Abstract: Systems and methods are presented for providing a machine learning model for segmenting an optical coherence tomography (OCT) image. A first OCT image is obtained, and then labeled with identified boundaries associated with different tissues in the first OCT image using a graph search algorithm. Portions of the labeled first OCT image are extracted to generate a first plurality of image tiles. A second plurality of image tiles is generated by manipulating at least one image tile from the first plurality of image tiles, such as by rotating and/or flipping the at least one image tile. The machine learning model is trained using the first plurality of image tiles and the second plurality of image tiles. The trained machine learning model is used to perform segmentation in a second OCT image.

Abstract: Systems and methods are presented for providing a machine learning model for segmenting an optical coherence tomography (OCT) image. A first OCT image is obtained, and then labeled with identified boundaries associated with different tissues in the first OCT image using a graph search algorithm. Portions of the labeled first OCT image are extracted to generate a first plurality of image tiles. A second plurality of image tiles is generated by manipulating at least one image tile from the first plurality of image tiles, such as by rotating and/or flipping the at least one image tile. The machine learning model is trained using the first plurality of image tiles and the second plurality of image tiles. The trained machine learning model is used to perform segmentation in a second OCT image.

Abstract: Apparatuses, systems, and methods for treating tissue abnormalities are disclosed. The tissue may be visualized for determining a presence of one or more abnormalities contained therein. Imaging data obtained by visualization may be used to determine the presence of one or more abnormalities. Each of the detected abnormalities may be identified and a treatment plan developed for treating the abnormalities. Treatment may be delivered to the abnormalities according to the treatment plan.

Abstract: An ophthalmic surgical microscope includes a beam coupler positioned along an optical path of the surgical microscope between a first eyepiece and magnifying/focusing optics, the beam coupler operable to direct the OCT imaging beam along a first portion of the optical path of the surgical microscope between the beam coupler and a patient's eye (an OCT image being generated based on a reflected portion of the OCT imaging beam). The surgical microscope additionally includes a real-time data projection unit operable to project the OCT image generated by the OCT system and a beam splitter positioned along the optical path of the surgical microscope between a second eyepiece and the magnifying/focusing optics. The beam splitter is operable to direct the projected OCT image along a second portion of the optical path of the surgical microscope between the beam splitter and the second eyepiece such that the projected OCT image is viewable through the second eyepiece.

Abstract: A method and system provide an optical coherence tomography system including a light source, an interferometric system, a processor and a memory. The interferometric system is optically coupled with the light source and includes at least one movable scanning mirror. The processor and memory are coupled with the interferometric system. The processor executes instructions stored in the memory to cause the movable scanning mirror to scan a plurality of points in a sample in at least one pattern. The at least one pattern is based on at least one of at least one Lissajous curve and at least one Spirograph curve.

Abstract: Systems and methods are presented for providing a machine learning model for segmenting an optical coherence tomography (OCT) image. A first OCT image is obtained, and then labeled with identified boundaries associated with different tissues in the first OCT image using a graph search algorithm. Portions of the labeled first OCT image are extracted to generate a first plurality of image tiles. A second plurality of image tiles is generated by manipulating at least one image tile from the first plurality of image tiles, such as by rotating and/or flipping the at least one image tile. The machine learning model is trained using the first plurality of image tiles and the second plurality of image tiles. The trained machine learning model is used to perform segmentation in a second OCT image.

Abstract: An ophthalmic surgical system includes a first imaging system configured to generate a first image of an eye, a second imaging system configured to generate a second image of the eye, and an image registration system to receive the first image generated by the first imaging system, receive the second image generated by a second imaging system, track a location of a distal tip of a surgical instrument in the first image, define a priority registration region in the first image, register the priority registration region in the first image with a corresponding region in the second image, and update the registration of the priority registration region in the first image with the corresponding region in the second image in real time, without registering portions of the first or second images that are outside the registration regions.

Abstract: Some embodiments of the present technology involve methods, devices, and systems for determining an orientation of a surgical tool during ophthalmic surgery. An example method includes performing an optical imaging scan in the surgical site, using a scan pattern that intersects the surgical tool and generating a scan image from the optical imaging scan. The example method further comprises analyzing the scan image to determine a location in the scan image corresponding to where the surgical tool intersected the optical imaging scan, and determining an orientation of the surgical tool, based on the determined location.

Abstract: A method for improving segmentation in optical coherence tomography imaging. The method comprises obtaining an OCT image of imaged tissue, generating a first feature image for at least a portion of the OCT image, and generating a second feature image for at least the portion of the OCT image, based on either the OCT image or the first feature image, by integrating image data in a first direction across the OCT image or first feature image. A third feature image is generated as a mathematical function of the first and second feature images, and layer segmentation for the OCT image is performed, based on the third feature image.

Abstract: Both visible and IR cameras are integrated without an increase in an optical stack height of a surgical microscope used for ophthalmic surgery. The IR camera may be used to directly and intraoperatively capture a scanning OCT measurement beam, which uses NIR light that is invisible to the human eye. An IR image from the IR camera taken from the same surgical field as displayed intraoperatively to a user of the surgical microscope may be displayed in an ocular to the user, enabling visualization of a location of an OCT scan along with actual visible images of the surgical field.

Abstract: A-lines are obtained from an OCT scan of the eye, some of which pass through the iris and the lens and some of which pass through the lens but not the iris. An interface is detected from the A-lines; at least some of this interface is assumed to correspond to either the anterior or posterior of the iris. For each A-line, a first metric is derived from pixels near the detected first interface, such that the first metric reflects an OCT signal intensity associated with the interface, and a second metric is derived from pixels further from the interface, such that the second metric reflects OCT signal attenuation below the detected interface. An attenuation parameter is calculated for each A-line, based on the first and second metrics, and the iris's edge is detected by determining whether each A-line passes through the iris, based on the attenuation parameter.

Abstract: An optical coherence tomography (OCT) system and method for cross view imaging using at least two B-scan images transformed and coupled to each other at an angle to generate a cross view image.

Abstract: Techniques and apparatus for producing sampled Optical Coherence Tomography (OCT) interference signals without aliasing, based on a swept-source OCT interference signal. An example apparatus comprises a k-clock circuit configured to selectively output a k-clock signal at any of a plurality of k-clock frequencies ranging from a minimum k-clock frequency to a maximum k-clock frequency, and an anti-aliasing filter configured to filter a swept-source OCT interference signal, to produce a filtered OCT interference signal, where the anti-aliasing filter has a cut-off frequency greater than one-half the minimum k-clock frequency but less than the minimum k-clock frequency. The apparatus further comprises an analog-to-digital (A/D) converter circuit configured to sample the filtered OCT interference signal at twice the k-clock frequency, to produce a sampled OCT interference signal.

Abstract: A method of automatically detecting a retinal feature using an ophthalmic imaging system and automatically providing at least one of an audio, visual, and tactile indication of the detected retinal feature to a user.

Abstract: The present disclosure provides a visualization system for performing optimized optical coherence tomography (OCT) by determining the absolute distance between the OCT source and a sample. The present disclosure also provides a method for optimizing OCT, which includes determining an absolute distance between the OCT source and a sample using data relating to the focal length or position of an autofocus imager lens.

Abstract: The present invention provides a method of imaging blood vessels or blood flow in blood vessels in an animal comprising: (i) injecting a lipid solution into the bloodstream of the animal; (ii) imaging the blood vessels by an imaging method; and (iii) calculating the blood flow velocity in the blood vessels.

Abstract: Apparatuses, systems, and methods for treating tissue abnormalities are disclosed. The tissue may be visualized for determining a presence of one or more abnormalities contained therein. Imaging data obtained by visualization may be used to determine the presence of one or more abnormalities. Each of the detected abnormalities may be identified and a treatment plan developed for treating the abnormalities. Treatment may be delivered to the abnormalities according to the treatment plan.

Abstract: The present disclosure provides a visualization system for performing optimized optical coherence tomography (OCT) by determining the absolute distance between the OCT source and a sample. The present disclosure also provides a method for optimizing OCT, which includes determining an absolute distance between the OCT source and a sample using data relating to the focal length or position of an autofocus imager lens.

Abstract: A method and system for extracting the zoom level of a microscope is disclosed. The method includes capturing a reference image; recording a first zoom level corresponding to a first magnification at which the reference image is captured; capturing a second image; determining a second zoom level by comparing the second image and the reference image, the second zoom level corresponding to a second magnification at which the second image is captured; and recording the second zoom level at a location accessible by a microscope application.

Abstract: The present disclosure provides a visualization system for performing optimized optical coherence tomography (OCT) by determining the absolute distance between the OCT source and a sample. The present disclosure also provides a method for optimizing OCT, which includes determining an absolute distance between the OCT source and a sample using data relating to the focal length or position of an autofocus imager lens.