Transfer learning networks with skip connections for classification of brain tumors
This article presents a transfer learning model via convolutional neural networks (CNNs) with skip connection topology, to avoid the vanishing gradient and time complexity, which are usually common in transfer learning networks. Three pretrained CNN architectures, namely AlexNet, VGG16 and GoogLeNet...
Gespeichert in:
| Veröffentlicht in: | International journal of imaging systems and technology 2021-09, Vol.31 (3), p.1564-1582 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1582 |
|---|---|
| container_issue | 3 |
| container_start_page | 1564 |
| container_title | International journal of imaging systems and technology |
| container_volume | 31 |
| creator | Alaraimi, Saleh Okedu, Kenneth E. Tianfield, Hugo Holden, Richard Uthmani, Omair |
| description | This article presents a transfer learning model via convolutional neural networks (CNNs) with skip connection topology, to avoid the vanishing gradient and time complexity, which are usually common in transfer learning networks. Three pretrained CNN architectures, namely AlexNet, VGG16 and GoogLeNet are employed to equip with skip connections. The transfer learning is implemented through fine‐tuning and freezing the CNN architectures with skip connections based on magnetic resonance imaging (MRI) slices of brain tumor dataset. Furthermore, in the preprocessing, a frequency‐domain information enhancement technique is employed for better image clarity. Performance evaluation is conducted on the transfer learning networks with skip connections to obtain improved accuracy in brain MRI classifications. |
| doi_str_mv | 10.1002/ima.22546 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2558034318</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2558034318</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3326-2222ca5539f6feb01af1874fc931d550acdd3e00698a58210494e3492dbac51e3</originalsourceid><addsrcrecordid>eNp1kE1PAjEQQBujiYge_AdNPHlYmH4t2yMhiiQYD-K5Kd1WC0uL7RLCv3dxvTqHmczkzUzyELonMCIAdOx3ekSp4OUFGhCQVXFOl2gAlZSF5GJyjW5y3gAQIkAM0Psq6ZCdTbixOgUfPnGw7TGmbcZH337hvPV7bGII1rQ-hoxdTNg0OmfvvNHnGY4Or5P2AbeHXUz5Fl053WR791eH6OP5aTV7KZZv88VsuiwMY7QsaBdGC8GkK51dA9GOVBPujGSkFgK0qWtmAUpZaVFRAlxyy7ik9VobQSwboof-7j7F74PNrdrEQwrdS0WFqIBxRqqOeuwpk2LOyTq1T52ldFIE1NmZ6jr166xjxz179I09_Q-qxeu03_gBpihuBQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2558034318</pqid></control><display><type>article</type><title>Transfer learning networks with skip connections for classification of brain tumors</title><source>Wiley Online Library All Journals</source><creator>Alaraimi, Saleh ; Okedu, Kenneth E. ; Tianfield, Hugo ; Holden, Richard ; Uthmani, Omair</creator><creatorcontrib>Alaraimi, Saleh ; Okedu, Kenneth E. ; Tianfield, Hugo ; Holden, Richard ; Uthmani, Omair</creatorcontrib><description>This article presents a transfer learning model via convolutional neural networks (CNNs) with skip connection topology, to avoid the vanishing gradient and time complexity, which are usually common in transfer learning networks. Three pretrained CNN architectures, namely AlexNet, VGG16 and GoogLeNet are employed to equip with skip connections. The transfer learning is implemented through fine‐tuning and freezing the CNN architectures with skip connections based on magnetic resonance imaging (MRI) slices of brain tumor dataset. Furthermore, in the preprocessing, a frequency‐domain information enhancement technique is employed for better image clarity. Performance evaluation is conducted on the transfer learning networks with skip connections to obtain improved accuracy in brain MRI classifications.</description><identifier>ISSN: 0899-9457</identifier><identifier>EISSN: 1098-1098</identifier><identifier>DOI: 10.1002/ima.22546</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley & Sons, Inc</publisher><subject>AlexNet ; Artificial neural networks ; Brain ; convolutional neural network (CNN) ; deep learning ; Freezing ; GoogLeNet ; Image enhancement ; Learning ; Magnetic resonance imaging ; Performance evaluation ; Topology ; transfer learning ; Tumors ; VGG</subject><ispartof>International journal of imaging systems and technology, 2021-09, Vol.31 (3), p.1564-1582</ispartof><rights>2021 Wiley Periodicals LLC.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3326-2222ca5539f6feb01af1874fc931d550acdd3e00698a58210494e3492dbac51e3</citedby><cites>FETCH-LOGICAL-c3326-2222ca5539f6feb01af1874fc931d550acdd3e00698a58210494e3492dbac51e3</cites><orcidid>0000-0002-9635-1029 ; 0000-0002-3695-8961</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fima.22546$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fima.22546$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids></links><search><creatorcontrib>Alaraimi, Saleh</creatorcontrib><creatorcontrib>Okedu, Kenneth E.</creatorcontrib><creatorcontrib>Tianfield, Hugo</creatorcontrib><creatorcontrib>Holden, Richard</creatorcontrib><creatorcontrib>Uthmani, Omair</creatorcontrib><title>Transfer learning networks with skip connections for classification of brain tumors</title><title>International journal of imaging systems and technology</title><description>This article presents a transfer learning model via convolutional neural networks (CNNs) with skip connection topology, to avoid the vanishing gradient and time complexity, which are usually common in transfer learning networks. Three pretrained CNN architectures, namely AlexNet, VGG16 and GoogLeNet are employed to equip with skip connections. The transfer learning is implemented through fine‐tuning and freezing the CNN architectures with skip connections based on magnetic resonance imaging (MRI) slices of brain tumor dataset. Furthermore, in the preprocessing, a frequency‐domain information enhancement technique is employed for better image clarity. Performance evaluation is conducted on the transfer learning networks with skip connections to obtain improved accuracy in brain MRI classifications.</description><subject>AlexNet</subject><subject>Artificial neural networks</subject><subject>Brain</subject><subject>convolutional neural network (CNN)</subject><subject>deep learning</subject><subject>Freezing</subject><subject>GoogLeNet</subject><subject>Image enhancement</subject><subject>Learning</subject><subject>Magnetic resonance imaging</subject><subject>Performance evaluation</subject><subject>Topology</subject><subject>transfer learning</subject><subject>Tumors</subject><subject>VGG</subject><issn>0899-9457</issn><issn>1098-1098</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp1kE1PAjEQQBujiYge_AdNPHlYmH4t2yMhiiQYD-K5Kd1WC0uL7RLCv3dxvTqHmczkzUzyELonMCIAdOx3ekSp4OUFGhCQVXFOl2gAlZSF5GJyjW5y3gAQIkAM0Psq6ZCdTbixOgUfPnGw7TGmbcZH337hvPV7bGII1rQ-hoxdTNg0OmfvvNHnGY4Or5P2AbeHXUz5Fl053WR791eH6OP5aTV7KZZv88VsuiwMY7QsaBdGC8GkK51dA9GOVBPujGSkFgK0qWtmAUpZaVFRAlxyy7ik9VobQSwboof-7j7F74PNrdrEQwrdS0WFqIBxRqqOeuwpk2LOyTq1T52ldFIE1NmZ6jr166xjxz179I09_Q-qxeu03_gBpihuBQ</recordid><startdate>202109</startdate><enddate>202109</enddate><creator>Alaraimi, Saleh</creator><creator>Okedu, Kenneth E.</creator><creator>Tianfield, Hugo</creator><creator>Holden, Richard</creator><creator>Uthmani, Omair</creator><general>John Wiley & Sons, Inc</general><general>Wiley Subscription Services, Inc</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-9635-1029</orcidid><orcidid>https://orcid.org/0000-0002-3695-8961</orcidid></search><sort><creationdate>202109</creationdate><title>Transfer learning networks with skip connections for classification of brain tumors</title><author>Alaraimi, Saleh ; Okedu, Kenneth E. ; Tianfield, Hugo ; Holden, Richard ; Uthmani, Omair</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3326-2222ca5539f6feb01af1874fc931d550acdd3e00698a58210494e3492dbac51e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>AlexNet</topic><topic>Artificial neural networks</topic><topic>Brain</topic><topic>convolutional neural network (CNN)</topic><topic>deep learning</topic><topic>Freezing</topic><topic>GoogLeNet</topic><topic>Image enhancement</topic><topic>Learning</topic><topic>Magnetic resonance imaging</topic><topic>Performance evaluation</topic><topic>Topology</topic><topic>transfer learning</topic><topic>Tumors</topic><topic>VGG</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Alaraimi, Saleh</creatorcontrib><creatorcontrib>Okedu, Kenneth E.</creatorcontrib><creatorcontrib>Tianfield, Hugo</creatorcontrib><creatorcontrib>Holden, Richard</creatorcontrib><creatorcontrib>Uthmani, Omair</creatorcontrib><collection>CrossRef</collection><jtitle>International journal of imaging systems and technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Alaraimi, Saleh</au><au>Okedu, Kenneth E.</au><au>Tianfield, Hugo</au><au>Holden, Richard</au><au>Uthmani, Omair</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Transfer learning networks with skip connections for classification of brain tumors</atitle><jtitle>International journal of imaging systems and technology</jtitle><date>2021-09</date><risdate>2021</risdate><volume>31</volume><issue>3</issue><spage>1564</spage><epage>1582</epage><pages>1564-1582</pages><issn>0899-9457</issn><eissn>1098-1098</eissn><abstract>This article presents a transfer learning model via convolutional neural networks (CNNs) with skip connection topology, to avoid the vanishing gradient and time complexity, which are usually common in transfer learning networks. Three pretrained CNN architectures, namely AlexNet, VGG16 and GoogLeNet are employed to equip with skip connections. The transfer learning is implemented through fine‐tuning and freezing the CNN architectures with skip connections based on magnetic resonance imaging (MRI) slices of brain tumor dataset. Furthermore, in the preprocessing, a frequency‐domain information enhancement technique is employed for better image clarity. Performance evaluation is conducted on the transfer learning networks with skip connections to obtain improved accuracy in brain MRI classifications.</abstract><cop>Hoboken, USA</cop><pub>John Wiley & Sons, Inc</pub><doi>10.1002/ima.22546</doi><tpages>19</tpages><orcidid>https://orcid.org/0000-0002-9635-1029</orcidid><orcidid>https://orcid.org/0000-0002-3695-8961</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0899-9457 |
| ispartof | International journal of imaging systems and technology, 2021-09, Vol.31 (3), p.1564-1582 |
| issn | 0899-9457 1098-1098 |
| language | eng |
| recordid | cdi_proquest_journals_2558034318 |
| source | Wiley Online Library All Journals |
| subjects | AlexNet Artificial neural networks Brain convolutional neural network (CNN) deep learning Freezing GoogLeNet Image enhancement Learning Magnetic resonance imaging Performance evaluation Topology transfer learning Tumors VGG |
| title | Transfer learning networks with skip connections for classification of brain tumors |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T23%3A04%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Transfer%20learning%20networks%20with%20skip%20connections%20for%20classification%20of%20brain%20tumors&rft.jtitle=International%20journal%20of%20imaging%20systems%20and%20technology&rft.au=Alaraimi,%20Saleh&rft.date=2021-09&rft.volume=31&rft.issue=3&rft.spage=1564&rft.epage=1582&rft.pages=1564-1582&rft.issn=0899-9457&rft.eissn=1098-1098&rft_id=info:doi/10.1002/ima.22546&rft_dat=%3Cproquest_cross%3E2558034318%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2558034318&rft_id=info:pmid/&rfr_iscdi=true |