Kestrel Corporation

Visionquest Biomedical LLC

The State University of New York

The University of New Mexico

University of Iowa Research Foundation

Peter Soliz

Paul Wiley Truitt

Gilberto Zamora

Simon Barriga

Carla Agurto

Vinayak Joshi

Honggang Yu

Marios Stephanou Pattichis

Leonard John Otten, Iii

Randy H Kardon

Herbert T Davis, Iii

Young H Kwon

Victor Manuel Murray Herrera

Eduardo S Barriga

Trilce Estrada

Daniel Tso

Carla Paola Agurto Rios

Jeremy Benson

Mark Wilson

Balaji Raman

Embodiments of the present invention provide a system and method to automatically screen images from a plurality of fundus cameras for a plurality of retinal diseases. The system comprises stacked autoencoders, amplitude modulation-frequency modulation filters, and artificial neural networks. An embodiment of the present invention uses a multi-class classifier, such as a support vector machine (multi-class SVM) classifier, to determine a plurality of retinal pathologies. An exemplary embodiment of the present invention is validated on a proprietary database of thousands of images (for example over 250,000 retinal images) from multiple cameras, ranging from the table-top fundus cameras to portable hand-held cameras.

Generalized retinal image screening system (GRIS)

Systems and methods of obtaining and recording fundus images by minimally trained persons, which includes a camera for obtaining images of a fundus of a subject's eye, in combination with mathematical methods to assign real time image quality classification to the images obtained based upon a set of criteria. The classified images will be further processed if the classified images are of sufficient image quality for clinical interpretation by machine-coded and/or human-based methods. Such systems and methods can thus automatically determine whether the quality of a retinal image is sufficient for computer-based eye disease screening. The system integrates global histogram features, textural features, and vessel density, as well as a local non-reference perceptual sharpness metric. A partial least square (PLS) classifier is trained to distinguish low quality images from normal quality images.

System and methods for automatic processing of digital retinal images in conjunction with an imaging device

A system and method for assessing a peripheral neuropathy risk wherein the system and method according to one embodiment of the present invention detects abnormality which may be directed to a probability, a stage, a category, or other indicator as to the degree of progression of the disease.

Thermal optical imager system and method for detection of peripheral neuropathy

Image and video processing using multi-scale amplitude-modulation frequency-modulation ('AM-FM') demodulation where a multi-scale filterbank with bandpass filters that correspond to each scale are used to calculate estimates for instantaneous amplitude, instantaneous phase, and instantaneous frequency. The image and video are reconstructed using the instantaneous amplitude and instantaneous frequency estimates and variable-spacing local linear phase and multi-scale least square reconstruction techniques. AM-FM demodulation is applicable in imaging modalities such as electron microscopy, spectral and hyperspectral devices, ultrasound, magnetic resonance imaging ('MRI'), positron emission tomography (&#x201c;PET&#x201d;), histology, color and monochrome images, molecular imaging, radiographs (&#x201c;X-rays&#x201d;), computer tomography (&#x201c;CT&#x201d;), and others. Specific applications include fingerprint identification, detection and diagnosis of retinal disease, malignant cancer tumors, cardiac image segmentation, atherosclerosis characterization, brain function, histopathology specimen classification, characterization of anatomical structure such as carotid artery walls and plaques or cardiac motion and as the basis for computer-aided diagnosis to name a few.

System and methods of amplitude-modulation frequency-modulation (AM-FM) demodulation for image and video processing

Medical images are automatically segmented by customizing the morphological segmentation of features identified in the image based upon statistical analysis of the features within each region to be analyzed. The statistical description of the features, as reported through a feature vector, informs the system as to which input variables to select for further segmentation analysis for features residing within the region of the image analyzed. By customizing the automatic segmentation analysis to produce an enhanced image, features within the image are characterized more efficiently and precisely. False positive identification of lesions are minimized without sacrifice of true positive identifications.

System and method for automation of morphological segmentation of bio-images

An enhanced entropy camera provides enhanced image quality by utilizing a custom analog-to-digital conversion function. The analog-to-digital conversion occurs according to a custom non-linear quantization function that provides enhanced entropy in the digitized image, yet avoids the harsh artifacts that tend to arise in images quantized according to a maximum entropy function. A plurality of custom non-linear functions are made available for selection depending upon imaging conditions, such as light intensity, pigmentation of the retina, or the part of the retina being imaged. Each of the plural non-linear quantization function comprises a distinct non-linear look up table for each of plural bands (e.g., red, green, and blue color channels).

Max entropy optimized retinal camera

A system and method for detecting a functional signal in retinal images. An optical imaging device comprises a stimulation light source, an interrogating light source, and a detector. The retina is stimulated by the stimulation light source. The retina is then illuminated by an interrogation light, and the reflected intensity from the retina is measured at an interrogating spectral band that indicates the state of hemoglobin saturation before and after visual stimulation. The optical changes that result from retinal neuronal activity are captured by the detector. The signal representing the state of hemoglobin saturation before and after visual stimulation is isolated. In an embodiment of the present invention, this signal is isolated using principle components analysis (PCA). In another embodiment of the present invention, blind source separation (BSS) and independent component analysis (ICA) algorithms such as extended spatial decorrelation and fast-ICA are used to isolate the functional signal from the retinal videos.

Method for detecting a functional signal in retinal images

An Optical Imaging Device of Retinal Function has been developed to detect changes in reflectance of near infrared light from the retina of human subjects in response to visual activation of the retina by a pattern stimulus. The measured changes in reflectance correspond in time to the onset and offset of the visual stimulus in the portion of the retina being stimulated. Any changes in reflectance can be measured by interrogating the retina with a light source. The light source may be presented to the retina via the cornea and pupil or through other tissues in and around the eye. Different wavelengths of interrogating light may be used to interrogate various layers of the retina. Additionally, various novel patterns and methods of stimulation have been developed for use with the imaging device and methods.

Device and method for optical imaging of retinal function

An ophthalmic instrument (for obtaining high resolution, wide field of area hyperspectral retinal images for various sized eyes) includes a fundus retinal imager, (which includes optics for illuminating and imaging the retina of the eye); apparatus for generating a real time image of the area being imaged and the location of the hyperspectral region of interest; a high efficiency spatially modulated common path Fourier transform hyperspectral imager, a high resolution detector optically coupled to the hyperspectral and fundus imager optics; and a computer (which is connected to the real time scene imager, the illumination source, and the high resolution camera) including an algorithm for recovery and calibration of the hyperspectral images.

Growing community of inventors

Albuquerque, NM, United States of America

Peter Soliz