No Cover Image

Journal article 373 views 59 downloads

Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images

Sachin S. Bahade, Michael Edwards, Xianghua Xie Orcid Logo

Journal of Image and Graphics, Volume: 11, Issue: 1, Pages: 15 - 20

Swansea University Author: Xianghua Xie Orcid Logo

  • 63059.pdf

    PDF | Version of Record

    This is an open access article distributed under the Creative Commons Attribution License (CC BYNC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is noncommercial and no modifications or adaptations are made.

    Download (2.42MB)

Check full text

DOI (Published version): 10.18178/joig.11.1.15-20

Abstract

Nuclei detection in histopathology images of can-cerous tissue stained with conventional hematoxylin and eosin stain is a challenging task due to the complexity and diversity of cell data. Deep learning techniques have produced encouraging results in the field of nuclei detection, where the main emp...

Full description

Published in: Journal of Image and Graphics
ISSN: 2301-3699
Published: EJournal Publishing 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa63059
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-04-03T12:28:13Z
last_indexed 2023-04-04T03:26:07Z
id cronfa63059
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>63059</id><entry>2023-04-03</entry><title>Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-04-03</date><deptcode>SCS</deptcode><abstract>Nuclei detection in histopathology images of can-cerous tissue stained with conventional hematoxylin and eosin stain is a challenging task due to the complexity and diversity of cell data. Deep learning techniques have produced encouraging results in the field of nuclei detection, where the main emphasis is on classification and regression-based methods. Recent research has demonstrated that regression-based techniques outperform classification. In this paper, we propose a classification model based on graph convolutions to classify nuclei, and similar models to detect nuclei using cascaded architecture. With nearly 29,000 annotated nuclei in a large dataset of cancer histology images, we evaluated the Convolutional Neural Network (CNN) and Graph Convolutional Networks (GCN) based approaches. Our findings demonstrate that graph convolutions perform better with a cascaded GCN architecture and are more stable than centre-of-pixel approach. We have compared our two-fold evaluation quantitative results with CNN-based models such as Spatial Constrained Convolutional Neural Network (SC-CNN) and Centre-of-Pixel Convolutional Neural Network (CP-CNN). We used two different loss functions, binary cross-entropy and focal loss function, and also investigated the behaviour of CP-CNN and GCN models to observe the effectiveness of CNN and GCN operators. The compared quantitative F1 score of cascaded-GCN shows an improvement of 6% compared to state-of-the-art methods.</abstract><type>Journal Article</type><journal>Journal of Image and Graphics</journal><volume>11</volume><journalNumber>1</journalNumber><paginationStart>15</paginationStart><paginationEnd>20</paginationEnd><publisher>EJournal Publishing</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2301-3699</issnPrint><issnElectronic/><keywords/><publishedDay>1</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-03-01</publishedDate><doi>10.18178/joig.11.1.15-20</doi><url>http://dx.doi.org/10.18178/joig.11.1.15-20</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-04-27T12:10:53.5858755</lastEdited><Created>2023-04-03T13:18:21.8227109</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Sachin S.</firstname><surname>Bahade</surname><order>1</order></author><author><firstname>Michael</firstname><surname>Edwards</surname><order>2</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>3</order></author></authors><documents><document><filename>63059__26962__8587d50aed704389bd6788002d575ab7.pdf</filename><originalFilename>63059.pdf</originalFilename><uploaded>2023-04-03T13:26:18.2966625</uploaded><type>Output</type><contentLength>2535348</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>This is an open access article distributed under the Creative Commons Attribution License (CC BYNC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is noncommercial and no modifications or adaptations are made.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 63059 2023-04-03 Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2023-04-03 SCS Nuclei detection in histopathology images of can-cerous tissue stained with conventional hematoxylin and eosin stain is a challenging task due to the complexity and diversity of cell data. Deep learning techniques have produced encouraging results in the field of nuclei detection, where the main emphasis is on classification and regression-based methods. Recent research has demonstrated that regression-based techniques outperform classification. In this paper, we propose a classification model based on graph convolutions to classify nuclei, and similar models to detect nuclei using cascaded architecture. With nearly 29,000 annotated nuclei in a large dataset of cancer histology images, we evaluated the Convolutional Neural Network (CNN) and Graph Convolutional Networks (GCN) based approaches. Our findings demonstrate that graph convolutions perform better with a cascaded GCN architecture and are more stable than centre-of-pixel approach. We have compared our two-fold evaluation quantitative results with CNN-based models such as Spatial Constrained Convolutional Neural Network (SC-CNN) and Centre-of-Pixel Convolutional Neural Network (CP-CNN). We used two different loss functions, binary cross-entropy and focal loss function, and also investigated the behaviour of CP-CNN and GCN models to observe the effectiveness of CNN and GCN operators. The compared quantitative F1 score of cascaded-GCN shows an improvement of 6% compared to state-of-the-art methods. Journal Article Journal of Image and Graphics 11 1 15 20 EJournal Publishing 2301-3699 1 3 2023 2023-03-01 10.18178/joig.11.1.15-20 http://dx.doi.org/10.18178/joig.11.1.15-20 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2023-04-27T12:10:53.5858755 2023-04-03T13:18:21.8227109 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Sachin S. Bahade 1 Michael Edwards 2 Xianghua Xie 0000-0002-2701-8660 3 63059__26962__8587d50aed704389bd6788002d575ab7.pdf 63059.pdf 2023-04-03T13:26:18.2966625 Output 2535348 application/pdf Version of Record true This is an open access article distributed under the Creative Commons Attribution License (CC BYNC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is noncommercial and no modifications or adaptations are made. true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images
spellingShingle Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images
Xianghua Xie
title_short Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images
title_full Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images
title_fullStr Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images
title_full_unstemmed Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images
title_sort Cascaded Graph Convolution Approach for Nuclei Detection in Histopathology Images
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Xianghua Xie
author2 Sachin S. Bahade
Michael Edwards
Xianghua Xie
format Journal article
container_title Journal of Image and Graphics
container_volume 11
container_issue 1
container_start_page 15
publishDate 2023
institution Swansea University
issn 2301-3699
doi_str_mv 10.18178/joig.11.1.15-20
publisher EJournal Publishing
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.18178/joig.11.1.15-20
document_store_str 1
active_str 0
description Nuclei detection in histopathology images of can-cerous tissue stained with conventional hematoxylin and eosin stain is a challenging task due to the complexity and diversity of cell data. Deep learning techniques have produced encouraging results in the field of nuclei detection, where the main emphasis is on classification and regression-based methods. Recent research has demonstrated that regression-based techniques outperform classification. In this paper, we propose a classification model based on graph convolutions to classify nuclei, and similar models to detect nuclei using cascaded architecture. With nearly 29,000 annotated nuclei in a large dataset of cancer histology images, we evaluated the Convolutional Neural Network (CNN) and Graph Convolutional Networks (GCN) based approaches. Our findings demonstrate that graph convolutions perform better with a cascaded GCN architecture and are more stable than centre-of-pixel approach. We have compared our two-fold evaluation quantitative results with CNN-based models such as Spatial Constrained Convolutional Neural Network (SC-CNN) and Centre-of-Pixel Convolutional Neural Network (CP-CNN). We used two different loss functions, binary cross-entropy and focal loss function, and also investigated the behaviour of CP-CNN and GCN models to observe the effectiveness of CNN and GCN operators. The compared quantitative F1 score of cascaded-GCN shows an improvement of 6% compared to state-of-the-art methods.
published_date 2023-03-01T12:10:52Z
_version_ 1764327531250450432
score 11.013082

Similar Items