SLIDE-Net: A Sequential Modeling Approach With Adaptive Fuzzy C-Mean Empowered Data Balancing Policy for IDC Detection
Breast cancer is a significant global health concern, with invasive ductal carcinoma (IDC) being a significant subtype. Detecting IDC is a challenging task that can be hindered by the oversight of important contextual cues within whole slide images (WSIs). To address this issue, we present the Seque...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on fuzzy systems 2024-10, Vol.32 (10), p.5557-5570 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 5570 |
---|---|
container_issue | 10 |
container_start_page | 5557 |
container_title | IEEE transactions on fuzzy systems |
container_volume | 32 |
creator | Kumar, Abhinav Tiwari, Harshit Singh, Rishav Singh, Amit Kumar Singh, Sanjay Kumar |
description | Breast cancer is a significant global health concern, with invasive ductal carcinoma (IDC) being a significant subtype. Detecting IDC is a challenging task that can be hindered by the oversight of important contextual cues within whole slide images (WSIs). To address this issue, we present the Sequential-LSTM Invasive Ductal Carcinoma Detection with EfficientNet (SLIDE-Net) framework. SLIDE-Net synchronizes tissue image patch locations within WSIs, allowing for comprehensive and subtle identification of IDC. The inherent issue of data imbalance in IDC datasets, particularly the variable density of positive IDC patches concerning WSI size, is effectively tackled through the introduction of adaptive fuzzy C-Mean as a data balancing policy. This novel approach enhances model efficacy and robustness, resulting in superior performance across key metrics, such as accuracy (86%), balanced accuracy (BAC) (86%), sensitivity (87%), specificity (86%), and GMean (86%). Our findings were substantiated by a comprehensive analysis revealing the significant cross-patch dependencies observed among patches of similar classes. When tested on the balanced PatchCAM dataset, SLIDE-Net once again showcased superiority with accuracy (89%), BAC (89%), F1-Score (87%), sensitivity (87%), and specificity (90%). This underscores the efficient utilization of shared contextual information within WSIs. These results firmly establish SLIDE-Net as a robust and reliable solution for accurate IDC detection. Our work not only advances the precision of IDC detection, but also contributes valuable insights into the intricate dynamics of histopathology image analysis, paving the way for enhanced diagnostic accuracy in the ongoing battle against breast cancer. |
doi_str_mv | 10.1109/TFUZZ.2024.3373534 |
format | Article |
fullrecord | <record><control><sourceid>crossref_RIE</sourceid><recordid>TN_cdi_ieee_primary_10460142</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10460142</ieee_id><sourcerecordid>10_1109_TFUZZ_2024_3373534</sourcerecordid><originalsourceid>FETCH-LOGICAL-c219t-f03b1233e5533e0ddfc882485d94b63641201c539f319671a8becd34b2c1c3173</originalsourceid><addsrcrecordid>eNpN0M1OwkAQwPGN0UREX8B42Bco7uxuv7zVAkoCagLEhEuz3U5lTWlru2Dg6S3iwcvMXP5z-BFyC2wAwML7xXi5Wg0443IghC9cIc9ID0IJDmNCnnc384Tj-cy7JFdt-8kYSBeCHtnNp5PhyHlB-0AjOsevLZbWqILOqgwLU37QqK6bSuk1fTd2TaNM1dbskI63h8Oexs4MVUlHm7r6xgYzOlRW0UdVqFIf47eqMHpP86qhk2FMh2hRW1OV1-QiV0WLN3-7T5bj0SJ-dqavT5M4mjqaQ2idnIkUuBDout1gWZbrIOAycLNQpp7wJHAG2hVhLiD0fFBBijoTMuUatABf9Ak__dVN1bYN5kndmI1q9gmw5CiX_MolR7nkT66L7k6RQcR_gfQ6NS5-AC7oaW4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>SLIDE-Net: A Sequential Modeling Approach With Adaptive Fuzzy C-Mean Empowered Data Balancing Policy for IDC Detection</title><source>IEEE Electronic Library (IEL)</source><creator>Kumar, Abhinav ; Tiwari, Harshit ; Singh, Rishav ; Singh, Amit Kumar ; Singh, Sanjay Kumar</creator><creatorcontrib>Kumar, Abhinav ; Tiwari, Harshit ; Singh, Rishav ; Singh, Amit Kumar ; Singh, Sanjay Kumar</creatorcontrib><description>Breast cancer is a significant global health concern, with invasive ductal carcinoma (IDC) being a significant subtype. Detecting IDC is a challenging task that can be hindered by the oversight of important contextual cues within whole slide images (WSIs). To address this issue, we present the Sequential-LSTM Invasive Ductal Carcinoma Detection with EfficientNet (SLIDE-Net) framework. SLIDE-Net synchronizes tissue image patch locations within WSIs, allowing for comprehensive and subtle identification of IDC. The inherent issue of data imbalance in IDC datasets, particularly the variable density of positive IDC patches concerning WSI size, is effectively tackled through the introduction of adaptive fuzzy C-Mean as a data balancing policy. This novel approach enhances model efficacy and robustness, resulting in superior performance across key metrics, such as accuracy (86%), balanced accuracy (BAC) (86%), sensitivity (87%), specificity (86%), and GMean (86%). Our findings were substantiated by a comprehensive analysis revealing the significant cross-patch dependencies observed among patches of similar classes. When tested on the balanced PatchCAM dataset, SLIDE-Net once again showcased superiority with accuracy (89%), BAC (89%), F1-Score (87%), sensitivity (87%), and specificity (90%). This underscores the efficient utilization of shared contextual information within WSIs. These results firmly establish SLIDE-Net as a robust and reliable solution for accurate IDC detection. Our work not only advances the precision of IDC detection, but also contributes valuable insights into the intricate dynamics of histopathology image analysis, paving the way for enhanced diagnostic accuracy in the ongoing battle against breast cancer.</description><identifier>ISSN: 1063-6706</identifier><identifier>EISSN: 1941-0034</identifier><identifier>DOI: 10.1109/TFUZZ.2024.3373534</identifier><identifier>CODEN: IEFSEV</identifier><language>eng</language><publisher>IEEE</publisher><subject>Adaptation models ; Adaptive fuzzy c-Mean ; Breast cancer ; Classification algorithms ; data balancing policy ; Deep learning ; Long short term memory ; Sensitivity ; sequential-modeling ; Solid modeling ; whole slide image (WSI)</subject><ispartof>IEEE transactions on fuzzy systems, 2024-10, Vol.32 (10), p.5557-5570</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c219t-f03b1233e5533e0ddfc882485d94b63641201c539f319671a8becd34b2c1c3173</cites><orcidid>0000-0003-2947-9046 ; 0000-0001-7359-2068 ; 0000-0001-9741-4020 ; 0009-0000-3860-2558 ; 0000-0002-9061-6313</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10460142$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10460142$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kumar, Abhinav</creatorcontrib><creatorcontrib>Tiwari, Harshit</creatorcontrib><creatorcontrib>Singh, Rishav</creatorcontrib><creatorcontrib>Singh, Amit Kumar</creatorcontrib><creatorcontrib>Singh, Sanjay Kumar</creatorcontrib><title>SLIDE-Net: A Sequential Modeling Approach With Adaptive Fuzzy C-Mean Empowered Data Balancing Policy for IDC Detection</title><title>IEEE transactions on fuzzy systems</title><addtitle>TFUZZ</addtitle><description>Breast cancer is a significant global health concern, with invasive ductal carcinoma (IDC) being a significant subtype. Detecting IDC is a challenging task that can be hindered by the oversight of important contextual cues within whole slide images (WSIs). To address this issue, we present the Sequential-LSTM Invasive Ductal Carcinoma Detection with EfficientNet (SLIDE-Net) framework. SLIDE-Net synchronizes tissue image patch locations within WSIs, allowing for comprehensive and subtle identification of IDC. The inherent issue of data imbalance in IDC datasets, particularly the variable density of positive IDC patches concerning WSI size, is effectively tackled through the introduction of adaptive fuzzy C-Mean as a data balancing policy. This novel approach enhances model efficacy and robustness, resulting in superior performance across key metrics, such as accuracy (86%), balanced accuracy (BAC) (86%), sensitivity (87%), specificity (86%), and GMean (86%). Our findings were substantiated by a comprehensive analysis revealing the significant cross-patch dependencies observed among patches of similar classes. When tested on the balanced PatchCAM dataset, SLIDE-Net once again showcased superiority with accuracy (89%), BAC (89%), F1-Score (87%), sensitivity (87%), and specificity (90%). This underscores the efficient utilization of shared contextual information within WSIs. These results firmly establish SLIDE-Net as a robust and reliable solution for accurate IDC detection. Our work not only advances the precision of IDC detection, but also contributes valuable insights into the intricate dynamics of histopathology image analysis, paving the way for enhanced diagnostic accuracy in the ongoing battle against breast cancer.</description><subject>Adaptation models</subject><subject>Adaptive fuzzy c-Mean</subject><subject>Breast cancer</subject><subject>Classification algorithms</subject><subject>data balancing policy</subject><subject>Deep learning</subject><subject>Long short term memory</subject><subject>Sensitivity</subject><subject>sequential-modeling</subject><subject>Solid modeling</subject><subject>whole slide image (WSI)</subject><issn>1063-6706</issn><issn>1941-0034</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpN0M1OwkAQwPGN0UREX8B42Bco7uxuv7zVAkoCagLEhEuz3U5lTWlru2Dg6S3iwcvMXP5z-BFyC2wAwML7xXi5Wg0443IghC9cIc9ID0IJDmNCnnc384Tj-cy7JFdt-8kYSBeCHtnNp5PhyHlB-0AjOsevLZbWqILOqgwLU37QqK6bSuk1fTd2TaNM1dbskI63h8Oexs4MVUlHm7r6xgYzOlRW0UdVqFIf47eqMHpP86qhk2FMh2hRW1OV1-QiV0WLN3-7T5bj0SJ-dqavT5M4mjqaQ2idnIkUuBDout1gWZbrIOAycLNQpp7wJHAG2hVhLiD0fFBBijoTMuUatABf9Ak__dVN1bYN5kndmI1q9gmw5CiX_MolR7nkT66L7k6RQcR_gfQ6NS5-AC7oaW4</recordid><startdate>20241001</startdate><enddate>20241001</enddate><creator>Kumar, Abhinav</creator><creator>Tiwari, Harshit</creator><creator>Singh, Rishav</creator><creator>Singh, Amit Kumar</creator><creator>Singh, Sanjay Kumar</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-2947-9046</orcidid><orcidid>https://orcid.org/0000-0001-7359-2068</orcidid><orcidid>https://orcid.org/0000-0001-9741-4020</orcidid><orcidid>https://orcid.org/0009-0000-3860-2558</orcidid><orcidid>https://orcid.org/0000-0002-9061-6313</orcidid></search><sort><creationdate>20241001</creationdate><title>SLIDE-Net: A Sequential Modeling Approach With Adaptive Fuzzy C-Mean Empowered Data Balancing Policy for IDC Detection</title><author>Kumar, Abhinav ; Tiwari, Harshit ; Singh, Rishav ; Singh, Amit Kumar ; Singh, Sanjay Kumar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c219t-f03b1233e5533e0ddfc882485d94b63641201c539f319671a8becd34b2c1c3173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adaptation models</topic><topic>Adaptive fuzzy c-Mean</topic><topic>Breast cancer</topic><topic>Classification algorithms</topic><topic>data balancing policy</topic><topic>Deep learning</topic><topic>Long short term memory</topic><topic>Sensitivity</topic><topic>sequential-modeling</topic><topic>Solid modeling</topic><topic>whole slide image (WSI)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kumar, Abhinav</creatorcontrib><creatorcontrib>Tiwari, Harshit</creatorcontrib><creatorcontrib>Singh, Rishav</creatorcontrib><creatorcontrib>Singh, Amit Kumar</creatorcontrib><creatorcontrib>Singh, Sanjay Kumar</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><jtitle>IEEE transactions on fuzzy systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kumar, Abhinav</au><au>Tiwari, Harshit</au><au>Singh, Rishav</au><au>Singh, Amit Kumar</au><au>Singh, Sanjay Kumar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SLIDE-Net: A Sequential Modeling Approach With Adaptive Fuzzy C-Mean Empowered Data Balancing Policy for IDC Detection</atitle><jtitle>IEEE transactions on fuzzy systems</jtitle><stitle>TFUZZ</stitle><date>2024-10-01</date><risdate>2024</risdate><volume>32</volume><issue>10</issue><spage>5557</spage><epage>5570</epage><pages>5557-5570</pages><issn>1063-6706</issn><eissn>1941-0034</eissn><coden>IEFSEV</coden><abstract>Breast cancer is a significant global health concern, with invasive ductal carcinoma (IDC) being a significant subtype. Detecting IDC is a challenging task that can be hindered by the oversight of important contextual cues within whole slide images (WSIs). To address this issue, we present the Sequential-LSTM Invasive Ductal Carcinoma Detection with EfficientNet (SLIDE-Net) framework. SLIDE-Net synchronizes tissue image patch locations within WSIs, allowing for comprehensive and subtle identification of IDC. The inherent issue of data imbalance in IDC datasets, particularly the variable density of positive IDC patches concerning WSI size, is effectively tackled through the introduction of adaptive fuzzy C-Mean as a data balancing policy. This novel approach enhances model efficacy and robustness, resulting in superior performance across key metrics, such as accuracy (86%), balanced accuracy (BAC) (86%), sensitivity (87%), specificity (86%), and GMean (86%). Our findings were substantiated by a comprehensive analysis revealing the significant cross-patch dependencies observed among patches of similar classes. When tested on the balanced PatchCAM dataset, SLIDE-Net once again showcased superiority with accuracy (89%), BAC (89%), F1-Score (87%), sensitivity (87%), and specificity (90%). This underscores the efficient utilization of shared contextual information within WSIs. These results firmly establish SLIDE-Net as a robust and reliable solution for accurate IDC detection. Our work not only advances the precision of IDC detection, but also contributes valuable insights into the intricate dynamics of histopathology image analysis, paving the way for enhanced diagnostic accuracy in the ongoing battle against breast cancer.</abstract><pub>IEEE</pub><doi>10.1109/TFUZZ.2024.3373534</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0003-2947-9046</orcidid><orcidid>https://orcid.org/0000-0001-7359-2068</orcidid><orcidid>https://orcid.org/0000-0001-9741-4020</orcidid><orcidid>https://orcid.org/0009-0000-3860-2558</orcidid><orcidid>https://orcid.org/0000-0002-9061-6313</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1063-6706 |
ispartof | IEEE transactions on fuzzy systems, 2024-10, Vol.32 (10), p.5557-5570 |
issn | 1063-6706 1941-0034 |
language | eng |
recordid | cdi_ieee_primary_10460142 |
source | IEEE Electronic Library (IEL) |
subjects | Adaptation models Adaptive fuzzy c-Mean Breast cancer Classification algorithms data balancing policy Deep learning Long short term memory Sensitivity sequential-modeling Solid modeling whole slide image (WSI) |
title | SLIDE-Net: A Sequential Modeling Approach With Adaptive Fuzzy C-Mean Empowered Data Balancing Policy for IDC Detection |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T16%3A14%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SLIDE-Net:%20A%20Sequential%20Modeling%20Approach%20With%20Adaptive%20Fuzzy%20C-Mean%20Empowered%20Data%20Balancing%20Policy%20for%20IDC%20Detection&rft.jtitle=IEEE%20transactions%20on%20fuzzy%20systems&rft.au=Kumar,%20Abhinav&rft.date=2024-10-01&rft.volume=32&rft.issue=10&rft.spage=5557&rft.epage=5570&rft.pages=5557-5570&rft.issn=1063-6706&rft.eissn=1941-0034&rft.coden=IEFSEV&rft_id=info:doi/10.1109/TFUZZ.2024.3373534&rft_dat=%3Ccrossref_RIE%3E10_1109_TFUZZ_2024_3373534%3C/crossref_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10460142&rfr_iscdi=true |