AUTOMATED DISEASE IDENTIFICATION BASED ON OPHTHALMIC IMAGES

    公开(公告)号:US20220319708A1

    公开(公告)日:2022-10-06

    申请号:US17709950

    申请日:2022-03-31

    Abstract: An example method includes identifying at least one image of an eye of a patient. The method further includes detecting, by a first computing model, at least one first feature in the at least one image and detecting, by a second computing model, at least one second feature in the at least one image. Further, using a third computing model that is different than the first computing model or the second computing model, the method includes identifying a likelihood that the patient has one or more diseases consistent with the at least one feature and the at least one second feature. A recommendation for care of the patient is generated based on the likelihood.

    Fundus image capturing
    4.
    发明授权

    公开(公告)号:US10993613B2

    公开(公告)日:2021-05-04

    申请号:US16229939

    申请日:2018-12-21

    Abstract: An example device is configured to capture an image of an eye. The device includes a camera configured to capture the image of the eye. The device also includes: a first base configured to be moved along a first axis to position the camera to capture the image of the eye; a second base configured to be moved along a second axis to position the camera to capture the image of the eye; and a third base configured to be moved along a third axis to position the camera to capture the image of the eye.

    REMOTE MANAGEMENT OF DEVICE USER INTERFACE CONTENT

    公开(公告)号:US20230298742A1

    公开(公告)日:2023-09-21

    申请号:US18183665

    申请日:2023-03-14

    CPC classification number: G16H40/40 G06F8/65

    Abstract: Software of devices, such as medical devices or other constrained devices configured to implement specific functions, can use content files to determine text strings or other content values to present in association with user interface elements. Devices can receive relevant content files, such as new versions of previously-stored content files or new content files containing text in different languages, from a remote content file repository. The software of the devices can accordingly update content values presented in user interfaces based on newly received content files, without the software being re-coded, the software being restarted, or the devices rebooting.

    INJECTION DEPTH INDICATION VIA INJECTION NEEDLE ILLUMINATION

    公开(公告)号:US20230083200A1

    公开(公告)日:2023-03-16

    申请号:US17943036

    申请日:2022-09-12

    Inventor: Allen R. Hart

    Abstract: A medical device includes a head having a base and a piercing member fluidly connected to the base. The medical device includes a tube having a proximal end, a distal end, a first central channel extending from the proximal end to distal end, and a longitudinal axis extending substantially centrally through the first central channel, the distal end of the tube being removably attached to the base. The medical device includes a plunger slidably disposed partly within the first central channel of the tube, the plunger defining a second central channel, and the longitudinal axis extending substantially centrally through the second central channel. In some examples, the medical device includes an optic assembly having a light source and a light pipe that is disposed partly within the second central channel and being configured to receive radiation emitted by the light source; and direct the radiation through the piercing member.

    Fundus Image Capture System
    8.
    发明申请

    公开(公告)号:US20190223719A1

    公开(公告)日:2019-07-25

    申请号:US16373315

    申请日:2019-04-02

    Abstract: A fundus image capture system operates to determine if the system has captured an image that identifies the fundus, a region of interest in the image, or the current field of view. According to the determination, the system can guide the user to operate the system to capture a desired fundus image.

    Automated disease identification based on ophthalmic images

    公开(公告)号:US12300385B2

    公开(公告)日:2025-05-13

    申请号:US17709950

    申请日:2022-03-31

    Abstract: An example method includes identifying at least one image of an eye of a patient. The method further includes detecting, by a first computing model, at least one first feature in the at least one image and detecting, by a second computing model, at least one second feature in the at least one image. Further, using a third computing model that is different than the first computing model or the second computing model, the method includes identifying a likelihood that the patient has one or more diseases consistent with the at least one feature and the at least one second feature. A recommendation for care of the patient is generated based on the likelihood.

Patent Agency Ranking