针对病理图像细胞形态差异大难题，提出动态专家路由模型SAGE。
SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation
- 通过双路径结构与形状自适应枢纽，实现输入驱动的动态专家选择
- 在EBHI、GlaS和DigestPath数据集上达91%以上分割准确率
- 适合需要灵活适应复杂病理图像的医疗视觉分析场景
细胞大小与形状的高度变异仍是百万像素级全切片图像（WSI）中计算机辅助癌症检测的主要障碍。现有卷积-变换器混合模型采用静态计算图与固定路由机制，导致冗余计算且难以适应输入变化。本文提出形状自适应门控专家（SAGE），一种输入自适应框架，支持异构视觉网络中的动态专家路由。SAGE通过双路径设计与分层门控，将静态主干重构为动态路由专家架构，并引入形状自适应枢纽（SA-Hub），统一卷积与变换器模块的特征表示。以ConvNeXt与Vision Transformer UNet为基础构建的SAGE-ConvNeXt+ViT-UNet，在EBHI上取得95.23%的Dice分数，GlaS Test A与Test B分别达到92.78%与91.42%的DSC，DigestPath在全切片级别（WSI level）达91.26% DSC，且在分布偏移下仍保持鲁棒性，能自适应平衡局部细节与全局上下文。SAGE为视觉网络中的动态专家路由提供了可扩展基础，推动灵活视觉推理的发展。
原文摘要 · Abstract (English)
The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static computation graphs with fixed routing. This leads to extra computation and makes it harder to adapt to changes in input. We propose Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks. SAGE reconfigures static backbones into dynamically routed expert architectures via a dual-path design with hierarchical gating and a Shape-Adapting Hub (SA-Hub) that harmonizes feature representations across convolutional and transformer modules. Embodied as SAGE with ConvNeXt and Vision Transformer UNet (SAGE-ConvNeXt+ViT-UNet), our model achieves a Dice score of 95.23% on EBHI, DSC scores of 92.78% and 91.42% on GlaS Test A and Test B, respectively, and 91.26% DSC at the WSI level on DigestPath, while exhibiting robust generalization under distribution shifts by adaptively balancing local refinement and global context. SAGE establishes a scalable foundation for dynamic expert routing in visual networks, thereby facilitating flexible visual reasoning. Project page: https://oxyzgiahuy.github.io/sage/
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。