Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed TomographyYeon Woong Chung 1,2, Dong Gyun Kang 3, Yong Oh Lee 4, Won-Kyung Cho 1,5
1College of Medicine, The Catholic University of Korea, 2Department of Ophthalmology, St. Vincent’s Hospital, 3Yeoncheon Public Medical Center, 4Department of Industrial and Data Engineering, Hongik University, 5Department of Ophthalmology, Uijeongbu St. Mary’s Hospital
An object segmentation protocol for orbital computed tomography (CT) images is introduced. The methods of labeling the ground truth of orbital structures by using super-resolution, extracting the volume of interest from CT images, and modeling multi-label segmentation using 2D sequential U-Net for orbital CT images are explained for supervised learning.
