TY  - JOUR
AU  - Sardhara, Trushal
AU  - Dadsena, Ravi
AU  - Aydin, Roland C.
AU  - Hilgers, Ralf-Dieter
AU  - Horn, Leon
AU  - Schulz, Jörg B.
AU  - Reetz, Kathrin
AU  - Romanzetti, Sandro
AU  - Dogan, Imis
AU  - Lischewski, Stella A.
AU  - Konrad, Kerstin
AU  - Pishnamaz, Miguel
AU  - Praster, Maximillian
AU  - Clavel, Thomas
AU  - Jankowski, Vera
AU  - Jankowski, Joachim
AU  - Pabst, Oliver
AU  - Marx-Schütt, Katharina
AU  - Marx, Nikolaus
AU  - Möllmann, Julia
AU  - Jacobsen, Malte
AU  - Dukart, Juergen
AU  - Eickhoff, Simon
TI  - Deep learning-based 3D reconstruction of dentate nuclei in Friedreich’s ataxia from T2*weighted MR images
JO  - Machine learning with applications
VL  - 22
SN  - 2666-8270
CY  - Amsterdam
PB  - Elsevier
M1  - FZJ-2026-00910
SP  - 100790 -
PY  - 2025
AB  - 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.
LB  - PUB:(DE-HGF)16
DO  - DOI:10.1016/j.mlwa.2025.100790
UR  - https://juser.fz-juelich.de/record/1052293
ER  -