Carl Zeiss Meditec Gmbh

Carl Zeiss Meditec Ag

Luis De Sisternes

Homayoun Bagherinia

Sophie Kubach

Matthew J Everett

Mary K Durbin

Conor Leahy

Jennifer Y Luu

Gregory G Anderson

Warren Lewis

Ali Fard

Katherine Makedonsky

Simon Bello

Aaron Lee

Theodore Spaide

Kevin Meng

Patrick Krawec

A system and/or method uses a trained U-Net neural network to remove flow artifacts from optical coherence tomography (OCT) angiography (OCTA) data. The trained U-Net receives as input both OCT structural volume data and OCTA volume data, but expands the OCTA volume data to include depth information. The U-Net applies dynamic pooling along the depth direction and weighs more heavily the portion of the data that follows (e.g., along the contours of) select retinal layers. In this manner the U-Net applies contextually different computations at different axial locations based at least in part on the depth index information and/or (e.g., proximity to) the select retinal layers. The U-net outputs OCT volume data of reduced flow artifacts as compared with the input OCTA data.

Correction of flow projection artifacts in octa volumes using neural networks

After OCT scans are acquired, error compensation is be applied anew by identifying motion tracking data that was collected simultaneously with (or closest in time to) each acquired OCT scan. The effects of any previously applied motion tracking information is removed from an OCT scan before applying the new motion tracking data, which may provide higher resolution motion tracking.

Post-processing method to improve LSO-based tracking in oct

Methods and systems are presented to analyze a retinal image of an eye and assigns features to known anatomical structures such as retinal layers. One example method includes receiving interferometric image data of an eye. A set of features is identified in the image data. A first subset of identified features is associated with known retinal structures using prior knowledge. A first set of characteristic metrics is determined of the first subset of features. A second set of characteristic metrics is determined of a second subset of features. Using the characteristic metrics of the first and the second sets, the second subset of features is associated with the retinal structures. Another example method includes dividing interferometric image data into patches. The image data in each patch is segmented to identify one or more layer boundaries. The segmentation results from each patch are stitched together into a single segmentation dataset.

Methods and systems to detect and classify retinal structures in interferometric imaging data

Various methods for the detection and enhanced visualization of a particular structure or pathology of interest in a human eye are discussed in the present disclosure. An example method to visualize a given pathology (e.g., CNV) in an eye includes collecting optical coherence tomography (OCT) image data of the eye from an OCT system. The OCT image data is segmented to identify two or more retinal layer boundaries located in the eye. The two or more retinal layer boundaries are located at different depth locations in the eye. One of the identified layer boundaries is moved and reshaped to optimize visualization of the pathology located between the identified layer boundaries. The optimized visualization is displayed or stored or for a further analysis thereof.

Methods for detection and enhanced visualization of pathologies in a human eye

An ophthalmic imaging system provides a user interface to facilitate the montaging of scan images collected with various imaging modalities, such as images collected with a fundus imaging system or an optical coherence tomography (OCT) system. The amount of each constituent image used in the montage is dependent upon its respective quality. During the collecting of scans (constituent images) for montaging, any scan may be designated for rescanning, such as if its current quality is deemed less than sufficient. In the case of using an OCT system to collect constituent images (e.g., cube scans), the scanned region of a constituent image may be modified based on physical characteristics of the eye being scanned.

Systems and methods for improved montaging of ophthalmic imaging data

A method and system for correction of decorrelation tail artifacts in optical coherence tomography (OCT) angiography volumetric data defines a movable target subvolume within the OCT-A volumetric data. The target subvolume is axially moveable within the OCT-A volumetric data in discrete axial steps. At each axial step, a reference subvolume corresponding to a depth location in the OCT A volumetric data is defined axially offset from the target subvolume. The reference subvolume may be defined within the OCT A volumetric data, or defined within a different (previously corrected) OCT-A volume. Irrespective, corrected OCT-A data that corrects for decorrelation tail artifacts in the target subvolume is defined using information in the reference subvolume and information in the target subvolume.

Correction of decorrelation tail artifacts in a whole OCT-A volume

Growing community of inventors

San Francisco, CA, United States of America

Luis De Sisternes