Abstract: System/Method/Device for labelling images in an automated manner to satisfy a performance of a different algorithm and then applying active learning to learn a deep learning model which would enable ‘real-time’ operation of quality assessment and with high accuracy.

Abstract: Systems and methods for improved interferometric imaging are presented. One embodiment is a partial field frequency-domain interferometric imaging system in which a light beam is scanned in two directions across a sample and the light scattered from the object is collected using a spatially resolved detector. The light beam could illuminate a spot, a line or a two-dimensional area on the sample. Additional embodiments with applicability to partial field as well as other types of interferometric systems are also presented.

Abstract: The system, method and device includes an optical coherence tomography (OCT) system switchable between single scan mode or multi-scan mode. This is achieved by use of multiple beam splitters to produce multiple OCT beams, but the system still uses a single light source, a single sample arm, and single reference arm to achieve a compact, more cost effective, system. Additionally presented is a spectral domain OCT system with a spectrometer having multiple grating, each providing a different depth and/or resolution imaging capability.

Abstract: The eye imaging system for producing images with reduced speckle artifacts may comprise a laser diode for providing a beam of radiation to the eye; a detector for collecting light returning from the eye and generating output signals in response thereto, the detector having a sensor integration time; a driver circuit for applying a modulated drive signal to the laser diode, the modulated drive signal inducing a spectral broadening of the beam of radiation during the sensor integration time. The laser diode may be a single-mode laser designed to operate at a fixed current and wavelength. The drive signal may be modulated by shaping a drive current pulse. The drive signal may be modulated by imposing an RF modulation on a drive current pulse. The drive signal may be further modulated by shaping a drive current pulse.

Abstract: A system/method/device for registering two OCT data sets defines multiple image pairs of corresponding 2D representations of one or more corresponding sub-volumes in the two OCT data sets. Matching landmarks in the multiple image pairs are identified, as a group, and a set of transformation parameters are defined based on matching landmarks from all of the image pairs. The two OCT data sets may then be registered based on the set of transformation parameters.

Abstract: An OCT system is constructed on a micro optical bench or semiconductor optical bench. The present OCT system may use free space optics and avoid the use of fiber optics.

Abstract: A medical ophthalmic system uses a patient-specific face mask to establish a predefined alignment between the ophthalmic system and an eye of a patient. The patient-specific face mask may optionally provide a light proof enclosure for the eye. The face mask may be coupled directly to an ophthalmic device, or its housing/enclosure, of the ophthalmic system. The face mask may be 3D printed based on a 3D model of the patient's face.

Abstract: Systems and methods for improved interferometric imaging are presented. One embodiment is a partial field frequency-domain interferometric imaging system in which a light beam is scanned in two directions across a sample and the light scattered from the object is collected using a spatially resolved detector. The light beam could illuminate a spot, a line or a two-dimensional area on the sample. Additional embodiments with applicability to partial field as well as other types of interferometric systems are also presented.

Abstract: Various methods for reducing artifacts in OCT images of an eye are described. In one exemplary method, three dimensional OCT image data of the eye is collected. Motion contrast information is calculated in the OCT image data. A first image and a second image are created from the motion contrast information. The first and the second images depict vasculature information regarding one or more upper portions and one or more deeper portions, respectively. The second image contains artifacts. Using an inverse calculation, a third image is determined that can be mixed with the first image to generate the second image. The third image depicts vasculature regarding the same one or more deeper portions as the second image but has reduced artifacts. A depth dependent correction method is also described that can be used in combination with the inverse problem based method to further reduce artifacts in OCT angiography images.

Abstract: An ophthalmic imaging system has a specialized graphical user interface GUI to convey information for manually adjusting control inputs to bring an eye into alignment with the system. The GUI uses color and size changes to indicate axial positioning information of the system relative to a patient's eye. Furthermore, no live feed of the patient's eye is needed. Rather, a graphic indicating the patient's eye is provided and its size is controlled to indicate axial information and to filter out momentary movements of the pupil.

Abstract: A system, method, and/or device for determinizing a quality measure of OCT structural data and/or OCTA functional data uses a machine learning model trained to provide a single overall quality measure, or a quality map distribution for the OCT/OCTA data based on the generation of multiple features maps extracted from one or more slab views of the OCT/OCTA data. The extracted feature maps may be different texture-type maps, and the machine model is trained to determine the quality measure based on the texture maps.

Abstract: The present application describes the addition of various feedback mechanisms including visual and audio feedback mechanisms to an ophthalmic diagnostic device to assist a subject to self-align to the device. The device may use the visual and non-visual feedback mechanisms independently or in combination with one another. The device may provide a means for a subject to provide feedback to the device to confirm that an alignment condition has been met. Alternatively, the device may have a means for sensing when acceptable alignment has been achieved. The device may capture diagnostic information during the alignment process or may capture after the alignment condition has been met.

Abstract: A System/Method/Device for automatic retinal layer segmentation from optical coherence tomography (OCT) implementing a deep learning machine model defined by any of multiple neural networks. The neural networks may use the feature of “attention”, and more specifically self-attention, such as by using transformers, to reduce the size of the OCT data and make the process more efficient. Additionally, new methods of data augmentation suitable for OCT data are presented.

Abstract: A System/Method/Device for segmenting the choroid-scleral layer from an optical coherent tomography (OCT) volume scan. The present system uses a deep learning machine model based on a neural network that include multiple convolution layers, but no deconvolution layers. Rather, the present neural network is based on a novel architecture based on the discrete cosine transform.

Abstract: A system and method for creating a composite retinal thickness map of an eye, including collecting, by an optical coherence tomography (OCT) device, a set of a plurality of optical coherence tomography (OCT) volume scans of the eye. At least one set of the plurality of OCT volume scans is collected by the OCT device by: segmenting a target upper retinal layer and a target lower retinal layer which is lower than the target upper retinal layer within an OCT volume scan; determining a thickness map of a candidate between the upper retinal layer and lower retinal layer, and a confidence map associated with the thickness map; selecting at least one thickness map as a reference thickness map; registering at least one thickness map to the reference thickness map; and selectively combining a region of the thickness map with a corresponding region of the reference thickness map to define a composite retinal thickness map.

Abstract: Various optical systems equipped with diode laser light sources are discussed in the present application. One example system includes a diode laser light source for providing a beam of radiation. The diode laser has a spectral output bandwidth when driven under equilibrium conditions. The system further includes a driver circuit to apply a pulse of drive current to the diode laser. The pulse causes a variation in the output wavelength of the diode laser during the pulse such that the spectral output bandwidth is at least two times larger than the spectral output bandwidth under the equilibrium conditions.

Abstract: 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.

Abstract: The present application describes the addition of various feedback mechanisms including visual and audio feedback mechanisms to an ophthalmic diagnostic device to assist a subject to elf align to the device. The device may use the visual and non-visual feedback mechanisms independently or in combination with one another. The device may provide a means for a subject to provide feedback to the device to confirm that an alignment condition has been met. Alternatively, the device may have a means for sensing when Acceptable alignment has been achieved. The device may capture diagnostic information during the alignment process or may capture after the alignment condition has been met.

Abstract: Various methods and systems for improved anterior segment optical coherence tomography (OCT) imaging are described. One example method includes collecting a set of B-scans over a range of different transverse locations on the cornea, segmenting each B-scan to identify an anterior corneal layer and an outer edge of Bowman's layer, calculating thickness values for each B-scan by computing the distance from the anterior corneal layer to the outer edge of the Bowman's layer, combining the thickness values from the B-scans to create a polar epithelial thickness map, converting the polar epithelial thickness map to a Cartesian epithelial thickness map using a fitting method, and storing or displaying the Cartesian epithelial thickness map or information derived from the Cartesian epithelial thickness map.

Abstract: Systems and methods for Broad Line Fundus Imaging (BLFI), an imaging approach that is a hybrid between confocal and widefield imaging systems, are presented. These systems and methods are focused on improving the quality and signal of broad line fundus images or imaging methods to create high contrast and high resolution fundus images. Embodiments related to improved pupil splitting, artifact removal, reflex minimization, adaptable field of view, instrument alignment and illumination details are considered.