公开(公告)号：US20250069226A1

公开(公告)日：2025-02-27

申请号：US18945634

申请日：2024-11-13

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jaemin PARK ,  Jongchan KIM

IPC: G06T7/00 ,  A61B3/14 ,  A61B5/00 ,  G06T7/12 ,  G06T7/70 ,  G16H50/20

Abstract: According to the present application, a computer-implemented method of predicting thyroid eye disease is disclosed. The method comprising: preparing a conjunctival hyperemia prediction model, a conjunctival edema prediction model, a lacrimal edema prediction model, an eyelid redness prediction model, and an eyelid edema prediction model, obtaining a facial image of an object, obtaining a first processed image and a second processed image from the facial image, wherein the first processed image is different from the second processed image, obtaining predicted values for each of a conjunctival hyperemia, a conjunctival edema and a lacrimal edema by applying the first processed image to the conjunctival hyperemia prediction model, the conjunctival edema prediction model, and the lacrimal edema prediction model, and obtaining predicted values for each of an eyelid redness and an eyelid edema by applying the second processed image to the eyelid redness prediction model and the eyelid edema prediction model.

公开(公告)号：US20230153999A1

公开(公告)日：2023-05-18

申请号：US18094064

申请日：2023-01-06

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jaemin PARK ,  Jongchan KIM

IPC: G06T7/00 ,  G06T7/70 ,  G06T7/12 ,  A61B5/00 ,  A61B3/14 ,  G16H50/20

CPC classification number: G06T7/0012 ,  G06T7/70 ,  G06T7/12 ,  A61B5/4824 ,  A61B5/4227 ,  A61B5/4878 ,  A61B3/14 ,  G16H50/20 ,  A61B5/445 ,  G06T2207/20021 ,  G06T2207/30201 ,  G06T2207/30041 ,  G06T2207/20132

Abstract: According to the present application, a computer-implemented method of predicting thyroid eye disease is disclosed. The method comprising: preparing a conjunctival hyperemia prediction model, a conjunctival edema prediction model, a lacrimal edema prediction model, an eyelid redness prediction model, and an eyelid edema prediction model, obtaining a facial image of an object, obtaining a first processed image and a second processed image from the facial image, wherein the first processed image is different from the second processed image, obtaining predicted values for each of a conjunctival hyperemia, a conjunctival edema and a lacrimal edema by applying the first processed image to the conjunctival hyperemia prediction model, the conjunctival edema prediction model, and the lacrimal edema prediction model, and obtaining predicted values for each of an eyelid redness and an eyelid edema by applying the second processed image to the eyelid redness prediction model and the eyelid edema prediction model.

公开(公告)号：US20230005144A1

公开(公告)日：2023-01-05

申请号：US17939040

申请日：2022-09-07

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jaemin PARK ,  Jongchan KIM

IPC: G06T7/00 ,  G06T7/70 ,  G06T7/12 ,  A61B5/00 ,  A61B3/14 ,  G16H50/20

Abstract: According to the present application, a computer-implemented method of predicting thyroid eye disease is disclosed. The method comprising: preparing a conjunctival hyperemia prediction model, a conjunctival edema prediction model, a lacrimal edema prediction model, an eyelid redness prediction model, and an eyelid edema prediction model, obtaining a facial image of an object, obtaining a first processed image and a second processed image from the facial image, wherein the first processed image is different from the second processed image, obtaining predicted values for each of a conjunctival hyperemia, a conjunctival edema and a lacrimal edema by applying the first processed image to the conjunctival hyperemia prediction model, the conjunctival edema prediction model, and the lacrimal edema prediction model, and obtaining predicted values for each of an eyelid redness and an eyelid edema by applying the second processed image to the eyelid redness prediction model and the eyelid edema prediction model.

公开(公告)号：US20250014751A1

公开(公告)日：2025-01-09

申请号：US18891429

申请日：2024-09-20

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jongchan KIM

IPC: G16H50/20 ,  G16H10/60 ,  G16H30/40

Abstract: Proposed is an eye-related sign prediction method that includes obtaining an image representing at least one eye, obtaining two or more individual predicted values and one consensus predicted value based on the image and a single diagnostic model, and determining a presence of the eye-related sign in the eye based on the consensus predicted value. The single diagnostic model is trained using training data to output predictions of two or more individual determination values and a prediction of one consensus value in response to an input image. The training data includes a clinical image multi-labeled with two or more individual determination values and one consensus value.

公开(公告)号：US20230337913A1

公开(公告)日：2023-10-26

申请号：US18209604

申请日：2023-06-14

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jaemin PARK ,  Jongchan KIM ,  Yoon Won TAK ,  Hwi Yeon KIM ,  Eun Yeong SIM

IPC: A61B3/14 ,  G06T7/00 ,  A61B5/00 ,  A61B5/107 ,  G06T7/62 ,  H04N23/60 ,  H04N23/611 ,  H04N23/63 ,  H04N23/698

CPC classification number: A61B3/14 ,  G06T7/0012 ,  A61B5/0077 ,  A61B5/1079 ,  A61B5/4227 ,  A61B5/7275 ,  G06T7/62 ,  H04N23/64 ,  H04N23/611 ,  H04N23/633 ,  H04N23/698 ,  G06T2207/30041

Abstract: A method of obtaining user information to analyze a Clinical Activity Score (CAS) of a user is provided. The method includes providing a guidance on a photographing device to indicate a proper position of at least one eye of the user, obtaining a facial image of the user in response to satisfying predetermined conditions. The facial image comprises at least one eye of the user. The predetermined conditions includes 1) whether a position of at least one eye is on a predetermined region, 2) whether a degree of rotation of a face of the user is within a predetermined range, 3) whether a degree of the user's smile is the same or less than a first predetermined value, and 4) whether a degree of ambient brightness is the same or less than a second predetermined value. The method further includes outputting inquiries on the photographing device, and obtaining user input.

公开(公告)号：US20230012806A1

公开(公告)日：2023-01-19

申请号：US17951681

申请日：2022-09-23

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jaemin PARK ,  Jongchan KIM ,  Yoon Won TAK ,  Hwi Yeon KIM ,  Eun Yeong SIM

IPC: A61B3/14 ,  H04N5/232 ,  G06T7/62 ,  G06T7/00 ,  A61B5/00 ,  A61B5/107

Abstract: The present application relates to a method of acquiring a side image for analyzing the degree of ocular proptosis. According to an embodiment, an image acquisition method is provided which is including: acquiring a front image of the subject's face while guidance is
Oven to satisfy a first photographing condition; generating panorama guidance on the basis of position information of a first point and a second point extracted from the front image; providing guidance on movement of a photographing device to acquire a preview image corresponding to the panorama guidance; and acquiring a side image of the subject's face while guidance is given to satisfy a second photographing condition. The first captured image shows iris areas of the subject, and the second captured image shows an outer canthus and a cornea of one of the subject's eyes.

公开(公告)号：US20230360219A1

公开(公告)日：2023-11-09

申请号：US18218142

申请日：2023-07-05

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jongchan KIM ,  Jaemin PARK

IPC: G06T7/00 ,  G16H50/20

CPC classification number: G06T7/0016 ,  G16H50/20 ,  G06T2207/30201 ,  G06T2207/30041 ,  G06T2207/20081

Abstract: According to the present application, provided is a computer-implemented method of predicting a clinical activity score for conjunctival hyperemia. The method described in the present application includes: training a conjunctival hyperemia prediction model using a training set; acquiring a first image include at least one eye of a subject and an outer region of an outline of the at least one eye; outputting, by the conjunctival hyperemia prediction model executing on a processor, a first predicted value for a conjunctival hyperemia, a first predicted value for the conjunctival edema, a first predicted value for an eyelid redness, a first predicted value for an eyelid edema, and a first predicted value for a lacrimal edema; to and generating a score for the conjunctival hyperemia based on the selected first predicted value for a conjunctival hyperemia.

公开(公告)号：US20230360204A1

公开(公告)日：2023-11-09

申请号：US18222271

申请日：2023-07-14

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jaemin PARK ,  Jongchan KIM

IPC: G06T7/00 ,  G06T7/70 ,  G06T7/12 ,  A61B5/00 ,  A61B3/14 ,  G16H50/20

CPC classification number: G06T7/0012 ,  G06T7/70 ,  G06T7/12 ,  A61B5/4824 ,  A61B5/4227 ,  A61B5/4878 ,  A61B3/14 ,  G16H50/20 ,  A61B5/445 ,  G06T2207/20021 ,  G06T2207/30201 ,  G06T2207/30041 ,  G06T2207/20132

Abstract: According to the present application, a computer-implemented method of predicting thyroid eye disease is disclosed. The method comprising: preparing a conjunctival hyperemia prediction model, a conjunctival edema prediction model, a lacrimal edema prediction model, an eyelid redness prediction model, and an eyelid edema prediction model, obtaining a facial image of an object, obtaining a first processed image and a second processed image from the facial image, wherein the first processed image is different from the second processed image, obtaining predicted values for each of a conjunctival hyperemia, a conjunctival edema and a lacrimal edema by applying the first processed image to the conjunctival hyperemia prediction model, the conjunctival edema prediction model, and the lacrimal edema prediction model, and obtaining predicted values for each of an eyelid redness and an eyelid edema by applying the second processed image to the eyelid redness prediction model and the eyelid edema prediction model.

公开(公告)号：US20230013792A1

公开(公告)日：2023-01-19

申请号：US17945270

申请日：2022-09-15

Applicant: THYROSCOPE INC.

Inventor： Kyubo SHIN ,  Jongchan KIM ,  Jaemin PARK

IPC: G06T7/00 ,  G16H50/20

Abstract: According to the present application, provided is a computer-implemented method of predicting a clinical activity score for conjunctival hyperemia. The method described in the present application includes: training a conjunctival hyperemia prediction model using a training set; acquiring a first image include at least one eye of a subject and an outer region of an outline of the at least one eye; outputting, by the conjunctival hyperemia prediction model executing on a processor, a first predicted value for a conjunctival hyperemia, a first predicted value for the conjunctival edema, a first predicted value for an eyelid redness, a first predicted value for an eyelid edema, and a first predicted value for a lacrimal edema; and generating a score for the conjunctival hyperemia based on the selected first predicted value for a conjunctival hyperemia.