Automated Deep Learning-based Segmentation of the Dentate Nucleus Using Quantitative Susceptibility Mapping MRI.

Journal: Radiology. Artificial intelligence
Published Date: Aug 6, 2025

Abstract

Purpose To develop a dentate nucleus (DN) segmentation tool using deep learning (DL) applied to brain MRI-based quantitative susceptibility mapping (QSM) images. Materials and Methods Brain QSM images from healthy controls and individuals with cerebellar ataxia or multiple sclerosis were collected from nine different datasets (2016-2023) worldwide for this retrospective study (ClinicalTrials.gov Identifier: NCT04349514). Manual delineation of the DN was performed by experienced raters. Automated segmentation performance was evaluated against manual reference segmentations following training with several DL architectures. A two-step approach was used, consisting of a localization model followed by DN segmentation. Performance metrics included intraclass correlation coefficient (ICC), Dice score, and Pearson correlation coefficient. Results The training and testing datasets comprised 328 individuals (age range, 11-64 years; 171 female), including 141 healthy individuals and 187 with cerebellar ataxia or multiple sclerosis. The manual tracing protocol produced reference standards with high intrarater (average ICC 0.91) and interrater reliability (average ICC 0.78). Initial DL architecture exploration indicated that the nnU-Net framework performed best. The two-step localization plus segmentation pipeline achieved a Dice score of 0.90 ± 0.03 and 0.89 ± 0.04 for left and right DN segmentation, respectively. In external testing, the proposed algorithm outperformed the current leading automated tool (mean Dice scores for left and right DN: 0.86 ± 0.04 vs 0.57 ± 0.22, < .001; 0.84 ± 0.07 vs 0.58 ± 0.24, < .001). The model demonstrated generalizability across datasets unseen during the training step, with automated segmentations showing high correlation with manual annotations (left DN: r = 0.74; < .001; right DN: r = 0.48; = .03). Conclusion The proposed model accurately and efficiently segmented the DN from brain QSM images. The model is publicly available (https://github.com/art2mri/DentateSeg). ©RSNA, 2025.

Authors

  • Diogo H Shiraishi
    Department of Neurology, School of Medical Sciences, University of Campinas (Unicamp), Rua Vital Brasil, 89-99, Cidade Universitária "Zeferino Vaz", Campinas, São Paulo, Brazil 13083-888.
  • Susmita Saha
    IBM Research - Australia, 204 Lygon Street, 3053 Carlton, VIC, Australia.
  • Isaac M Adanyeguh
    Center for Magnetic Resonance Research, Department of Radiology, University of Minnesota, Minneapolis, Minn.
  • Sirio Cocozza
    Department of Advanced Biomedical Sciences, University of Naples "Federico II," Via Pansini 5, 80131 Naples, Italy.
  • Louise A Corben
  • Andreas Deistung
    Medical Physics Group, Institute for Diagnostic and Interventional Radiology, University Hospital Jena, Jena, Germany; Department of Neurology, Essen University Hospital, University of Duisburg-Essen, Essen, Germany.
  • Martin B Delatycki
  • Imis Dogan
    Department of Neurology, RWTH Aachen University, Aachen, Germany.
  • William Gaetz
    Department of Radiology, Children's Hospital of Philadelphia, Philadelphia, Pa.
  • Nellie Georgiou-Karistianis
    Turner Institute for Brain and Mental Health, Monash University, Clayton VIC3800, Australia. Electronic address: nellie.georgiou-karistianis@monash.edu.
  • Simon Graf
    University Clinic and Outpatient Clinic for Radiology, Department for Radiation Medicine, University Hospital Halle (Saale), University Medicine Halle, Halle (Saale), Germany.
  • Marina Grisoli
    Department of Neuroradiology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy.
  • Pierre-Gilles Henry
    Center for Magnetic Resonance Research, Department of Radiology, University of Minnesota, Minneapolis, Minn.
  • Gustavo M Jarola
    Department of Neurology, School of Medical Sciences, University of Campinas (Unicamp), Rua Vital Brasil, 89-99, Cidade Universitária "Zeferino Vaz", Campinas, São Paulo, Brazil 13083-888.
  • James M Joers
    Center for Magnetic Resonance Research, Department of Radiology, University of Minnesota, Minneapolis, MN, USA.
  • Christian Langkammer
    Department of Neurology, Medical University of Graz, Auenbruggerplatz 22, 8036 Graz, Austria.
  • Christophe Lenglet
  • Jiakun Li
    Department of Urology and Institutes for Systems Genetics, Frontiers Science Center for Disease-related Molecular Network, West China Hospital, Sichuan University, No. 37, Guoxue Alley, Chengdu, 610212, China.
  • Camila C Lobo
    Department of Neurology, School of Medical Sciences, University of Campinas (Unicamp), Rua Vital Brasil, 89-99, Cidade Universitária "Zeferino Vaz", Campinas, São Paulo, Brazil 13083-888.
  • Eric F Lock
    Division of Biostatistics, School of Public Health, University of Minnesota, Minneapolis, MN 55455, USA.
  • David R Lynch
    Department of Neurology, Children's Hospital of Philadelphia, Philadelphia, Pa.
  • Thomas H Mareci
    Department of Biochemistry and Molecular Biology, University of Florida, Gainesville, Fla.
  • Alberto R M Martinez
    Department of Neurology, School of Medical Sciences, University of Campinas (Unicamp), Rua Vital Brasil, 89-99, Cidade Universitária "Zeferino Vaz", Campinas, São Paulo, Brazil 13083-888.
  • Serena Monti
    Institute of Biostructures and Bioimaging, Italian National Research Council, Naples, Italy.
  • Anna Nigri
    Department of Neuroradiology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy.
  • Massimo Pandolfo
    Department of Neurology and Neurosurgery, McGill University, Montreal, Canada.
  • Kathrin Reetz
    Department of Neurology, RWTH Aachen University, Germany; JARA-Brain Institute Molecular Neuroscience and Neuroimaging, Forschungszentrum Jülich, Germany.
  • Timothy P Roberts
    Department of Radiology, Children's Hospital of Philadelphia, Philadelphia, Pa.
  • Sandro Romanzetti
    Department of Neurology, RWTH Aachen University, Germany.
  • David A Rudko
    Department of Neurology and Neurosurgery, McGill University, Montreal, Canada.
  • Alessandra Scaravilli
    Department of Advanced Biomedical Sciences, University "Federico II", Naples, Italy.
  • Jörg B Schulz
    Department of Neurology, RWTH Aachen University, Aachen, Germany.
  • S H Subramony
    Department of Neurology and the Fixel Institute for Neurological Diseases, University of Florida, Gainesville, Fla.
  • Dagmar Timmann
    Department of Neurology, Essen University Hospital, University of Duisburg-Essen, Essen, Germany.
  • Marcondes C França
    Department of Neurology, School of Medical Sciences, University of Campinas (Unicamp), Rua Vital Brasil, 89-99, Cidade Universitária "Zeferino Vaz", Campinas, São Paulo, Brazil 13083-888.
  • Ian H Harding
    Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Australia.
  • Thiago J R Rezende
    Department of Neurology, School of Medical Sciences, University of Campinas (Unicamp), Rua Vital Brasil, 89-99, Cidade Universitária "Zeferino Vaz", Campinas, São Paulo, Brazil 13083-888.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals