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: 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.