Fast Predictive Simple Geodesic Regression

Abstract

Analyzing large-scale imaging studies with thousands of images is computationally expensive. To assess localized morphological differences, deformable image registration is a key tool. However, as registrations are costly to compute, large-scale studies frequently require large compute clusters. This paper explores a fast predictive approximation to image registration. In particular, it uses these fast registrations to approximate a simplified geodesic regression model to capture longitudinal brain changes. The resulting approach is orders of magnitude faster than the optimization-based regression approach and hence facilitates large-scale analysis on a single graphics processing unit. We show results on 2D and 3D brain magnetic resonance images from OASIS and ADNI.

Publication
Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support - Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Qu├ębec City, QC, Canada, September 14, 2017, Proceedings
Zhipeng Ding
Zhipeng Ding
Graduate Student in Computer Science

My research interests include image registration and machine learning.

Xiao Yang
Xiao Yang
Ph.D. in Computer Science

My research focuses on image registration via deep learning.

Marc Niethammer
Marc Niethammer
Professor of Computer Science

My research interests include image registration, image segmentation, shape analysis, machine learning, and biomedical applications.

Related