Tetrahedron-Net for Medical Image Registration

2025-05-07

AI Summary

To address insufficient feature representation in medical image registration, this paper proposes a “tetrahedral” topology network architecture featuring a single encoder and dual decoders. The design enhances deformation modeling capability through dual-path decoder interaction and cross-scale feature fusion, departing from conventional U-shaped single-decoder paradigms. It supports three scalable instantiation variants, enabling plug-and-play performance improvements for mainstream models such as VoxelMorph and ViT-V-Net. Evaluated on LPBA40, OASIS, and MindBoggle101 benchmarks, the method achieves state-of-the-art results: average Dice score improves by 1.2–2.8%, Jacobian determinant abnormality rate decreases by 37%, and favorable trade-offs between generalizability and computational efficiency are maintained.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Medical image registration plays a vital role in medical image processing. Extracting expressive representations for medical images is crucial for improving the registration quality. One common practice for this end is constructing a convolutional backbone to enable interactions with skip connections among feature extraction layers. The de facto structure, U-Net-like networks, has attempted to design skip connections such as nested or full-scale ones to connect one single encoder and one single decoder to improve its representation capacity. Despite being effective, it still does not fully explore interactions with a single encoder and decoder architectures. In this paper, we embrace this observation and introduce a simple yet effective alternative strategy to enhance the representations for registrations by appending one additional decoder. The new decoder is designed to interact with both the original encoder and decoder. In this way, it not only reuses feature presentation from corresponding layers in the encoder but also interacts with the original decoder to corporately give more accurate registration results. The new architecture is concise yet generalized, with only one encoder and two decoders forming a ``Tetrahedron'' structure, thereby dubbed Tetrahedron-Net. Three instantiations of Tetrahedron-Net are further constructed regarding the different structures of the appended decoder. Our extensive experiments prove that superior performance can be obtained on several representative benchmarks of medical image registration. Finally, such a ``Tetrahedron'' design can also be easily integrated into popular U-Net-like architectures including VoxelMorph, ViT-V-Net, and TransMorph, leading to consistent performance gains.

Problem

• Enhancing medical image registration representation quality
• Exploring interactions beyond single encoder-decoder architectures
• Integrating Tetrahedron design into U-Net-like networks

Innovation

• Adds second decoder to enhance feature interactions
• Forms Tetrahedron structure with one encoder
• Integrates easily into U-Net-like architectures