Training Nuclei Detection Algorithms with Simple Annotations

Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection...

Full description

Saved in:
Bibliographic Details
Published in:Journal of pathology informatics Vol. 8; no. 1; p. 21
Main Authors: Kost, Henning, Homeyer, André, Molin, Jesper, Lundström, Claes, Hahn, Horst Karl
Format: Journal Article
Language:English
Published: India Elsevier Inc 01.01.2017
Wolters Kluwer India Pvt. Ltd
Medknow Publications & Media Pvt. Ltd
Medknow Publications & Media Pvt Ltd
Elsevier
Subjects:
ISSN:2153-3539, 2229-5089, 2153-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.
AbstractList Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible.BACKGROUNDGenerating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible.We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images.METHODSWe compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images.A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality.RESULTSA Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality.With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.CONCLUSIONSWith appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.
Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.
Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.
Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.
ArticleNumber 21
Author Molin, Jesper
Hahn, Horst Karl
Homeyer, André
Kost, Henning
Lundström, Claes
AuthorAffiliation 4 Center for Medical Image Science and Visualization, Linköping University, 58183 Linköping, Sweden
1 Fraunhofer Institute for Medical Image Computing MEVIS, 28359 Bremen, Germany
2 Department of Applied Information Technology, Chalmers University of Technology, 41258 Gothenburg, Sweden
3 Sectra AB, 58330 Linköping, Sweden
AuthorAffiliation_xml – name: 3 Sectra AB, 58330 Linköping, Sweden
– name: 2 Department of Applied Information Technology, Chalmers University of Technology, 41258 Gothenburg, Sweden
– name: 4 Center for Medical Image Science and Visualization, Linköping University, 58183 Linköping, Sweden
– name: 1 Fraunhofer Institute for Medical Image Computing MEVIS, 28359 Bremen, Germany
Author_xml – sequence: 1
  givenname: Henning
  surname: Kost
  fullname: Kost, Henning
  email: henning.kost@mevis.fraunhofer.de
  organization: Fraunhofer Institute for Medical Image Computing MEVIS, 28359 Bremen, Germany
– sequence: 2
  givenname: André
  surname: Homeyer
  fullname: Homeyer, André
  organization: Fraunhofer Institute for Medical Image Computing MEVIS, 28359 Bremen, Germany
– sequence: 3
  givenname: Jesper
  surname: Molin
  fullname: Molin, Jesper
  organization: Department of Applied Information Technology, Chalmers University of Technology, 41258 Gothenburg
– sequence: 4
  givenname: Claes
  surname: Lundström
  fullname: Lundström, Claes
  organization: Sectra AB, 58330 Linköping, Sweden
– sequence: 5
  givenname: Horst Karl
  surname: Hahn
  fullname: Hahn, Horst Karl
  organization: Fraunhofer Institute for Medical Image Computing MEVIS, 28359 Bremen, Germany
BackLink https://www.ncbi.nlm.nih.gov/pubmed/28584683$$D View this record in MEDLINE/PubMed
https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-140749$$DView record from Swedish Publication Index (Linköpings universitet)
https://research.chalmers.se/publication/254086$$DView record from Swedish Publication Index (Chalmers tekniska högskola)
BookMark eNp1kl1r2zAYhc3oWLuud7segd3sYun0ZdmCbRDafRTKdtFut0KWXyVKFCmT7Ib--yl1M5qwGISM_ZzzHqTzsjjywUNRvMbonGFEP8xX9jwvSSWunhUnBJd0TEsqjp68HxdnKc1RfijFGNUvimNSlzXjNT0pPt5GZb3109GPXjuwo0voQHc2-NHETUO03WyZRuu8jW7scuVgNPE-dGpDpFfFc6NcgrPH_bT49fXL7cX38fXPb1cXk-ux5iWdjrUxpKHEEK6AsEbrnENUSHBuWlC4EcZQRTVmAnQlKGKmZA0YorDmuKaMnhZXg28b1Fyuol2qeC-DsvLhQ4hTqWJnc34JIJo8gmSpYoyXCiPTtBTXpGm5QSZ73QxeaQ2rvtlxi5BART2TeqbcEmKSCSSqG05FRWSrBZGsAiQFGCaVqDhpGp2PGWfX8UHXS_t78pDR2V5ihiomMv954DO8hFaD76JyO7LdP97O5DTcyZKVqMSbge8eDWL400Pq5NImDc4pD6FPEgvEGeel4Bl9u4fOQx99vrBMMUJKVqMN9eZpon9RtlXJABkAHUNKEYzUduhBDmidxEhuKik3ddxWMove74m2vgfwTwO-Dq7L579w_RqizHkWPqz_q5EEy22Hs54PeshtvLNZmrQFr6G1Mbc618UeGsz2hNplS63cAu4Py_4CCFQgqQ
CitedBy_id crossref_primary_10_1016_j_jpi_2022_100011
crossref_primary_10_1016_j_neucom_2019_08_103
crossref_primary_10_1007_s11831_019_09366_4
crossref_primary_10_1111_his_14356
crossref_primary_10_3390_app13084842
crossref_primary_10_1016_j_compmedimag_2018_08_010
crossref_primary_10_1186_s12911_022_01826_5
Cites_doi 10.1002/path.2130
10.1016/j.neucom.2016.01.034
10.1186/1471-2105-15-9
10.4103/2153-3539.186902
10.1145/1007730.1007733
10.4103/2153-3539.92033
10.1109/TMI.2016.2525803
10.1200/JCO.2010.30.5037
10.1109/TMI.2015.2481436
10.1145/361002.361007
10.1097/PAS.0b013e318263207c
10.1111/jmi.12001
ContentType Journal Article
Copyright 2017 The Authors
Copyright Medknow Publications & Media Pvt. Ltd. 2017
Copyright: © 2017 Journal of Pathology Informatics 2017
Copyright_xml – notice: 2017 The Authors
– notice: Copyright Medknow Publications & Media Pvt. Ltd. 2017
– notice: Copyright: © 2017 Journal of Pathology Informatics 2017
DBID 6I.
AAFTH
AAYXX
CITATION
NPM
3V.
7X7
7XB
8FE
8FG
8FI
8FJ
8FK
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FYUFA
GHDGH
GNUQQ
HCIFZ
JQ2
K7-
K9.
M0S
P5Z
P62
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
7X8
5PM
ABXSW
ADTPV
AOWAS
D8T
DG8
ZZAVC
ABBSD
F1S
DOA
DOI 10.4103/jpi.jpi_3_17
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
PubMed
ProQuest Central (Corporate)
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
ProQuest SciTech Collection
ProQuest Technology Collection
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
Technology collection
ProQuest One Community College
ProQuest Central Korea
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
ProQuest Health & Medical Complete (Alumni)
Health & Medical Collection (Alumni Edition)
ProQuest advanced technologies & aerospace journals
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
ProQuest Publicly Available Content
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
SWEPUB Linköpings universitet full text
SwePub
SwePub Articles
SWEPUB Freely available online
SWEPUB Linköpings universitet
SwePub Articles full text
SWEPUB Chalmers tekniska högskola full text
SWEPUB Chalmers tekniska högskola
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
Publicly Available Content Database
Computer Science Database
ProQuest Central Student
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
ProQuest Technology Collection
Health Research Premium Collection (Alumni)
ProQuest SciTech Collection
ProQuest Hospital Collection (Alumni)
Advanced Technologies & Aerospace Database
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Publicly Available Content Database


PubMed




Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2153-3539
EndPage 21
ExternalDocumentID oai_doaj_org_article_ee9b4bc21c6a4465a10fbd3182bd6f0f
oai_research_chalmers_se_08b63972_dc92_47e0_9ef4_a9762bbc1531
oai_DiVA_org_liu_140749
PMC5450511
28584683
10_4103_jpi_jpi_3_17
10.4103/jpi.jpi_3_17_21_Training
S2153353922004254
Genre Journal Article
GroupedDBID .1-
.FO
0R~
5VS
7X7
8FE
8FG
8FI
8FJ
AAKDD
AALRI
AAXUO
AAYWO
ABDBF
ABUWG
ACGFS
ACUHS
ACVFH
ADBBV
ADCNI
ADRAZ
ADVLN
AEGXH
AEUPX
AEXQZ
AFJKZ
AFKRA
AFPUW
AFRHN
AIGII
AITUG
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
AOIJS
APXCP
ARAPS
BAWUL
BCNDV
BENPR
BGLVJ
CCPQU
DIK
E3Z
EBS
EJD
EOJEC
ESX
F5P
FDB
FYUFA
GROUPED_DOAJ
GX1
H13
HCIFZ
HMCUK
HYE
IAO
IHR
IL9
IPNFZ
ITC
K6V
K7-
KQ8
M41
M48
M~E
O5R
O5S
OBODZ
OK1
P62
PHGZM
PHGZT
PIMPY
PQGLB
PROAC
RIG
RNS
ROL
RPM
TUS
UKHRP
Z5R
6I.
AAFTH
ABXLX
AFCTW
RMW
W3E
ALIPV
AAYXX
AFFHD
CITATION
NPM
3V.
7XB
8FK
AZQEC
DWQXO
GNUQQ
JQ2
K9.
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
PRINS
7X8
PUEGO
5PM
ABXSW
ADTPV
AOWAS
D8T
DG8
ZZAVC
ABBSD
F1S
ID FETCH-LOGICAL-c653g-cff2b32f26ae24bcc331970966fdea1b9ff3a3c149ec79304f54bef2a1c618343
IEDL.DBID 7X7
ISSN 2153-3539
2229-5089
IngestDate Fri Oct 03 12:41:35 EDT 2025
Wed Nov 05 04:50:00 EST 2025
Tue Nov 04 17:27:02 EST 2025
Tue Nov 04 01:44:51 EST 2025
Wed Oct 01 07:41:50 EDT 2025
Sat Nov 29 15:07:27 EST 2025
Thu Apr 03 06:55:52 EDT 2025
Wed Nov 05 20:48:00 EST 2025
Tue Nov 18 21:18:15 EST 2025
Tue Jun 17 22:46:05 EDT 2025
Fri Feb 23 02:40:33 EST 2024
Tue Oct 14 19:36:34 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords training set generation
nuclei detection
machine learning
Active learning
Language English
License This is an open access article under the CC BY-NC-ND license.
http://creativecommons.org/licenses/by-nc-sa/3.0
This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License, which allows others to remix, tweak, and build upon the work non-commercially, as long as the author is credited and the new creations are licensed under the identical terms.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c653g-cff2b32f26ae24bcc331970966fdea1b9ff3a3c149ec79304f54bef2a1c618343
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
OpenAccessLink https://www.proquest.com/docview/1942254806?pq-origsite=%requestingapplication%
PMID 28584683
PQID 1942254806
PQPubID 2035654
PageCount 1
ParticipantIDs doaj_primary_oai_doaj_org_article_ee9b4bc21c6a4465a10fbd3182bd6f0f
swepub_primary_oai_research_chalmers_se_08b63972_dc92_47e0_9ef4_a9762bbc1531
swepub_primary_oai_DiVA_org_liu_140749
pubmedcentral_primary_oai_pubmedcentral_nih_gov_5450511
proquest_miscellaneous_1906466596
proquest_journals_1942254806
pubmed_primary_28584683
crossref_citationtrail_10_4103_jpi_jpi_3_17
crossref_primary_10_4103_jpi_jpi_3_17
wolterskluwer_medknow_10_4103_jpi_jpi_3_17_21_Training
elsevier_sciencedirect_doi_10_4103_jpi_jpi_3_17
elsevier_clinicalkey_doi_10_4103_jpi_jpi_3_17
PublicationCentury 2000
PublicationDate 20170101
PublicationDateYYYYMMDD 2017-01-01
PublicationDate_xml – month: 1
  year: 2017
  text: 20170101
  day: 01
PublicationDecade 2010
PublicationPlace India
PublicationPlace_xml – name: India
– name: Mumbai
PublicationTitle Journal of pathology informatics
PublicationTitleAlternate J Pathol Inform
PublicationYear 2017
Publisher Elsevier Inc
Wolters Kluwer India Pvt. Ltd
Medknow Publications & Media Pvt. Ltd
Medknow Publications & Media Pvt Ltd
Elsevier
Publisher_xml – name: Elsevier Inc
– name: Wolters Kluwer India Pvt. Ltd
– name: Medknow Publications & Media Pvt. Ltd
– name: Medknow Publications & Media Pvt Ltd
– name: Elsevier
References Xu, Luo, Wang, Gilmore, Madabhushi (bib8) 2016; 191
Pechenizkiy, Puuronen, Tsymbal (bib13) 2006
Omohundro (bib15) 1987; 1
Molin, Bodén, Treanor, Fjeld, Lundström (bib17) 2016
Sirinukunwattana, Raza, Tsang, Snead, Cree, Rajpoot (bib11) 2016; 35
Kost, Homeyer, Bult, Balkenhol, van der Laak, Hahn (bib18) 2016
Xing, Xie, Yang (bib7) 2016; 35
Arteta, Lempitsky, Noble, Zisserman (bib5) 2012
Janowczyk, Madabhushi (bib9) 2016; 7
Vink, Van Leeuwen, Van Deurzen, De Haan (bib4) 2013; 249
Bentley (bib14) 1975; 18
Settles (bib16) 2009
Tang, Gonen, Hedvat, Modlin, Klimstra (bib3) 2012; 36
Speirs, Walker (bib2) 2007; 211
Gul-Mohammed, Arganda-Carreras, Andrey, Galy, Boudier (bib10) 2014; 15
Kårsnäs, Dahl, Larsen (bib6) 2011; 2
Chawla, Japkowicz, Kotcz (bib12) 2004; 6
Mahmoud, Paish, Powe, Macmillan, Grainge, Lee (bib1) 2011; 29
Janowczyk (10.4103/jpi.jpi_3_17_bib9) 2016; 7
Xing (10.4103/jpi.jpi_3_17_bib7) 2016; 35
Arteta (10.4103/jpi.jpi_3_17_bib5) 2012
Omohundro (10.4103/jpi.jpi_3_17_bib15) 1987; 1
Kårsnäs (10.4103/jpi.jpi_3_17_bib6) 2011; 2
Gul-Mohammed (10.4103/jpi.jpi_3_17_bib10) 2014; 15
Mahmoud (10.4103/jpi.jpi_3_17_bib1) 2011; 29
Kost (10.4103/jpi.jpi_3_17_bib18) 2016
Sirinukunwattana (10.4103/jpi.jpi_3_17_bib11) 2016; 35
Speirs (10.4103/jpi.jpi_3_17_bib2) 2007; 211
Tang (10.4103/jpi.jpi_3_17_bib3) 2012; 36
Settles (10.4103/jpi.jpi_3_17_bib16) 2009
Molin (10.4103/jpi.jpi_3_17_bib17)
Xu (10.4103/jpi.jpi_3_17_bib8) 2016; 191
Pechenizkiy (10.4103/jpi.jpi_3_17_bib13) 2006
Chawla (10.4103/jpi.jpi_3_17_bib12) 2004; 6
Bentley (10.4103/jpi.jpi_3_17_bib14) 1975; 18
Vink (10.4103/jpi.jpi_3_17_bib4) 2013; 249
21483002 - J Clin Oncol. 2011 May 20;29(15):1949-55
24423252 - BMC Bioinformatics. 2014 Jan 14;15:9
17236182 - J Pathol. 2007 Apr;211(5):499-506
22811956 - J Pathol Inform. 2011;2:S12
28154470 - Neurocomputing. 2016 May 26;191:214-223
26863654 - IEEE Trans Med Imaging. 2016 May;35(5):1196-1206
26415167 - IEEE Trans Med Imaging. 2016 Feb;35(2):550-66
23252774 - J Microsc. 2013 Feb;249(2):124-35
23285570 - Med Image Comput Comput Assist Interv. 2012;15(Pt 1):348-56
23026928 - Am J Surg Pathol. 2012 Dec;36(12):1761-70
27563488 - J Pathol Inform. 2016 Jul 26;7:29
References_xml – volume: 211
  start-page: 499
  year: 2007
  end-page: 506
  ident: bib2
  article-title: New perspectives into the biological and clinical relevance of oestrogen receptors in the human breast
  publication-title: J Pathol
– volume: 249
  start-page: 124
  year: 2013
  end-page: 135
  ident: bib4
  article-title: Efficient nucleus detector in histopathology images
  publication-title: J Microsc
– volume: 35
  start-page: 1196
  year: 2016
  end-page: 1206
  ident: bib11
  article-title: Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images
  publication-title: IEEE Trans Med Imaging
– volume: 2
  start-page: S12
  year: 2011
  ident: bib6
  article-title: Learning histopathological patterns
  publication-title: J Pathol Inform
– volume: 191
  start-page: 214
  year: 2016
  end-page: 223
  ident: bib8
  article-title: A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images
  publication-title: Neurocomputing
– volume: 18
  start-page: 509
  year: 1975
  end-page: 517
  ident: bib14
  article-title: Multidimensional binary search trees used for associative searching
  publication-title: Commun ACM
– volume: 6
  start-page: 1
  year: 2004
  end-page: 6
  ident: bib12
  article-title: Editorial: Special issue on learning from imbalanced data sets
  publication-title: SIGKDD Explor Newsl
– volume: 35
  start-page: 550
  year: 2016
  end-page: 566
  ident: bib7
  article-title: An automatic learning-based framework for robust nucleus segmentation
  publication-title: IEEE Trans Med Imaging
– year: 2016
  ident: bib18
  article-title: A generic nuclei detection method for histopathological breast images
  publication-title: Medical Imaging 2016: Digital Pathology. Bellingham; Washington USA
– year: 2009
  ident: bib16
  article-title: Active Learning Literature Survey. Computer Sciences Technical Report 1648
– volume: 29
  start-page: 1949
  year: 2011
  end-page: 1955
  ident: bib1
  article-title: Tumor-infiltrating CD8+ lymphocytes predict clinical outcome in breast cancer
  publication-title: J Clin Oncol
– volume: 7
  start-page: 29
  year: 2016
  ident: bib9
  article-title: Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases
  publication-title: J Pathol Inform
– start-page: 348
  year: 2012
  end-page: 356
  ident: bib5
  article-title: Learning to detect cells using non-overlapping extremal regions
  publication-title: Medical Image Computing and Computer-Assisted Intervention-MICCAI 2012
– start-page: 553
  year: 2006
  end-page: 558
  ident: bib13
  article-title: The impact of sample reduction on PCA-based feature extraction for supervised learning
  publication-title: Proceedings of the 2006 ACM Symposium on Applied Computing (SAC)
– year: 2016
  ident: bib17
  article-title: Scale Stain: Multi-Resolution Feature Enhancement in Pathology Visualization
– volume: 15
  start-page: 9
  year: 2014
  ident: bib10
  article-title: A generic classification-based method for segmentation of nuclei in 3D images of early embryos
  publication-title: BMC Bioinformatics
– volume: 1
  start-page: 273
  year: 1987
  end-page: 347
  ident: bib15
  article-title: Efficient algorithms with neural network behavior
  publication-title: Complex Syst
– volume: 36
  start-page: 1761
  year: 2012
  end-page: 1770
  ident: bib3
  article-title: Objective quantification of the Ki67 proliferative index in neuroendocrine tumors of the gastroenteropancreatic system: A comparison of digital image analysis with manual methods
  publication-title: Am J Surg Pathol
– volume: 211
  start-page: 499
  year: 2007
  ident: 10.4103/jpi.jpi_3_17_bib2
  article-title: New perspectives into the biological and clinical relevance of oestrogen receptors in the human breast
  publication-title: J Pathol
  doi: 10.1002/path.2130
– volume: 191
  start-page: 214
  year: 2016
  ident: 10.4103/jpi.jpi_3_17_bib8
  article-title: A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.01.034
– year: 2016
  ident: 10.4103/jpi.jpi_3_17_bib18
  article-title: A generic nuclei detection method for histopathological breast images
– ident: 10.4103/jpi.jpi_3_17_bib17
– volume: 15
  start-page: 9
  year: 2014
  ident: 10.4103/jpi.jpi_3_17_bib10
  article-title: A generic classification-based method for segmentation of nuclei in 3D images of early embryos
  publication-title: BMC Bioinformatics
  doi: 10.1186/1471-2105-15-9
– start-page: 553
  year: 2006
  ident: 10.4103/jpi.jpi_3_17_bib13
  article-title: The impact of sample reduction on PCA-based feature extraction for supervised learning
– volume: 7
  start-page: 29
  year: 2016
  ident: 10.4103/jpi.jpi_3_17_bib9
  article-title: Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases
  publication-title: J Pathol Inform
  doi: 10.4103/2153-3539.186902
– volume: 6
  start-page: 1
  year: 2004
  ident: 10.4103/jpi.jpi_3_17_bib12
  article-title: Editorial: Special issue on learning from imbalanced data sets
  publication-title: SIGKDD Explor Newsl
  doi: 10.1145/1007730.1007733
– volume: 1
  start-page: 273
  year: 1987
  ident: 10.4103/jpi.jpi_3_17_bib15
  article-title: Efficient algorithms with neural network behavior
  publication-title: Complex Syst
– volume: 2
  start-page: S12
  year: 2011
  ident: 10.4103/jpi.jpi_3_17_bib6
  article-title: Learning histopathological patterns
  publication-title: J Pathol Inform
  doi: 10.4103/2153-3539.92033
– volume: 35
  start-page: 1196
  year: 2016
  ident: 10.4103/jpi.jpi_3_17_bib11
  article-title: Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2016.2525803
– year: 2009
  ident: 10.4103/jpi.jpi_3_17_bib16
– volume: 29
  start-page: 1949
  year: 2011
  ident: 10.4103/jpi.jpi_3_17_bib1
  article-title: Tumor-infiltrating CD8+ lymphocytes predict clinical outcome in breast cancer
  publication-title: J Clin Oncol
  doi: 10.1200/JCO.2010.30.5037
– volume: 35
  start-page: 550
  year: 2016
  ident: 10.4103/jpi.jpi_3_17_bib7
  article-title: An automatic learning-based framework for robust nucleus segmentation
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2015.2481436
– volume: 18
  start-page: 509
  year: 1975
  ident: 10.4103/jpi.jpi_3_17_bib14
  article-title: Multidimensional binary search trees used for associative searching
  publication-title: Commun ACM
  doi: 10.1145/361002.361007
– start-page: 348
  year: 2012
  ident: 10.4103/jpi.jpi_3_17_bib5
  article-title: Learning to detect cells using non-overlapping extremal regions
– volume: 36
  start-page: 1761
  year: 2012
  ident: 10.4103/jpi.jpi_3_17_bib3
  article-title: Objective quantification of the Ki67 proliferative index in neuroendocrine tumors of the gastroenteropancreatic system: A comparison of digital image analysis with manual methods
  publication-title: Am J Surg Pathol
  doi: 10.1097/PAS.0b013e318263207c
– volume: 249
  start-page: 124
  year: 2013
  ident: 10.4103/jpi.jpi_3_17_bib4
  article-title: Efficient nucleus detector in histopathology images
  publication-title: J Microsc
  doi: 10.1111/jmi.12001
– reference: 23252774 - J Microsc. 2013 Feb;249(2):124-35
– reference: 28154470 - Neurocomputing. 2016 May 26;191:214-223
– reference: 23026928 - Am J Surg Pathol. 2012 Dec;36(12):1761-70
– reference: 24423252 - BMC Bioinformatics. 2014 Jan 14;15:9
– reference: 23285570 - Med Image Comput Comput Assist Interv. 2012;15(Pt 1):348-56
– reference: 17236182 - J Pathol. 2007 Apr;211(5):499-506
– reference: 26415167 - IEEE Trans Med Imaging. 2016 Feb;35(2):550-66
– reference: 21483002 - J Clin Oncol. 2011 May 20;29(15):1949-55
– reference: 22811956 - J Pathol Inform. 2011;2:S12
– reference: 26863654 - IEEE Trans Med Imaging. 2016 May;35(5):1196-1206
– reference: 27563488 - J Pathol Inform. 2016 Jul 26;7:29
SSID ssj0000331108
Score 2.0315976
Snippet Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour...
Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to...
Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour...
SourceID doaj
swepub
pubmedcentral
proquest
pubmed
crossref
wolterskluwer
elsevier
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 21
SubjectTerms Active learning
Algorithms
Annotations
Breast cancer
Cancer
Classification
Extraction
Image detection
Machine learning
Markers
Nuclei
Nuclei detection
Pathology
Run time (computers)
Teaching methods
Tessellation
Training
Training set generation
Visualization
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQhRAXxJtAQUECLihsYjtOLHEpj4pDqTiUqjfLz27KNlttduHvM7aTsFFbuHDIJZ4kyueZ8Uw8-QahV5DoEK0ZzpitdUZdacDmjM2IKW1lieUm9Iw8PqgOD-uTE_5tq9WXrwmL9MARuJm1XFGlcaGZ9ORessidMqCJWBnmcue9b17xrWQq-GBCfH277ywHJp2RkvBY9U6LnMzOLpp3cAgiQp-yP-tRoO2fLEuXw87L1ZM9xygM_Fr6Le7uR6hw31qn9u-iO32Ame7FF7uHbtj2Prr1td9Cf4DeH_VNIdLWUxk3qbHrUI7VpnJxulw16_l5l_rPs2nXeOrgVLbtMm7Ydw_R9_3PRx-_ZH0LhUyzkpxm2jmsCHaYSYsBRg248ArSFuaMlYXizhFJNKRJVoOl5jBZVFmHJcANxk7JI7TTLlv7BKVaccUlNUVdKcpMrmrKpa2k8Yx6eS0T9HYAUuieX9y3uVgIyDM87MJDPsCeoNej9EXk1bhG7oOfk1HGs2GHE6AjotcR8S8dSVA2zKgYfjgFFwk3aq556GyU7wORGGD85YrdQVFE7wQ6UXAK3pLWOUvQy3EYzNfvycjWLjdeBmJCxkoOMo-jXo3vimsfHdYkQdVE4yZgTEfaZh4owiEuBm9bJOhN1M3JJZ-a472A36LZQOoHQSRP0MEVgj3f1FzoeWjm04nOirxWfjMYC6M5FrSyueDWUSEhsMVKabA3eC6bmII4j_92XomdwIUYVP_p_5juZ-g29sFX-FC2i3bWq419jm7qn-umW70IjuI32zR1aQ
  priority: 102
  providerName: Directory of Open Access Journals
Title Training Nuclei Detection Algorithms with Simple Annotations
URI https://www.clinicalkey.com/#!/content/1-s2.0-S2153353922004254
https://dx.doi.org/10.4103/jpi.jpi_3_17
http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2017;volume=8;issue=1;spage=21;epage=21;aulast=Kost;type=0
https://www.ncbi.nlm.nih.gov/pubmed/28584683
https://www.proquest.com/docview/1942254806
https://www.proquest.com/docview/1906466596
https://pubmed.ncbi.nlm.nih.gov/PMC5450511
https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-140749
https://research.chalmers.se/publication/254086
https://doaj.org/article/ee9b4bc21c6a4465a10fbd3182bd6f0f
Volume 8
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2153-3539
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331108
  issn: 2229-5089
  databaseCode: DOA
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2153-3539
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000331108
  issn: 2229-5089
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: AUTh Library subscriptions: ProQuest Central
  customDbUrl:
  eissn: 2153-3539
  dateEnd: 20220131
  omitProxy: false
  ssIdentifier: ssj0000331108
  issn: 2229-5089
  databaseCode: BENPR
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 2153-3539
  dateEnd: 20220131
  omitProxy: false
  ssIdentifier: ssj0000331108
  issn: 2229-5089
  databaseCode: K7-
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 2153-3539
  dateEnd: 20220131
  omitProxy: false
  ssIdentifier: ssj0000331108
  issn: 2229-5089
  databaseCode: 7X7
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest advanced technologies & aerospace journals
  customDbUrl:
  eissn: 2153-3539
  dateEnd: 20220131
  omitProxy: false
  ssIdentifier: ssj0000331108
  issn: 2229-5089
  databaseCode: P5Z
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2153-3539
  dateEnd: 20220131
  omitProxy: false
  ssIdentifier: ssj0000331108
  issn: 2229-5089
  databaseCode: PIMPY
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpR3LjtMw0IJdhLjwfgSWKkjABYUmdprEEhLaha5AbKsKLauFi-VX2kA3KU0LN76dseNkqfZx4VAf6snDM-PxvDKD0HMwdIiUCQ4SnckgzgcK9pzSAVEDnWqiqbI9I48O0vE4Oz6mE-dwq11aZSsTraBWlTQ-8j4Y28B6cRYmbxc_A9M1ykRXXQuNq2jbtM02fJ4ep52PJSTEZLmb_nIY0wB0EdrkvsdRSPrfF8Vr-DHCbLey01PJFu_fOJzOKp9ncyhdpVGY-F2ZQHf9w-a5_3Na7d_633XeRjednurvNox1B13R5V10feQi8ffQm0PXW8IvTUXkwld6ZbO6Sp_Pp3DD1eyk9o2X168LU4HY52VZNXH_-j76sj88fPchcJ0YApkMyDSQeY4FwTlOuMaxkBIQS1OwfpJcaR4JmueEEwnWlpaw4UOgeSx0jnkkE5AZMXmAtsqq1I-QLwUVlMcKyCXiRIUiiynXKVemMF-YcQ-9ainBpCtTbrplzBmYK4ZuzNCspZuHXnTQi6Y8xwVwe4aoHYwpqm3_qJZT5vYo05oKWByGl-amjhyPwlwoEHpYqCQPcw8FLUuw9rtVkLRwo-KCh_Y7eKfPNHrKJVfstEzBnCyp2SlHeOhZNw1SwIR2eKmrtYEB1TJJBhRgHjaM2a0VZ0bJzIiH0g2W3UDG5kxZzGylcVCvQWhHHnrZMPfGJe-Lo12Lv3mxBgsSdFHqoYNzAF3ZqhmTM9sTqGa1ZmEmTEwZMyUpZnGqQ0Z1HjMO-jEWQsJJDM9NNvYSO2k-ET0XdwxHrGX9x5fj8Qm6gY12Zj1pO2hrtVzrp-ia_LUq6mXPyhA7Zj20vTccTz73rKsGxk9pAOPozxDGyeAbzE8-jiZf_wIrgIp7
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwELZKQcCF9yNQIEiUCwqb2NkklkCoUKpWu11xWKrejF_ZDWyTZbNLxZ_iNzJ2HiXq49YDh72sJ47jfDP-xp7MIPQKHB0iZYS9SCfSC9O-Ap1T2iOqr2NNNFW2ZuTBMB6NksND-mUN_Wm-hTFhlY1NtIZaFdLskffA2QbohYkffZj_9EzVKHO62pTQqGAx0L-PwWUr3-9tw_vdxHjn8_jTrldXFfBk1CcTT6YpFgSnOOIah0JKAiiMgclHqdI8EDRNCScSPActAbw-jD8UOsU8kBHgPyTQ7xV0NSRJbPRqEHvtno4PXQVVETyMqQfch1ax9mHgk973efYWfowwWx3tZBW0xQI6i-Fpsns6ZrPObAoNx4U5WC9_2Lj6f1bHndv_27zeQbdqHu5uVYpzF63p_B66vl9HGtxH78Z17Qw3NxmfM1fppY1ay10-m8ADLKdHpWt2sd0yMxmWXZ7nRRXXUD5AXy9l7A_Rel7k-jFypaCC8lAFSSzCSPkiCSnXMVcm8aCfcAe9ad48k3UadlMNZMbAHTM4YQYjDU4ctNlKz6v0I-fIfTQgamVM0nD7R7GYsNoGMa2pgIfDMGhu8uTxwE-FAqOOhYpSP3WQ10CQNd_lwkoCHWXn3LTXytd8reJhF1yx0YCQ1bayZCcIdNDLthmsnDm64rkuVkYGqHMU9SnIPKoUoX1WnBgSnRAHxR0V6UxGtyXPpjaTOrgPsCgFDnpdKVPnku3sYMvO3yxbgYcMXJs6aHiGYJ2Wa8rk1NY8KlmpmZ8Ic2aOmZIUszDWPqM6DRkH_o-FkMA04L5RR3fZUfUJ7Jlzx3DAGug_uXgeX6Abu-P9IRvujQZP0U1smKjdNdxA68vFSj9D1-SvZVYunlv75aJvl63YfwFQweA7
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=Training+Nuclei+Detection+Algorithms+with+Simple+Annotations&rft.jtitle=Journal+of+pathology+informatics&rft.au=Kost%2C+Henning&rft.au=Homeyer%2C+Andr%C3%A9&rft.au=Molin%2C+Jesper&rft.au=Lundstr%C3%B6m%2C+Claes&rft.date=2017-01-01&rft.issn=2229-5089&rft.volume=8&rft_id=info:doi/10.4103%2Fjpi.jpi_3_17&rft.externalDocID=oai_DiVA_org_liu_140749
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2153-3539&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2153-3539&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2153-3539&client=summon