EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Towards an Informed Choice of Diffusion MRI Image Contrasts for Cerebellar Segmentation

Jon Haitz Legarreta iD, Zhou Lan, Yuqian Chen iD, Fan Zhang iD, Edward H Yeterian, Nikos Makris, Richard J Rushmore, Yogesh Rathi iD, Lauren J O'Donnell iD

Human Brain Mapping · 2025

DOI: 10.1002/hbm.70317 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Human Brain Mapping, 2025. Verfasst von Jon Haitz Legarreta und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Brigham and Women's Hospital, Mass General Brigham, Boston, Massachusetts, USA. Hauptthemen laut MEDLINE: Cerebellum, Diffusion Magnetic Resonance Imaging, Image Processing, Computer-Assisted, White Matter. Die Arbeit nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIMH NIH HHS, National Institutes of Health (NIH), NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The fine‐grained segmentation of cerebellar structures is an essential step towards supplying increasingly accurate anatomically informed analyses, including, for example, white matter diffusion magnetic resonance imaging (MRI) tractography. Cerebellar tissue segmentation is typically performed on structural MRI data, such as T1‐weighted data, while connectivity between segmented regions is mapped using diffusion MRI tractography data. Small deviations in structural to diffusion MRI data co‐registration may negatively impact connectivity analyses. Reliable segmentation of brain tissue performed directly on diffusion MRI data helps to circumvent such inaccuracies. Diffusion MRI enables the computation of many image contrasts, including a variety of tissue microstructure maps. While multiple methods have been proposed for the segmentation of cerebellar structures using diffusion MRI, little attention has been paid to the systematic evaluation of the performance of different available input image contrasts for the segmentation task. In this work, we evaluate and compare the segmentation performance of diffusion MRI‐derived contrasts on the cerebellar segmentation task. Specifically, we include spherical mean (diffusion‐weighted image average) and b0 (non‐diffusion‐weighted image average) contrasts, local signal parameterization contrasts (diffusion tensor and kurtosis fit maps), and the structural T1‐weighted MRI contrast that is most commonly employed for the task. We train a popular deep‐learning architecture using a publicly available dataset (HCP‐YA) on a set of cerebellar white and gray matter region labels obtained from the atlas‐based SUIT cerebellar segmentation pipeline employing T1‐weighted data. By training and testing using many diffusion‐MRI‐derived image inputs, we find that the spherical mean image computed from b = 1000 s/mm 2 shell data provides stable performance across different metrics and significantly outperforms the tissue microstructure contrasts that are traditionally used in machine learning segmentation methods for diffusion MRI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CerebellumDiffusion Magnetic Resonance ImagingImage Processing, Computer-AssistedWhite MatterNeuroimagingDiffusion Tensor ImagingHumansAdultMaleFemaleYoung Adult

Stichwörter der Autor:innen

cerebellumdeep learningdiffusion MRIsegmentation

Autor:innen und Institutionen

  • Department of Radiology, Brigham and Women's Hospital, Mass General Brigham, Boston, Massachusetts, USA.
  • Harvard Medical School, Boston, Massachusetts, USA.
  • Center for Clinical Investigation, Brigham and Women's Hospital, Mass General Brigham, Boston, Massachusetts, USA.
  • Department of Anatomy and Neurobiology, Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA.
  • Department of Psychology, Colby College, Waterville, Maine, USA.
  • Department of Psychiatry, Brigham and Women's Hospital, Mass General Brigham, Boston, Massachusetts, USA.

ORCID-Profile: Jon Haitz Legarreta, Yuqian Chen, Fan Zhang, Yogesh Rathi, Lauren J O'Donnell

Förderung

  • NIMH NIH HHS
  • National Institutes of Health (NIH)
  • NINDS NIH HHS

Zitieren

APA

Legarreta, J. H., Lan, Z., Chen, Y., Zhang, F., Yeterian, E. H., Makris, N., Rushmore, R. J., Rathi, Y., & O'Donnell, L. J. (2025). Towards an Informed Choice of Diffusion MRI Image Contrasts for Cerebellar Segmentation. Human Brain Mapping. https://doi.org/10.1002/hbm.70317

Vancouver

Legarreta JH, Lan Z, Chen Y, Zhang F, Yeterian EH, Makris N, et al. Towards an Informed Choice of Diffusion MRI Image Contrasts for Cerebellar Segmentation. Human Brain Mapping. 2025. doi:10.1002/hbm.70317

BibTeX
@article{Legarreta2025,
  author = {Legarreta, Jon Haitz and Lan, Zhou and Chen, Yuqian and Zhang, Fan and Yeterian, Edward H and Makris, Nikos and Rushmore, Richard J and Rathi, Yogesh and O'Donnell, Lauren J},
  title = {Towards an Informed Choice of Diffusion MRI Image Contrasts for Cerebellar Segmentation},
  journal = {Human Brain Mapping},
  year = {2025},
  doi = {10.1002/hbm.70317}
}
Kostenlos starten →