The General Hospital Corporation

Ona Wu

Gregory Sorensen

Ramon Gilberto Gonzalez

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.

Automatic segmentation of acute ischemic stroke lesions in computed tomography data

Methods for computing perfusion parameters are described. The methods are typically used to analyze magnetic resonance (MR) and other image data and to calculate tissue perfusion parameters such as blood flow in the brain or in tissues in other organs such as the heart. The methods employ a block-circulant matrix for deconvolving the perfusion parameters from the image data.

Delay-compensated calculation of tissue blood flow

A method of evaluating novel stroke treatments includes generating a risk map indicative of the probability of tissue infarction on voxel-by-voxel basis and selecting a probability range for evaluating the therapeutic effect of the novel treatment. In one particular embodiment, tissue having a fifty percent probability of tissue infarction is selected. A novel treatment that has a reduced level of overall actual infarction as compared to the predicted value is indicative of therapeutic effect.

Growing community of inventors

Cambridge, MA, United States of America

Ona Wu