US 12,307,675 B2
Systems and methods for segmenting objects in medical images
László Ruskó, Budapest (HU); Vanda Czipczer, Budapest (HU); Bernadett Kolozsvári, Budapest (HU); Richárd Zsámboki, Budapest (HU); Tao Tan, Noord Brabant (NL); Balázs Péter Cziria, Budapest (HU); Attila Márk Rádics, Budapest (HU); Lehel Ferenczi, Budapest (HU); Fei Mian, Waukesha, WI (US); Hongxiang Yi, Excelsior, MN (US); and Florian Wiesinger, Freising (DE)
Assigned to GE PRECISION HEALTHCARE LLC, Wauwatosa, WI (US)
Filed by GE Precision Healthcare LLC, Wauwatosa, WI (US)
Filed on Mar. 23, 2022, as Appl. No. 17/656,171.
Prior Publication US 2023/0306601 A1, Sep. 28, 2023
Int. Cl. G06T 7/11 (2017.01); G06T 7/00 (2017.01); G06T 7/12 (2017.01); G06T 11/00 (2006.01); G06T 11/20 (2006.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01)
CPC G06T 7/11 (2017.01) [G06T 7/0012 (2013.01); G06T 7/12 (2017.01); G06T 11/001 (2013.01); G06T 11/203 (2013.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G06T 2207/30168 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for segmenting structures in one or more medical images, comprising:
receiving an input dataset including a set of medical images, a structure list specifying a set of structures to be segmented, and a segmentation protocol;
performing an input check on the input dataset, the input check including analyzing one or more medical images from the set of medical images to determine if the one or more medical images comply with segmentation parameters dictated at least in part by the segmentation protocol;
determining whether the one or more medical images have passed the input check and removing any medical images from the one or more medical images that do not pass the input check to form a final set of medical images;
segmenting each structure from the structure list using one or more segmentation models and the final set of medical images;
receiving a set of segmentations output from the one or more segmentation models;
processing the set of segmentations to generate a final set of segmentations; and
displaying and/or saving in memory the final set of segmentations,
wherein performing the input check on the input dataset further includes, for each medical image of the one or more medical images:
analyzing each medical image to determine if each medical image has at least a threshold image quality; and
indicating that each medical image that does not have at least the threshold image quality does not pass the input check, and indicating that each medical image that does have at least the threshold image quality does pass the input check.