Home > Publications Database > AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images. > print

001     138551
005     20240321220447.0
024 7 _ |a 10.1109/TMI.2016.2528120
|2 doi
024 7 _ |a pmid:26891484
|2 pmid
024 7 _ |a 0278-0062
|2 ISSN
024 7 _ |a 1558-0062
|2 ISSN
024 7 _ |a 1558-254X
|2 ISSN
024 7 _ |a altmetric:5637754
|2 altmetric
037 _ _ |a DZNE-2020-04873
041 _ _ |a English
082 _ _ |a 620
100 1 _ |a Albarqouni, Shadi
|0 P:(DE-2719)2810881
|b 0
|e First author
245 _ _ |a AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images.
260 _ _ |a New York, NY
|c 2016
|b IEEE
264 _ 1 |3 print
|2 Crossref
|b Institute of Electrical and Electronics Engineers (IEEE)
|c 2016-05-01
336 7 _ |a article
|2 DRIVER
336 7 _ |a Output Types/Journal article
|2 DataCite
336 7 _ |a Journal Article
|b journal
|m journal
|0 PUB:(DE-HGF)16
|s 1586966677_28672
|2 PUB:(DE-HGF)
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
520 _ _ |a The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration.
536 _ _ |a 341 - Molecular Signaling (POF3-341)
|0 G:(DE-HGF)POF3-341
|c POF3-341
|f POF III
|x 0
588 _ _ |a Dataset connected to CrossRef, PubMed,
650 _ 2 |a Breast Neoplasms: diagnostic imaging
|2 MeSH
650 _ 2 |a Crowdsourcing: methods
|2 MeSH
650 _ 2 |a Female
|2 MeSH
650 _ 2 |a Histocytochemistry
|2 MeSH
650 _ 2 |a Humans
|2 MeSH
650 _ 2 |a Image Interpretation, Computer-Assisted: methods
|2 MeSH
650 _ 2 |a Internet
|2 MeSH
650 _ 2 |a Machine Learning
|2 MeSH
650 _ 2 |a Mitosis: physiology
|2 MeSH
650 _ 2 |a Neural Networks, Computer
|2 MeSH
650 _ 2 |a Video Games
|2 MeSH
700 1 _ |a Baur, Christoph
|b 1
700 1 _ |a Achilles, Felix
|b 2
700 1 _ |a Belagiannis, Vasileios
|b 3
700 1 _ |a Demirci, Stefanie
|b 4
700 1 _ |a Navab, Nassir
|b 5
773 1 8 |a 10.1109/tmi.2016.2528120
|b : Institute of Electrical and Electronics Engineers (IEEE), 2016-05-01
|n 5
|p 1313-1321
|3 journal-article
|2 Crossref
|t IEEE Transactions on Medical Imaging
|v 35
|y 2016
|x 0278-0062
773 _ _ |a 10.1109/TMI.2016.2528120
|g Vol. 35, no. 5, p. 1313 - 1321
|0 PERI:(DE-600)2068206-2
|n 5
|q 35:5<1313 - 1321
|p 1313-1321
|t IEEE transactions on medical imaging
|v 35
|y 2016
|x 0278-0062
909 C O |p VDB
|o oai:pub.dzne.de:138551
910 1 _ |a Deutsches Zentrum für Neurodegenerative Erkrankungen
|0 I:(DE-588)1065079516
|k DZNE
|b 0
|6 P:(DE-2719)2810881
913 1 _ |a DE-HGF
|b Forschungsbereich Gesundheit
|l Erkrankungen des Nervensystems
|1 G:(DE-HGF)POF3-340
|0 G:(DE-HGF)POF3-341
|2 G:(DE-HGF)POF3-300
|v Molecular Signaling
|x 0
914 1 _ |y 2016
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
915 _ _ |a JCR
|0 StatID:(DE-HGF)0100
|2 StatID
|b IEEE T MED IMAGING : 2017
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0600
|2 StatID
|b Ebsco Academic Search
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b ASC
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Clarivate Analytics Master Journal List
915 _ _ |a WoS
|0 StatID:(DE-HGF)0110
|2 StatID
|b Science Citation Index
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
915 _ _ |a WoS
|0 StatID:(DE-HGF)0111
|2 StatID
|b Science Citation Index Expanded
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1110
|2 StatID
|b Current Contents - Clinical Medicine
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1160
|2 StatID
|b Current Contents - Engineering, Computing and Technology
915 _ _ |a IF >= 5
|0 StatID:(DE-HGF)9905
|2 StatID
|b IEEE T MED IMAGING : 2017
920 1 _ |0 I:(DE-2719)1013012
|k AG Alamoudi
|l Cryo-electron microscopy and tomography
|x 0
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a I:(DE-2719)1013012
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21