US 12,266,121 B2
Medical image data creation apparatus for training, medical image data creation method for training and non-transitory recording medium in which program is recorded
Joji Sakamoto, Hachioji (JP); Akihiro Kubota, Kokubunji (JP); and Yamato Kanda, Hino (JP)
Assigned to OLYMPUS CORPORATION, Tokyo (JP)
Filed by OLYMPUS CORPORATION, Tokyo (JP)
Filed on Jul. 14, 2022, as Appl. No. 17/864,574.
Application 17/864,574 is a continuation of application No. PCT/JP2020/001783, filed on Jan. 20, 2020.
Prior Publication US 2022/0351396 A1, Nov. 3, 2022
Int. Cl. G06T 7/00 (2017.01); G06T 7/38 (2017.01)
CPC G06T 7/38 (2017.01) [G06T 2207/20081 (2013.01); G06T 2207/30096 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A medical image data creation apparatus for training comprising:
at least one processor comprising hardware, wherein the at least one processor is configured to:
acquire a first medical image in a first observation mode;
acquire a second medical image that is obtained by photographing a substantially same spot as in the first medical image in a second observation mode different from the first observation mode;
perform alignment of the first medical image and the second medical image;
create lesion region information concerning a lesion part in the second medical image, the alignment of which is performed; and
create medical image data for training a model by machine learning, wherein the medical image data is a set of data of the first medical image and mask region information in which the lesion region information in the second medical image, the alignment of which is performed, is associated with the first medical image.