SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

TL;DR

SAGE introduces a dynamic, input-adaptive framework for histopathology image segmentation that improves accuracy and robustness by reconfiguring static neural networks into flexible expert architectures.

Contribution

The paper presents SAGE, a novel framework enabling dynamic expert routing in visual networks, enhancing adaptability and performance in heterogeneous histopathology image segmentation.

Findings

Achieved high Dice scores on multiple datasets.

Demonstrated robustness under distribution shifts.

Enabled flexible visual reasoning in histopathology.

Abstract

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, 92.78\%/91.42\% DSC on GlaS Test A/Test B, 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.