Efficient segmentation and classification of the tumor using improved encoder-decoder architecture in brain MRI images

Primary diagnosis of brain tumors is crucial to improve treatment outcomes for patient survival. T1-weighted contrast-enhanced images of Magnetic Resonance Imaging (MRI) provide the most anatomically relevant images. But even with many advancements, day by day in the medical field, assessing tumor s...

Full description

Saved in:
Bibliographic Details
Published in:International journal of electrical and computer engineering systems Vol. 13; no. 8; pp. 643 - 651
Main Authors: Ingle, Archana, Roja, Mani, Sankhe, Manoj, Patkar, Deepak
Format: Journal Article
Language:English
Published: 10.11.2022
ISSN:1847-6996, 1847-7003
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Primary diagnosis of brain tumors is crucial to improve treatment outcomes for patient survival. T1-weighted contrast-enhanced images of Magnetic Resonance Imaging (MRI) provide the most anatomically relevant images. But even with many advancements, day by day in the medical field, assessing tumor shape, size, segmentation, and classification is very difficult as manual segmentation of MRI images with high precision and accuracy is indeed a time-consuming and very challenging task. So newer digital methods like deep learning algorithms are used for tumor diagnosis which may lead to far better results. Deep learning algorithms have significantly upgraded the research in the artificial intelligence field and help in better understanding medical images and their further analysis. The work carried out in this paper presents a fully automatic brain tumor segmentation and classification model with encoder-decoder architecture that is an improvisation of traditional UNet architecture achieved by embedding three variants of ResNet like ResNet 50, ResNet 101, and ResNext 50 with proper hyperparameter tuning. Various data augmentation techniques were used to improve the model performance. The overall performance of the model was tested on a publicly available MRI image dataset containing three common types of tumors. The proposed model performed better in comparison to several other deep learning architectures regarding quality parameters including Dice Similarity Coefficient (DSC) and Mean Intersection over Union (Mean IoU) thereby enhancing the tumor analysis.
AbstractList Primary diagnosis of brain tumors is crucial to improve treatment outcomes for patient survival. T1-weighted contrast-enhanced images of Magnetic Resonance Imaging (MRI) provide the most anatomically relevant images. But even with many advancements, day by day in the medical field, assessing tumor shape, size, segmentation, and classification is very difficult as manual segmentation of MRI images with high precision and accuracy is indeed a time-consuming and very challenging task. So newer digital methods like deep learning algorithms are used for tumor diagnosis which may lead to far better results. Deep learning algorithms have significantly upgraded the research in the artificial intelligence field and help in better understanding medical images and their further analysis. The work carried out in this paper presents a fully automatic brain tumor segmentation and classification model with encoder-decoder architecture that is an improvisation of traditional UNet architecture achieved by embedding three variants of ResNet like ResNet 50, ResNet 101, and ResNext 50 with proper hyperparameter tuning. Various data augmentation techniques were used to improve the model performance. The overall performance of the model was tested on a publicly available MRI image dataset containing three common types of tumors. The proposed model performed better in comparison to several other deep learning architectures regarding quality parameters including Dice Similarity Coefficient (DSC) and Mean Intersection over Union (Mean IoU) thereby enhancing the tumor analysis.
Author Patkar, Deepak
Sankhe, Manoj
Ingle, Archana
Roja, Mani
Author_xml – sequence: 1
  givenname: Archana
  surname: Ingle
  fullname: Ingle, Archana
  organization: TSEC, University of Mumbai, EXTC Department, Mumbai, India
– sequence: 2
  givenname: Mani
  surname: Roja
  fullname: Roja, Mani
  organization: TSEC, University of Mumbai, EXTC Department, Mumbai, India
– sequence: 3
  givenname: Manoj
  surname: Sankhe
  fullname: Sankhe, Manoj
  organization: MPSTME, NMIMS University, EXTC Department, Mumbai, India
– sequence: 4
  givenname: Deepak
  surname: Patkar
  fullname: Patkar, Deepak
  organization: Nanavati Max Super Speciality Hospital, Medical Services and Imaging Department, Mumbai, India
BookMark eNotkE1LAzEQhoMoWGuvnvMHds0maZI9SqlaqAii55CP2TbSZkuSFvz3hraXeebrHYb3Ad3GMQJCTx1pGe3V_Dn8goPcdqxVLb9Bk05x2UhC2O01F30v7tEs52AJEXNBlCITdFoOQ3ABYsEZNvtKU8IYsYkeu52p23V8aY0DLlvA5bgfEz7mEDc47A9pPIHHEN3oITUezsQmuW0o4MoxAQ4R22Rq_PhaVYnZQH5Ed4PZZZhdOUU_r8vvxXuz_nxbLV7WjaOSlsZSD2CIUIIDUGqFJNJKKrntjKPArHCUs94MPfGCzCWXnhjrCdS6o4qxKWovd10ac04w6EOqH6Q_3RF9Nk5fjNMd00pz9g_OnGbs
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.32985/ijeces.13.8.4
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
EISSN 1847-7003
EndPage 651
ExternalDocumentID 10_32985_ijeces_13_8_4
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
M~E
ID FETCH-LOGICAL-c272t-b2deea06864ee22b6707b7274b1ac2e3b6c2439af90d605747d0abd0e90d12833
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000933517500004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1847-6996
IngestDate Sat Nov 29 04:07:56 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 8
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c272t-b2deea06864ee22b6707b7274b1ac2e3b6c2439af90d605747d0abd0e90d12833
OpenAccessLink https://ijeces.ferit.hr/index.php/ijeces/article/download/1213/203
PageCount 9
ParticipantIDs crossref_primary_10_32985_ijeces_13_8_4
PublicationCentury 2000
PublicationDate 2022-11-10
PublicationDateYYYYMMDD 2022-11-10
PublicationDate_xml – month: 11
  year: 2022
  text: 2022-11-10
  day: 10
PublicationDecade 2020
PublicationTitle International journal of electrical and computer engineering systems
PublicationYear 2022
SSID ssib006560880
ssib044740766
Score 2.2729154
Snippet Primary diagnosis of brain tumors is crucial to improve treatment outcomes for patient survival. T1-weighted contrast-enhanced images of Magnetic Resonance...
SourceID crossref
SourceType Index Database
StartPage 643
Title Efficient segmentation and classification of the tumor using improved encoder-decoder architecture in brain MRI images
Volume 13
WOSCitedRecordID wos000933517500004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1847-7003
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044740766
  issn: 1847-6996
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Pb9MwFLbK4MAFgQDBNpAPSByqjNR2E-c4QRE7bELTkHaLYscZaTdnatNqJ_7V_St7tlPHqTiMA5e0tRr3x_v03vfs9z4j9ElRUbFpSaOs4JCgqCmNBNDWiFNAc0LFZFJW9rCJ9OyMX15mP0ej-20vzOY61Zrf3WW3_9XUMAbGNq2z_2BuPykMwHMwOlzB7HB9lOFnVhTCbPGv1NVN11rkSo6locqmNsjzREM72_VNsxyv7aJBbdcYgIQafctSLaNS2cfxYMOh1mNhjpYYn56fwC3gklYhyR2uMgbaFO7MHa9PILsTJeDDvChiJy3tmf6JvnIFz0Yit9A-iJw388L1GunarxIVevFbdaPNvN8daxeujPybguC7CBc6IEe2xXaBb4ZAGiVZ1iln92NpHNOBQ6cBcHngnROnCNUF-sQp3e7GEEoybvQ26rmSpjCNHvEj1kfLbYXAThD1pY2QVNkZcnd_PqE5z9kT9JSk08zUHJ7-mfUOD_hm4EAZSyG_tvvr_sc6oVE75ZfBVwqIVMCILl6iF10qg48dBF-hkdKv0cbDD4fww2BvPIQfbioM8MMWftjCD2_hh3fgh0P44VpjCz8M8MMOfm_Qr--zi68_ou5sj0iSlLSRIKVShelPYkoRIpI0TgVwaSYmhSTgQRJJgCsXVRaXkHFD0lvGhShjBa-BUlH6Fu3pRqt3CE8rGZOqqBRlikkmBOPGA1EhgezTkr5Hn7d_VH7rJFzyv1tp_9HvPEDPe4geor12uVYf0DO5aevV8qM18gMOQZyV
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=Efficient+segmentation+and+classification+of+the+tumor+using+improved+encoder-decoder+architecture+in+brain+MRI+images&rft.jtitle=International+journal+of+electrical+and+computer+engineering+systems&rft.au=Ingle%2C+Archana&rft.au=Roja%2C+Mani&rft.au=Sankhe%2C+Manoj&rft.au=Patkar%2C+Deepak&rft.date=2022-11-10&rft.issn=1847-6996&rft.eissn=1847-7003&rft.volume=13&rft.issue=8&rft.spage=643&rft.epage=651&rft_id=info:doi/10.32985%2Fijeces.13.8.4&rft.externalDBID=n%2Fa&rft.externalDocID=10_32985_ijeces_13_8_4
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1847-6996&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1847-6996&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1847-6996&client=summon