US 11,900,601 B2
Loading deep learning network models for processing medical images
Hans Harald Zachmann, Toronto (CA); Simona Rabinovici-Cohen, Haifa (IL); and Shaked Brody, Jerusalem (IL)
Assigned to Merative US L.P., Ann Arbor, MI (US)
Filed by MERATIVE US L.P., Ann Arbor, MI (US)
Filed on Feb. 17, 2023, as Appl. No. 18/170,789.
Application 18/170,789 is a division of application No. 16/664,542, filed on Oct. 25, 2019, granted, now 11,593,932.
Prior Publication US 2023/0206437 A1, Jun. 29, 2023
Int. Cl. G06N 5/04 (2023.01); G06T 7/00 (2017.01); G06F 9/455 (2018.01)
CPC G06T 7/0012 (2013.01) [G06F 9/45558 (2013.01); G06N 5/04 (2013.01); G06F 2009/4557 (2013.01); G06F 2009/45575 (2013.01); G06F 2009/45583 (2013.01); G06T 2207/20081 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A system for processing medical imaging exams using a plurality of deep learning models, the system comprising:
an electronic processor configured to
create, in response to startup of an application using an algorithm configured to process medical images using one or more of a plurality of models, a server process supporting a programming language associated with the algorithm, wherein the plurality of models are based on the same or different deep learning frameworks;
access a first set of one or more medical images;
determine a first set of one or more models included in the plurality of models for processing the first set of one or more medical images;
in response to the first set of one or more models not being loaded into a memory of the server process, load the first set of one or more models into the memory of the server process to create a first set of in-memory models;
process the first set of one or more medical images with the server process using the algorithm and the first set of in-memory models;
output at least one result of the processing of the first set of one or more medical images;
maintain the first set of in-memory models in the memory of the server process after processing the first set of one or more medical images;
access a second set of one or more medical images;
determine a second set of one or more models included in the plurality of models for processing the second set of one or more medical images;
in response to at least one model in the second set of one or more models not being loaded into the memory of the server process, load the at least one model into the memory of the server process to create a second set of in-memory models;
process the second set of one or more medical images with the server process using the algorithm, the first set of in-memory models, and the second set of in-memory models;
output at least one result of the processing of the second set of one or more medical images;
maintain the first set of in-memory models and the second set of in-memory models in the memory of the server process after processing the second set of one or more medical images; and
execute the server process to process one or more additional sets of one or more medical images until explicitly terminated by the application.