File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Multi-scope Analysis Driven Hierarchical Graph Transformer for Whole Slide Image Based Cancer Survival Prediction

TitleMulti-scope Analysis Driven Hierarchical Graph Transformer for Whole Slide Image Based Cancer Survival Prediction
Authors
KeywordsContextual interaction
Graph neural network
Survival prediction
Transformer
Whole slide image
Issue Date8-Oct-2023
Abstract

Cancer survival prediction requires considering not only the biological morphology but also the contextual interactions of tumor and surrounding tissues. The major limitation of previous learning frameworks for whole slide image (WSI) based survival prediction is that the contextual interactions of pathological components (e.g., tumor, stroma, lymphocyte, etc.) lack sufficient representation and quantification. In this paper, we proposed a multi-scope analysis driven Hierarchical Graph Transformer (HGT) to overcome this limitation. Specifically, we first utilize a multi-scope analysis strategy, which leverages an in-slide superpixel and a cross-slide clustering, to mine the spatial and semantic priors of WSIs. Furthermore, based on the extracted spatial prior, a hierarchical graph convolutional network is proposed to progressively learn the topological features of the variant microenvironments ranging from patch-level to tissue-level. In addition, guided by the identified semantic prior, tissue-level features are further aggregated to represent the meaningful pathological components, whose contextual interactions are established and quantified by the designed Transformer-based prediction head. We evaluated the proposed framework on our collected Colorectal Cancer (CRC) cohort and two public cancer cohorts from the TCGA project, i.e., Liver Hepatocellular Carcinoma (LIHC) and Kidney Clear Cell Carcinoma (KIRC). Experimental results demonstrate that our proposed method yields superior performance and richer interpretability compared to the state-of-the-art approaches.


Persistent Identifierhttp://hdl.handle.net/10722/339357
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHou, W-
dc.contributor.authorHe, Y-
dc.contributor.authorYao, B-
dc.contributor.authorYu, L-
dc.contributor.authorYu, R-
dc.contributor.authorGao, F-
dc.contributor.authorWang, L -
dc.date.accessioned2024-03-11T10:35:57Z-
dc.date.available2024-03-11T10:35:57Z-
dc.date.issued2023-10-08-
dc.identifier.urihttp://hdl.handle.net/10722/339357-
dc.description.abstract<p>Cancer survival prediction requires considering not only the biological morphology but also the contextual interactions of tumor and surrounding tissues. The major limitation of previous learning frameworks for whole slide image (WSI) based survival prediction is that the contextual interactions of pathological components (<em>e.g.</em>, tumor, stroma, lymphocyte, <em>etc.</em>) lack sufficient representation and quantification. In this paper, we proposed a multi-scope analysis driven Hierarchical Graph Transformer (HGT) to overcome this limitation. Specifically, we first utilize a multi-scope analysis strategy, which leverages an in-slide superpixel and a cross-slide clustering, to mine the spatial and semantic priors of WSIs. Furthermore, based on the extracted spatial prior, a hierarchical graph convolutional network is proposed to progressively learn the topological features of the variant microenvironments ranging from patch-level to tissue-level. In addition, guided by the identified semantic prior, tissue-level features are further aggregated to represent the meaningful pathological components, whose contextual interactions are established and quantified by the designed Transformer-based prediction head. We evaluated the proposed framework on our collected Colorectal Cancer (CRC) cohort and two public cancer cohorts from the TCGA project, <em>i.e.</em>, Liver Hepatocellular Carcinoma (LIHC) and Kidney Clear Cell Carcinoma (KIRC). Experimental results demonstrate that our proposed method yields superior performance and richer interpretability compared to the state-of-the-art approaches.<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.subjectContextual interaction-
dc.subjectGraph neural network-
dc.subjectSurvival prediction-
dc.subjectTransformer-
dc.subjectWhole slide image-
dc.titleMulti-scope Analysis Driven Hierarchical Graph Transformer for Whole Slide Image Based Cancer Survival Prediction-
dc.typeConference_Paper-
dc.identifier.doi10.1007/978-3-031-43987-2_72-
dc.identifier.scopuseid_2-s2.0-85174694835-
dc.identifier.volume14225 LNCS-
dc.identifier.spage745-
dc.identifier.epage754-
dc.identifier.isiWOS:001109635100072-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats