DeepAI AI Chat
Log In Sign Up

DDR-Net: Dividing and Downsampling Mixed Network for Diffeomorphic Image Registration

by   Ankita Joshi, et al.
University of Georgia
Shanghai Jiao Tong University

Deep diffeomorphic registration faces significant challenges for high-dimensional images, especially in terms of memory limits. Existing approaches either downsample original images, or approximate underlying transformations, or reduce model size. The information loss during the approximation or insufficient model capacity is a hindrance to the registration accuracy for high-dimensional images, e.g., 3D medical volumes. In this paper, we propose a Dividing and Downsampling mixed Registration network (DDR-Net), a general architecture that preserves most of the image information at multiple scales. DDR-Net leverages the global context via downsampling the input and utilizes the local details from divided chunks of the input images. This design reduces the network input size and its memory cost; meanwhile, by fusing global and local information, DDR-Net obtains both coarse-level and fine-level alignments in the final deformation fields. We evaluate DDR-Net on three public datasets, i.e., OASIS, IBSR18, and 3DIRCADB-01, and the experimental results demonstrate our approach outperforms existing approaches.


page 5

page 6

page 7


CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning

Image registration is a fundamental building block for various applicati...

DeepFLASH: An Efficient Network for Learning-based Medical Image Registration

This paper presents DeepFLASH, a novel network with efficient training a...

Dual-Stream Pyramid Registration Network

We propose a Dual-Stream Pyramid Registration Network (referred as Dual-...

Learning Mutually Local-global U-nets For High-resolution Retinal Lesion Segmentation in Fundus Images

Diabetic retinopathy is the most important complication of diabetes. Ear...

Affordance Template Registration via Human-in-the-loop Corrections

Affordance Templates (ATs) are a method for parameterizing objects for a...