Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Zhengrui, Sun, Qichen, Ma, Jiabo, Feng, Lishuang, Wang, Jinzhuo, Chen, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918032956194816
author Guo, Zhengrui
Sun, Qichen
Ma, Jiabo
Feng, Lishuang
Wang, Jinzhuo
Chen, Hao
author_facet Guo, Zhengrui
Sun, Qichen
Ma, Jiabo
Feng, Lishuang
Wang, Jinzhuo
Chen, Hao
contents Whole slide image (WSI) analysis presents significant computational challenges due to the massive number of patches in gigapixel images. While transformer architectures excel at modeling long-range correlations through self-attention, their quadratic computational complexity makes them impractical for computational pathology applications. Existing solutions like local-global or linear self-attention reduce computational costs but compromise the strong modeling capabilities of full self-attention. In this work, we propose Querent, i.e., the query-aware long contextual dynamic modeling framework, which achieves a theoretically bounded approximation of full self-attention while delivering practical efficiency. Our method adaptively predicts which surrounding regions are most relevant for each patch, enabling focused yet unrestricted attention computation only with potentially important contexts. By using efficient region-wise metadata computation and importance estimation, our approach dramatically reduces computational overhead while preserving global perception to model fine-grained patch correlations. Through comprehensive experiments on biomarker prediction, gene mutation prediction, cancer subtyping, and survival analysis across over 10 WSI datasets, our method demonstrates superior performance compared to the state-of-the-art approaches. Codes are available at https://github.com/dddavid4real/Querent.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18984
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images
Guo, Zhengrui
Sun, Qichen
Ma, Jiabo
Feng, Lishuang
Wang, Jinzhuo
Chen, Hao
Computer Vision and Pattern Recognition
Whole slide image (WSI) analysis presents significant computational challenges due to the massive number of patches in gigapixel images. While transformer architectures excel at modeling long-range correlations through self-attention, their quadratic computational complexity makes them impractical for computational pathology applications. Existing solutions like local-global or linear self-attention reduce computational costs but compromise the strong modeling capabilities of full self-attention. In this work, we propose Querent, i.e., the query-aware long contextual dynamic modeling framework, which achieves a theoretically bounded approximation of full self-attention while delivering practical efficiency. Our method adaptively predicts which surrounding regions are most relevant for each patch, enabling focused yet unrestricted attention computation only with potentially important contexts. By using efficient region-wise metadata computation and importance estimation, our approach dramatically reduces computational overhead while preserving global perception to model fine-grained patch correlations. Through comprehensive experiments on biomarker prediction, gene mutation prediction, cancer subtyping, and survival analysis across over 10 WSI datasets, our method demonstrates superior performance compared to the state-of-the-art approaches. Codes are available at https://github.com/dddavid4real/Querent.
title Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.18984