% 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{Gotkowski:294877,
      author       = {K. Gotkowski$^*$ and C. Lüth$^*$ and P. F. Jäger$^*$ and
                      S. Ziegler$^*$ and L. Krämer$^*$ and S. Denner$^*$ and S.
                      Xiao$^*$ and N. Disch$^*$ and K. H. Maier-Hein$^*$ and F.
                      Isensee$^*$},
      title        = {{E}mbarrassingly {S}imple {S}cribble {S}upervision for 3{D}
                      {M}edical {S}egmentation},
      publisher    = {arXiv},
      reportid     = {DKFZ-2024-02587},
      year         = {2024},
      abstract     = {Traditionally, segmentation algorithms require dense
                      annotations for training, demanding significant annotation
                      efforts, particularly within the 3D medical imaging field.
                      Scribble-supervised learning emerges as a possible solution
                      to this challenge, promising a reduction in annotation
                      efforts when creating large-scale datasets. Recently, a
                      plethora of methods for optimized learning from scribbles
                      have been proposed, but have so far failed to position
                      scribble annotation as a beneficial alternative. We relate
                      this shortcoming to two major issues: 1) the complex nature
                      of many methods which deeply ties them to the underlying
                      segmentation model, thus preventing a migration to more
                      powerful state-of-the-art models as the field progresses and
                      2) the lack of a systematic evaluation to validate
                      consistent performance across the broader medical domain,
                      resulting in a lack of trust when applying these methods to
                      new segmentation problems. To address these issues, we
                      propose a comprehensive scribble supervision benchmark
                      consisting of seven datasets covering a diverse set of
                      anatomies and pathologies imaged with varying modalities. We
                      furthermore propose the systematic use of partial losses,
                      i.e. losses that are only computed on annotated voxels.
                      Contrary to most existing methods, these losses can be
                      seamlessly integrated into state-of-the-art segmentation
                      methods, enabling them to learn from scribble annotations
                      while preserving their original loss formulations. Our
                      evaluation using nnU-Net reveals that while most existing
                      methods suffer from a lack of generalization, the proposed
                      approach consistently delivers state-of-the-art performance.
                      Thanks to its simplicity, our approach presents an
                      embarrassingly simple yet effective solution to the
                      challenges of scribble supervision. Source code as well as
                      our extensive scribble benchmarking suite will be made
                      publicly available upon publication.},
      keywords     = {Computer Vision and Pattern Recognition (cs.CV) (Other) /
                      FOS: Computer and information sciences (Other)},
      cin          = {E230 / E290},
      cid          = {I:(DE-He78)E230-20160331 / I:(DE-He78)E290-20160331},
      pnm          = {315 - Bildgebung und Radioonkologie (POF4-315)},
      pid          = {G:(DE-HGF)POF4-315},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.48550/ARXIV.2403.12834},
      url          = {https://inrepo02.dkfz.de/record/294877},
}