Abstract: An ischemic stroke mimic is detected, or otherwise predicted, based on medical images acquired from a subject. Medical image data, which include medical images acquired from a head of the subject, are accessed with a computer system. A machine learning model (e.g., one or more deep convolutional neural networks) is trained on training data to estimate a probability of an acute intracranial abnormality being depicted in a medical image. Intracranial abnormality prediction data are generated by inputting the medical image data to the machine learning model. The intracranial abnormality prediction data include an intracranial abnormality probability score for each of the medical images in the medical image data. An ischemic stroke mimic classification for the medical image data is generated based on the intracranial abnormality prediction data, and may be displayed to a user with the computer system.

Abstract: Systems and techniques for generating and/or employing a medical imaging stroke model are presented. In one example, a system employs a convolutional neural network to generate output data regarding a brain anatomical region based on diffusion-weighted imaging (DWI) data associated with the brain anatomical region and apparent diffusion coefficient (ADC) data associated with the brain anatomical region. The system also detects presence or absence of a medical stroke condition associated with the brain anatomical region based on the output data.

Abstract: Lesions associated with acute ischemic stroke are automatically segmented in images acquired with computed tomography (“CT”) using a trained machine learning algorithm (e.g., a neural network). The machine learning algorithm is trained on labeled data and associated CT data (e.g., non-contrast CT data and CT angiography source image (“CTA-SI”) data). The labeled data can include segmented data indicating lesions, which are generated by segmenting diffusion-weighted magnetic resonance images acquired within a specified time window from when the associated CT data were acquired. CT data (e.g., non-contrast CT data and CTA-SI data) acquired from a subject are then acquired and input to the trained machine learning algorithm to generate output as segmented CT data, which indicate lesions in the subject.

Abstract: Systems and methods for rapid, accurate, fully-automated, brain hemorrhage deep learning (DL) based assessment tools are provided, to assist clinicians in the detection & characterization of hemorrhages or bleeds. Images may be acquired from a subject using an imaging source, and preprocessed to cleanup, reformat, and perform any needed interpolation prior to being analyzed by an artificial intelligence network, such as a convolutional neural network (CNN). The artificial intelligence network identifies and labels regions of interest in the image, such as identifying any hemorrhages or bleeds. An output for a user may also include a confidence value associated with the identification.

Abstract: Systems and techniques for generating and/or employing a medical imaging stroke model are presented. In one example, a system employs a convolutional neural network to generate output data regarding a brain anatomical region based on diffusion-weighted imaging (DWI) data associated with the brain anatomical region and apparent diffusion coefficient (ADC) data associated with the brain anatomical region. The system also detects presence or absence of a medical stroke condition associated with the brain anatomical region based on the output data.

Abstract: Systems and methods for rapid, accurate, fully-automated, brain hemorrhage deep learning (DL) based assessment tools are provided, to assist clinicians in the detection & characterization of hemorrhages or bleeds. Images may be acquired from a subject using an imaging source, and preprocessed to cleanup, reformat, and perform any needed interpolation prior to being analyzed by an artificial intelligence network, such as a convolutional neural network (CNN). The artificial intelligence network identifies and labels regions of interest in the image, such as identifying any hemorrhages or bleeds. An output for a user may also include a confidence value associated with the identification.

Abstract: Lesions associated with acute ischemic stroke are automatically segmented in images acquired with computed tomography (“CT”) using a trained machine learning algorithm (e.g., a neural network). The machine learning algorithm is trained on labeled data and associated CT data (e.g., non-contrast CT data and CT angiography source image (“CTA-SI”) data). The labeled data can include segmented data indicating lesions, which are generated by segmenting diffusion-weighted magnetic resonance images acquired within a specified time window from when the associated CT data were acquired. CT data (e.g., non-contrast CT data and CTA-SI data) acquired from a subject are then acquired and input to the trained machine learning algorithm to generate output as segmented CT data, which indicate lesions in the subject.

Abstract: A cart assembly includes a base with wheels, a shelf support structure orthogonally arranged with respect to the base, one or more shelves supported by the support structure, and a swivel mechanism. The swivel mechanism is coupled to the base and the shelf support structure to provide an axis of rotation, such that the shelf support structure and the shelf or shelves are selectively rotatable with respect to the axis. The swivel mechanism may include a race that defines a socket on a circumference of the race. A pin is selectively engageable with the socket to prevent rotation of the race and the support structure. The shelf may include a thermoformed plastic tray, or three shelves arranged at three different levels of the shelf support structure. Some of the shelves may fold against and secure to the shelf support structure.

Abstract: A portable exercise device comprising a clamp, configured to removably coupled to an object, which includes: a spacing member; a first clamping member coupled to the spacing member and extending therefrom; a second clamping member spaced from the first clamping member, coupled to the spacing member, and extending from the spacing member. A clamping device, coupled to the second clamping member, which includes: a pressure reducing plate, disposed between and substantially parallel to each of the first clamping member and the second clamping; and an adjustment device mechanically coupled to the pressure reducing plate, configure to adjust a position of the pressure reducing plate. A plurality of attachment members coupled to and each extending outwardly from the clamp. A plurality of exercise handlebars composed of a substantially rigid elongated member removably coupled to the attachment members which include: a coupling member, a gripping portion, and a spring portion.

Abstract: A method of simultaneous multinuclear magnetic resonance imaging and spatially localized NMR spectroscopy is disclosed. Clinical implementation of the disclosed method allows routine in vivo NMR spectroscopy studies without significantly increasing the time of conventional MR imaging studies. A unique sequence of rf excitation and magnetic gradient pulses is used which allows chemical shift imaging data to be acquired simultaneously with conventional imaging data. A deconvolution method extracts the chemical shift information for analysis and display.