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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thai, Gia Huy, Vu, Hoang-Nguyen, Phan, Anh-Minh, Ly, Quang-Thinh, Dinh, Tram, Nguyen, Thi-Ngoc-Truc, Ho, Nhat
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918402792095744
author Thai, Gia Huy
Vu, Hoang-Nguyen
Phan, Anh-Minh
Ly, Quang-Thinh
Dinh, Tram
Nguyen, Thi-Ngoc-Truc
Ho, Nhat
author_facet Thai, Gia Huy
Vu, Hoang-Nguyen
Phan, Anh-Minh
Ly, Quang-Thinh
Dinh, Tram
Nguyen, Thi-Ngoc-Truc
Ho, Nhat
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation
Thai, Gia Huy
Vu, Hoang-Nguyen
Phan, Anh-Minh
Ly, Quang-Thinh
Dinh, Tram
Nguyen, Thi-Ngoc-Truc
Ho, Nhat
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.18493