BEKAR, OGUZCAN PARK, SANMIN 이득희 2024-01-12T03:40:49Z 2024-01-12T03:40:49Z 2023-01-10 2022-08-25 https://pubs.kist.re.kr/handle/201004/77136 Computer-Assisted Spine Surgery, in which the creation of 3D models plays an important role, provides great convenience to surgeons in preoperative surgical planning. For this purpose, computed tomography images are preferred because the bone structures are evident. Segmentation, the core process of creating a 3D model, is time-consuming when done manually. However, the segmentation has been shortened with recent developments in deep learning. Thus, we demonstrate an automated segmentation process with the Mask R-CNN model on the Detectron2 platform that enables rapid and correct prediction of vertebrae in 2D CT images. Index Terms―segmentation, deep learning, detectron2 English ACCAS 2D CT Vertebra Instance Segmentation for Computed-Assisted Spine Surgery Conference 1 The 18th Asian Conference on Computer Aided Surgery (ACCAS 2022) The 18th Asian Conference on Computer Aided Surgery (ACCAS 2022) TH KKU Science Park, Khon Kaen 2022-08-24 Proceeding of the 18th Asian Conference on Computer Aided Surgery (ACCAS 2022)