% 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”.

@INPROCEEDINGS{Roy:280940,
      author       = {Roy, Saikat and Kügler, David and Reuter, Martin},
      title        = {{A}re 2.5{D} approaches superior to 3{D} deep networks in
                      whole brain segmentation?},
      volume       = {172},
      publisher    = {ML Research Press},
      reportid     = {DZNE-2025-01023},
      pages        = {988 - 1004},
      year         = {2022},
      comment      = {Proceedings of Machine Learning Research},
      booktitle     = {Proceedings of Machine Learning
                       Research},
      abstract     = {Segmentation of 3D volumes with a large number of labels,
                      small convoluted structures, and lack of contrast between
                      various structural boundaries is a difficult task. While
                      recent methodological advances across many segmentation
                      tasks are dominated by 3D architectures, currently the
                      strongest performing method for whole brain segmentation is
                      FastSurferCNN, a 2.5D approach. To shed light on the nuanced
                      differences between 2.5D and various 3D approaches, we
                      perform a thorough and fair comparison and suggest a
                      spatially-ensembled 3D architecture. Interestingly, we
                      observe training memory intensive 3D segmentation on
                      full-view images does not outperform the 2.5D approach. A
                      shift to training on patches even while evaluating on
                      full-view solves these limitations of both memory and
                      performance limitations at the same time. We demonstrate
                      significant performance improvements over state-of-the-art
                      3D methods on both Dice Similarity Coefficient and
                      especially average Hausdorff Distance measures across five
                      datasets. Finally, our validation across variations of
                      neurodegenerative disease states and scanner manufacturers,
                      shows we outperform the previously leading 2.5D approach
                      FastSurferCNN demonstrating robust segmentation performance
                      in realistic settings. Our code is available online at
                      github.com/Deep-MI/3d-neuro-seg.},
      month         = {Jul},
      date          = {2022-07-06},
      organization  = {5th International Conference on
                       Medical Imaging with Deep Learning,
                       Zurich (Switzerland), 6 Jul 2022 - 8
                       Jul 2022},
      cin          = {AG Reuter},
      cid          = {I:(DE-2719)1040310},
      pnm          = {354 - Disease Prevention and Healthy Aging (POF4-354)},
      pid          = {G:(DE-HGF)POF4-354},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      url          = {https://pub.dzne.de/record/280940},
}