GuidedMorph: Two-Stage Deformable Registration for Breast MRI

2025-05-19

AI Summary

In breast MRI multiphase image registration, dense glandular tissue exhibits complex, non-rigid deformations, making it challenging for conventional methods to simultaneously achieve global anatomical alignment and accurate local motion tracking. To address this, we propose a two-stage deformable registration framework. The first stage employs a single-scale global registration network for coarse alignment; the second stage introduces a dual-space transformation network (DSTN) fusion mechanism coupled with an Euclidean distance transform (EDT)-based shape-preserving deformation strategy to precisely model fine-grained glandular motion. The framework is compatible with VoxelMorph and TransMorph backbones and supports both segmentation-guided and segmentation-free inputs. Evaluated on the ISPY2 and an internal dataset, our method achieves a 13.01% improvement in Dice score for dense tissue, a 3.13% gain in whole-breast Dice, and a 1.21% increase in SSIM—outperforming state-of-the-art learning-based approaches across all metrics.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Accurately registering breast MR images from different time points enables the alignment of anatomical structures and tracking of tumor progression, supporting more effective breast cancer detection, diagnosis, and treatment planning. However, the complexity of dense tissue and its highly non-rigid nature pose challenges for conventional registration methods, which primarily focus on aligning general structures while overlooking intricate internal details. To address this, we propose extbf{GuidedMorph}, a novel two-stage registration framework designed to better align dense tissue. In addition to a single-scale network for global structure alignment, we introduce a framework that utilizes dense tissue information to track breast movement. The learned transformation fields are fused by introducing the Dual Spatial Transformer Network (DSTN), improving overall alignment accuracy. A novel warping method based on the Euclidean distance transform (EDT) is also proposed to accurately warp the registered dense tissue and breast masks, preserving fine structural details during deformation. The framework supports paradigms that require external segmentation models and with image data only. It also operates effectively with the VoxelMorph and TransMorph backbones, offering a versatile solution for breast registration. We validate our method on ISPY2 and internal dataset, demonstrating superior performance in dense tissue, overall breast alignment, and breast structural similarity index measure (SSIM), with notable improvements by over 13.01% in dense tissue Dice, 3.13% in breast Dice, and 1.21% in breast SSIM compared to the best learning-based baseline.

Problem

• Aligning breast MR images from different time points for tumor tracking
• Addressing challenges in dense tissue registration with non-rigid deformations
• Improving accuracy in breast structure alignment and similarity metrics

Innovation

• Two-stage framework for dense tissue alignment
• Dual Spatial Transformer Network for fusion
• Euclidean distance transform for precise warping