Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation

The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patie...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of medical imaging (Bellingham, Wash.) Ročník 4; číslo 4; s. 041311
Hlavní autoři: Alex, Varghese, Vaidhya, Kiran, Thirunavukkarasu, Subramaniam, Kesavadas, Chandrasekharan, Krishnamurthi, Ganapathy
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 01.10.2017
Témata:
ISSN:2329-4302
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patients ([Formula: see text], 40, 65). The results show negligible loss in performance even when SDAE was fine-tuned using 20 labeled patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach in which a network pretrained with high grade glioma data was fine-tuned using LGG image patches. The networks were also shown to generalize well and provide good segmentation on unseen BraTS 2013 and BraTS 2015 test data. The manuscript also includes the use of a single layer DAE, referred to as novelty detector (ND). ND was trained to accurately reconstruct nonlesion patches. The reconstruction error maps of test data were used to localize lesions. The error maps were shown to assign unique error distributions to various constituents of the glioma, enabling localization. The ND learns the nonlesion brain accurately as it was also shown to provide good segmentation performance on ischemic brain lesions in images from a different database.
AbstractList The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patients ([Formula: see text], 40, 65). The results show negligible loss in performance even when SDAE was fine-tuned using 20 labeled patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach in which a network pretrained with high grade glioma data was fine-tuned using LGG image patches. The networks were also shown to generalize well and provide good segmentation on unseen BraTS 2013 and BraTS 2015 test data. The manuscript also includes the use of a single layer DAE, referred to as novelty detector (ND). ND was trained to accurately reconstruct nonlesion patches. The reconstruction error maps of test data were used to localize lesions. The error maps were shown to assign unique error distributions to various constituents of the glioma, enabling localization. The ND learns the nonlesion brain accurately as it was also shown to provide good segmentation performance on ischemic brain lesions in images from a different database.
The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patients ([Formula: see text], 40, 65). The results show negligible loss in performance even when SDAE was fine-tuned using 20 labeled patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach in which a network pretrained with high grade glioma data was fine-tuned using LGG image patches. The networks were also shown to generalize well and provide good segmentation on unseen BraTS 2013 and BraTS 2015 test data. The manuscript also includes the use of a single layer DAE, referred to as novelty detector (ND). ND was trained to accurately reconstruct nonlesion patches. The reconstruction error maps of test data were used to localize lesions. The error maps were shown to assign unique error distributions to various constituents of the glioma, enabling localization. The ND learns the nonlesion brain accurately as it was also shown to provide good segmentation performance on ischemic brain lesions in images from a different database.The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patients ([Formula: see text], 40, 65). The results show negligible loss in performance even when SDAE was fine-tuned using 20 labeled patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach in which a network pretrained with high grade glioma data was fine-tuned using LGG image patches. The networks were also shown to generalize well and provide good segmentation on unseen BraTS 2013 and BraTS 2015 test data. The manuscript also includes the use of a single layer DAE, referred to as novelty detector (ND). ND was trained to accurately reconstruct nonlesion patches. The reconstruction error maps of test data were used to localize lesions. The error maps were shown to assign unique error distributions to various constituents of the glioma, enabling localization. The ND learns the nonlesion brain accurately as it was also shown to provide good segmentation performance on ischemic brain lesions in images from a different database.
Author Krishnamurthi, Ganapathy
Vaidhya, Kiran
Alex, Varghese
Kesavadas, Chandrasekharan
Thirunavukkarasu, Subramaniam
Author_xml – sequence: 1
  givenname: Varghese
  surname: Alex
  fullname: Alex, Varghese
  organization: Indian Institute of Technology Madras, Department of Engineering Design, Chennai, India
– sequence: 2
  givenname: Kiran
  surname: Vaidhya
  fullname: Vaidhya, Kiran
  organization: Indian Institute of Technology Madras, Department of Engineering Design, Chennai, India
– sequence: 3
  givenname: Subramaniam
  surname: Thirunavukkarasu
  fullname: Thirunavukkarasu, Subramaniam
  organization: Indian Institute of Technology Madras, Department of Engineering Design, Chennai, India
– sequence: 4
  givenname: Chandrasekharan
  surname: Kesavadas
  fullname: Kesavadas, Chandrasekharan
  organization: Sree Chitra Tirunal Institute for Medical Sciences and Technology, Department of Radiology, Trivandrum, India
– sequence: 5
  givenname: Ganapathy
  surname: Krishnamurthi
  fullname: Krishnamurthi, Ganapathy
  organization: Indian Institute of Technology Madras, Department of Engineering Design, Chennai, India
BackLink https://www.ncbi.nlm.nih.gov/pubmed/29285516$$D View this record in MEDLINE/PubMed
BookMark eNo1kM1PwzAMxXMYYmPszgn1yKUjTtI1OaKJj6EhDsC55MOditpkJC0S_z0dDFl6frZ-epJ9RiY-eCTkAugSAMprWD4-bZZiLCqAA0zIjHGmcsEpm5JFSh-UUgBaMBCnZMoUk0UBqxl5f8GuScMe41eT0GUt6ugbv8uGdFCHPjS_Tg99QG-Dw5iyOsTMRN34kU9N8CPXo-0PTnuXJdx16Ht9WJyTk1q3CRfHPidvd7ev64d8-3y_Wd9sc1tQ2ecKS2okrUHw2oHW1ki0glFTrhxIp0zBwbDScIpWFU4qjmjHgYMtZS0Nm5Orv9x9DJ8Dpr4a77LYttpjGFIFSjIpWMHliF4e0cF06Kp9bDodv6v_r7AfI95nDA
CitedBy_id crossref_primary_10_1016_j_media_2019_03_009
crossref_primary_10_3390_informatics8030059
crossref_primary_10_1016_j_media_2020_101840
crossref_primary_10_1136_bmjopen_2020_042660
crossref_primary_10_1016_j_media_2021_101978
crossref_primary_10_1016_j_compbiomed_2018_05_027
crossref_primary_10_1038_s41598_020_80675_6
crossref_primary_10_3390_s21248507
crossref_primary_10_1007_s42979_021_00784_5
crossref_primary_10_3390_biology10111134
crossref_primary_10_3390_jimaging7040066
crossref_primary_10_1002_ima_70106
crossref_primary_10_1007_s11042_024_19313_6
crossref_primary_10_1007_s11548_021_02504_z
crossref_primary_10_1007_s11042_020_08898_3
crossref_primary_10_1007_s11548_021_02326_z
crossref_primary_10_1016_j_engappai_2025_110583
crossref_primary_10_3390_info13100472
crossref_primary_10_1016_j_media_2023_102963
crossref_primary_10_1177_20552076221074122
crossref_primary_10_1016_j_neuroimage_2020_117012
crossref_primary_10_1016_j_media_2022_102472
crossref_primary_10_1016_j_media_2020_101693
ContentType Journal Article
DBID NPM
7X8
DOI 10.1117/1.JMI.4.4.041311
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
ExternalDocumentID 29285516
Genre Journal Article
GroupedDBID 0R~
4.4
ABJNI
ACGFS
ADMLS
AKROS
ALMA_UNASSIGNED_HOLDINGS
EBS
EJD
FQ0
HYE
M4X
NPM
O9-
OK1
RPM
SPBNH
7X8
ID FETCH-LOGICAL-c508t-9e70b80f143fd1aacb8ec420b76d18d9b531b27b30ec95d893eec30e31c78f8b2
IEDL.DBID 7X8
ISICitedReferencesCount 45
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000418469600011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2329-4302
IngestDate Thu Oct 02 10:27:21 EDT 2025
Mon Jul 21 05:28:40 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords deep learning
stacked denoising autoencoder
magnetic resonance imaging
denoising autoencoder
gliomas
brain lesion
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c508t-9e70b80f143fd1aacb8ec420b76d18d9b531b27b30ec95d893eec30e31c78f8b2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://www.ncbi.nlm.nih.gov/pmc/articles/5730366
PMID 29285516
PQID 1982842538
PQPubID 23479
ParticipantIDs proquest_miscellaneous_1982842538
pubmed_primary_29285516
PublicationCentury 2000
PublicationDate 2017-10-01
PublicationDateYYYYMMDD 2017-10-01
PublicationDate_xml – month: 10
  year: 2017
  text: 2017-10-01
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of medical imaging (Bellingham, Wash.)
PublicationTitleAlternate J Med Imaging (Bellingham)
PublicationYear 2017
SSID ssj0001105214
Score 2.2787325
Snippet The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. Stacked denoising...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 041311
Title Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation
URI https://www.ncbi.nlm.nih.gov/pubmed/29285516
https://www.proquest.com/docview/1982842538
Volume 4
WOSCitedRecordID wos000418469600011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFA7qRHzxfpk3Ivja2SbZmjyJiEPFjYEKe6u5dezBdtrO3-85bceeBEEKpYUUmtvJl3O-nI-Qq55BrgV3AQd0HAjmVGAsdIgXzrOIa0DQlWrJczwcyvFYjRqHW9HQKhc2sTLULrfoI7-GzTHDkBGXN7PPAFWjMLraSGiskhYHKIOUrngslz6WCI-mikpfjqlAcCTz1JHKKL6OOk-Dx46AKxSYdOZ3jFmtNf3t__7lDtlqUCa9rYfFLlnx2R7ZGDRx9H3y_oIyb_MZGorCO9poR0wo0uAnFGxRPq2e9LzMMdUl0p0p4FtqUFICyqOTDcqVFZMrozpztPCTj-YkU3ZA3vr3r3cPQaO1EFiAaGWgfBwaGaYAn1IXaW2N9Faw0MQ9F0mnDMxVw2LDQ29V1wHK8d7CC49sLFNp2CFZy_LMHxPKLWx7Xc9ribn10q4RWgmPGkVd7aVWbXK5aLsE6ooBCp35fF4ky9Zrk6O6A5JZnXQjYYpJDOqd_OHrU7LJcPWtOHdnpJXCTPbnZN1-l9Pi66IaJHAfjgY_qiDHrw
linkProvider ProQuest
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=Semisupervised+learning+using+denoising+autoencoders+for+brain+lesion+detection+and+segmentation&rft.jtitle=Journal+of+medical+imaging+%28Bellingham%2C+Wash.%29&rft.au=Alex%2C+Varghese&rft.au=Vaidhya%2C+Kiran&rft.au=Thirunavukkarasu%2C+Subramaniam&rft.au=Kesavadas%2C+Chandrasekharan&rft.date=2017-10-01&rft.issn=2329-4302&rft.volume=4&rft.issue=4&rft.spage=041311&rft_id=info:doi/10.1117%2F1.JMI.4.4.041311&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2329-4302&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2329-4302&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2329-4302&client=summon