% 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{Gaubert:195012,
      author       = {Gaubert, Malo and Dell Orco, Andrea and Lange, Catharina
                      and Garnier-Crussard, Antoine and Zimmermann, Isabella and
                      Dyrba, Martin and Duering, Marco and Ziegler, Gabriel and
                      Peters, Oliver and Preis, Lukas and Priller, Josef and
                      Spruth, Eike Jakob and Schneider, Anja and Fliessbach, Klaus
                      and Wiltfang, Jens and Schott, Björn H. and Maier,
                      Franziska and Glanz, Wenzel and Buerger, Katharina and
                      Janowitz, Daniel and Perneczky, Robert and Rauchmann,
                      Boris-Stephan and Teipel, Stefan and Kilimann, Ingo and
                      Laske, Christoph and Munk, Matthias H. and Spottke, Annika
                      and Roy, Nina and Dobisch, Laura and Ewers, Michael and
                      Dechent, Peter and Haynes, John Dylan and Scheffler, Klaus
                      and Düzel, Emrah and Jessen, Frank and Wirth, Miranka},
      title        = {{P}erformance evaluation of automated white matter
                      hyperintensity segmentation algorithms in a multicenter
                      cohort on cognitive impairment and dementia},
      journal      = {Frontiers in psychiatry},
      volume       = {13},
      issn         = {1664-0640},
      address      = {Lausanne},
      publisher    = {Frontiers Research Foundation},
      reportid     = {DZNE-2023-00191},
      pages        = {1010273},
      year         = {2023},
      note         = {The DELCODE study was funded by the German Center for
                      Neurodegenerative Diseases (reference no. BN012). The
                      DELCODE study was supported by the Max-Delbrück-centrum
                      für Molekulare Medizin in der Helmholtz-Gemeinschaft (MDC),
                      Freie Universität Berlin Center for Cognitive Neuroscience
                      Berlin (CCNB), Nuklearmedizin und Klinische Molekulare
                      Bildgebung—Univeristätsklinikum Tübingen Bernstein
                      Center für Computional Neuroscience Berlin,
                      Universitätsmedizin Göttingen Core Facility MR-Research
                      Göttingen, Institut für Klinische Radiologie Klinikum der
                      Universität München, and Universitätsklinikum Tübingen
                      MR-Forschungszentrum.},
      abstract     = {White matter hyperintensities (WMH), a biomarker of small
                      vessel disease, are often found in Alzheimer's disease (AD)
                      and their advanced detection and quantification can be
                      beneficial for research and clinical applications. To
                      investigate WMH in large-scale multicenter studies on
                      cognitive impairment and AD, appropriate automated WMH
                      segmentation algorithms are required. This study aimed to
                      compare the performance of segmentation tools and provide
                      information on their application in multicenter research.We
                      used a pseudo-randomly selected dataset (n = 50) from the
                      DZNE-multicenter observational Longitudinal Cognitive
                      Impairment and Dementia Study (DELCODE) that included 3D
                      fluid-attenuated inversion recovery (FLAIR) images from
                      participants across the cognitive continuum. Performances of
                      top-rated algorithms for automated WMH segmentation [Brain
                      Intensity Abnormality Classification Algorithm (BIANCA),
                      lesion segmentation toolbox (LST), lesion growth algorithm
                      (LGA), LST lesion prediction algorithm (LPA), pgs, and
                      $sysu_media]$ were compared to manual reference segmentation
                      (RS).Across tools, segmentation performance was moderate for
                      global WMH volume and number of detected lesions. After
                      retraining on a DELCODE subset, the deep learning algorithm
                      $sysu_media$ showed the highest performances with an average
                      Dice's coefficient of 0.702 (±0.109 SD) for volume and a
                      mean F1-score of 0.642 (±0.109 SD) for the number of
                      lesions. The intra-class correlation was excellent for all
                      algorithms (>0.9) but BIANCA (0.835). Performance improved
                      with high WMH burden and varied across brain regions.To
                      conclude, the deep learning algorithm, when retrained,
                      performed well in the multicenter context. Nevertheless, the
                      performance was close to traditional methods. We provide
                      methodological recommendations for future studies using
                      automated WMH segmentation to quantify and assess WMH along
                      the continuum of cognitive impairment and AD dementia.},
      keywords     = {Alzheimer’s disease (Other) / Alzheimer’s disease
                      (Other) / FLAIR (Other) / aging (Other) / deep learning
                      (Other) / evaluation (Other) / white matter hyperintensities
                      segmentation (Other)},
      cin          = {AG Wirth / AG Donix / AG Düzel / AG Teipel / AG Dirnagl /
                      AG Priller / AG Endres / AG Schneider / Patient Studies Bonn
                      / AG Wiltfang / AG Fischer / AG Jessen / AG Dichgans /
                      Clinical Research Platform (CRP) / AG Simons / Delcode},
      ddc          = {610},
      cid          = {I:(DE-2719)1710011 / I:(DE-2719)1710008 /
                      I:(DE-2719)5000006 / I:(DE-2719)1510100 / I:(DE-2719)1810002
                      / I:(DE-2719)5000007 / I:(DE-2719)1811005 /
                      I:(DE-2719)1011305 / I:(DE-2719)1011101 / I:(DE-2719)1410006
                      / I:(DE-2719)1410002 / I:(DE-2719)1011102 /
                      I:(DE-2719)5000022 / I:(DE-2719)1011401 / I:(DE-2719)1110008
                      / I:(DE-2719)5000034},
      pnm          = {353 - Clinical and Health Care Research (POF4-353) / 352 -
                      Disease Mechanisms (POF4-352) / 351 - Brain Function
                      (POF4-351)},
      pid          = {G:(DE-HGF)POF4-353 / G:(DE-HGF)POF4-352 /
                      G:(DE-HGF)POF4-351},
      experiment   = {EXP:(DE-2719)DELCODE-20140101},
      typ          = {PUB:(DE-HGF)16},
      pmc          = {pmc:PMC9877422},
      pubmed       = {pmid:36713907},
      doi          = {10.3389/fpsyt.2022.1010273},
      url          = {https://pub.dzne.de/record/195012},
}