Memorial Sloan Kettering Cancer Center

Chensu Xie

Hassan Muhammad

Presented herein are systems and methods for determining scores from biomedical images. A computing system may identify a plurality of tiles in a first biomedical image derived from a sample of a subject. Each tile may correspond to features of the sample. The computing system may apply the plurality of tiles to a machine learning (ML) model. The ML model may include: an encoder to generate a plurality of feature vectors based on the plurality of tiles; a clusterer to select a subset from the plurality of feature vectors; and an aggregator to determine a first score indicative of a time to an event for the subject resulting from the features of the sample. The model may be trained in accordance with a loss derived from second scores determined for second biomedical images. The computing system may store an association between the score and the first biomedical image.

Determining scores indicative of times to events from biomedical images

Presented herein are systems and methods for feature detection in images. A computing system may identify a biomedical image having features. The computing system may apply the biomedical image to a feature detection model. The feature detection model may include an encoder-decoder block to generate a feature map corresponding to the biomedical image, a confidence map generator having a second set of parameters to generate a confidence map using the feature map, and a localization map generator to generate a localization map using the feature map. The computing system may generate a resultant map based on the confidence map and the localization map. The resultant map identifying one or more points corresponding to the one or more features. The computing system may provide the one or more points identified in the resultant map for the biomedical image.

Growing community of inventors

New York, NY, United States of America

Chensu Xie