EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatic deep learning segmentation of the hippocampus on high‐resolution diffusion magnetic resonance imaging and its application to the healthy lifespan

Dylan Miller, Cory Efird, Kevin Grant Solar, Christian Beaulieu, Dana Cobzas

NMR in Biomedicine · 2024

DOI: 10.1002/nbm.5227 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NMR in Biomedicine, 2024. Verfasst von Dylan Miller und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada. Hauptthemen laut MEDLINE: Hippocampus, Deep Learning, Diffusion Magnetic Resonance Imaging. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council, Women and Children's Health Research Institute, University Hospital Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffusion tensor imaging (DTI) can provide unique contrast and insight into microstructural changes with age or disease of the hippocampus, although it is difficult to measure the hippocampus because of its comparatively small size, location, and shape. This has been markedly improved by the advent of a clinically feasible 1‐mm isotropic resolution 6‐min DTI protocol at 3 T of the hippocampus with limited brain coverage of 20 axial‐oblique slices aligned along its long axis. However, manual segmentation is too laborious for large population studies, and it cannot be automatically segmented directly on the diffusion images using traditional T 1 or T 2 image‐based methods because of the limited brain coverage and different contrast. An automatic method is proposed here that segments the hippocampus directly on high‐resolution diffusion images based on an extension of well‐known deep learning architectures like UNet and UNet++ by including additional dense residual connections. The method was trained on 100 healthy participants with previously performed manual segmentation on the 1‐mm DTI, then evaluated on typical healthy participants (n = 53), yielding an excellent voxel overlap with a Dice score of ~ 0.90 with manual segmentation; notably, this was comparable with the inter‐rater reliability of manually delineating the hippocampus on diffusion magnetic resonance imaging (MRI) (Dice score of 0.86). This method also generalized to a different DTI protocol with 36% fewer acquisitions. It was further validated by showing similar age trajectories of volumes, fractional anisotropy, and mean diffusivity from manual segmentations in one cohort (n = 153, age 5–74 years) with automatic segmentations from a second cohort without manual segmentations (n = 354, age 5–90 years). Automated high‐resolution diffusion MRI segmentation of the hippocampus will facilitate large cohort analyses and, in future research, needs to be evaluated on patient groups.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HippocampusDeep LearningDiffusion Magnetic Resonance ImagingHumansAdultMiddle AgedAgedMaleFemaleYoung AdultLongevityImage Processing, Computer-AssistedAutomationAged, 80 and overDiffusion Tensor ImagingAdolescent

Stichwörter der Autor:innen

automated segmentationconvolutional neural networkdeep learningdiffusion magnetic resonance imaginghippocampus

Autor:innen und Institutionen

  • Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada.
  • Department of Computer Science, MacEwan University, Edmonton, Alberta, Canada.
  • Department of Biomedical Engineering, Faculty of Medicine and Dentistry, University of Alberta, Edmonton, Alberta, Canada.
  • Department of Radiology and Diagnostic Imaging, Faculty of Medicine and Dentistry, University of Alberta, Edmonton, Alberta, Canada.

Förderung

  • Natural Sciences and Engineering Research Council
  • Women and Children's Health Research Institute
  • University Hospital Foundation
  • CIHR
  • Canada Research Chair (Tier 1) program
  • Canada Foundation for Innovation
  • Alberta Innovation and Advanced Education
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Miller, D., Efird, C., Solar, K. G., Beaulieu, C., & Cobzas, D. (2024). Automatic deep learning segmentation of the hippocampus on high‐resolution diffusion magnetic resonance imaging and its application to the healthy lifespan. NMR in Biomedicine. https://doi.org/10.1002/nbm.5227

Vancouver

Miller D, Efird C, Solar KG, Beaulieu C, Cobzas D. Automatic deep learning segmentation of the hippocampus on high‐resolution diffusion magnetic resonance imaging and its application to the healthy lifespan. NMR in Biomedicine. 2024. doi:10.1002/nbm.5227

BibTeX
@article{Miller2024,
  author = {Miller, Dylan and Efird, Cory and Solar, Kevin Grant and Beaulieu, Christian and Cobzas, Dana},
  title = {Automatic deep learning segmentation of the hippocampus on high‐resolution diffusion magnetic resonance imaging and its application to the healthy lifespan},
  journal = {NMR in Biomedicine},
  year = {2024},
  doi = {10.1002/nbm.5227}
}
Kostenlos starten →