Loading…
VGGIN-Net: Deep Transfer Network for Imbalanced Breast Cancer Dataset
In this paper, we have presented a novel deep neural network architecture involving transfer learning approach, formed by freezing and concatenating all the layers till block4 pool layer of VGG16 pre-trained model (at the lower level) with the layers of a randomly initialized naïve Inception block m...
Saved in:
Published in: | IEEE/ACM transactions on computational biology and bioinformatics 2023-01, Vol.20 (1), p.752-762 |
---|---|
Main Authors: | , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c349t-272853caac0b0015cb4c79478e8b2f45539037a18772f8c75938b2dadf18ecc23 |
---|---|
cites | cdi_FETCH-LOGICAL-c349t-272853caac0b0015cb4c79478e8b2f45539037a18772f8c75938b2dadf18ecc23 |
container_end_page | 762 |
container_issue | 1 |
container_start_page | 752 |
container_title | IEEE/ACM transactions on computational biology and bioinformatics |
container_volume | 20 |
creator | Saini, Manisha Susan, Seba |
description | In this paper, we have presented a novel deep neural network architecture involving transfer learning approach, formed by freezing and concatenating all the layers till block4 pool layer of VGG16 pre-trained model (at the lower level) with the layers of a randomly initialized naïve Inception block module (at the higher level). Further, we have added the batch normalization, flatten, dropout and dense layers in the proposed architecture. Our transfer network, called VGGIN-Net, facilitates the transfer of domain knowledge from the larger ImageNet object dataset to the smaller imbalanced breast cancer dataset. To improve the performance of the proposed model, regularization was used in the form of dropout and data augmentation. A detailed block-wise fine tuning has been conducted on the proposed deep transfer network for images of different magnification factors. The results of extensive experiments indicate a significant improvement of classification performance after the application of fine-tuning. The proposed deep learning architecture with transfer learning and fine-tuning yields the highest accuracies in comparison to other state-of-the-art approaches for the classification of BreakHis breast cancer dataset. The articulated architecture is designed in a way that it can be effectively transfer learned on other breast cancer datasets. |
doi_str_mv | 10.1109/TCBB.2022.3163277 |
format | article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_proquest_miscellaneous_2645470814</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9744541</ieee_id><sourcerecordid>2773453419</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-272853caac0b0015cb4c79478e8b2f45539037a18772f8c75938b2dadf18ecc23</originalsourceid><addsrcrecordid>eNpdkE1PAjEQhhujEUR_gDExTbx4WezndutNFkQSghf02nS7swkILLa7Mf57uwE9eOrHPDPz5kHompIhpUQ_LPPRaMgIY0NOU86UOkF9KqVKtE7FaXcXMpE65T10EcKaECY0EeeoxyUXWgjdR5P36XS2SBbQPOIxwB4vvd2FCjyOX1-1_8BV7fFsW9iN3Tko8ciDDQ3Ou5fHY9vYAM0lOqvsJsDV8Rygt-fJMn9J5q_TWf40T1zc1yRMsUxyZ60jBSFUukI4pYXKICtYJaTkmnBlaaYUqzKnpOaxUNqyohk4x_gA3R_m7n392UJozHYVHGxiNqjbYFgqpFAkoyKid__Qdd36XUxnoiguogGqI0UPlPN1CB4qs_errfXfhhLTOTadY9M5NkfHsef2OLkttlD-dfxKjcDNAVgBwF9ZKxHDUf4DjM18sQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2773453419</pqid></control><display><type>article</type><title>VGGIN-Net: Deep Transfer Network for Imbalanced Breast Cancer Dataset</title><source>IEEE Electronic Library (IEL) Journals</source><source>Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list)</source><creator>Saini, Manisha ; Susan, Seba</creator><creatorcontrib>Saini, Manisha ; Susan, Seba</creatorcontrib><description>In this paper, we have presented a novel deep neural network architecture involving transfer learning approach, formed by freezing and concatenating all the layers till block4 pool layer of VGG16 pre-trained model (at the lower level) with the layers of a randomly initialized naïve Inception block module (at the higher level). Further, we have added the batch normalization, flatten, dropout and dense layers in the proposed architecture. Our transfer network, called VGGIN-Net, facilitates the transfer of domain knowledge from the larger ImageNet object dataset to the smaller imbalanced breast cancer dataset. To improve the performance of the proposed model, regularization was used in the form of dropout and data augmentation. A detailed block-wise fine tuning has been conducted on the proposed deep transfer network for images of different magnification factors. The results of extensive experiments indicate a significant improvement of classification performance after the application of fine-tuning. The proposed deep learning architecture with transfer learning and fine-tuning yields the highest accuracies in comparison to other state-of-the-art approaches for the classification of BreakHis breast cancer dataset. The articulated architecture is designed in a way that it can be effectively transfer learned on other breast cancer datasets.</description><identifier>ISSN: 1545-5963</identifier><identifier>EISSN: 1557-9964</identifier><identifier>DOI: 10.1109/TCBB.2022.3163277</identifier><identifier>PMID: 35349449</identifier><identifier>CODEN: ITCBCY</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Artificial neural networks ; Breast cancer ; Breast Neoplasms - diagnostic imaging ; Classification ; Computer architecture ; convolutional neural networks ; Datasets ; Deep learning ; Feature extraction ; Female ; fine tuning ; Freezing ; Humans ; Inception module ; Knowledge management ; Machine learning ; Neural networks ; Neural Networks, Computer ; Performance enhancement ; pre-trained model ; Regularization ; Task analysis ; Transfer learning ; VGG16</subject><ispartof>IEEE/ACM transactions on computational biology and bioinformatics, 2023-01, Vol.20 (1), p.752-762</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-272853caac0b0015cb4c79478e8b2f45539037a18772f8c75938b2dadf18ecc23</citedby><cites>FETCH-LOGICAL-c349t-272853caac0b0015cb4c79478e8b2f45539037a18772f8c75938b2dadf18ecc23</cites><orcidid>0000-0002-6709-6591 ; 0000-0003-4807-6787</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9744541$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,786,790,27957,27958,55147</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/35349449$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Saini, Manisha</creatorcontrib><creatorcontrib>Susan, Seba</creatorcontrib><title>VGGIN-Net: Deep Transfer Network for Imbalanced Breast Cancer Dataset</title><title>IEEE/ACM transactions on computational biology and bioinformatics</title><addtitle>TCBB</addtitle><addtitle>IEEE/ACM Trans Comput Biol Bioinform</addtitle><description>In this paper, we have presented a novel deep neural network architecture involving transfer learning approach, formed by freezing and concatenating all the layers till block4 pool layer of VGG16 pre-trained model (at the lower level) with the layers of a randomly initialized naïve Inception block module (at the higher level). Further, we have added the batch normalization, flatten, dropout and dense layers in the proposed architecture. Our transfer network, called VGGIN-Net, facilitates the transfer of domain knowledge from the larger ImageNet object dataset to the smaller imbalanced breast cancer dataset. To improve the performance of the proposed model, regularization was used in the form of dropout and data augmentation. A detailed block-wise fine tuning has been conducted on the proposed deep transfer network for images of different magnification factors. The results of extensive experiments indicate a significant improvement of classification performance after the application of fine-tuning. The proposed deep learning architecture with transfer learning and fine-tuning yields the highest accuracies in comparison to other state-of-the-art approaches for the classification of BreakHis breast cancer dataset. The articulated architecture is designed in a way that it can be effectively transfer learned on other breast cancer datasets.</description><subject>Artificial neural networks</subject><subject>Breast cancer</subject><subject>Breast Neoplasms - diagnostic imaging</subject><subject>Classification</subject><subject>Computer architecture</subject><subject>convolutional neural networks</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Feature extraction</subject><subject>Female</subject><subject>fine tuning</subject><subject>Freezing</subject><subject>Humans</subject><subject>Inception module</subject><subject>Knowledge management</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Performance enhancement</subject><subject>pre-trained model</subject><subject>Regularization</subject><subject>Task analysis</subject><subject>Transfer learning</subject><subject>VGG16</subject><issn>1545-5963</issn><issn>1557-9964</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNpdkE1PAjEQhhujEUR_gDExTbx4WezndutNFkQSghf02nS7swkILLa7Mf57uwE9eOrHPDPz5kHompIhpUQ_LPPRaMgIY0NOU86UOkF9KqVKtE7FaXcXMpE65T10EcKaECY0EeeoxyUXWgjdR5P36XS2SBbQPOIxwB4vvd2FCjyOX1-1_8BV7fFsW9iN3Tko8ciDDQ3Ou5fHY9vYAM0lOqvsJsDV8Rygt-fJMn9J5q_TWf40T1zc1yRMsUxyZ60jBSFUukI4pYXKICtYJaTkmnBlaaYUqzKnpOaxUNqyohk4x_gA3R_m7n392UJozHYVHGxiNqjbYFgqpFAkoyKid__Qdd36XUxnoiguogGqI0UPlPN1CB4qs_errfXfhhLTOTadY9M5NkfHsef2OLkttlD-dfxKjcDNAVgBwF9ZKxHDUf4DjM18sQ</recordid><startdate>202301</startdate><enddate>202301</enddate><creator>Saini, Manisha</creator><creator>Susan, Seba</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QQ</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-6709-6591</orcidid><orcidid>https://orcid.org/0000-0003-4807-6787</orcidid></search><sort><creationdate>202301</creationdate><title>VGGIN-Net: Deep Transfer Network for Imbalanced Breast Cancer Dataset</title><author>Saini, Manisha ; Susan, Seba</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-272853caac0b0015cb4c79478e8b2f45539037a18772f8c75938b2dadf18ecc23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Breast cancer</topic><topic>Breast Neoplasms - diagnostic imaging</topic><topic>Classification</topic><topic>Computer architecture</topic><topic>convolutional neural networks</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Feature extraction</topic><topic>Female</topic><topic>fine tuning</topic><topic>Freezing</topic><topic>Humans</topic><topic>Inception module</topic><topic>Knowledge management</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Performance enhancement</topic><topic>pre-trained model</topic><topic>Regularization</topic><topic>Task analysis</topic><topic>Transfer learning</topic><topic>VGG16</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Saini, Manisha</creatorcontrib><creatorcontrib>Susan, Seba</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEEE Xplore</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE/ACM transactions on computational biology and bioinformatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Saini, Manisha</au><au>Susan, Seba</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>VGGIN-Net: Deep Transfer Network for Imbalanced Breast Cancer Dataset</atitle><jtitle>IEEE/ACM transactions on computational biology and bioinformatics</jtitle><stitle>TCBB</stitle><addtitle>IEEE/ACM Trans Comput Biol Bioinform</addtitle><date>2023-01</date><risdate>2023</risdate><volume>20</volume><issue>1</issue><spage>752</spage><epage>762</epage><pages>752-762</pages><issn>1545-5963</issn><eissn>1557-9964</eissn><coden>ITCBCY</coden><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>In this paper, we have presented a novel deep neural network architecture involving transfer learning approach, formed by freezing and concatenating all the layers till block4 pool layer of VGG16 pre-trained model (at the lower level) with the layers of a randomly initialized naïve Inception block module (at the higher level). Further, we have added the batch normalization, flatten, dropout and dense layers in the proposed architecture. Our transfer network, called VGGIN-Net, facilitates the transfer of domain knowledge from the larger ImageNet object dataset to the smaller imbalanced breast cancer dataset. To improve the performance of the proposed model, regularization was used in the form of dropout and data augmentation. A detailed block-wise fine tuning has been conducted on the proposed deep transfer network for images of different magnification factors. The results of extensive experiments indicate a significant improvement of classification performance after the application of fine-tuning. The proposed deep learning architecture with transfer learning and fine-tuning yields the highest accuracies in comparison to other state-of-the-art approaches for the classification of BreakHis breast cancer dataset. The articulated architecture is designed in a way that it can be effectively transfer learned on other breast cancer datasets.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>35349449</pmid><doi>10.1109/TCBB.2022.3163277</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-6709-6591</orcidid><orcidid>https://orcid.org/0000-0003-4807-6787</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1545-5963 |
ispartof | IEEE/ACM transactions on computational biology and bioinformatics, 2023-01, Vol.20 (1), p.752-762 |
issn | 1545-5963 1557-9964 |
language | eng |
recordid | cdi_proquest_miscellaneous_2645470814 |
source | IEEE Electronic Library (IEL) Journals; Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list) |
subjects | Artificial neural networks Breast cancer Breast Neoplasms - diagnostic imaging Classification Computer architecture convolutional neural networks Datasets Deep learning Feature extraction Female fine tuning Freezing Humans Inception module Knowledge management Machine learning Neural networks Neural Networks, Computer Performance enhancement pre-trained model Regularization Task analysis Transfer learning VGG16 |
title | VGGIN-Net: Deep Transfer Network for Imbalanced Breast Cancer Dataset |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T08%3A46%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=VGGIN-Net:%20Deep%20Transfer%20Network%20for%20Imbalanced%20Breast%20Cancer%20Dataset&rft.jtitle=IEEE/ACM%20transactions%20on%20computational%20biology%20and%20bioinformatics&rft.au=Saini,%20Manisha&rft.date=2023-01&rft.volume=20&rft.issue=1&rft.spage=752&rft.epage=762&rft.pages=752-762&rft.issn=1545-5963&rft.eissn=1557-9964&rft.coden=ITCBCY&rft_id=info:doi/10.1109/TCBB.2022.3163277&rft_dat=%3Cproquest_pubme%3E2773453419%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c349t-272853caac0b0015cb4c79478e8b2f45539037a18772f8c75938b2dadf18ecc23%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2773453419&rft_id=info:pmid/35349449&rft_ieee_id=9744541&rfr_iscdi=true |