公开(公告)号：US20240119648A1

公开(公告)日：2024-04-11

申请号：US18101148

申请日：2023-01-25

Applicant: Korea Advanced Institute of Science and Technology

Inventor： In Gwun JANG ,  Bong-Ju CHUN ,  Hyukjin KOH

IPC: G06T11/00 ,  G06T3/40 ,  G06T7/00 ,  G06T7/11 ,  G06T7/136 ,  G16H30/40 ,  G16H50/20

CPC classification number: G06T11/008 ,  G06T3/4046 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/136 ,  G16H30/40 ,  G16H50/20 ,  G06T2207/10081 ,  G06T2207/20016 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30008 ,  G06T2210/41 ,  G06T2211/40

Abstract: Provided are a method and device for deep learning-based patch-wise three-dimensional (3D) bone microstructure reconstruction from clinical CT scan data. A computer device may be configured to segment a low-resolution skeletal image into a plurality of low-resolution image patches, to acquire a plurality of high-resolution image patches from the low-resolution image patches, respectively, using a pretrained artificial neural network, and to reconstruct a high-resolution bone microstructure by assembling and postprocessing the high-resolution image patches.