% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Albarqouni:138551,
      author       = {Albarqouni, Shadi and Baur, Christoph and Achilles, Felix
                      and Belagiannis, Vasileios and Demirci, Stefanie and Navab,
                      Nassir},
      title        = {{A}gg{N}et: {D}eep {L}earning {F}rom {C}rowds for {M}itosis
                      {D}etection in {B}reast {C}ancer {H}istology {I}mages.},
      journal      = {IEEE transactions on medical imaging},
      volume       = {35},
      number       = {5},
      issn         = {0278-0062},
      address      = {New York, NY},
      publisher    = {IEEE},
      reportid     = {DZNE-2020-04873},
      pages        = {1313-1321},
      year         = {2016},
      abstract     = {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.},
      keywords     = {Breast Neoplasms: diagnostic imaging / Crowdsourcing:
                      methods / Female / Histocytochemistry / Humans / Image
                      Interpretation, Computer-Assisted: methods / Internet /
                      Machine Learning / Mitosis: physiology / Neural Networks,
                      Computer / Video Games},
      cin          = {AG Alamoudi},
      ddc          = {620},
      cid          = {I:(DE-2719)1013012},
      pnm          = {341 - Molecular Signaling (POF3-341)},
      pid          = {G:(DE-HGF)POF3-341},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:26891484},
      doi          = {10.1109/TMI.2016.2528120},
      url          = {https://pub.dzne.de/record/138551},
}