提出新型脑图像配准网络，提升精度与效率
FF-PNet: A Pyramid Network Based on Feature and Field for Brain Image Registration
- 并行设计特征与形变场融合模块，高效提取粗细特征
- 在LPBA和OASIS数据集上显著优于主流方法，Dice系数更高
- 仅用传统CNN无注意力机制，仍实现高精度，适合医学影像领域
近年来，可变形医学图像配准技术取得显著进展。然而，现有模型在并行提取粗粒度与细粒度特征方面仍显低效。为此，我们构建了一种基于特征与形变场的金字塔配准网络（FF-PNet）。针对粗粒度特征提取，设计了残差特征融合模块（RFFM）；针对细粒度图像形变，提出了残差形变场融合模块（RDFFM）。通过两模块并行运作，模型能有效处理复杂图像形变。值得注意的是，FF-PNet编码阶段仅使用传统卷积神经网络，未引入注意力机制或多层感知机，却仍显著提升配准精度，充分展现了RFFM与RDFFM卓越的特征解码能力。我们在LPBA和OASIS数据集上进行了大量实验，结果表明，该网络在骰子相似系数（Dice Similarity Coefficient）等指标上持续优于主流方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。