EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL‐Based Cortical Thickness Estimates

Timo Blattner iD, David Romascano iD, Richard McKinley iD, Michael Rebsamen iD, Anke Salmen iD, Maximilian Pistor iD, Robert Hoepner iD, Roland Wiest iD, Piotr Radojewski iD, Christian Rummel iD, Milena Capiglioni iD

Human Brain Mapping · 01.06.2026 · 47 (8)

DOI: 10.1002/hbm.70560 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Human Brain Mapping, online erschienen am 07.06.2026. Verfasst von Timo Blattner und 10 weiteren Autor:innen. Beteiligte Einrichtung: Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspita…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning, Cerebral Cortex, Multiple Sclerosis, Relapsing-Remitting. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cortical thickness measurements from MRI are increasingly used as biomarkers for neurodegenerative disease progression. However, variations in MRI acquisition parameters, such as inversion time (TI) and repetition time (TR), which are common in clinical settings, can compromise the reliability and sensitivity of these measurements. We fine‐tuned a deep‐learning‐based segmentation tool (DL+DiReCT) to reduce its dependence to image contrast variations by training it on simulated MPRAGE images derived from quantitative relaxation maps. Fine‐tuning markedly reduced contrast sensitivity, with the Pearson correlation coefficient decreasing from to . Evaluation on a synthetic atrophy dataset demonstrated that our model accurately replicated atrophy trends with minimal underestimation, outperforming FreeSurfer and SynthSeg. When applied to a dataset of relapsing–remitting multiple sclerosis (RRMS) patients, the fine‐tuned model showed a substantial reduction in contrast sensitivity and maintained stable performance after controlling for covariates such as age, sex, field strength, and Expanded Disability Status Scale (EDSS) score. Overall, the proposed approach achieves robust contrast invariance without sacrificing sensitivity to cortical atrophy, offering a practical improvement for longitudinal and multi‐center clinical studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingDeep LearningCerebral CortexMultiple Sclerosis, Relapsing-RemittingImage Processing, Computer-AssistedNeuroimagingBrain Cortical ThicknessHumansFemaleMaleAdultMiddle AgedAtrophy

Stichwörter der Autor:innen

MRbrain morphometrycontrastcortical thicknessdeep learningmultiple sclerosisrobustness

Autor:innen und Institutionen

  • Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.
  • Balgrist University Hospital, Zurich, Switzerland.
  • Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland.
  • Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, Sitem-Insel, Bern, Switzerland.
  • European Campus Rottal-Inn, Technische Hochschule Deggendorf, Pfarrkirchen, Germany.
  • High-Field MR Center, Max Planck Institute for Biological Cybernetics, Tübingen, Germany.

ORCID-Profile: Timo Blattner, David Romascano, Richard McKinley, Michael Rebsamen, Anke Salmen, Maximilian Pistor, Robert Hoepner, Roland Wiest, Piotr Radojewski, Christian Rummel, Milena Capiglioni

Förderung

  • Wellcome Trust
  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Zitieren

APA

Blattner, T., Romascano, D., McKinley, R., Rebsamen, M., Salmen, A., Pistor, M., Hoepner, R., Wiest, R., Radojewski, P., Rummel, C., & Capiglioni, M. (2026). Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL‐Based Cortical Thickness Estimates. Human Brain Mapping, 47(8). https://doi.org/10.1002/hbm.70560

Vancouver

Blattner T, Romascano D, McKinley R, Rebsamen M, Salmen A, Pistor M, et al. Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL‐Based Cortical Thickness Estimates. Human Brain Mapping. 2026;47(8). doi:10.1002/hbm.70560

BibTeX
@article{Blattner2026,
  author = {Blattner, Timo and Romascano, David and McKinley, Richard and Rebsamen, Michael and Salmen, Anke and Pistor, Maximilian and Hoepner, Robert and Wiest, Roland and Radojewski, Piotr and Rummel, Christian and Capiglioni, Milena},
  title = {Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL‐Based Cortical Thickness Estimates},
  journal = {Human Brain Mapping},
  year = {2026},
  volume = {47},
  number = {8},
  doi = {10.1002/hbm.70560}
}
Kostenlos starten →