DEEP LEARNING FOR NEW AND ENLARGING LESIONS

Abstract: a method may include training a machine learning model to identify new lesions and/or enlarging lesions that developed within a multitemporal image input between a first timepoint and a second timepoint. the multitemporal image input includes a first image acquired at the first timepoint and a second image acquired at the second timepoint. the machine learning model is trained by at least generating a first representation of the multitemporal image input from the first timepoint to the second timepoint, a second representation of the multitemporal image input from the second timepoint to the first timepoint, a third representation of the multitemporal image input, and a lesion mask identifying the one or more new lesions and/or enlarging lesions. the method also includes applying the trained machine learning model to generate a lesion mask for a patient. related methods and articles of manufacture are also disclosed.

Inventor(s): Anitha Priya KRISHNAN, Zhuang SONG, Richard Alan Duray CARANO

CPC Classification: G06T7/0016 ({involving temporal comparison})

Search for rejections for patent application number 20250166202