CARL ZEISS MEDITEC, INC.

Systems, methods and devices are disclosed for registering different ophthalmic images of different modalities including different fundus imager modalities and OCT/OCTA modalities.

A system, method and device are disclosed for determining a quality index of Optical Coherence Tomography data. The method of determining a quality index (or matric) of Optical Coherence Tomography data may comprise using a distance probability function to determine a quality index, wherein the quality index is calculated from an OCT quality map, wherein the best OCT quality maps are modeled as a subspace and wherein the distance of an OCT quality map to the subspace is a measure of the OCT quality.

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.

An ophthalmic system/device (e.g., OCT or fundus imager) provides easy alignment for a patient with no, or minimal, assistance from a technician. This is achieved in a low cost device by using various patient-customized mechanisms that provide an initial rough alignment that brings the patient within an expected alignment range of the device. The ophthalmic device then provides a fine alignment by means of a custom mechanical guide operated by a single motor.

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.

Retinal layer segmentation in optical coherence tomography (OCT) data is improved by using OCT angiography (OCTA) data to enhance a target retinal layer within the OCT data that may lack sufficient definition for segmentation. The OCT data is enhanced based on a mixture of the OCT data and OCTA data, such that contrast in the OCT data is enhanced in areas where OCT and OCTA data are dissimilar, and is reduced in areas where the OCT and OCTA data are similar. The target retinal layer in the OCT data is segmented based on the enhanced data. Two en face images of the OCTA data that include the target retinal layer are used to check for errors in the segmentation of the target retinal layer in the OCT data. Identified errors are replaced with an approximation based on the locations of top and bottom retinal layers of one of the en face images.

Embodiments herein disclose a method and system for staging diabetic kidney disease using deep learning techniques. An image capturing unit captures a set of ophthalmic images of a user. The ophthalmic images set undergoes pre-processing before being fed to a first deep learning module. The first deep learning module extracts pathological data indicative of vascular abnormalities from the pre-processed set of ophthalmic images. The first deep learning module quantifies the extracted pathological data, and maps them to a stage of diabetic retinopathy and urine protein levels. A second deep learning module receives as input the quantified pathological data, the mapped diabetic retinopathy stage and urine protein levels, and clinical and demographic parameters. Based on this input, the second deep learning module predicts a stage of diabetic kidney disease.

A system, method and/or device for obtaining interferometric measurements using multiple light sources to image, in sequence, a location on a sample, where the light sources have different spectral wavelength bands, and adjacent spectral wavelength bands overlap each other. The respective interferometric measurements are combined mathematically to define a composite interferometric measurement for the location on the sample. The composite interferometric measurement has a greater axial resolution than that of any of the individual light sources.

Various techniques for providing a low-cost ophthalmic imaging system, such an OCT or fundus imagers are presented. Cost is reduced by using a K-minor as a scanning component. The K-mirror is positioned at a retina conjugate. A beam splitter is positioned at the pupil conjugate and may be used to provide pupil splitting functionality. The beam splitter's shape and area conform to the focal light footprint of an illumination source such that it spans only a fraction of a collection window. 2D FFT is applied to capture spectra for purposes of selectively removing complex conjugate components and for extracting patient pupil to system collection pupil alignment. Consequently, pupil alignment is achieved by use of captured OCT data without the need for additional pupil cameras.

A system, method, or device for imaging the anterior segment of an eye includes a contactless adapter/lens that may be attached to an existing ophthalmic imaging system to redirect the imaging system's light beam to traverse the pupil of the eye at a steep angle. In particular, the steep angle is determined to permit the ophthalmic imaging system to image zonules under the iris, and which would typically be blocked by the iris and not accessible for imaging.