CPC G06T 7/11 (2017.01) [A61B 6/032 (2013.01); A61B 6/037 (2013.01); A61B 6/463 (2013.01); A61B 6/466 (2013.01); A61B 6/481 (2013.01); A61B 6/505 (2013.01); A61B 6/507 (2013.01); A61B 6/5205 (2013.01); A61B 6/5241 (2013.01); A61B 6/5247 (2013.01); A61K 51/0455 (2013.01); G06F 18/214 (2023.01); G06V 20/64 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01); G06V 30/2504 (2022.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G06V 2201/031 (2022.01); G06V 2201/033 (2022.01)] | 30 Claims |
1. A method for automatically analyzing medical images to detect lesions within a subject while correcting for a signal from one or more background tissue regions in which a radiopharmaceutical accumulates under normal circumstances without lesions necessarily being present, the method comprising:
(a) receiving, by a processor of a computing device, a 3D functional image of the subject, said 3D functional image having been acquired following administration of the radiopharmaceutical to the subject;
(b) receiving, by the processor, a 3D anatomical image of the subject obtained using an anatomical imaging modality and comprising a graphical representation of tissue within the subject;
(c) automatically identifying, by the processor, using one or more machine learning modules, one or more volumes within the 3D anatomical image, each volume corresponding to a particular one of the one or more background tissue regions in which the radiopharmaceutical accumulates under normal circumstances without lesions necessarily being present;
(d) determining, by the processor, using the one or more volumes within the 3D anatomical image identified in step (c), one or more 3D background volumes within the 3D functional image, each 3D background volume within the 3D functional image corresponding to a particular one of the one or more volumes identified within the 3D anatomical image; and
(e) automatically detecting, by the processor, one or more hotspots within the 3D functional image using the one or more 3D background volumes determined within the 3D functional image to correct for the signal from the one or more background tissue regions.
|