CROWn：面向三维医学分割的抗混叠下采样与相位校准融合统一框架
CROWn: A Unified Framework for Anti-Aliased Downsampling and Phase-Calibrated Fusion in 3D Medical Segmentation
把采样理论引入分割网络的降采样与跳连环节：用多相分解+子带共注意力在抽取时抑制混叠，用空间到深度重排+相位注意力对齐高分辨率跳连，可直接迁移到任何带各向异性体素或跨尺度融合的 3D 分割/检测骨干。
原文依据 performs axis-aware polyphase analysis with pooled-subband co-attention and explicit anti-alias low-pass
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论精确的三维医学图像分割是诊断、治疗规划与纵向随访的临床基石。然而，常规采集中的各向异性体素间距与异质重建会引入下采样混叠与跨尺度失配，导致边界模糊、拓扑破碎并削弱可靠性。现有的 U 形 CNN 或 Transformer 设计既无法在抽取阶段控制混叠的注入，也未能在解码器融合前显式对齐高分辨率证据，从而在设备与协议变化下产生不稳定的接口。我们提出陪集纤维化微局部共注意力网络（CROWn），这是一个将采样理论与表征学习耦合起来、以联合抑制混叠并校准跨尺度融合的通用分割框架。CROWn 由两个互补组件构成。微局部多相共注意力抽取器（μPCAD）执行轴感知的多相分析，结合池化子带共注意力与显式抗混叠低通，在下采样过程中引导与边界相关的高频证据并衰减虚假相位成分。八相陪集纤维化（OCF）对高分辨率跳连进行抗混叠处理，通过三维空间到深度重排将其重构为陪集，并施加带边缘门控调制的相位注意力，从而向解码器提供紧凑、相位对齐且边界感知的特征。在涵盖 CT、MRI 与 OCT 的 15 个公开数据集上的大量评估表明，CROWn 相对 17 种近期领先方法取得最优性能，提升了重叠度与拓扑一致性，持续降低边界误差，同时保持可控的训练与推理开销。代码已公开于 https://github.com/IMOP-lab/CROWn。
英文原文摘要 1764 字符
Precise 3D medical image segmentation is a clinical cornerstone for diagnosis, therapy planning, and longitudinal monitoring. However, routine acquisition with anisotropic voxel spacing and heterogeneous reconstruction induces downsampling aliasing and cross-scale misalignment that blur boundaries, fragment topology, and undermine reliability. Existing U-shaped CNN or Transformer designs neither control alias injection at decimation nor explicitly align high-resolution evidence before decoder fusion, leading to unstable interfaces under device and protocol variability. We introduce the Coset-fibRated micrO-local co-attention Network (CROWn), a general segmentation framework that couples sampling theory with representation learning to jointly suppress aliasing and calibrate cross-scale fusion. CROWn comprises two complementary components. The Microlocal Polyphase Co-Attentive Decimator (\muPCAD) performs axis-aware polyphase analysis with pooled-subband co-attention and explicit anti-alias low-pass, routing boundary-relevant high-frequency evidence while attenuating spurious phase components during downsampling. The Octaphase Coset Fibration (OCF) anti-aliases high-resolution skips, restructures them via 3D space-to-depth into cosets, and applies phase attention with edge-gated modulation to deliver compact, phase-aligned, boundary-aware features to the decoder. Extensive evaluations across 15 publicly available datasets spanning CT, MRI, and OCT demonstrate CROWn's state-of-the-art performance against 17 recent leading methods, improves overlap and topological consistency, consistently reduces boundary errors, while maintaining controlled training and inference cost. The code is publicly available at https://github.com/IMOP-lab/CROWn.