File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis

TitleHIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis
Authors
KeywordsGraph neural network
Hierarchical representation
Interaction
Vision transformer
WSI analysis
Issue Date1-Oct-2023
Abstract

In computation pathology, the pyramid structure of gigapixel Whole Slide Images (WSIs) has recently been studied for capturing various information from individual cell interactions to tissue microenvironments. This hierarchical structure is believed to be beneficial for cancer diagnosis and prognosis tasks. However, most previous hierarchical WSI analysis works (1) only characterize local or global correlations within the WSI pyramids and (2) use only unidirectional interaction between different resolutions, leading to an incomplete picture of WSI pyramids. To this end, this paper presents a novel Hierarchical Interaction Graph-Transformer (i.e., HIGT) for WSI analysis. With Graph Neural Network and Transformer as the building commons, HIGT can learn both short-range local information and long-range global representation of the WSI pyramids. Considering that the information from different resolutions is complementary and can benefit each other during the learning process, we further design a novel Bidirectional Interaction block to establish communication between different levels within the WSI pyramids. Finally, we aggregate both coarse-grained and fine-grained features learned from different levels together for slide-level prediction. We evaluate our methods on two public WSI datasets from TCGA projects, i.e., kidney carcinoma (KICA) and esophageal carcinoma (ESCA). Experimental results show that our HIGT outperforms both hierarchical and non-hierarchical state-of-the-art methods on both tumor subtyping and staging tasks.


Persistent Identifierhttp://hdl.handle.net/10722/340959
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorGuo, Z-
dc.contributor.authorZhao, W-
dc.contributor.authorWang, S-
dc.contributor.authorYu, L-
dc.date.accessioned2024-03-11T10:48:35Z-
dc.date.available2024-03-11T10:48:35Z-
dc.date.issued2023-10-01-
dc.identifier.urihttp://hdl.handle.net/10722/340959-
dc.description.abstract<p>In computation pathology, the pyramid structure of gigapixel Whole Slide Images (WSIs) has recently been studied for capturing various information from individual cell interactions to tissue microenvironments. This hierarchical structure is believed to be beneficial for cancer diagnosis and prognosis tasks. However, most previous hierarchical WSI analysis works (1) only characterize local or global correlations within the WSI pyramids and (2) use only unidirectional interaction between different resolutions, leading to an incomplete picture of WSI pyramids. To this end, this paper presents a novel Hierarchical Interaction Graph-Transformer (<em>i.e.</em>, HIGT) for WSI analysis. With Graph Neural Network and Transformer as the building commons, HIGT can learn both short-range local information and long-range global representation of the WSI pyramids. Considering that the information from different resolutions is complementary and can benefit each other during the learning process, we further design a novel Bidirectional Interaction block to establish communication between different levels within the WSI pyramids. Finally, we aggregate both coarse-grained and fine-grained features learned from different levels together for slide-level prediction. We evaluate our methods on two public WSI datasets from TCGA projects, <em>i.e.</em>, kidney carcinoma (KICA) and esophageal carcinoma (ESCA). Experimental results show that our HIGT outperforms both hierarchical and non-hierarchical state-of-the-art methods on both tumor subtyping and staging tasks.<br></p>-
dc.languageeng-
dc.relation.ispartof26th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2023 (08/10/2023-12/10/2023, Vancouver, Canada)-
dc.subjectGraph neural network-
dc.subjectHierarchical representation-
dc.subjectInteraction-
dc.subjectVision transformer-
dc.subjectWSI analysis-
dc.titleHIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis-
dc.typeConference_Paper-
dc.identifier.doi10.1007/978-3-031-43987-2_73-
dc.identifier.scopuseid_2-s2.0-85174746024-
dc.identifier.volume14225 LNCS-
dc.identifier.spage755-
dc.identifier.epage764-
dc.identifier.isiWOS:001109635100073-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats