% 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{Szustakowski:281112,
      author       = {Szustakowski, Karol and Frank, Luk and Esser, Julia and
                      Gründemann, Jan and Piraud, Marie},
      title        = {{P}reserving instance continuity and length in segmentation
                      through connectivity-aware loss computation},
      publisher    = {arXiv},
      reportid     = {DZNE-2025-01073},
      year         = {2025},
      abstract     = {In many biomedical segmentation tasks, the preservation of
                      elongated structure continuity and length is more important
                      than voxel-wise accuracy. We propose two novel loss
                      functions, Negative Centerline Loss and Simplified Topology
                      Loss, that, applied to Convolutional Neural Networks (CNNs),
                      help preserve connectivity of output instances. Moreover, we
                      discuss characteristics of experiment design, such as
                      downscaling and spacing correction, that help obtain
                      continuous segmentation masks. We evaluate our approach on a
                      3D light-sheet fluorescence microscopy dataset of axon
                      initial segments (AIS), a task prone to discontinuity due to
                      signal dropout. Compared to standard CNNs and existing
                      topology-aware losses, our methods reduce the number of
                      segmentation discontinuities per instance, particularly in
                      regions with missing input signal, resulting in improved
                      instance length calculation in downstream applications. Our
                      findings demonstrate that structural priors embedded in the
                      loss design can significantly enhance the reliability of
                      segmentation for biological applications.},
      keywords     = {Computer Vision and Pattern Recognition (cs.CV) (Other) /
                      FOS: Computer and information sciences (Other) / I.4.6;
                      I.2.10 (Other)},
      cin          = {AG Gründemann},
      cid          = {I:(DE-2719)5000069},
      pnm          = {351 - Brain Function (POF4-351) / Helmholtz AI - Helmholtz
                      Artificial Intelligence Coordination Unit – Local Unit FZJ
                      (E.40401.62) / Helmholtz AI Consultant Team FB Information
                      (E54.303.11)},
      pid          = {G:(DE-HGF)POF4-351 / G:(DE-Juel-1)E.40401.62 /
                      G:(DE-Juel-1)E54.303.11},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.48550/ARXIV.2509.03154},
      url          = {https://pub.dzne.de/record/281112},
}