US 11,682,485 B2
Methods and systems for adaptive radiotherapy treatment planning using deep learning engines
Hannu Laaksonen, Espoo (FI); Janne Nord, Espoo (FI); and Sami Petri Perttu, Helsinki (FI)
Assigned to SIEMENS HEALTHINEERS INTERNATIONAL AG, (CH)
Filed by SIEMENS HEALTHINEERS INTERNATIONAL AG, Palo Alto, CA (US)
Filed on Sep. 27, 2022, as Appl. No. 17/953,346.
Application 17/953,346 is a continuation of application No. 16/145,673, filed on Sep. 28, 2018, granted, now 11,475,991.
Prior Publication US 2023/0020911 A1, Jan. 19, 2023
Int. Cl. G16H 30/40 (2018.01); A61N 5/10 (2006.01); G06N 3/08 (2023.01); G16H 20/40 (2018.01); G16B 40/00 (2019.01)
CPC G16H 30/40 (2018.01) [A61N 5/1031 (2013.01); A61N 5/1038 (2013.01); A61N 5/1039 (2013.01); G06N 3/08 (2013.01); G16B 40/00 (2019.02); G16H 20/40 (2018.01); A61N 2005/1041 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for a computer system to perform adaptive radiotherapy treatment planning, wherein the method comprises:
obtaining treatment image data associated with a first imaging modality, wherein the treatment image data is acquired during a treatment phase of a patient;
obtaining planning image data associated with a second imaging modality, wherein the planning image data is acquired prior to the treatment phase to generate a treatment plan for the patient;
determining whether a difference between the treatment image data and the planning image data exceeds a threshold;
in response to determination that the difference exceeds the threshold,
transforming the treatment image data associated with the first imaging modality to generate transformed image data associated with the second imaging modality; and
processing, using a first deep learning engine, the transformed image data to generate output data for updating the treatment plan;
otherwise, processing, using a second deep learning engine, the treatment image data and the planning image data to generate output data for updating the treatment plan.