset maximum number of times of trial, the control subsystem controls the voice prompt unit to inform the user that the fundus image cannot be obtained and please go to an ophthalmologic clinic;
(e) a voice prompt unit for emitting a preset sound (e.g., a prompt tone, a prerecorded voice, etc.) for prompting a user (e.g., prompting a user to hold the head against a forehead rail, hold the posture still, look ahead, take a picture again, complete acquisition of a fundus image to allow the head to move away from a fully automatic fundus camera, etc.);
(f-1) an identification unit; the user identification unit is a module with a fingerprint information acquisition function, and/or a module with an iris information acquisition function, and/or a module with a card information reading function (such as an IC card reader), and the identity identification unit is in signal connection with the control subsystem. Wherein the module having the iris information acquisition function may be a second iris recognition module provided independently or an iris recognition module of the camera body (21).
And (f-2) a user information subsystem, wherein the user information subsystem comprises a user database and is used for calling the personal information of the corresponding user from the user database according to the identification information (such as fingerprints, card identification information, iris information, account passwords and the like) acquired by the identity identification unit. Wherein the personal information includes: name, gender, age, and/or identification (identification number, social security number, etc.); the personal information may also include a fingerprint, a past medical history, and previously acquired fundus images and diagnosis results of fundus diseases, and the like. And the (f) user information subsystem further comprises a user registration unit for creating new user information in the user database and associating the corresponding identification information with the new user information. Preferably, the diagnosis system is further configured to store the acquired fundus image and/or the diagnosis result of the fundus disease in the corresponding user information, and to be used for the next diagnosis of the fundus disease. As shown in fig. 4, the user information subsystem is local and directly connected with the identification unit through signals; alternatively, as shown in fig. 5, the user information subsystem is located in the cloud and is in signal connection with the identity recognition unit via the control subsystem.
(g) The image auditing unit is used for auditing whether the image acquired by the full-automatic fundus camera meets a preset image standard (namely whether the image meets the requirement of an image required by analysis and diagnosis), and is in signal connection with the control subsystem; and
(h) and the result output unit is in signal connection with the analysis and diagnosis unit (local) (figure 4) or the control subsystem (figure 5). Preferably, the diagnosis result output unit is an intelligent terminal (for example, a handheld terminal of a user with a set of software installed thereon, or a terminal for a doctor to retrieve user information), a printer, and/or an interface (such as a USB interface) capable of connecting with an external storage device.
In another preferred example, as shown in fig. 1, the activation unit is independent of the fully automatic fundus camera (for example, a user can trigger activation of the fully automatic fundus camera by the activation unit to acquire a fundus image under the control of the photographing control unit); alternatively, as shown in fig. 2 and 3, the activation unit is integrated with the fully automatic fundus camera (for example, the user activates the fully automatic fundus camera by the activation unit to acquire a fundus image under the control of the photographing control unit). In one embodiment, the fully automatic fundus camera is a self-designed fully automatic fundus camera or a fully automatic fundus camera known in the art (e.g., a topokang TRC-NW400 fundus camera, or a CENTERvue DRS).
In another preferred example, the activation unit is integrated with the fully automatic fundus camera.
In another preferred example, the activation unit is integrated in the fully automatic fundus camera.
In another preferred example, the starting unit is of a manual trigger type or an automatic trigger type, and after the starting or delaying of the manual or automatic trigger starting unit is started for 0.1-10 s (preferably 0.1-3s), the fundus camera is started to shoot the fundus of the user.
In another preferred example, as shown in fig. 1 and 2, the activation unit is of the manual triggering type and comprises a manual trigger switch (27) for the user to self-activate the fundus camera; preferably, the manual trigger type starting unit is a key switch.
In one embodiment, as shown in fig. 2, the manual trigger switch is provided to a base (user end portion) of the fully automatic fundus camera.
In another embodiment, as shown in fig. 1, the manual trigger switch is independently provided at the periphery of the fully automatic fundus camera (the periphery is such that the manual trigger switch can be turned on when the user places the chin on the mandibular rest of the fully automatic fundus camera).
In a preferred embodiment, as shown in fig. 3, the activation unit is auto-triggering (i.e. it is a self-priming in-place activation unit) and is used to automatically turn on the fully automatic fundus camera when the user is in place (i.e. has fixed the forehead to the forehead rail and faces the camera with the optical head straight); and the starting unit includes: the automatic photographing device comprises a positioning detector for detecting whether the head of a user is positioned or not and a starting control unit in signal connection with the positioning detector, wherein the starting control unit is provided with a timer, the timer counts the time after positioning, which is recorded as t1, and when t1 is greater than or equal to the preset positioning time t0 (namely t1 is greater than or equal to t0), the starting control unit sends a starting signal to start an automatic photographing program of the full-automatic fundus camera. Preferably, t0 is 2-10 seconds, preferably 3-10 seconds, more preferably 4-8 seconds. Preferably, the timer starts timing after detecting that the head of the user is in place and continues timing with the head kept in place; if the in-position detector detects a deviation or departure of the user's head, the timer terminates the timing and returns the timing to 0.
As shown in fig. 3, in a specific embodiment, the detector (i.e., in-position detector) of the auto-triggered start unit (i.e., in-position self-starting start unit) includes: a second sensor (262) provided to the forehead rail (22) for detecting whether the user is holding the forehead against the forehead rail. In another embodiment, the detector further comprises a third sensor (261) provided on the support bars (26a, 26b) (the third sensor is composed of two parts and provided on the first support bar (26a) and the second support bar (26b), respectively, and the third sensor on the first support bar is not shown), and the third sensor is used for detecting whether the user faces the front. Preferably, the second sensor is a pressure sensor; and/or the third sensor is a distance sensor. In a preferred embodiment, the third sensors are respectively arranged at corresponding positions of the support rod (26a) and the support rod (26b) (i.e. the third sensors respectively arranged at the first support rod (26a) and the second support rod (26b) are positioned at the same horizontal position).
In a preferred embodiment, when the distance to the face of the user obtained by the distance sensor located at the support bar (26a) is close to or equal to the distance to the face of the user obtained by the distance sensor located at the support bar (26b) (the distance differs by ≦ 1cm, preferably ≦ 0.5 cm); and when the pressure sensed by the second pressure sensor is uniformly distributed; it is judged that the head of the user is in place.
The automatic trigger starting unit (namely the in-position self-starting unit) of the fundus disease diagnosis system obviously reduces the in-position misjudgment rate of a user through the combination of multiple sensors (detectors), thereby greatly improving the success rate of acquiring fundus images. In addition, the sensor is used for judging whether the user is in place or not, so that the misjudgment of the user on the place caused by less experience is avoided.
As shown in fig. 6, in a specific embodiment, the method for the user to perform self-service diagnosis by the system of the present invention is as follows:
1. confirming identity information:
under the control of the control subsystem, a voice prompt unit prompts a user to place an identity card or a medical insurance card on a card reader to identify the identity, or prompts the user to carry out fingerprint identification, or prompts the user to input an account password, and calls personal information of the user corresponding to identification information from a user database through a user information subsystem according to the obtained identification information; if the personal information of the corresponding user is not found in the user database, the user is prompted to register the personal information and associate the personal information with the identification information.
2. The user is in position by himself:
under the control of the control subsystem, the user is prompted by the voice prompt unit to sit in front of the fundus camera and face right ahead, and the chin is placed on the mandible support, and the forehead abuts against the forehead crosspiece.
Preferably, after a time interval (e.g., 1 minute), the first sensor located on the mandibular rest again audibly prompts the user if it does not detect that the user has placed the mandible on the mandibular rest.
3. Starting the fundus camera:
after the user is in place, the starting unit automatically starts the full-automatic fundus camera to acquire a fundus image (when the system shown in figure 3 is used); or
Under the control of the control subsystem, prompting the user via the voice prompt unit to manually activate the fully automatic fundus camera, e.g., turning on a manual trigger switch of the activation unit (e.g., pressing an activation button) to acquire a fundus image (when using the apparatus of fig. 1 or 2);
4. automatic fundus image acquisition by fundus camera
Under the control of the control subsystem, prompting a user to start photographing by the voice prompt unit, asking the user to fix the head position, not move, looking ahead, and/or watching an optical head of the camera body, preferably watching a cursor positioned at the center of the optical head (lens);
and the fully automatic fundus camera starts to take a picture under the control of the picture taking control unit to acquire a fundus image of the user;
in one particular embodiment of the present invention,
(4.1) confirming whether the eye position meets the photographing requirement (namely whether the optical head is basically positioned right in front of the eyes of the patient) according to the eye position information obtained by the iris recognition module;
if the detection requirement is not met, adjusting the relative position of the camera body and the user;
if the iris recognition module can not obtain the eye position information, the eye position information is fed back to the control subsystem through the photographing control unit, and then the voice prompt unit of the voice system prompts the user to see the right front again.
(4.2) when the eye position meets the photographing requirement, the optical head moves to the pupil position of the left eye or the right eye under the control of the pupil searching and calibrating module and is calibrated; under the control of an automatic focusing module, automatically focusing on a shooting center (such as yellow spots and video discs); under the control of the brightness adjusting module, adjusting the flash brightness during photographing; taking fundus images of the left or right eye; the optical head is moved to the eye where photographing is not performed, and the fundus image of the other eye is photographed in the same process;
two different fundus images are collected by each eye, namely 1 fundus image with the macula lutea as the center and 1 fundus image with the optic disc as the center; the shooting process does not need the user to cooperate with moving the head position, and the camera automatically finds the shooting center and focuses.
5. Examination of fundus images
Under the control of the control subsystem, the fundus image of the user is transmitted to an image auditing unit for auditing.
And if the obtained fundus image meets the analysis standard after the examination is qualified, prompting the user that the photographing is finished.
And if the examination is unqualified, the obtained fundus image does not meet the analysis standard, prompting the user to take a picture again. Generally, the repeated attempts are not more than 3 times, and if the acquisition is still unsuccessful after 3 times, the user is prompted to visit the ophthalmology department.
6. Fundus image analysis
Under the control of the control subsystem, the fundus images meeting the standard are transmitted to the analysis and diagnosis unit, the fundus images are read, analyzed and diagnosed by the built-in Artificial Intelligence (AI) fundus disease diagnosis software, and the diagnosis result (namely the primary screening result) is fed back to the user through the result output unit.
The main advantages of the invention include:
(a) the fundus diagnosis system can realize fundus examination and obtain a detection result through self-operation or automatic operation by a user or users in a fully automatic manner without the assistance of medical care personnel, and time cost, labor cost and diagnosis and treatment cost are greatly saved.
(b) The system can conveniently, efficiently and accurately carry out fundus image information acquisition and instant diagnosis on users who receive and use the system in each grade of medical institutions including basic medical institutions, provides great convenience for preliminary screening of fundus diseases, saves medical resources to a great extent, improves diagnosis and treatment efficiency, and provides reliable reference for the work of clinicians.
(c) The full-automatic intelligent fundus disease diagnosis system can provide DR auxiliary medical diagnosis information for community doctors, quickly and timely obtain correct diagnosis results, is beneficial to comprehensively promoting DR community screening, solves the problem that ophthalmic resources and eye protection service capability in China are seriously insufficient, and has great social and economic significance.
(d) The full-automatic intelligent fundus disease diagnosis system is convenient to use, almost has no requirement on the use level of users, and is particularly suitable for the aged users.
(e) The fundus disease diagnosis system belongs to a user self-service diagnosis system and is beneficial to protecting the privacy of users.
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. The following examples are experimental procedures without specific conditions noted, or according to the manufacturer's recommendations.
Example 1
The system shown in fig. 3 is adopted, and is placed in a community, and volunteers perform self-detection (without assistance of workers).
The general flow of using the system is as follows:
1. the voice prompts the volunteer to put the identity card or the medical insurance card on the card reader to identify the identity.
2. The voice prompts the examinee to sit in front of the fundus camera.
3. The voice prompts the examinee to face right ahead, place the chin on the mandible support, and the forehead abuts against the forehead crosspiece.
4. The fundus camera automatically starts to collect fundus pictures after the head position of the fundus diagnosis system is adjusted, the voice prompts a user to start photographing, the user is asked to fix the head position, and a cursor of a detected eye watching the center of a camera lens does not need to move
5. The fundus camera automatically and sequentially takes fundus images of the right eye and the left eye, and each eye takes two or more pictures (for example, two pictures are taken, the position of the picture is 1 picture taking the macula lutea as the center, and the position of the picture is 1 picture taking the optic disc as the center). The camera automatically finds the shooting center and focuses without the cooperation of a user with moving the head position in the shooting process
6. If the first image acquisition does not meet the standard, the system prompts the user to try acquisition again, the repeated attempts do not exceed 3 times, the acquisition is still not successful after 3 times, and the user is prompted to visit the ophthalmology department
7. And prompting the completion of the acquisition of the binocular fundus picture by voice.
Through examination, the average time for acquiring fundus images (including 2 left eyes and 2 right eyes) of each volunteer is 2-3 minutes. (volunteers sit on the fundus camera to start photographing and start timing)
The obtained fundus images are analyzed by the analysis and diagnosis unit and a doctor respectively, and the obtained results are consistent.
All documents referred to herein are incorporated by reference into this application as if each were individually incorporated by reference. Furthermore, it should be understood that various changes and modifications of the present invention can be made by those skilled in the art after reading the above teachings of the present invention, and these equivalents also fall within the scope of the present invention as defined by the appended claims.
Claims (10)
1. A full-automatic intelligent fundus disease diagnosis system is characterized by comprising:
(a) a fully automatic fundus camera (2) comprising: a photographing control unit, a base (25), and a camera body (21) having an optical head (24) provided on the base, a mandibular rest (23), and a forehead rail support; the full-automatic fundus camera is used for photographing the fundus of the user under the control of the photographing control unit so as to acquire a fundus image of the user;
(b) the starting unit is in signal connection with the photographing control unit and is used for starting an automatic photographing program of the full-automatic fundus camera to acquire a fundus image of a user; wherein the activation unit is arranged to be controlled by the user and/or arranged to be activated automatically when the user is in position;
(c) an analysis diagnosis unit for analyzing a fundus image of the user acquired by the fully-automatic fundus camera and performing diagnosis of a fundus disease; and
(d) a control subsystem in signal connection with the fully automatic fundus camera and the analytical diagnostic unit.
2. The diagnostic system of claim 1, wherein the forehead rail support includes a forehead rail (22), and a first support bar (26a) and a second support bar (26 b).
3. The diagnostic system of claim 1, wherein the activation unit is manually-triggered and comprises a manual trigger switch (27) for self-activation of the fundus camera by a user;
the manual trigger switch is arranged on a base of the full-automatic fundus camera; or independently provided in the periphery of the fully automatic fundus camera.
4. The diagnostic system of claim 1, wherein the activation unit is auto-triggered, and wherein the auto-triggered activation unit comprises a seating detector for detecting whether the head of the user is seated.
5. The diagnostic system of claim 4, wherein the in-position detector comprises: a second sensor (262) disposed on the forehead rail (22).
6. The diagnostic system of claim 5, wherein the second sensor is a pressure sensor.
7. The diagnostic system of claim 4, wherein the in-position detector further comprises: and a third sensor provided on the first support rod (26a) and the second support rod (26 b).
8. The diagnostic system of claim 7, wherein the third sensor is a distance sensor.
9. The diagnostic system of claim 7, wherein the third sensor provided on the first support bar (26a) and the third sensor provided on the second support bar (26b) are symmetrically disposed.
10. The diagnostic system according to claim 1, characterized in that the mandibular rest (23) of the fully automatic fundus camera is further provided with a first sensor, which is a pressure sensor and is in signal connection with the camera control unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910081646.XA CN111481165A (en) | 2019-01-28 | 2019-01-28 | Full-automatic intelligent fundus disease diagnosis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910081646.XA CN111481165A (en) | 2019-01-28 | 2019-01-28 | Full-automatic intelligent fundus disease diagnosis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111481165A true CN111481165A (en) | 2020-08-04 |
Family
ID=71788588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910081646.XA Pending CN111481165A (en) | 2019-01-28 | 2019-01-28 | Full-automatic intelligent fundus disease diagnosis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111481165A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112057037A (en) * | 2020-09-30 | 2020-12-11 | 宁波市眼科医院 | Automatic change ophthalmology inspection robot |
| CN112084961A (en) * | 2020-09-11 | 2020-12-15 | 宁波市眼科医院 | Artificial intelligence ophthalmopathy screening diagnosis and treatment system based on ophthalmic robot |
| CN112102941A (en) * | 2020-09-11 | 2020-12-18 | 宁波市眼科医院 | Eye disease screening robot carrying on eye fundus photo screening system |
| CN113273960A (en) * | 2021-07-19 | 2021-08-20 | 中山大学中山眼科中心 | Wearable ophthalmopathy self-diagnosis equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043553A1 (en) * | 2013-09-30 | 2015-04-02 | xVYSOKE UCENI TECHNICKE V BRNE | Ophthalmic diagnostic apparatus and method of its operation |
| CN106821303A (en) * | 2017-04-10 | 2017-06-13 | 上海健康医学院 | A kind of autonomous type Fundus photography imaging system and method |
| CN108553079A (en) * | 2017-05-04 | 2018-09-21 | 深圳硅基仿生科技有限公司 | Lesion identifying system based on eye fundus image |
| CN210277126U (en) * | 2019-01-28 | 2020-04-10 | 上海市眼病防治中心 | Full-automatic intelligent fundus disease diagnosis system |
-
2019
- 2019-01-28 CN CN201910081646.XA patent/CN111481165A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043553A1 (en) * | 2013-09-30 | 2015-04-02 | xVYSOKE UCENI TECHNICKE V BRNE | Ophthalmic diagnostic apparatus and method of its operation |
| CN106821303A (en) * | 2017-04-10 | 2017-06-13 | 上海健康医学院 | A kind of autonomous type Fundus photography imaging system and method |
| CN108553079A (en) * | 2017-05-04 | 2018-09-21 | 深圳硅基仿生科技有限公司 | Lesion identifying system based on eye fundus image |
| CN210277126U (en) * | 2019-01-28 | 2020-04-10 | 上海市眼病防治中心 | Full-automatic intelligent fundus disease diagnosis system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112084961A (en) * | 2020-09-11 | 2020-12-15 | 宁波市眼科医院 | Artificial intelligence ophthalmopathy screening diagnosis and treatment system based on ophthalmic robot |
| CN112102941A (en) * | 2020-09-11 | 2020-12-18 | 宁波市眼科医院 | Eye disease screening robot carrying on eye fundus photo screening system |
| CN112084961B (en) * | 2020-09-11 | 2021-05-14 | 宁波市眼科医院 | Artificial intelligence ophthalmopathy screening diagnosis and treatment system based on ophthalmic robot |
| CN112057037A (en) * | 2020-09-30 | 2020-12-11 | 宁波市眼科医院 | Automatic change ophthalmology inspection robot |
| CN113273960A (en) * | 2021-07-19 | 2021-08-20 | 中山大学中山眼科中心 | Wearable ophthalmopathy self-diagnosis equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111481165A (en) | Full-automatic intelligent fundus disease diagnosis system | |
| US11766172B2 (en) | Ophthalmic examination and disease management with multiple illumination modalities | |
| EP1349488B1 (en) | System and method for eye screening | |
| US5943116A (en) | System for imaging an ocular fundus semi-automatically at high resolution and wide field | |
| CN210277126U (en) | Full-automatic intelligent fundus disease diagnosis system | |
| US7232220B2 (en) | System for vision examination utilizing telemedicine | |
| US20210290056A1 (en) | Systems and methods for capturing, annotating and sharing ophthalmic images obtained using a hand held computer | |
| KR101637314B1 (en) | Apparatus to image and analyses the eyes and fundus oculi and its method thereof | |
| US10713483B2 (en) | Pupil edge detection in digital imaging | |
| CN108392174B (en) | Automatic examination method and system for retinopathy of prematurity | |
| CN110870759A (en) | Quality control method and system for remote fundus screening and storage device | |
| WO2011029531A1 (en) | Optometrist client | |
| CN113889268A (en) | Physical examination system and physical examination method for driver | |
| CN113077889A (en) | Artificial intelligence ophthalmopathy screening service method and system | |
| EP2218398A1 (en) | Person recognition method and device incorporating the anatomic location of the retina as a biometric constant, corresponding to the physiological location of the projection of the visual axis | |
| US20220104703A1 (en) | Methods and apparatus for screening for maladies by retinal scan | |
| KR101369565B1 (en) | Pupil measuring system with smart device and method for measuring pupil by using the system | |
| CN112022084A (en) | Fundus inspection system | |
| KR20210104381A (en) | System and method for diagnosing eye by online | |
| KR20200049182A (en) | The method and system for pre-perimetric glaucoma diagnosis | |
| US20230190097A1 (en) | Cataract detection and assessment | |
| KR20220029799A (en) | AI-based system and method for remote diagnosis eye diseases | |
| KR20220093781A (en) | Wearable neurological disease diagnosis device and the method | |
| CN115497229A (en) | Using method and system of unmanned self-service portable mydriasis-free fundus camera | |
| MXPA99008987A (en) | A system for imaging an ocular fundus semi-automatically at high resolution and wide field |
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 |