MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hang, Chen, Xiang, Hu, Renjiu, Liu, Dongdong, Li, Gaolei, Wang, Rongguang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917719266295808
author Zhang, Hang
Chen, Xiang
Hu, Renjiu
Liu, Dongdong
Li, Gaolei
Wang, Rongguang
author_facet Zhang, Hang
Chen, Xiang
Hu, Renjiu
Liu, Dongdong
Li, Gaolei
Wang, Rongguang
contents Many existing learning-based deformable image registration methods impose constraints on deformation fields to ensure they are globally smooth and continuous. However, this assumption does not hold in cardiac image registration, where different anatomical regions exhibit asymmetric motions during respiration and movements due to sliding organs within the chest. Consequently, such global constraints fail to accommodate local discontinuities across organ boundaries, potentially resulting in erroneous and unrealistic displacement fields. In this paper, we address this issue with MemWarp, a learning framework that leverages a memory network to store prototypical information tailored to different anatomical regions. MemWarp is different from earlier approaches in two main aspects: firstly, by decoupling feature extraction from similarity matching in moving and fixed images, it facilitates more effective utilization of feature maps; secondly, despite its capability to preserve discontinuities, it eliminates the need for segmentation masks during model inference. In experiments on a publicly available cardiac dataset, our method achieves considerable improvements in registration accuracy and producing realistic deformations, outperforming state-of-the-art methods with a remarkable 7.1\% Dice score improvement over the runner-up semi-supervised method. Source code will be available at https://github.com/tinymilky/Mem-Warp.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08093
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters
Zhang, Hang
Chen, Xiang
Hu, Renjiu
Liu, Dongdong
Li, Gaolei
Wang, Rongguang
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Signal Processing
Many existing learning-based deformable image registration methods impose constraints on deformation fields to ensure they are globally smooth and continuous. However, this assumption does not hold in cardiac image registration, where different anatomical regions exhibit asymmetric motions during respiration and movements due to sliding organs within the chest. Consequently, such global constraints fail to accommodate local discontinuities across organ boundaries, potentially resulting in erroneous and unrealistic displacement fields. In this paper, we address this issue with MemWarp, a learning framework that leverages a memory network to store prototypical information tailored to different anatomical regions. MemWarp is different from earlier approaches in two main aspects: firstly, by decoupling feature extraction from similarity matching in moving and fixed images, it facilitates more effective utilization of feature maps; secondly, despite its capability to preserve discontinuities, it eliminates the need for segmentation masks during model inference. In experiments on a publicly available cardiac dataset, our method achieves considerable improvements in registration accuracy and producing realistic deformations, outperforming state-of-the-art methods with a remarkable 7.1\% Dice score improvement over the runner-up semi-supervised method. Source code will be available at https://github.com/tinymilky/Mem-Warp.
title MemWarp: Discontinuity-Preserving Cardiac Registration with Memorized Anatomical Filters
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Signal Processing
url https://arxiv.org/abs/2407.08093