Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration

TL;DR

The paper introduces DySNet, a dynamic network for deformable medical image registration that adaptively adjusts receptive fields and weights to effectively handle the combinatorial explosion of feature relationships.

Contribution

It proposes a novel dynamic stream network with adaptive modules to better model relevant feature relationships in DMIR, addressing the combinatorial explosion problem.

Findings

DySNet outperforms state-of-the-art DMIR methods.

The adaptive modules improve focus on relevant feature relationships.

The model demonstrates strong generalization across datasets.

Abstract

Combinatorial explosion problem caused by dual inputs presents a critical challenge in Deformable Medical Image Registration (DMIR). Since DMIR processes two images simultaneously as input, the combination relationships between features has grown exponentially, ultimately the model considers more interfering features during the feature modeling process. Introducing dynamics in the receptive fields and weights of the network enable the model to eliminate the interfering features combination and model the potential feature combination relationships. In this paper, we propose the Dynamic Stream Network (DySNet), which enables the receptive fields and weights to be dynamically adjusted. This ultimately enables the model to ignore interfering feature combinations and model the potential feature relationships. With two key innovations: 1) Adaptive Stream Basin (AdSB) module dynamically adjusts the shape of the receptive field, thereby enabling the model to focus on the feature relationships with greater correlation. 2) Dynamic Stream Attention (DySA) mechanism generates dynamic weights to search for more valuable feature relationships. Extensive experiments have shown that DySNet consistently outperforms the most advanced DMIR methods, highlighting its outstanding generalization ability. Our code will be released on the website: https://github.com/ShaochenBi/DySNet.