Abstract: In certain embodiments, a system, a computer-implemented method, and computer-readable medium are disclosed for performing integrated analysis of MSI and OCT images to diagnose eye disorders. MSI and OCT are processed using separate input machine learning models to create input feature maps that are input to an intermediate machine learning model. The intermediate machine learning model processes the input feature maps and outputs a final feature map that is processed by one or more output machine learning models that output one or more estimated representations of a pathology of the eye of the patient.

Abstract: In certain embodiments, a system, a computer-implemented method, and computer-readable medium are disclosed for performing integrated analysis of MSI and OCT images to diagnose eye disorders. MSI and OCT are processed using separate input machine learning models to create input feature maps that are input to an intermediate machine learning model. The intermediate machine learning model processes the input feature maps and outputs a final feature map that is processed by one or more output machine learning models that output one or more estimated representations of a pathology of the eye of the patient. A single device captures OCT and non-OCT images using (a) a sensor of a first imaging device that is shared with a second imaging device and/or (b) an optical component for directing light form the retina to the first imaging device or the second imaging device.

Abstract: In certain embodiments, a system, a computer-implemented method, and computer-readable medium are disclosed for light efficient fluorescence imaging. The retina is flashed with broadband light and returned light is imaged after passing through one or more filters, such as notch filers, low-pass filters, and high-pass filters. Images may be captured with a single camera or at least two cameras, one capturing transmitted light from the filter and the other capturing returned light. Images may be combined by subtraction and/or addition to obtain a combined image representing light within a passband whereas no passband filters are used during imaging.

Abstract: In certain embodiments, a system, a computer-implemented method, and computer-readable medium for generating multispectral imaging (MSI) based on performing an analytical MSI operation are described. The analytical MSI operation includes synchronizing a scan of a target by a broadband imaging device with a generation of a plurality of light signals, from a plurality of broadband illumination sources, directed towards the target. A set of spectral information associated with the target is generated, based on the scan of the target with the broadband imaging device. A set of multispectral imaging (MSI) information associated with the target is generated, based on performing an MSI operation using at least the set of spectral information. Ophthalmic information is determined based on the set of MSI information.

Abstract: Particular embodiments disclosed herein provide an alignment guide for aligning a toric IOL during surgery. An image with a reference axis is obtained, such as from a digital microscope, and processed, such as using an autoencoder, to label alignment marks on the IOL and possibly other features of the IOL. The label is processed, such as using a logistic regression model, to estimate an IOL axis of the IOL intersecting the alignment marks. An output image is generated from the image that has superimposed thereon guides to a surgeon, such as a line representing the IOL axis, a rotation direction indicator, and a number or other representation of a difference between the reference axis and the IOL axis. Tracking of features of the IOL may be performed across multiple images to predict the location of features not represented in a particular image.

Abstract: In certain embodiments, an ophthalmic system and computer-implemented method for analyzing multiple spectral information to generate ophthalmic information are described. In an exemplary ophthalmic system, multiple spectral information associated with an eye of a patient is captured via an imaging system. A first set of information and a second set of information are extracted from the multiple spectral information. A visualization of the multiple spectral information is generated using the first set of information. The first set of information and the second set of information are evaluated using different deep learning models to generate ophthalmic information. The ophthalmic information is sent to a user for diagnostic evaluation.

Abstract: In certain embodiments, an ophthalmic system and computer-implemented method for performing ophthalmic image registration are described. The ophthalmic image registration includes obtaining a plurality of images of an eye of a user. Within each image of the plurality of images, a segmented region(s) of the eye within the image is determined based on evaluating the image with a neural network(s), and a set of point features of the eye within the segmented region(s) of the eye is determined based on evaluating the image with the neural network(s). A set of transformation information for transforming at least one of the plurality of images is generated based on performing one or more image processing operations on the set of point features within each image of the plurality of images. At least one of the plurality of images is transformed, based on the set of transformation information.

Abstract: Certain embodiments provide a method of performing ophthalmic surgical procedures. The method includes ingesting and preparing pre-operative data and intra-operative data associated with a patient's eye for further processing. In certain embodiments, the method further includes integrating the pre-operative data and intra-operative data to generate context sensitive data for further processing. The method also includes classifying and annotating the pre-operative data, the intra-operative data, and the context sensitive data. The method also includes extracting one or more actionable inferences from the pre-operative data, the intra-operative data, context sensitive data, and the classified and annotated data. The method further includes triggering, based on the one or more actionable inferences, one or more actions on an imaging system or a surgical system.

Abstract: According to one aspect, a sensor clearing system is arranged to remove precipitation and/or other contamination from a sensor. A sensor clearing system which is suitable for use on an autonomous vehicle includes an axial fan and a duct arrangement. The axial fan is configured to provide air flow that is routed through the duct arrangement. The duct arrangement directs the air flow towards a sensor, e.g., a lidar, at a velocity and/or with a force that is selected to cause any precipitation on a surface of the sensor, e.g., a lens of a lidar, to be removed.

Abstract: A storage management subsystem monitors usage of the data stored by a data storage system. Based at least in part on the monitored usage of the stored data, a storage profile is determined for the stored data. The storage profile indicates a first time period during which a first portion of the stored data is anticipated to be accessed and a second portion of the stored data is not anticipated to be accessed and a second time period during which the first portion of the stored data is not anticipated to be accessed. During at least the first time period, the first portion of the data is stored in a decompressed format and the second portion of the data is stored in a compressed format. During at least the second time period, the first portion of the data is stored in the compressed format.

Abstract: A storage management subsystem monitors usage of the data stored by a data storage system. Based at least in part on the monitored usage of the stored data, a storage profile is determined for the stored data. The storage profile indicates a first time period during which a first portion of the stored data is anticipated to be accessed and a second portion of the stored data is not anticipated to be accessed and a second time period during which the first portion of the stored data is not anticipated to be accessed. During at least the first time period, the first portion of the data is stored in a decompressed format and the second portion of the data is stored in a compressed format. During at least the second time period, the first portion of the data is stored in the compressed format.

Abstract: An apparatus is provided. The apparatus may include an elongated shaft including a passage terminating at a nozzle including a dispersion plate and tapered sidewalls between the dispersion plate and the elongated shaft. The tapered side walls may define a single opening, an outer surface of the sidewalls may define a tapered exit for the opening, an inner surface of the sidewalls may define a non-tapered entrance into the opening, the nozzle is sized to be received by a transmission case inlet, and an internal diameter of the passage is less than the tapered exit.

Abstract: A method of manufacturing a substrate is provided. The method comprises, in some aspects, a) providing a support; b) forming a template by attaching a plurality of polymeric nanoparticles some or all having a core-shell structure to the support, wherein the core comprises a first polymer and the shell comprises a second polymer; and c) forming the metal nanoarray substrate by attaching a plurality of metallic nanoparticles to at least some of the polymeric nanoparticles of the template. A biosensor comprising a substrate manufactured by the method, and a method for the detection of an analyte in a sample by surface enhanced Raman spectroscopy (SERS) is also provided.