Deep Convolutional Neural Network for Non-rigid Image Registration
This addresses the need for faster registration in applications like medical image analysis for tracking or disease diagnosis, though it appears incremental as it applies a known method (CNN) to a known bottleneck.
The paper tackles the problem of non-rigid image registration, which is computationally expensive with existing methods, and shows that a deep convolutional neural network can perform it efficiently with significantly less computational time than conventional approaches like Diffeomorphic Demons or Pyramiding.
Images taken at different times or positions undergo transformations such as rotation, scaling, skewing, and more. The process of aligning different images which have undergone transformations can be done via registration. Registration is desirable when analyzing time-series data for tracking, averaging, or differential diagnoses of diseases. Efficient registration methods exist for rigid (including linear or affine) transformations; however, for non-rigid (also known as non-affine) transformations, current methods are computationally expensive and time-consuming. In this report, I will explore the ability of a deep neural network (DNN) and, more specifically, a deep convolutional neural network (CNN) to efficiently perform non-rigid image registration. The experimental results show that a CNN can be used for efficient non-rigid image registration and in significantly less computational time than a conventional Diffeomorphic Demons or Pyramiding approach.