% 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{Upschulte:892373,
      author       = {Upschulte, Eric and Harmeling, Stefan and Amunts, Katrin
                      and Dickscheid, Timo},
      title        = {{C}ontour {P}roposal {N}etworks for {B}iomedical {I}nstance
                      {S}egmentation},
      journal      = {Medical image analysis},
      issn         = {1361-8415},
      address      = {Amsterdam [u.a.]},
      publisher    = {Elsevier Science},
      reportid     = {FZJ-2021-02034},
      pages        = {102371 -},
      year         = {2022},
      abstract     = {We present a conceptually simple framework for object
                      instance segmentation called Contour Proposal Network (CPN),
                      which detects possibly overlapping objects in an image while
                      simultaneously fitting closed object contours using an
                      interpretable, fixed-sized representation based on Fourier
                      Descriptors. The CPN can incorporate state of the art object
                      detection architectures as backbone networks into a
                      single-stage instance segmentation model that can be trained
                      end-to-end. We construct CPN models with different backbone
                      networks, and apply them to instance segmentation of cells
                      in datasets from different modalities. In our experiments,
                      we show CPNs that outperform U-Nets and Mask R-CNNs in
                      instance segmentation accuracy, and present variants with
                      execution times suitable for real-time applications. The
                      trained models generalize well across different domains of
                      cell types. Since the main assumption of the framework are
                      closed object contours, it is applicable to a wide range of
                      detection problems also outside the biomedical domain. An
                      implementation of the model architecture in PyTorch is
                      freely available.},
      cin          = {INM-1},
      ddc          = {610},
      cid          = {I:(DE-Juel1)INM-1-20090406},
      pnm          = {525 - Decoding Brain Organization and Dysfunction
                      (POF4-525) / JL SMHB - Joint Lab Supercomputing and Modeling
                      for the Human Brain (JL SMHB-2021-2027) / HIBALL - Helmholtz
                      International BigBrain Analytics and Learning Laboratory
                      (HIBALL) (InterLabs-0015) / HBP SGA3 - Human Brain Project
                      Specific Grant Agreement 3 (945539) / Helmholtz AI -
                      Helmholtz Artificial Intelligence Coordination Unit –
                      Local Unit FZJ (E.40401.62)},
      pid          = {G:(DE-HGF)POF4-525 / G:(DE-Juel1)JL SMHB-2021-2027 /
                      G:(DE-HGF)InterLabs-0015 / G:(EU-Grant)945539 /
                      G:(DE-Juel-1)E.40401.62},
      typ          = {PUB:(DE-HGF)25},
      eprint       = {2104.03393},
      howpublished = {arXiv:2104.03393},
      archivePrefix = {arXiv},
      SLACcitation = {$\%\%CITATION$ = $arXiv:2104.03393;\%\%$},
      url          = {https://juser.fz-juelich.de/record/892373},
}