Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images

Abstract In computational pathology, extracting and representing spatial features from gigapixel whole slide images (WSIs) are fundamental tasks, but due to their large size, WSIs are typically segmented into smaller tiles. A critical aspect of analyzing WSIs is how information across tiles is aggre...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruiwen Ding, Kha-Dinh Luong, Erika Rodriguez, Ana Cristina Araujo Lemos da Silva, William Hsu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-99042-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687850440720384
author Ruiwen Ding
Kha-Dinh Luong
Erika Rodriguez
Ana Cristina Araujo Lemos da Silva
William Hsu
author_facet Ruiwen Ding
Kha-Dinh Luong
Erika Rodriguez
Ana Cristina Araujo Lemos da Silva
William Hsu
author_sort Ruiwen Ding
collection DOAJ
description Abstract In computational pathology, extracting and representing spatial features from gigapixel whole slide images (WSIs) are fundamental tasks, but due to their large size, WSIs are typically segmented into smaller tiles. A critical aspect of analyzing WSIs is how information across tiles is aggregated to predict outcomes such as patient prognosis. We introduce a model that combines a message-passing graph neural network (GNN) with a state space model (Mamba) to capture both local and global spatial relationships among the tiles in WSIs. The model’s effectiveness was demonstrated in predicting progression-free survival among patients with early-stage lung adenocarcinomas (LUAD). We compared the model with other state-of-the-art methods for tile-level information aggregation in WSIs, including statistics-based, multiple instance learning (MIL)-based, GNN-based, and GNN-transformer-based aggregation. Our model achieved the highest c-index (0.70) and has the largest number of parameters among comparison models yet maintained a short inference time. Additional experiments showed the impact of different types of node features and different tile sampling strategies on model performance. Code: https://github.com/rina-ding/gat-mamba .
format Article
id doaj-art-4a299b9c266b411ab83fe861fb8b87ea
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-4a299b9c266b411ab83fe861fb8b87ea2025-08-20T03:22:12ZengNature PortfolioScientific Reports2045-23222025-05-0115111310.1038/s41598-025-99042-4Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide imagesRuiwen Ding0Kha-Dinh Luong1Erika Rodriguez2Ana Cristina Araujo Lemos da Silva3William Hsu4Medical and Imaging Informatics, Department of Radiological Sciences, Department of Bioengineering, University of CaliforniaDepartment of Computer Science, University of California, Santa BarbaraDepartment of Pathology and Laboratory Sciences, University of CaliforniaDepartment of Pathology, Federal University of UberlandiaMedical and Imaging Informatics, Department of Radiological Sciences, Department of Bioengineering, University of CaliforniaAbstract In computational pathology, extracting and representing spatial features from gigapixel whole slide images (WSIs) are fundamental tasks, but due to their large size, WSIs are typically segmented into smaller tiles. A critical aspect of analyzing WSIs is how information across tiles is aggregated to predict outcomes such as patient prognosis. We introduce a model that combines a message-passing graph neural network (GNN) with a state space model (Mamba) to capture both local and global spatial relationships among the tiles in WSIs. The model’s effectiveness was demonstrated in predicting progression-free survival among patients with early-stage lung adenocarcinomas (LUAD). We compared the model with other state-of-the-art methods for tile-level information aggregation in WSIs, including statistics-based, multiple instance learning (MIL)-based, GNN-based, and GNN-transformer-based aggregation. Our model achieved the highest c-index (0.70) and has the largest number of parameters among comparison models yet maintained a short inference time. Additional experiments showed the impact of different types of node features and different tile sampling strategies on model performance. Code: https://github.com/rina-ding/gat-mamba .https://doi.org/10.1038/s41598-025-99042-4
spellingShingle Ruiwen Ding
Kha-Dinh Luong
Erika Rodriguez
Ana Cristina Araujo Lemos da Silva
William Hsu
Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images
Scientific Reports
title Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images
title_full Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images
title_fullStr Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images
title_full_unstemmed Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images
title_short Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images
title_sort combining graph neural network and mamba to capture local and global tissue spatial relationships in whole slide images
url https://doi.org/10.1038/s41598-025-99042-4
work_keys_str_mv AT ruiwending combininggraphneuralnetworkandmambatocapturelocalandglobaltissuespatialrelationshipsinwholeslideimages
AT khadinhluong combininggraphneuralnetworkandmambatocapturelocalandglobaltissuespatialrelationshipsinwholeslideimages
AT erikarodriguez combininggraphneuralnetworkandmambatocapturelocalandglobaltissuespatialrelationshipsinwholeslideimages
AT anacristinaaraujolemosdasilva combininggraphneuralnetworkandmambatocapturelocalandglobaltissuespatialrelationshipsinwholeslideimages
AT williamhsu combininggraphneuralnetworkandmambatocapturelocalandglobaltissuespatialrelationshipsinwholeslideimages