Multi-scale Residual Segmentation Network for Histopathological Image

Deep learning is used in all areas of the image processing like object detection/localization, synthetic image generation, segmentation, tracking, and others. It is frequently used especially in medical image segmentation field since it provides rapid response during the treatment process. The fact...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:DÜMF Mühendislik Dergisi
Hlavní autori: Bozdağ, Zehra, Talu, Muhammed Fatih
Médium: Journal Article
Jazyk:Turkish
Vydavateľské údaje: 24.09.2024
ISSN:1309-8640
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Deep learning is used in all areas of the image processing like object detection/localization, synthetic image generation, segmentation, tracking, and others. It is frequently used especially in medical image segmentation field since it provides rapid response during the treatment process. The fact that natural images contain different types of noise, patterns, and structures and the lack of distinctive quantitative information still makes the segmentation problem very challenging. The classical networks having high parameters have a long training time. The need of less training time for high parameter networks and high segmentation accuracy has led us to develop a new network. In this study, a state-of-the-art autoencoder network (MSRSegNet) is proposed to perform segmentation. Unlike conventional autoencoder approaches, it consists of encoder, fusion and decoder blocks. In encoder and decoder blocks, Multi-scale Residual Blocks are used to share information between blocks and to detect features on different scales. In fusion block, Atrous Spatial Pyramid Pooling (ASPP) module is used to preserve multi-scale contextual information. Information sharing between blocks has increased the ability of the proposed method to capture global features. The performance parameters of mean intersection over unit (mIOU) and pixel accuracy (PA) is used to compare the results. As a result, it was observed that the proposed segmentation network has high accuracy (69% mIoU) and fast segmentation performance (0.061sec. for an image with 256x256)
AbstractList Deep learning is used in all areas of the image processing like object detection/localization, synthetic image generation, segmentation, tracking, and others. It is frequently used especially in medical image segmentation field since it provides rapid response during the treatment process. The fact that natural images contain different types of noise, patterns, and structures and the lack of distinctive quantitative information still makes the segmentation problem very challenging. The classical networks having high parameters have a long training time. The need of less training time for high parameter networks and high segmentation accuracy has led us to develop a new network. In this study, a state-of-the-art autoencoder network (MSRSegNet) is proposed to perform segmentation. Unlike conventional autoencoder approaches, it consists of encoder, fusion and decoder blocks. In encoder and decoder blocks, Multi-scale Residual Blocks are used to share information between blocks and to detect features on different scales. In fusion block, Atrous Spatial Pyramid Pooling (ASPP) module is used to preserve multi-scale contextual information. Information sharing between blocks has increased the ability of the proposed method to capture global features. The performance parameters of mean intersection over unit (mIOU) and pixel accuracy (PA) is used to compare the results. As a result, it was observed that the proposed segmentation network has high accuracy (69% mIoU) and fast segmentation performance (0.061sec. for an image with 256x256)
Author Talu, Muhammed Fatih
Bozdağ, Zehra
Author_xml – sequence: 1
  givenname: Zehra
  orcidid: 0000-0002-1119-5275
  surname: Bozdağ
  fullname: Bozdağ, Zehra
– sequence: 2
  givenname: Muhammed Fatih
  orcidid: 0000-0003-1166-8404
  surname: Talu
  fullname: Talu, Muhammed Fatih
BookMark eNotzz1PwzAUhWEPRaKUjuz5Ay7XsePYI6oKrVRAgu7RtWMXiySu7ESIf89HO53pPdJzQ2ZDHBwhdwxWpQBW3rdT71esApBSzsiccdBUSQHXZJlzMCBEzYVQfE42z1M3Bpotdq54czm0E3bFuzv2bhhxDHEoXtz4FdNn4WMqtiGP8YTjR-ziMfxGxa7Ho7slVx677JaXXZDD4-aw3tL969Nu_bCntq4lRW517RVHBOaFYehMy0tdWq0NV7xFxqTTFi2CEZW2UtXAlbGWAVhTOb4g9HxrU8w5Od-cUugxfTcMmn958ydvLnL-A5bUUWc
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.24012/dumf.1500666
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
ExternalDocumentID 10_24012_dumf_1500666
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
EN8
ID FETCH-LOGICAL-c776-a3c97f83aa01f4b1aebd3292c99b383da116e9caca0b459c687038bcc100cb5e3
ISSN 1309-8640
IngestDate Sat Nov 29 05:13:57 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language Turkish
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c776-a3c97f83aa01f4b1aebd3292c99b383da116e9caca0b459c687038bcc100cb5e3
ORCID 0000-0002-1119-5275
0000-0003-1166-8404
OpenAccessLink http://doi.org/10.24012/dumf.1500666
ParticipantIDs crossref_primary_10_24012_dumf_1500666
PublicationCentury 2000
PublicationDate 2024-09-24
PublicationDateYYYYMMDD 2024-09-24
PublicationDate_xml – month: 09
  year: 2024
  text: 2024-09-24
  day: 24
PublicationDecade 2020
PublicationTitle DÜMF Mühendislik Dergisi
PublicationYear 2024
SSID ssib044734483
ssib054345673
Score 2.2690077
Snippet Deep learning is used in all areas of the image processing like object detection/localization, synthetic image generation, segmentation, tracking, and others....
SourceID crossref
SourceType Index Database
Title Multi-scale Residual Segmentation Network for Histopathological Image
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  issn: 1309-8640
  databaseCode: M~E
  dateStart: 20100101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://road.issn.org
  omitProxy: false
  ssIdentifier: ssib044734483
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV07T8MwELZ4DSwIBIi3MiAWFGhiO45HKK1AogiJDmyV7SS0gqZV2qKKgd_OnZOG8BjKwGJZUWw5_qLzd74XIceMsyRRGp1bdeKygBo3BF7qYlBVQCMZKmORvhV3d-Hjo7wvqreNbDkBkabhdCqH_wo1PAOwMXT2D3CXk8ID6APo0ALs0M4FvA2pdUew91iSYZQHWz3ET_0iyijFIF90x7IehjZNCJYlLoXgTV999Q-6QmO6rLeapy3sXda7cRr1gJ8-g7TK8OKj1OkHb5FCeiqb1ugRd7NS6rfVy8Tevk66eFkenTZhMd3qpYPPXGuHqchJNMyEQZ5p6bsUBpLgYVrXaNJPzoBwoor0edzMTOzfTqHSNxC0EjtBB4d3iuGLZNkXXKLPXuu9MRMYjAkK6mUpYDBMlgfWq6BcYJ5X1c54Xl1QhYdUCEV7nawVmoBzkSO4QRbG2SZpVNBzZug5VfScAj0H0HN-oOdY9LZIu9lo16_dotKFa4QIXEWNFElIlap5CdOeinVEfekbKTUNaaQ8L4ilUUbVNOPSBCBkaaiN8Wo1o3lMt8lSOkjjHeIgI0HLNOeGMmGY1FIAgxM-N9zTTOySk9lnd4Z5PpPOrzu-N--L-2T18w85IEvjbBIfkhXzOu6NsiOL1wf6uj10
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multi-scale+Residual+Segmentation+Network+for+Histopathological+Image&rft.jtitle=D%C3%9CMF+M%C3%BChendislik+Dergisi&rft.au=Bozda%C4%9F%2C+Zehra&rft.au=Talu%2C+Muhammed+Fatih&rft.date=2024-09-24&rft.issn=1309-8640&rft_id=info:doi/10.24012%2Fdumf.1500666&rft.externalDBID=n%2Fa&rft.externalDocID=10_24012_dumf_1500666
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1309-8640&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1309-8640&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1309-8640&client=summon