% 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{EstradaLeon:162724,
      author       = {Estrada Leon, Edgar Santiago and Lu, Ran and Diers, Kersten
                      and Zeng, Weiyi and Ehses, Philipp and Stöcker, Tony and
                      Breteler, Monique and Reuter, Martin},
      title        = {{A}utomated olfactory bulb segmentation on high
                      resolutional {T}2-weighted {MRI}.},
      journal      = {NeuroImage},
      volume       = {242},
      issn         = {1053-8119},
      address      = {Orlando, Fla.},
      publisher    = {Academic Press},
      reportid     = {DZNE-2021-01381},
      pages        = {118464},
      year         = {2021},
      note         = {CC BY},
      abstract     = {The neuroimage analysis community has neglected the
                      automated segmentation of the olfactory bulb (OB) despite
                      its crucial role in olfactory function. The lack of an
                      automatic processing method for the OB can be explained by
                      its challenging properties (small size, location, and poor
                      visibility on traditional MRI scans). Nonetheless, recent
                      advances in MRI acquisition techniques and resolution have
                      allowed raters to generate more reliable manual annotations.
                      Furthermore, the high accuracy of deep learning methods for
                      solving semantic segmentation problems provides us with an
                      option to reliably assess even small structures. In this
                      work, we introduce a novel, fast, and fully automated deep
                      learning pipeline to accurately segment OB tissue on
                      sub-millimeter T2-weighted (T2w) whole-brain MR images. To
                      this end, we designed a three-stage pipeline: (1)
                      Localization of a region containing both OBs using
                      FastSurferCNN, (2) Segmentation of OB tissue within the
                      localized region through four independent AttFastSurferCNN -
                      a novel deep learning architecture with a self-attention
                      mechanism to improve modeling of contextual information, and
                      (3) Ensemble of the predicted label maps. For this work,
                      both OBs were manually annotated in a total of 620 T2w
                      images for training (n=357) and testing. The OB pipeline
                      exhibits high performance in terms of boundary delineation,
                      OB localization, and volume estimation across a wide range
                      of ages in 203 participants of the Rhineland Study (Dice
                      Score (Dice): 0.852, Volume Similarity (VS): 0.910, and
                      Average Hausdorff Distance (AVD): 0.215 mm). Moreover, it
                      also generalizes to scans of an independent dataset never
                      encountered during training, the Human Connectome
                      Project (HCP), with different acquisition parameters and
                      demographics, evaluated in 30 cases at the native 0.7 mm
                      HCP resolution (Dice: 0.738, VS: 0.790, and AVD: 0.340 mm),
                      and the default 0.8 mm pipeline resolution (Dice: 0.782,
                      VS: 0.858, and AVD: 0.268 mm). We extensively validated our
                      pipeline not only with respect to segmentation accuracy but
                      also to known OB volume effects, where it can sensitively
                      replicate age effects (β=-0.232, p<.01). Furthermore, our
                      method can analyze a 3D volume in less than a minute (GPU)
                      in an end-to-end fashion, providing a validated, efficient,
                      and scalable solution for automatically assessing OB
                      volumes.},
      keywords     = {Adult / Aged / Deep Learning / Female / Humans / Image
                      Processing, Computer-Assisted: methods / Magnetic Resonance
                      Imaging: methods / Male / Middle Aged / Neural Networks,
                      Computer / Olfactory Bulb: diagnostic imaging /
                      Convolutional neural networks (Other) / Deep learning
                      (Other) / Olfactory bulb (Other) / Semantic segmentation
                      (Other)},
      cin          = {AG Breteler / AG Reuter / AG Stöcker},
      ddc          = {610},
      cid          = {I:(DE-2719)1012001 / I:(DE-2719)1040310 /
                      I:(DE-2719)1013026},
      pnm          = {354 - Disease Prevention and Healthy Aging (POF4-354)},
      pid          = {G:(DE-HGF)POF4-354},
      experiment   = {EXP:(DE-2719)Rhineland Study-20190321},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:34389442},
      pmc          = {pmc:PMC8473894},
      doi          = {10.1016/j.neuroimage.2021.118464},
      url          = {https://pub.dzne.de/record/162724},
}