Multi-Temporal Image Registration

Biomedical Imaging, UC San Deigo, 2020

A sequence of images is usually captured to observe the change of health status in medical diagnosis. Since it usually takes years to capture a sequence, images easily suffer from severe deformation due to the changes in placement of measuring instrument. The misalignment in image sequence makes it a time-consuming process for physicians to match corresponding patterns/features for diagnosis. In this paper, we propose a coarse-to-fine pipeline for retinal image registration based on convolutional neural network. By leveraging the three components of the pipeline: feature matching, outlier rejection, and local registration, we recover the deformation and accurately align multi-temporal image sequences. Experimental results show that the proposed network is robust to severe deformation as well as illumination and contrast variations. Furthermore, with the proposed registration pipeline, the change of image patterns over time can be clearly observed through visualized analysis.