Registration is open - make plans to attend
Get pricing and details
>
Conference 12033 > Paper 12033-77
Paper 12033-77

Deep pancreas segmentation through quantification of pancreatic uncertainty on abdominal CT images

In person: 24 February 2022 • 5:10 PM - 5:30 PM PST

Abstract

Pancreas segmentation is very challenging due to the uncertain area arising from variability in the location and morphology of pancreas. The purpose of this study is to improve the performance of pancreas segmentation by improving the level of confidence through multi-scale prediction network (MP-Net) for areas with high uncertainty. First, the pancreas is localized using 2D U-Net on the three-orthogonal planes and by combining through a majority voting. Second, pancreas segmentation is performed in the localized area using a 2D MP-Net. Our deep pancreas segmentation can be used to reduce intra- and inter-patient variations for understanding the shape of pancreas.

Presenter

Seoul Women's Univ. (Korea, Republic of)
Hyeon Dham Yoon received the B.S. from the Department of Software Convergence, Major of Visual Communication Design, and department of Digital Media Design and Applications, Seoul Women’s University in 2020. Fields of interest are medical artificial intelligence, deep learning, image segmentation, and image processing.
Presenter/Author
Seoul Women's Univ. (Korea, Republic of)
Author
Seoul Women's Univ. (Korea, Republic of)
Author
Seoul Women's Univ. (Korea, Republic of)