WO2024095261A1 - Système et procédé de diagnostic et de traitement de divers troubles du mouvement et de diverses maladies de l'œil - Google Patents

Système et procédé de diagnostic et de traitement de divers troubles du mouvement et de diverses maladies de l'œil Download PDF

Info

Publication number
WO2024095261A1
WO2024095261A1 PCT/IL2023/051119 IL2023051119W WO2024095261A1 WO 2024095261 A1 WO2024095261 A1 WO 2024095261A1 IL 2023051119 W IL2023051119 W IL 2023051119W WO 2024095261 A1 WO2024095261 A1 WO 2024095261A1
Authority
WO
WIPO (PCT)
Prior art keywords
eye
distance
pupil
camera
user
Prior art date
Application number
PCT/IL2023/051119
Other languages
English (en)
Inventor
Ilan Shimshoni
Ahmad KHATIB
Shmuel RAZ
Original Assignee
Carmel Haifa University Economic Corporation Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Carmel Haifa University Economic Corporation Ltd. filed Critical Carmel Haifa University Economic Corporation Ltd.
Publication of WO2024095261A1 publication Critical patent/WO2024095261A1/fr

Links

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
    • A61B3/02—Subjective types, i.e. testing apparatus requiring the active assistance of the patient
    • A61B3/08—Subjective types, i.e. testing apparatus requiring the active assistance of the patient for testing binocular or stereoscopic vision, e.g. strabismus
    • 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
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G06V40/193—Preprocessing; Feature extraction

Definitions

  • the present invention relates generally to methods of diagnosing eye disorders. More specifically, the present invention relates to using a method for the diagnosis and treatment of various movement eye disorders using computer vision.
  • Convergence Insufficiency is characterized by a decreased ability to converge the eyes and maintain binocular fusion while focusing on a near target.
  • patients In searching for the most common complaints of (CI), patients often complain of eye strain when reading, closing one eye when reading, or blurred vision after short periods of near work.
  • the diagnosis of primary CI is based on the patient’s presenting symptoms and the clinical signs.
  • the etiology of isolated CI not related to trauma or neurological disease, has not been completely determined. Although CI can present at almost any age, it is most common in the children and young adult population, and it is presented in 11 - 19 percent of children with an exodeviation.
  • Exotropia is a form of strabismus (eye misalignment) in which one or both eyes turn outward. It is the opposite of crossed eyes, or esotropia. Exotropia may occur from time to time (intermittent exotropia) or may be constant and is found in every age group. The most common signs of CI include a large near point of convergence (NPC) and exodeviation near the NPC. Exodeviation occurs when the patient can no longer maintain fusion, this is referred to as the break point.
  • NPC near point of convergence
  • Exodeviation occurs when the patient can no longer maintain fusion, this is referred to as the break point.
  • NPC Near Point of Convergence
  • CI treatment aims to reduce NPC. This is done by using the same principle of the diagnostic test.
  • the patient performs a set of exercises to strengthen the eye muscles, by bringing a certain obj ect closer to the patient’ s face to the point of fixation loss in a repetitive manner.
  • test reliability depends on both the examiner’s as well as the patient’s performance. Several factors might affect the test results such as room illumination, examiner’s distraction, and patient’s cooperation being sometimes challenging or misleading, for example, in young children, mentally retarded patients, or even with normal adults. Moreover, the test is usually performed several times by the ophthalmologist to assure that the patient understands and performs well.
  • NPC Near Point of Convergence Test
  • NPC Near Point of Convergence Test
  • the needed equipment A fixation target and a ruler as can be seen in ( Figure 2).
  • the fixation target could be a pen or a pencil.
  • a tiny toy of a common character can be used, and it should be with small details that are clear to see.
  • Figures 3,4 a special ruler is illustrated which is used for the convergence and accommodation test. In case of high-level myopia or hypermetropia or in case of presbyopia, the needed correction should be done in advance, prior to applying the test.
  • the way the test is performed may have great importance, and this directly affects the results. It therefore may be considered appropriate to perform the test.
  • the examiner will start moving the fixation object slowly and smoothly close to the patient’s nose. (4) The patient will be instructed to pay attention, when the fixation object is seen double or very blurry. Also, the examiner should explain to the patient that the object can become a bit blurry, and that he should blink and still need to continue to fixate on it.
  • the examiner should observe the patient’ s both eyes because some patients do not notice diplopia - when one of the eyes is not fixating to the object. As a result, this point is the near point of the convergence. In some cases, the patient was given instructions to ignore, what might be minor NPC, but still, the patient might report bit blurry as very blurry, since patients are bias.
  • orthoptic therapy is the primary treatment modality used by most eye care professionals for the treatment of CI.
  • the plasticity of the fusional convergence reflex system allows patients to improve their convergence amplitudes with simple exercises.
  • the primary treatment modalities for CI include home-based exercise, office-based visual therapy (OBVT) exercises, computer vergence exercises or a combination of these.
  • Gradual Convergence Exercises e.g., pencil pushups
  • BSV binocular single vision
  • OBVT office-based visual therapy
  • Strabismus is a condition in which the eyes do not properly align with each other when looking at an object. The condition may be present occasionally or constantly. Strabismus is considered a common disease, with a prevalence in the general population that can reach 5% while in children the prevalence is up to 7.1%. If present during a large part of childhood, it may result in amblyopia (also called lazy eye), which is a very important visual disorder that is caused by inability of eye-brain to work together effectively and it results in decreased vision in an eye that otherwise typically appears normal or loss of depth perception. If strabismus onset is during adulthood, it is more likely to result in double vision.
  • Diagnosis of strabismus by an ophthalmologist or specialist in the field is made as a gold standard by the "Cover/Uncover Test” .
  • the examiner asks the subject to look at a target, covers one eye at a time and observes the behavior of the other opened eye in those moments.
  • the displacement of the eye in a certain direction can give the examiner an indication if subject has strabismus, as well as an assessment of the type of strabismus, and sometimes a rough assessment of the degree of strabismus depending on the examiner's experience.
  • a highlight experienced examiner needs to use an additional equipment called “Prism Bar”.
  • MediaPipe Model is a nonlimiting example, for an ML solutions for live and streaming media and the Eye Tracking, illustrated in Figure 5, is an end-to-end neural network-based model that created a 3D mesh of 468 points represented on the human face. It relies on a single RGB camera input without the need for special sensors or additional instrumentation. This model detects the face in the original image, crops it as a rectangle (as illustrated in Figure 6), which is provided as an input to the mesh prediction neural network, outputting vectors of 3D figures. In the training phase, they use a dataset of close to 30k images taken by different phones, used in different capturing and lighting conditions. In addition, in order to obtain the structure of a real face, 3D morphable models (3DMM) were used.
  • 3DMM 3D morphable models
  • the final full model as shown in Figure 6 detects and crops, as input, a face image in 256x256 size, then extracting a 64 x 64 feature map.
  • the division into submodels allows for obtaining 478 landmarks and creating a feature map of 24x24 specially for the eye area, from which the special area of the iris is extracted as a separate output. This allows for more free behavior of the iris regardless of other landmarks of the eye.
  • Some aspects of the invention may be directed to a system and method for diagnosis and treatment of various eye disorders,
  • the method may include, receiving from a camera a stream of images comprising the eyes of a user; identifying a temporal location of the iris and the pupil center of each eye in each image; determining a temporal distance between the pupils in each image; determining a distance between the camera and the iris of each eye; calculating a temporal near point of convergence (NPC) for the user, based on the temporal distance between the pupils and the distance between the camera the iris of each eye; and diagnosing an eye disorder if the NPC is larger than a first threshold value.
  • NPC temporal near point of convergence
  • the method further comprises identifying a movement of the eyelids, eyebrows, and changes in pupil size, and wherein diagnosing the eye disorder is based on the movement of the eyelids, eyebrows and changes in pupil size.
  • the method further comprises: determining for each eye a temporal distance between the bridge of the nose and the pupil of each eye; and determining for each eye separately an eye disorder based on the temporal distances between the bridge of the nose and the pupil of each eye.
  • the method further comprises: detecting changes in the distance between the pupils as function of the distance between the camera and the iris of each eye; and diagnosing the eye disorder based if the detected changes are larger than a second threshold valueA
  • Some additional aspects of the invention may directed to a method for diagnosis and treatment of strabismus comprising: (a) sending, via a user interface, instruction to a user to cover a first eye; (b) receiving from, a camera a first stream of images comprising the first and a second eye of a user; (c) identifying a location of the pupil of the second eye, in an image taken at the moment before a visual axis of the first eye is covered by the user; (d) determining a length of movement of the pupil of the second eye, in consecutive images; (e) repeating steps (a)-(d) when the second eye is instructed to be covered; and determining strabismus in at least one of the first eye and the second eye based on the length of movement of the pupil of each eye.
  • the method may further include repeating periodically steps (a)-(e); and estimating an effectiveness of a treatment provided to the user based on the length of movement of the pupil of each eye.
  • Figures 1, 2, 3, and 4 are images of NPC tests
  • Figure 5 is an illustration of MediaPipie Model architecture
  • Figure 6 is an illustration of facial mesh for MediaPipie Model
  • Figure 7A is a flowchart of a method of diagnosis and treatment of various eye disorders according to some embodiments of the invention.
  • Figure 7B is an image and illustration of the focus of the eyes, showing key points on the eyelid (red) and iris (blue) including the center of the pupil according to some embodiments of the invention
  • Figure 7C is a graph showing raw measurements, taken from a healthy user, of the temporal distance between the pupils (PD) vs. the distance between the camera and the iris of each eye and the result of a smoothing algorithm, according to some embodiments of the invention.
  • Figures 7D and 7E are smoothened PD graphs of a healthy user (7D) in comparison to a user suffering from an eye disorder, according to some embodiments of the invention.
  • Figure 7F shows smoothened graph showing the distance between each pupil and the nose median and the distance between the camera and the iris of each eye, according to some embodiments of the invention.
  • Figure 8 is an illustration of the distance from eye to camera (d) calculated by using Focal Length (f) and the iris size according to some embodiments of the invention
  • Figure 9 is an illustration of Face Image Processing: a. Full face image with the cut line b. Image of the cut section which will be used later c. Face image after the smartphone becomes very close to the subject d. new face image after processing, according to some embodiments of the invention;
  • Figure 10 includes images of faces before and after being processed according to some embodiments of the invention.
  • Figure 12 is a flowchart of a method for diagnosis and treatment of strabismus, according to some embodiments of the invention.
  • Figure 13 is an image showing a step in the method of Figure 12, according to some embodiments of the invention.
  • Figure 14 is a block diagram, depicting a computing device which may be included in a system for diagnosis and treatment of various eye disorders according to some embodiments of the invention.
  • the terms “plurality” and “a plurality” as used herein may include, for example, “multiple” or “two or more”.
  • the terms “plurality” or “a plurality” may be used throughout the specification to describe two or more components, devices, elements, units, parameters, or the like.
  • the term “set” when used herein may include one or more items.
  • Embodiments of the present invention disclose a method and a system for the diagnosis and treatment of various eye movement disorders.
  • Such a system may diagnose patients who have CI- a disorder characterized by a decreased ability to converge the eyes and maintain binocular fusion while focusing on a near target, achieving that by using only the front camera of the smartphone with no need of additional equipment.
  • the system and method use are a face recognition platform, for example, MediaPipe Face Mesh, and a machine learning model for face and eye tracking, such as, Iris.
  • Some embodiments of the invention are directed to the development of an automatic CI detection and therapeutic application in smartphones, that could replace the typical test.
  • the goal is to have an automatic system, for detection and treatment, that replaces the typical test procedure which has its own limitations: 1) The need for a professional tester. 2) In order to obtain high accuracy, special equipment is needed and is usually not available. 3) Collaboration of the subject: Ability to detect blurred vision or diplopia and report immediately to the examiner. 4) Patients with difficulty in verbal expression will not be able to undergo the test. 5) The above includes children and mental retardation.
  • embodiments of the invention may include producing a simple smart system that requires minimum execution skill, and minimum cooperation from the patient, and gives results with high accuracy.
  • the system is suitable for children. Patients can undergo the test by themselves without the need for the presence of an ophthalmologist at any time and as much as they want.
  • FIG. 7 A is a flowchart of a method of diagnosis and treatment of various eye disorders according to some embodiments of the invention.
  • the method of Figure 7 A may be performed by any computing device, for example, computing device 10 discussed and illustrated in Figure 14.
  • a stream of images comprising the eyes of a user may be received from a camera, for example, the camera of a smartphone 12, illustrated in Figure 14.
  • a temporal location of the pupil center of each eye may be identified in each image.
  • the MediaPipe model may monitor eye movements in different situations, over time. For example, the model may detect the abnormal movement that the eyes make as soon as the fixation ability is lost (the “break point”) while performing the Near Point of Convergence (NPC) Test.
  • NPC Near Point of Convergence
  • a distance between the temporal pupils in each image may be determined, for example, by using the MediaPipe model which may also determine the temporal distance between the eyes and the pupils, which is also called the temporal Pupillary Distance (PD).
  • MediaPipe may determine the location of the pupil center in each frame. This position, which is in 2D, and the coordinates of x and y obtained are the position in relation to the width or height of the image. And the use of image size in pixels gives the position x and y from the (0,0) point which is the comer of the image, and as a result the distance between the pupils is obtained in pixels.
  • the fact that the size of the iris is relatively constant in the wide population may be useful.
  • One of these advantages may be the ability to convert the distance between the pupils from percent or pixels to millimeters in any given frame.
  • the Pupillary Distance (PD) may be calculated using equation (1), as illustrated in Figure 8.
  • the “PD” is the pupillary distance in millimeters- which is the distance between the center of the eyes
  • the “RightEyeCenter.X” is the landmark’s X component of the center of right iris in pixels
  • the “LeftEyeCenter.X’ is the landmark’s X component of the center of left iris in pixels.
  • a distance between the camera the iris of each eye may be determined.
  • Iris Related Depth Estimation is based on the fact that the size of the iris (in ophthalmology known as w-t-w white to white) is uniformly sized in a wide population with minimal differences. The estimated w-t-w is 11.7 ⁇ 0.5 mm. The method was tested for images received from several types of smartphones with good results and less than 10% error.
  • the Iris-Camera distance (Distance-From-Camera (d)) in millimeters(mm) can be calculated without additional equipment, as seen in equation (2) and illustrated in Figure 8.
  • the Distance-From-Camera (d) is the distance between the iris of one eye to the smartphone camera in millimeters
  • the Focal-Length (f) is the FL of the smartphone camera in pixels
  • “Iris Diameter” is the diameter of the iris, of the same eye, in pixels.
  • the “FLp” is the camera focal length in pixels
  • the “FLmm” is the camera focal length in millimeters
  • the “PS” is the size of one pixel of the camera in millimeters
  • W is the width of the smartphone camera, which is the maximal width of an image that this camera can produce in pixels
  • Wr is real width- which is the width of the frame’s image that in pixels.
  • r was used because the resulting image is smaller than the maximum resolution the camera can produce, and when the best resolution is produced then this value is equal to 1.
  • the original NPC test measures the distance between the center of the face- eye level -and the target to which the subject is staring at. Therefore, to be more accurate, and after calculating the distance of the camera from the eye, a system and method according to embodiments of the invention, performs another simple calculation, using similar triangles, and updates the distance to a central point between the eyes and not from the eye itself.
  • the determined temporal PD may be plotted vs. the distance from camera (d) during the test, as illustrated in Figure 7C as the two eyes are trying to focus on a target presented on the screen associated with the camera.
  • the raw data produced from the stream of images contains noise. Therefore, a smoothing algorithm was applied to the data resulting in a smooth graph.
  • a Gaussian smoothing with a fixed sigma was performed, which resulted in a clear trend of progress and easy tracking of the change in PD in relation to the video’s frame number and in relation to the distance from the face.
  • step 150 the NPC for the user was calculated, based on the distance between the pupils and the distance between the camera the iris of each eye.
  • a nonlimiting example is given below.
  • a user study was conducted to explore the technical and clinical potential of the mobile system. Excluded from the study: Patients with chronic eye diseases including history of eye surgery. Subjects wearing spectacles were included in our study.
  • NPC near point of convergence test
  • step 160 an eye disorder is diagnosed if the NPC is larger than the first threshold value.
  • NPC detection according to embodiments of the invention is highly and significantly correlated with the Ruler, and medium-high correlated with the Pencil.
  • the Pencil and the Ruler didn’t show a high correlation.
  • Figure 11 shows that our method is eligible for CI detection, assuming that the upper value of the normal NPC point in the general population is 13.41cm (e.g., the first threshold value). Shifting the focus to the comparison between the automated system and the human systems, a big match can be seen apart from patient number 10, which is the only time the system is alone on one of the two sides of the threshold. Only in two subjects (number 1 and 3) there was a mismatch between the manual and the automatic tests, suggesting excellent preliminary results.
  • the PD may be plotted vs. the distance of the iris of each eye from the camera, in order to provide additional data assisting in diagnosing eye disorder.
  • NPC Near Point of Convergence
  • Break Point is the point of maximal convergence, which is the point of minimal PD as well.
  • NPC Near Point of Convergence
  • Figure7C the behavior of the healthy eyes during focusing shows a clear single NPC “breaking point” (which can be set as the first threshold value) at which the eyes can no longer be focused, at the end of the focusing process.
  • minor breaking points can be identified by small changes (e.g., the first derivative) of in PD as a function of the distance between the camera and the iris of each eye. These small changes can set a second threshold value for diagnosing the eye disorder.
  • the method may include detecting changes in the PD as a function of the distance between the camera and the iris of each eye; and diagnosing the eye disorder based if the detected changes are larger than a second threshold value.
  • the detection of these changes may also prevent a false negative determination of the real NPC of the user, as the first NPC “breaking point” is at a larger distance than the final “breaking point”.
  • detecting a movement of the eyelids, and eyebrows, and changes in pupil size may provide additional data that may allow diagnosing the eye disorder based also on the movement of the eyelids, and eyebrows and changes in pupil size. These movements may also be included in the Al algorithm and may improve the prediction accuracy of the Al algorithm.
  • FIG. 7F shows the distance between each pupil and the nose median plotted against the distance between the camera and the iris of each eye, during focusing of the eyes, according to some embodiments of the invention.
  • each eye has different focusing behavior.
  • the right eye shows a smooth and normal behavior with one distinctive breaking point, while the left eye shows several minor breaking points, the first one already at 250 mm.
  • each eye has a number of minor NPCs, points that can vary in number and location from eye to eye.
  • each eye has one Major NPC, which can be different in its location from the other eye and from the major NPC of both eyes together, which is actually, the final result of the state of art NPC test.
  • Such a diagnosing method may allow diagnosing the “weak” or unhealthy eye, and therefore providing more suitable treatment for the unhealthy eye. For example, instead of providing focusing exercises for both eyes, only the unhealthy eye will be exercised to strengthen convergence or accommodation of the eye. In yet another example, vision tests may be conducted on each eye, and correcting glasses may be provided to the unhealthy eye. Lazy eye treatments associated with weak convergence ability may be performed, including refractive correction (regardless of age or presence of presbyopia), patch therapy, atropine therapy.
  • the method may include determining for each eye a temporal distance between the bridge of the nose and the pupil of each eye and determining for each eye separately an eye disorder based on the temporal distances between the bridge of the nose and the pupil of each eye.
  • Convergence Insufficiency Application for assessing convergence insufficiency - At first the ophthalmologist performed the near point of convergence test (NPC) three times on the participants, and the near convergence points will be computed. These points will be used as ground truth reference points. Then the participants will be instructed to use the mobile app, in this case the near convergence points were computed automatically, three times. Finally, the average of the computed near convergence points in two tests, manually by the ophthalmologist and automatically by the mobile app are compared to evaluate the efficiency of the system. Machine learning methodologies will be applied using the ophthalmologist ground truth for the training of the machine.
  • NPC near point of convergence test
  • Therapeutic application for convergence insufficiency The therapeutic system relies on the principle of practice, the goal of which is to strengthen the patient’ s convergence ability by gradually training the patient’s visual system which results in a lower NPC value.
  • Our system gives the patient the option to build a training program that suits his lifestyle: the number of trainings per day (2 or 3 trainings), the number of repetitions of the exercise in each training set (5, 10 or 15 repetitions) and the duration of the training period (1,2 or 3 months).
  • the system displays the NPC values obtained in each exercise, the average of the results, the percentage of improvement from the training set he did, and a graph describing the number of training set versus the average of the measurements in that practice.
  • the system keeps all the information received from the treatment system, giving a reminder to the patient before any training set.
  • the system transmits to the attending ophthalmologist, once a week, the results of the training sets, with the appropriate graphs including comparison and the patient’s progress rate, and by relying on these data the attending ophthalmologist will be able to recommend a change in treatment plan.
  • the main treatment for a lazy eye that caused by strabismus is closure of the good eye, with or without glasses depending on the patient's condition, in this way the weak eye is forced to work and take on more role in the vision process.
  • Non treating of amblyopic eye can lead to severe vision damage, irreversible, can lead to blindness in difficult situations.
  • the treatment plan which includes a decision on which eye to close, the time of closing a day, the duration of the closing plan, is determined by a single examination of the patient by an ophthalmologist every few months (sometimes half a year or more).
  • a home self-examination of the patient in the system can give a very important indication of the effectiveness of the treatment plan, the need to change the treatment plan metrics before visiting the attending ophthalmologist, which will be very helpful in treatment and give the ophthalmologist a much broader view over the patient medical condition.
  • the system may give an assessment of the color vision of the patient by a short test - exposing the patient to various color images that will appear in front of him on the phone screen, without the need for user response, but evaluates the change in convergence-accommodation in response to a change in colors.
  • the system relies on two well-known principles in the literature: the first is the change in accommodation in response to a change in colors, and that the change in convergence and accommodation requires identification of the object to which one is looking.
  • the system is important for any user who wants to know the status of his color vision in a fast, smart, simplified way, but it is especially important in its ability to test color vision in the speechless or impaired communication skills, in children, in patients with mental retardation and certain cognitive condition and others.
  • Figure 12 is a flowchart of a method for diagnosis and treatment of strabismus according to some embodiments of the invention.
  • the method of Figure 12 may be performed by a similar system performing the method of Figure 7 A (e.g., computing device 10 of Figure 14) or by any other suitable system.
  • a user may receive, from a user interface, instructions to cover his/her first eye (e.g., by his/her hand).
  • the user may receive from his/her smartphone 12 audio messages, illustrated in Figure 14, see on the screen visual instructions of literal instructions for covering the left eye.
  • step 1220 a first stream of images comprising the first and second eye of a user is received from a camera, for example, the camera of smartphone 12.
  • a location of the pupil of the first eye may be identified in an image taken at a moment before a visual axis of the first eye is covered by the user. Such an image is illustrated in Figure 13, where the location of the pupil of the right eye is detected at a moment before a visual axis of the right eye is covered.
  • the controller may use similar methods to the ones discussed with respect to step 120.
  • a length of movement of the pupil of the second eye is determined from consecutive images.
  • Computing device 10 may recognize in each consecutive image following the image taken at a moment before a visual axis of the first eye is covered by the user, the location of the pupil of the first eye.
  • Computing device 10 may then calculate the total length the pupil moved from the initial location at the image taken at a moment before the visual axis of the first eye is covered by the user, to the final location at which the pupil stops moving.
  • the temporal location of the pupil of the first eye may be plotted as a function of time or image number (e.g., frame number) and a smoothing algorithm may be conducted (e.g., as discussed herein above) in other to filter undesired noise from the detection.
  • steps 1210-1240 may be repeated for the second eye.
  • strabismus is determined in at least one of the first eye and the second eye based on the length of movement of the pupil of each eye. For example, strabismus is determined if the length of movement of the pupil of at least one eye is greater than a threshold value.
  • the method may include performing an Automated Bielschowsky three-step test, for calculating a rotation degree of the face.
  • the method may have the ability to diagnose almost all types of strabismus. The method may further be able to decide which is the squinting eye, which muscle is problematic, and also if it is a muscle weakness or restriction, and to give a good estimate of the degree of strabismus.
  • the system and method may allow self-diagnosis without the need for the presence of an expert in the field during the test, due to minimal actions required of the patient such as holding the smartphone in front of the face.
  • An application running on smartphone 12 and/or computing device 10 may be able to differentiate between permanent strabismus; "Tropia”, and non-permanent strabismus; “Phoria”, and “Intermittent Strabismus”, if it is “Horizontal” or “Vertical” or “oblique” strabismus, deciding which is the squinting eye, which muscle is problematic, and also if it is a muscle weakness or restriction and give an estimation of the strabismus's angle.
  • the system may provide a diagnosis of the medical problem and an initial recommendation to the patient for the next step in diagnosis or treatment, as well as our system will be able to interface with other systems of telemedicine.
  • the diagnosis may be based on iris-pupil tracking of each eye separately which obtained from the video captured by “selfie” camera of the smartphone, and it is all based on the principle that both eyes work in full synergism including the motility system, while disruption in this synergism will lead to medical problems such as strabismus, which is a large package of eye diseases most of which are treatable.
  • the system and method may allow an early detection of diseases which can prevent lazy eye (Amblyopia), one of the serious ophthalmology problems, that because after certain age there are no longer proven treatments for this disorder, neither in literature nor in practice.
  • Latent Strabismus may be detected.
  • Latent Strabismus is a group of strabismus, which appear at certain conditions and not regularly.
  • the theory is that impaired binocular vision (for various reasons) will result in the inability of the brain and eyes to maintain a single image in the subject's visual field and this is manifested in strabismus.
  • We will improve the system's capabilities so that it can work continuously and for a long time, it can help diagnose the above types of strabismus, and give a lot of information for the characterization of this strabismus, information that an ophthalmologist will not be able to get in one or more tests at his clinic.
  • the system can detect the moment when the patient experiences the first strabismus event.
  • the strabismus events that have been in the given time range, which can give an indication of the time the patient is reading and working in one eye without his notice, which has many implications for the quality of work or learning of the subject.
  • the above data can greatly help the ophthalmologist in assessing the patient's medical status and prescribing him a treatment plan and follow-up accordingly and even monitoring the effectiveness of the various treatments including surgical one.
  • the method may further include repeating periodically steps 1210-1240 and estimating effectiveness of a treatment provided to the user based on the length of movement of the pupil of each eye.
  • the main treatment for a lazy eye that is caused by strabismus is closure of the good eye, with or without glasses depending on the patient's condition, in this way the weak eye is forced to work and take on more role in the vision process.
  • No treatment of amblyopic eye can lead to severe vision damage, irreversible, which can lead to blindness in difficult situations.
  • the treatment plan which includes a decision on which eye to close, the time needs for closing a day, the duration of the closing plan, all that is determined, may be periodically tested and updated according to the progress of the user.
  • a method according to embodiments of the invention may include a home selfexamination of the patient, at to a known schedule. This method may provide a very important indication of the effectiveness of the treatment plan, the need to change the treatment plan metrics before visiting the attending ophthalmologist, which will be very helpful in treatment and give the ophthalmologist a much broader view over the patient medical status.
  • Some additional embodiments of the invention may be directed to an automatic accommodation range detection.
  • the same ruler which used to check the (NPC, illustrated in Figure 3) is used to determine the "Accommodation Range", which basically reflects the range in which the subject has the ability to read lines from a distance close to the face in a sharp and clear manner.
  • the system accoridng to embodiments of the invention has the ability to detect changes in accommodation based on changes in eye movements and pupil size and other signs that may indicate loss of accommodation or being into state of accommodation, which has its own clinical reflections. This capability enriches the benefits of our system and strengthens our belief that our system will further contribute to science and medicine.
  • the algorithm disclosed herein above may be used while presenting to the user a line with a plurality (e.g., 4-6) letter or symbols, lowing the user to identify the letters or symbols during the test.
  • the algorithm may calculate the point at which the user loses focus, and the point of return to focus. The algorithm may use these calculation to determine accommodation range.
  • Computing device 10 may include a processor or controller 2 that may be, for example, a central processing unit (CPU) processor, a chip or any suitable computing or computational device, an operating system 3, a memory 4, executable code 5, a storage system 6, input devices 7 and output devices 8.
  • processor 2 or one or more controllers or processors, possibly across multiple units or devices
  • More than one computing device 10 may be included in, and one or more computing devices 10 may act as the components of, a system according to embodiments of the invention.
  • Operating system 3 may be or may include any code segment (e.g., one similar to executable code 5 described herein) designed and/or configured to perform tasks involving coordination, scheduling, arbitration, supervising, controlling or otherwise managing operation of computing device 10, for example, scheduling execution of software programs or tasks or enabling software programs or other modules or units to communicate.
  • Operating system 3 may be a commercial operating system. It will be noted that an operating system 3 may be an optional component, e.g., in some embodiments, a system may include a computing device that does not require or include an operating system 3.
  • Memory 4 may be or may include, for example, a Random Access Memory (RAM), a read only memory (ROM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a double data rate (DDR) memory chip, a Flash memory, a volatile memory, a nonvolatile memory, a cache memory, a buffer, a short term memory unit, a long term memory unit, or other suitable memory units or storage units.
  • Memory 4 may be or may include a plurality of possibly different memory units.
  • Memory 4 may be a computer or processor non-transitory readable medium, or a computer non-transitory storage medium, e.g., a RAM.
  • a non-transitory storage medium such as memory 4, a hard disk drive, another storage device, etc. may store instructions or code which when executed by a processor may cause the processor to carry out methods as described herein.
  • Executable code 5 may be any executable code, e.g., an application, a program, a process, task or script. Executable code 5 may be executed by processor or controller 2 possibly under control of operating system 3. For example, executable code 5 may be an application that may diagnose, and treat of various eye disorders as further described herein. Although, for the sake of clarity, a single item of executable code 5 is shown in Figure 14, a system according to some embodiments of the invention may include a plurality of executable code segments similar to executable code 5 that may be loaded into memory 4 and cause processor 2 to carry out methods described herein.
  • Storage system 6 may be or may include, for example, a flash memory as known in the art, a memory that is internal to, or embedded in, a micro controller or chip as known in the art, a hard disk drive, a CD-Recordable (CD-R) drive, a Blu-ray disk (BD), a universal serial bus (USB) device or other suitable removable and/or fixed storage unit.
  • Previously recorded NPCs may be stored in storage system 6 and may be loaded from storage system 6 into memory 4 where it may be processed by processor or controller 2.
  • memory 4 may be a non-volatile memory having the storage capacity of storage system 6. Accordingly, although shown as a separate component, storage system 6 may be embedded or included in memory 4.
  • Input devices 7 may be or may include any suitable input devices, components or systems, e.g., a detachable keyboard or keypad, a mouse and the like.
  • Output devices 8 may include one or more (possibly detachable) displays or monitors, speakers and/or any other suitable output devices.
  • Any applicable input/output (RO) devices may be connected to Computing device 10 as shown by blocks 7 and 8.
  • NIC network interface card
  • USB universal serial bus
  • any suitable number of input devices 7 and output device 8 may be operatively connected to Computing device 10 as shown by blocks 7 and 8.
  • a system may include components such as, but not limited to, a plurality of central processing units (CPU) or any other suitable multi-purpose or specific processors or controllers (e.g., similar to element 2), a plurality of input units, a plurality of output units, a plurality of memory units, and a plurality of storage units.
  • CPU central processing units
  • controllers e.g., similar to element 2
  • a neural network e.g. a neural network implementing machine learning
  • a NN may be configured or trained for a specific task, e.g., pattern recognition or classification. Training a NN for the specific task may involve adjusting these weights based on examples.
  • Each neuron of an intermediate or last layer may receive an input signal, e.g., a weighted sum of output signals from other neurons, and may process the input signal using a linear or nonlinear function (e.g., an activation function).
  • a linear or nonlinear function e.g., an activation function
  • the results of the input and intermediate layers may be transferred to other neurons and the results of the output layer may be provided as the output of the NN.
  • the neurons and links within a NN are represented by mathematical constructs, such as activation functions and matrices of data elements and weights.
  • a processor e.g., CPUs or graphics processing units (GPUs), or a dedicated hardware device may perform the relevant calculations.
  • a system may be implemented as a software module, a hardware module or any combination thereof.
  • system may be or may include a computing device such as element 1 of Figure 1, and may be adapted to execute one or more modules of executable code (e.g., element 5 of Figurel4) to diagnose and treat various eye disorders, as further described herein.
  • modules of executable code e.g., element 5 of Figurel4

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Ophthalmology & Optometry (AREA)
  • Human Computer Interaction (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Eye Examination Apparatus (AREA)

Abstract

L'invention concerne un système et un procédé de diagnostic et de traitement d'au moins un trouble oculaire. Le procédé peut consister en la réception, à partir d'une caméra, d'un flux d'images comprenant les yeux d'un utilisateur ; l'identification d'un emplacement d'un centre de pupille de chaque œil dans chaque image ; la détermination d'une distance entre les pupilles dans chaque image ; la détermination d'une distance entre la caméra et l'iris de chaque œil ; le calcul d'un point de convergence proche (NPC) pour l'utilisateur, sur la base de la distance entre les pupilles et la distance entre la caméra et l'iris de chaque œil ; et le diagnostic d'un trouble oculaire si le NPC est supérieur à une valeur seuil.
PCT/IL2023/051119 2022-10-31 2023-10-31 Système et procédé de diagnostic et de traitement de divers troubles du mouvement et de diverses maladies de l'œil WO2024095261A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202263420949P 2022-10-31 2022-10-31
US63/420,949 2022-10-31

Publications (1)

Publication Number Publication Date
WO2024095261A1 true WO2024095261A1 (fr) 2024-05-10

Family

ID=90929874

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IL2023/051119 WO2024095261A1 (fr) 2022-10-31 2023-10-31 Système et procédé de diagnostic et de traitement de divers troubles du mouvement et de diverses maladies de l'œil

Country Status (1)

Country Link
WO (1) WO2024095261A1 (fr)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130076884A1 (en) * 2010-03-19 2013-03-28 Fittingbox Method and device for measuring an interpupillary distance
US20150219934A1 (en) * 2012-07-03 2015-08-06 Reverse Engineering, Lda System for the measurement of the interpupillary distance using a device equipped with a screen and a camera
US20150265146A1 (en) * 2012-10-02 2015-09-24 University Hospitals Of Cleveland Apparatus and methods for diagnosis of strabismus
US20160270653A1 (en) * 2013-11-07 2016-09-22 Ohio State Innovation Foundation Automated detection of eye alignment
US20180064333A1 (en) * 2016-09-08 2018-03-08 Howard P. Apple Device for screening convergence insufficiency and related methods
US20190046029A1 (en) * 2016-02-16 2019-02-14 Massachusetts Eye And Ear Infirmary Mobile device application for ocular misalignment measurement
WO2021107394A1 (fr) * 2019-11-27 2021-06-03 고큐바테크놀로지 주식회사 Procédé de suivi de pupille pour l'œil dans diverses conditions, et système de diagnostic médical l'utilisant
US20210169322A1 (en) * 2017-09-05 2021-06-10 Neurolens, Inc. System for measuring binocular alignment with adjustable displays and eye trackers
CN115191931A (zh) * 2022-07-25 2022-10-18 深圳创维新世界科技有限公司 斜视检测方法、设备及计算机可读存储介质

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130076884A1 (en) * 2010-03-19 2013-03-28 Fittingbox Method and device for measuring an interpupillary distance
US20150219934A1 (en) * 2012-07-03 2015-08-06 Reverse Engineering, Lda System for the measurement of the interpupillary distance using a device equipped with a screen and a camera
US20150265146A1 (en) * 2012-10-02 2015-09-24 University Hospitals Of Cleveland Apparatus and methods for diagnosis of strabismus
US20160270653A1 (en) * 2013-11-07 2016-09-22 Ohio State Innovation Foundation Automated detection of eye alignment
US20190046029A1 (en) * 2016-02-16 2019-02-14 Massachusetts Eye And Ear Infirmary Mobile device application for ocular misalignment measurement
US20180064333A1 (en) * 2016-09-08 2018-03-08 Howard P. Apple Device for screening convergence insufficiency and related methods
US20210169322A1 (en) * 2017-09-05 2021-06-10 Neurolens, Inc. System for measuring binocular alignment with adjustable displays and eye trackers
WO2021107394A1 (fr) * 2019-11-27 2021-06-03 고큐바테크놀로지 주식회사 Procédé de suivi de pupille pour l'œil dans diverses conditions, et système de diagnostic médical l'utilisant
CN115191931A (zh) * 2022-07-25 2022-10-18 深圳创维新世界科技有限公司 斜视检测方法、设备及计算机可读存储介质

Similar Documents

Publication Publication Date Title
US9844317B2 (en) Method and system for automatic eyesight diagnosis
de Almeida et al. Computational methodology for automatic detection of strabismus in digital images through Hirschberg test
JP7166473B2 (ja) 眼検査
Kuwahara et al. Eye fatigue estimation using blink detection based on Eye Aspect Ratio Mapping (EARM)
JP2022542473A (ja) 視力を予測するための眼の画像を処理するための深層学習の使用
KR102344493B1 (ko) 인공 지능 기반의 스마트 안진 검사 시스템, 방법 및 프로그램
EP3900638A1 (fr) Dispositif de diagnostic d'une maladie cérébrale
JP2024512045A (ja) メンタルヘルスを診断および監視するための視覚システム
de Almeida et al. Surgical planning for horizontal strabismus using support vector regression
JP2024138393A (ja) 活動性甲状腺眼症の医学的治療のための病院訪問ガイダンスのための方法、及びこれを実行するためのシステム
CN116634920A (zh) 主观屈光检查系统
CN113873981A (zh) 功能恢复训练系统、功能恢复训练装置以及程序
WO2024095261A1 (fr) Système et procédé de diagnostic et de traitement de divers troubles du mouvement et de diverses maladies de l'œil
CN115666366B (zh) 用于评估受试者的视力的系统
US20230363637A1 (en) Remote subjective refraction techniques
KR102460451B1 (ko) 가시광선의 동공 반사 이미지를 이용한 굴절이상 측정 방법
Dunn Quantifying perception and oculomotor instability in infantile nystagmus
Clark et al. Applied artificial intelligence techniques for identifying the lazy eye vision disorder
Quang et al. Mobile traumatic brain injury assessment system
Saavedra-Peña Saccade latency determination using video recordings from consumer-grade devices
Davies et al. Validation of a Novel Smartphone Pupillometer Application Compared to a Dedicated Clinical Pupillometer in the Measurement of the Pupillary Light Reflex of Healthy Volunteers.
Wei Unobtrusive Refractive Power Monitoring Using Eyewear-based EOG and Eye-Tracking
DO HYONG The Study of Visual Attention: From Raw Data to an Interdisciplinary Environment
Ahmad Zahidi Characteristics and impact of nystagmus on visual acuity and eye movements in children with and without Down’s syndrome
Torii et al. Real Time Measurement and Processing of Pupillary Light Reflex for Early Detection of Disease.

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23885245

Country of ref document: EP

Kind code of ref document: A1