US 11,972,564 B2
Recording medium, information processing device, information processing method, trained model generation method, and correlation image output device
Felix Julian Brandenburg, Tokyo (JP); Akihiro Okuno, Tokyo (JP); and Yuki Aoyama, Tokyo (JP)
Assigned to Splink, Inc., Tokyo (JP)
Appl. No. 18/020,834
Filed by Splink, Inc., Tokyo (JP)
PCT Filed Aug. 14, 2020, PCT No. PCT/JP2020/030905
§ 371(c)(1), (2) Date Feb. 10, 2023,
PCT Pub. No. WO2022/034691, PCT Pub. Date Feb. 17, 2022.
Prior Publication US 2023/0230233 A1, Jul. 20, 2023
Int. Cl. G06T 7/00 (2017.01); G06V 10/25 (2022.01); G16H 30/20 (2018.01); G16H 50/20 (2018.01)
CPC G06T 7/0012 (2013.01) [G06V 10/25 (2022.01); G16H 30/20 (2018.01); G16H 50/20 (2018.01); G06T 2207/10088 (2013.01); G06T 2207/30016 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A computer readable non-transitory recording medium recording a computer program causing a computer to execute processes of:
acquiring an MRI image of a subject; and
inputting the acquired MRI image to a trained model, the trained model composed of a neural network including an input layer, an intermediate layer, and an output layer outputs a correlation image from the output layer and generated by machine learning, that, which is an image in which the correlation coefficient is specified for a cluster unit that is set of voxels, a voxel unit, or a region of interest unit between a magnetic susceptibility capable of being specified on the basis of the MRI image and amyloid β estimated without PET imaging in a case where the MRI image is input to the input layer, and outputting the correlation image, which is an image in which the correlation coefficient is specified for a cluster unit that is set of voxels, a voxel unit, or a region of interest unit between the magnetic susceptibility of the subject and amyloid β estimated without PET imaging.