PMRNet：面向医学图像分割的物理信息多尺度细化网络
PMRNet: Physics-informed Multi-scale Refinement Network for Medical Image Segmentation
用熵驱动的扩散机制以线性复杂度逼近全局感受野，并用重正化群式下采样保留信息，这套「伪全局感受野 + 边界感知解码」的组合可直接迁移到其他需要低算力密集预测的视觉任务。
原文依据 a Pseudo-Global Receptive Field module achieving near-global context with linear complexity through entropy-driven diffusion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论医学图像分割既要求高精度，也要求计算效率，然而现有方法面临一个关键的两难：卷积神经网络缺乏全局上下文，而 Transformer 在资源受限设备上部署时开销过高。为应对这一挑战，本文提出物理信息多尺度细化网络（PMRNet），融合辛几何、重正化群理论与熵扩散来引导特征学习。PMRNet 包含三项创新：（1）物理信息编码器，采用增强辛卷积进行边界检测，并采用受重正化群启发的下采样以保留信息；（2）伪全局感受野模块，通过熵驱动的扩散以线性复杂度获得接近全局的上下文；（3）边界感知解码器，用于精确勾勒边界。PMRNet 仅有 0.87M 参数和 3.43 GFLOPs，在具有挑战性的 Clinic 数据集上取得 87.25% 的 IoU 和 92.56% 的 Dice，在 12 个医学影像数据集上优于参数量多出 100 倍的最优（SOTA）模型，同时保持计算效率。代码见 https://github.com/KangBoce/PMRNet。
英文原文摘要 1183 字符
Medical image segmentation demands both high accuracy and computational efficiency, yet existing methods face a critical trade-off: CNNs lack global context while transformers incur prohibitive costs for deployment on resource-constrained devices. To address this challenge, we propose a Physics-informed Multi-scale Refinement Network (PMRNet), integrating symplectic geometry, renormalization group theory, and entropy diffusion to guide feature learning. PMRNet features three innovations: (1) a physics-informed encoder with Enhanced Symplectic Convolution for boundary detection and Renormalization Group-inspired Downsampling for information preservation; (2) a Pseudo-Global Receptive Field module achieving near-global context with linear complexity through entropy-driven diffusion; and (3) a boundary-aware decoder for precise delineation. With only 0.87M parameters and 3.43 GFLOPs, PMRNet achieves 87.25% IoU and 92.56% Dice on the challenging Clinic dataset, outperforming state-of-the-art (SOTA) models with even 100x more parameters across 12 medical imaging datasets while maintaining computational efficiency. Code is available at https://github.com/KangBoce/PMRNet.