Slicer 网络
Slicer Networks
AI总结：
本文提出 Slicer Network，通过可学习双边网格与 splatting-blurring-slicing 实现保边低频近似，在医学图像配准和病灶分割中提升精度与效率。
摘要：
在医学成像中，扫描结果通常会显示具有不同对比度但内部强度或纹理一致的对象。这一特征使得低频近似可用于分割和形变场估计等任务。然而，将这一概念融入用于医学图像分析的神经网络架构仍未得到充分研究。本文提出 Slicer Network，这是一种旨在利用这些特征的新型架构。Slicer Network 由一个利用 vision transformers 等模型进行特征提取的编码器，以及一个采用可学习双边网格的 slicer 组成，通过 splatting-blurring-slicing 过程有策略地细化并上采样特征图。这为网络输出引入了保边低频近似，有效扩大了感受野。该增强不仅降低了计算复杂度，还提升了整体性能。在不同医学成像应用（包括无监督和基于关键点的图像配准以及病灶分割）中的实验，验证了 Slicer Network 在准确性和效率方面的提升。
英文摘要：
In medical imaging, scans often reveal objects with varied contrasts but consistent internal intensities or textures. This characteristic enables the use of low-frequency approximations for tasks such as segmentation and deformation field estimation. Yet, integrating this concept into neural network architectures for medical image analysis remains underexplored. In this paper, we propose the Slicer Network, a novel architecture designed to leverage these traits. Comprising an encoder utilizing models like vision transformers for feature extraction and a slicer employing a learnable bilateral grid, the Slicer Network strategically refines and upsamples feature maps via a splatting-blurring-slicing process. This introduces an edge-preserving low-frequency approximation for the network outcome, effectively enlarging the effective receptive field. The enhancement not only reduces computational complexity but also boosts overall performance. Experiments across different medical imaging applications, including unsupervised and keypoints-based image registration and lesion segmentation, have verified the Slicer Network's improved accuracy and efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
