% 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{Sardhara:1052293,
      author       = {Sardhara, Trushal and Dadsena, Ravi and Aydin, Roland C.
                      and Hilgers, Ralf-Dieter and Horn, Leon and Schulz, Jörg B.
                      and Reetz, Kathrin and Romanzetti, Sandro and Dogan, Imis
                      and Lischewski, Stella A. and Konrad, Kerstin and Pishnamaz,
                      Miguel and Praster, Maximillian and Clavel, Thomas and
                      Jankowski, Vera and Jankowski, Joachim and Pabst, Oliver and
                      Marx-Schütt, Katharina and Marx, Nikolaus and Möllmann,
                      Julia and Jacobsen, Malte and Dukart, Juergen and Eickhoff,
                      Simon},
      title        = {{D}eep learning-based 3{D} reconstruction of dentate nuclei
                      in {F}riedreich’s ataxia from {T}2*weighted {MR} images},
      journal      = {Machine learning with applications},
      volume       = {22},
      issn         = {2666-8270},
      address      = {Amsterdam},
      publisher    = {Elsevier},
      reportid     = {FZJ-2026-00910},
      pages        = {100790 -},
      year         = {2025},
      abstract     = {Dentate nucleus (DN) degeneration is a key
                      neuropathological feature in Friedreich’s ataxia (FRDA),
                      and its accurate quantification is critical for
                      understanding disease progression. However, its
                      visualization and volumetry require iron-sensitive imaging
                      techniques and time-consuming segmentation procedures,
                      posing challenges for conventional ML approaches due to
                      small datasets typical of rare diseases. We present a
                      transfer learning–based machine learning pipeline for
                      automated DN segmentation that directly uses standard
                      T2*-weighted Magnetic Resonance Imaging (MRI), which
                      highlights the DN without additional processing, and is
                      designed to perform robustly with limited annotated data.
                      Using 38 manually labeled subjects (18 FRDA, 20 controls),
                      the model was validated via five-fold cross-validation and
                      an independent hold-out test set, achieving Dice scores of
                      0.81–0.87 and outperforming classical atlas-based methods.
                      Pretraining improved performance by $∼10\%$ in patients
                      and $>5\%$ in controls. Applied to 181 longitudinal scans
                      from 33 FRDA patients and 33 controls, the model revealed
                      significantly reduced DN volumes in FRDA, with reductions
                      correlating with disease duration and clinical severity over
                      time. Our approach provides a scalable and reproducible
                      segmentation framework, requiring minimal annotated data and
                      no preprocessing, while demonstrating robust performance
                      across cross-validation and independent testing.
                      Additionally, it enables the first longitudinal volumetric
                      analysis of DN in FRDA using standard T2*-weighted MRI,
                      demonstrating its practical utility for monitoring
                      neurodegenerative changes. Overall, this work illustrates
                      how transfer learning can overcome data scarcity in rare
                      diseases and provides a robust methodology for automated MRI
                      segmentation in both research and clinical applications.},
      cin          = {INM-7},
      ddc          = {004},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {5251 - Multilevel Brain Organization and Variability
                      (POF4-525)},
      pid          = {G:(DE-HGF)POF4-5251},
      typ          = {PUB:(DE-HGF)16},
      doi          = {10.1016/j.mlwa.2025.100790},
      url          = {https://juser.fz-juelich.de/record/1052293},
}