US 12,254,990 B2
Methods and systems for determining health of an organ based on medical image data using artificial intelligence
Ahmed Sherif Fouad Hosny, San Francisco, CA (US); and Hugo J Aerts, Brookline, MA (US)
Assigned to Ambient, Inc., Brookline, MA (US)
Filed by Ambient, Inc., Brookline, MA (US)
Filed on Sep. 4, 2024, as Appl. No. 18/824,511.
Prior Publication US 2024/0428949 A1, Dec. 26, 2024
Int. Cl. G16H 50/30 (2018.01); G06T 7/00 (2017.01)
CPC G16H 50/30 (2018.01) [G06T 7/0012 (2013.01); G06T 2207/10081 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for evaluating health of an organ, comprising:
receiving, by one or more processors, medical image data associated with the organ, the organ comprising a thymus, the medical image data comprising a computed tomography scan;
generating a classification output, utilizing artificial intelligence, by applying a machine learning model to the received medical image data, the machine learning model trained based on a set of images associated with a plurality of thymus, at least a number of the set of images comprising labeled images, the labeled images labeled to indicate levels of fatty degeneration or non-fat attenuation in the thymus, the machine learning model generated utilizing at least supervised learning techniques;
outputting, using the one or more processors, a health score based on the classification output; and
applying a clinical solution based on the health score, the clinical solution comprising administering one or both of immunotherapy and chemotherapy.