Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation

Gastric cancer is a malignant tumor with high incidence. Computer-aided screening systems for gastric cancer pathological images can contribute to reducing the workload of specialists and improve the efficiency of disease diagnosis. Due to the high resolution of images, it is common to divide the wh...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu Xiang, Xiaofeng Wu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	gastric pathological images classification graph convolutional networks multiple instance learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/39dee28062f7451aa218de003735fae8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:39dee28062f7451aa218de003735fae8
record_format	dspace
spelling	oai:doaj.org-article:39dee28062f7451aa218de003735fae82021-11-11T15:23:48ZMultiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation10.3390/app1121103682076-3417https://doaj.org/article/39dee28062f7451aa218de003735fae82021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10368https://doaj.org/toc/2076-3417Gastric cancer is a malignant tumor with high incidence. Computer-aided screening systems for gastric cancer pathological images can contribute to reducing the workload of specialists and improve the efficiency of disease diagnosis. Due to the high resolution of images, it is common to divide the whole slide image (WSI) into a set of image patches with overlap before utilizing deep neural networks for further analysis. However, not all patches split from the same cancerous WSI contain information of cancerous issues. This restriction naturally satisfies the assumptions of multiple instance learning (MIL). Moreover, the spatial topological structure relationships between local areas in a WSI are destroyed in the process of patch partitioning. Most existing multiple instance classification (MIC) methods fail to take into account the topological relationships between instances. In this paper, we propose a novel multiple instance classification framework based on graph convolutional networks (GCNs) for gastric microscope image classification. Firstly, patch embeddings were generated by feature extraction. Then, a graph structure was introduced to model the spatial topological structure relationships between instances. Additionally, a graph classification model with hierarchical pooling was constructed to achieve this multiple instance classification task. To certify the effectiveness and generalization of our method, we conducted comparative experiments on two different modes of gastric cancer pathological image datasets. The proposed method achieved average fivefold cross-validation precisions of 91.16% and 98.26% for gastric cancer classification on the two datasets, respectively.Xu XiangXiaofeng WuMDPI AGarticlegastric pathological images classificationgraph convolutional networksmultiple instance learningTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10368, p 10368 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	gastric pathological images classification graph convolutional networks multiple instance learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	gastric pathological images classification graph convolutional networks multiple instance learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Xu Xiang Xiaofeng Wu Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation
description	Gastric cancer is a malignant tumor with high incidence. Computer-aided screening systems for gastric cancer pathological images can contribute to reducing the workload of specialists and improve the efficiency of disease diagnosis. Due to the high resolution of images, it is common to divide the whole slide image (WSI) into a set of image patches with overlap before utilizing deep neural networks for further analysis. However, not all patches split from the same cancerous WSI contain information of cancerous issues. This restriction naturally satisfies the assumptions of multiple instance learning (MIL). Moreover, the spatial topological structure relationships between local areas in a WSI are destroyed in the process of patch partitioning. Most existing multiple instance classification (MIC) methods fail to take into account the topological relationships between instances. In this paper, we propose a novel multiple instance classification framework based on graph convolutional networks (GCNs) for gastric microscope image classification. Firstly, patch embeddings were generated by feature extraction. Then, a graph structure was introduced to model the spatial topological structure relationships between instances. Additionally, a graph classification model with hierarchical pooling was constructed to achieve this multiple instance classification task. To certify the effectiveness and generalization of our method, we conducted comparative experiments on two different modes of gastric cancer pathological image datasets. The proposed method achieved average fivefold cross-validation precisions of 91.16% and 98.26% for gastric cancer classification on the two datasets, respectively.
format	article
author	Xu Xiang Xiaofeng Wu
author_facet	Xu Xiang Xiaofeng Wu
author_sort	Xu Xiang
title	Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation
title_short	Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation
title_full	Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation
title_fullStr	Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation
title_full_unstemmed	Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation
title_sort	multiple instance classification for gastric cancer pathological images based on implicit spatial topological structure representation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/39dee28062f7451aa218de003735fae8
work_keys_str_mv	AT xuxiang multipleinstanceclassificationforgastriccancerpathologicalimagesbasedonimplicitspatialtopologicalstructurerepresentation AT xiaofengwu multipleinstanceclassificationforgastriccancerpathologicalimagesbasedonimplicitspatialtopologicalstructurerepresentation
_version_	1718435359842369536

Multiple Instance Classification for Gastric Cancer Pathological Images Based on Implicit Spatial Topological Structure Representation

Ejemplares similares