Embodiments described herein use deep learning to automate measurement of key morphokinetic embryo features associated with viability and quality, in particular those relevant for clinical in-vitro fertilization (IVF). Systems and methods may, for example, acquire one or more digital images of one or more embryos; select one or more embryos in each digital image; and for each selected embryo, (i) computationally characterize the zona pellucida, detect the degree of fragmentation in the embryo, and for each embryo with a low fragmentation score, computationally classify the embryo's developmental stage based on whether cells constituting the embryo exceed a threshold number (e.g., nine). For an embryo consisting of a single cell, pronuclei may be detected and counted. Based on these measurements, a viability score may be assigned to the embryo.

Systems and methods for localizing an upper eyelid in an image of a subject are provided. An image of an eye of the subject is obtained in electronic format. The image is inputted into a trained neural network comprising at least 10,000 parameters, thereby obtaining a set of coordinates for an upper eyelid in the image. This obtaining and inputting can be repeated over the course of a non-zero duration thereby obtaining a corresponding set of coordinates for the upper eyelid in each image in a plurality of images. Each corresponding set of coordinates for the upper eyelid from each image in the plurality of images can be used to determine whether the subject is afflicted with a neurological condition.

A computer-implemented method of detecting and quantifying a spinal curve is disclosed herein. The method comprises obtaining an infrared radiometer camera, positioning the infrared radiometer camera for receiving thermal data for a spine of a subject, the camera being horizontally spaced about ½ meters to about 3 meters from the spine, scanning at least a portion of the spine with the infrared radiometer camera to obtain the thermal data, analyzing the thermal data using machine learning software which uses a classification algorithm to determine the presence of the spinal curve, and calculating a first Cobb angle for the curve of the subject's spine. Corresponding systems and additional methods also are disclosed.

A set of pre-operative images may be captured of an anatomical structure using an endoscopic camera. Each captured image is associated with a position and orientation of the camera at the moment of capture using image guided surgery (IGS) techniques. This image data and position data may be used to create a navigation map of captured images. During a surgical procedure on the anatomical structure, a real-time endoscopic view may be captured and displayed to a surgeon. The IGS navigation system may determine the position and orientation of the real-time image; and select an appropriate pre-operative image from the navigation map to display to the surgeon in addition to the real-time image.

A plurality of image projections are acquired at faster than cardiac rate. A spatiotemporal reconstruction of cardiac frequency angiographic phenomena in three spatial dimensions is generated from two dimensional image projections using physiological coherence at cardiac frequency. Complex valued methods may be used to operate on the plurality of image projections to reconstruct a higher dimensional spatiotemporal object. From a plurality of two spatial dimensional angiographic projections, a 3D spatial reconstruction of moving pulse waves and other cardiac frequency angiographic phenomena is obtained. Reconstruction techniques for angiographic data obtained from biplane angiography devices are also provided herein.

A time sequenced series of optical images of a patient is obtained at a rate faster than cardiac frequency, wherein the time sequenced series of images capture one or more physical properties of intrinsic contrast. A cross-correland signal from the patient is obtained. A cross-correlated wavelet transform analysis is applied to the time sequenced series of optical images to yield a spatiotemporal representation of cardiac frequency phenomena. The cross-correlated wavelet transform analysis comprises performing a wavelet transform on the time-sequenced series of optical images to obtain a wavelet transformed signal, cross-correlating the wavelet transformed signal with the cross-correland signal to obtain a cross-correlated signal, filtering the cross-correlated signal at cardiac frequency to obtain a filtered signal, and performing an inverse wavelet transform on the filtered signal to obtain a spatiotemporal representation of the time sequenced series of optical images. Images of the cardiac frequency phenomena are generated.

In accordance with various embodiments, provided is a scalp management service provision server for providing a hair loss prevention service and scalp care service for a user, including: a DB management unit interlocked with the scalp management service provision server and configured to obtain a scalp image of the user from a scalp care device including a camera; a scalp condition diagnosis unit configured to determine a scalp condition of the user based on the obtained scalp image; a hair condition diagnosis unit configured to determine a hair condition of the user based on the obtained scalp image; a hair loss diagnosis unit configured to provide a current hair loss progress degree of the user and a hair loss prediction simulation of the user based on the scalp condition and the hair condition; a scalp care solution provision unit configured to provide information about a scalp analysis result and hair analysis result of the user through a user terminal of the user and to determine a scalp care product for the user from among a number of scalp care products included in a scalp care product DB; and a remote care device control unit configured to remotely control the scalp care device with a control value determined according to the scalp analysis result and hair analysis result of the user.

Techniques disclosed herein facilitate tracking the degree to which a size of a biological structure changes over time. In some instances, an initial biological image (collected at a first time) can be segmented to characterized a boundary and size. A subsequent biological image can be processed to identify a deformation and/or transformation variable (e.g., one or more Jacobian matrices and/or one or more Jacobian determinants). The deformation and/or transformation variable(s) and initial segmentation can be used to predict a size of the biological structure at a subsequent time. The predicted size may inform a treatment recommendation.

A computer system for determining onset of an acute coronary syndrome (ACS) event in a remote computing environment comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories is provided. The stored program instructions include capturing, using a camera, a first image at a first time of an iris and a pupil of a first eye of a user; following the capturing of the first image, identifying in the first image a first iris information; capturing, using the camera, a second image at a second time of the iris and the pupil of the first eye of the user; following the capturing of the second image, identifying in the second image a second iris information; determining whether the first iris information is within an allowable range of the second iris information; and providing an indication of a likely ACS event based on a determination of whether the first iris information is within the allowable range of the second iris information.

DCE MR images are obtained from a MR scanner and under a free-breathing protocol is provided. A neural network assigns a perfusion metric to DCE MR images. The neural network includes an input layer configured to receive at least one DCE MR image representative of a first contrast enhancement state and of a first respiratory motion state and at least one further DCE MR image representative of a second contrast enhancement state and of a second respiratory motion state. The neural network further includes an output layer configured to output at least one perfusion metric based on the at least one DCE MR image and the at least one further DCE MR image. The neural network with interconnections between the input layer and the output layer is trained by a plurality of datasets, each of the datasets having an instance of the at least one DCE MR image and of the at least one further DCE MR image for the input layer and the at least one perfusion metric for the output layer.