FF-PNet: A Pyramid Network Based on Feature and Field for Brain Image Registration

TL;DR

FF-PNet introduces a pyramid network with specialized modules for efficient coarse and fine feature extraction, significantly improving brain image registration accuracy without complex attention mechanisms.

Contribution

The paper proposes a novel pyramid registration network with parallel modules for feature and deformation field fusion, enhancing registration performance in brain imaging.

Findings

Outperforms existing methods in Dice Similarity Coefficient

Effective handling of complex deformations

Achieves high registration accuracy without attention mechanisms

Abstract

In recent years, deformable medical image registration techniques have made significant progress. However, existing models still lack efficiency in parallel extraction of coarse and fine-grained features. To address this, we construct a new pyramid registration network based on feature and deformation field (FF-PNet). For coarse-grained feature extraction, we design a Residual Feature Fusion Module (RFFM), for fine-grained image deformation, we propose a Residual Deformation Field Fusion Module (RDFFM). Through the parallel operation of these two modules, the model can effectively handle complex image deformations. It is worth emphasizing that the encoding stage of FF-PNet only employs traditional convolutional neural networks without any attention mechanisms or multilayer perceptrons, yet it still achieves remarkable improvements in registration accuracy, fully demonstrating the superior feature decoding capabilities of RFFM and RDFFM. We conducted extensive experiments on the LPBA and OASIS datasets. The results show our network consistently outperforms popular methods in metrics like the Dice Similarity Coefficient.