Verily Life Sciences LLC

Google Inc.

Eliezer Glik

Sam Kavusi

Ryan Kramer

Honglei Wu

Seung Ah Lee

Chinmay Belthangady

Todd Whitehurst

Lin Yang

Peter Wubbels

Daniel Robert Adema

Ozan Cakmakci

Shreyas Potnis

Georges Goetz

Aaron Haywood Stoertz

Kira Whitehouse

Sunny Virmani

Ian Atkinson

Corey Walsh

Improved techniques of detecting angular misalignment between a display and a waveguide of a smartglasses device includes providing a detection mechanism for the display such that the location of a misalignment can indicate how to compensate for the misalignment.

Alignment of waveguide and display in smartglasses

Introduced here are approaches to ensuring that digital images generated during diagnostic sessions are properly associated with the appropriate patients. By implementing these approaches, a diagnostic platform can minimize the time needed to manually input information prior to a diagnostic session and improve the accuracy of this information.

Detection, identification, and verification of patients involved in diagnostic sessions

Introduced here are retinal cameras having optical stops whose size and/or position can be modified to increase the size of the space in which an eye can move while being imaged. In some embodiments, an optical stop is mechanically moved to recover retinal image quality as the subject shifts their eye. In some embodiments, an optical stop is digitally created using a pixelated liquid crystal display (LCD) layer having multiple pixels that are individually controllably. In some embodiments, multiple non-pixelated LCD layers are connected to one another to form a variable transmission stack, and each LCD layer within the variable transmission stack may be offset from the other LCD layers. In such embodiments, the optical stop can be moved by changing which LCD layer is active at a given point in time.

Retinal cameras having movable optical stops

The technology described herein is directed to a fundus camera and, more specifically, to a fundus camera having a display that projects active visual alignment stimuli onto an eye of an examinee via one or more components of an optimal assembly. The active visual alignment stimuli are dynamically adjusted to guide an examinee toward optical alignment for fundus imaging.

Active visual alignment stimuli in fundus photography

Introduced here are diagnostic platforms able to optimize computer-aided diagnostic (CADx) models by simulating the optical performance of an imaging device based on its mechanical components. For example, a diagnostic platform may acquire a source image associated with a confirmed diagnosis of a medical condition, simulate optical performance based on design data corresponding to a virtual prototype of the imaging device, generate a training image by altering the source image based on the optical performance, apply a diagnostic model to the training image, and then determine whether the performance of the diagnostic model meets a specified performance threshold. If the diagnostic model fails to meet the specified performance threshold, the diagnostic platform can automatically optimize the diagnostic model for the imaging device by altering its underlying algorithm(s).

Diagnostic model optimization for variations in mechanical components of imaging devices

Eye cups and retinal imaging systems including an eye cup are described. In an embodiment, the eye cup is shaped to couple with an eyepiece lens assembly. In an embodiment, the eye cup includes a concave socket shaped to couple to a periorbital region of an eye, the concave socket defining a viewing aperture positioned to align with a pupil of the eye along a longitudinal axis of the viewing aperture when the concave socket is coupled to the periorbital region; and a flange extending from the concave socket away from the longitudinal axis and shaped to couple with a lateral margin of the periorbital region when the concave socket is coupled to the periorbital region. In an embodiment, an outer edge of the flange extends farther from the longitudinal axis than an outer edge of portion of the concave socket.

Eye cup for passive feedback for fundus camera alignment

A head-wearable display device is configured to support a plurality of combiners (e.g., at least two combiners) to expand an eyebox associated with the head-wearable display device. The plurality of combiners may expand the pupil and the head-wearable display device may be configured to align the magnification between the plurality of combiners, such that a single magnified virtual image with an expanded eyebox may be delivered to the user.

Optical design of a dual combiner in head-wearable display

Introduced here are approaches to assessing whether digital features (or simply 'features') detected in digital images by detection models are representative of artifacts that can obscure actual pathologies. A diagnostic platform may characterize each digital feature detected in a digital image based on its likelihood of being an artifact. For instance, a digital feature could be characterized as being representative of an artifact caused by improper illumination, an artifact caused by a physical element that is adhered to the lens through which light is collected by an imaging device, or a pathological feature indicative of a disease.

Distinguishing artifacts from pathological features in digital images

A dynamic illuminator includes a central aperture, a ring of inner light sources, a plurality of primary illumination arrays, and a plurality of secondary illumination arrays. The ring of inner light sources is arranged around the central aperture. The plurality of primary illumination arrays extends along radial axes from the central aperture outside of the ring of inner light sources, wherein the primary illumination arrays each includes a plurality of primary light sources. The plurality of secondary illumination arrays is disposed along secondary axes extending from the central aperture outside of the ring of inner light sources. The secondary illumination arrays each includes a plurality of secondary light sources. The secondary axes of the secondary illumination arrays are disposed angularly between adjacent ones of the primary illumination arrays.

Retinal camera with dynamic illuminator for expanding eyebox

Introduced here are retinal cameras having optical stops whose size can be adjusted to enable self-alignment by naturally guiding an eye toward a specified location. Generally, a retinal camera will constrict the bounds of an optical stop until the optical stop is aligned with the eye. In some embodiments, the optical stop is mechanically resized as a subject shifts their eye. In some embodiments, the optical stop is digitally created using a pixelated liquid crystal display (LCD) layer having multiple pixels that are individually controllably. In some embodiments, multiple non-pixelated LCD layers are connected to one another to form a variable transmission stack. In such embodiments, the size of the optical stop can be varied by changing which LCD layer(s) are active at a given point in time.

Retinal cameras having variably sized optical stops that enable self-alignment

A retinal imaging system includes an eyepiece lens assembly, an image sensor, a dynamic fixation target viewable through the eyepiece lens assembly, and a controller coupled to the image sensor and the dynamic fixation target. The controller includes logic that causes the retinal imaging system to perform operations including: acquiring a first image of the eye, analyzing the first image to determine whether a misalignment between the eye and the eyepiece lens assembly is present; in response to determining the misalignment is present, adjusting a visual position of the dynamic fixation target to encourage the eye to rotate in a direction that compensates for the misalignment, and acquiring the retinal image of the eye after adjusting the visual position of the dynamic fixation target.

Dynamic eye fixation for retinal imaging

A retinal imaging system includes an image sensor for acquiring a retinal image and an illuminator for illuminating a retina to acquire the retinal image. The illuminator surrounds an aperture through which an image path for the retinal image passes before reaching the image sensor. Illumination sources surround the aperture.

Growing community of inventors

San Francisco, CA, United States of America

Eliezer Glik