EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets

Benjamin Billot iD, Colin Magdamo, You Cheng, Steven E Arnold iD, Sudeshna Das iD, Juan Eugenio Iglesias

Proceedings of the National Academy of Sciences · 28.02.2023 · 120 (9)

DOI: 10.1073/pnas.2216399120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 21.02.2023. Verfasst von Benjamin Billot und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Medical Image Computing, University College London, London WC1V 6LJ, UK. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Neuroimaging. Die Arbeit wurde bisher 267-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EC | European Research Council (ERC), UKRI | EPSRC | EPSRC Centre for Doctoral Training in Medical Imaging (EPSRC CDT in Medical Imaging), Alzheimer's Research UK (ARUK).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Every year, millions of brain MRI scans are acquired in hospitals, which is a figure considerably larger than the size of any research dataset. Therefore, the ability to analyze such scans could transform neuroimaging research. Yet, their potential remains untapped since no automated algorithm is robust enough to cope with the high variability in clinical acquisitions (MR contrasts, resolutions, orientations, artifacts, and subject populations). Here, we present SynthSeg + , an AI segmentation suite that enables robust analysis of heterogeneous clinical datasets. In addition to whole-brain segmentation, SynthSeg + also performs cortical parcellation, intracranial volume estimation, and automated detection of faulty segmentations (mainly caused by scans of very low quality). We demonstrate SynthSeg + in seven experiments, including an aging study on 14,000 scans, where it accurately replicates atrophy patterns observed on data of much higher quality. SynthSeg + is publicly released as a ready-to-use tool to unlock the potential of quantitative morphometry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingNeuroimagingMachine LearningBrainAlgorithmsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

clinical brain MRIdeep learningdomain-agnosticsegmentation

Autor:innen und Institutionen

  • Centre for Medical Image Computing, University College London, London WC1V 6LJ, UK.
  • Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114.
  • Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Cambridge, MA 02129.
  • Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02138.

ORCID-Profile: Benjamin Billot, Steven E Arnold, Sudeshna Das

Förderung

  • EC | European Research Council (ERC)
  • UKRI | EPSRC | EPSRC Centre for Doctoral Training in Medical Imaging (EPSRC CDT in Medical Imaging)
  • Alzheimer's Research UK (ARUK)
  • NIA NIH HHS
  • HHS | NIH | National Institute on Aging (NIA)

Zitieren

APA

Billot, B., Magdamo, C., Cheng, Y., Arnold, S. E., Das, S., & Iglesias, J. E. (2023). Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets. Proceedings of the National Academy of Sciences, 120(9). https://doi.org/10.1073/pnas.2216399120

Vancouver

Billot B, Magdamo C, Cheng Y, Arnold SE, Das S, Iglesias JE. Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets. Proceedings of the National Academy of Sciences. 2023;120(9). doi:10.1073/pnas.2216399120

BibTeX
@article{Billot2023,
  author = {Billot, Benjamin and Magdamo, Colin and Cheng, You and Arnold, Steven E and Das, Sudeshna and Iglesias, Juan Eugenio},
  title = {Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2023},
  volume = {120},
  number = {9},
  doi = {10.1073/pnas.2216399120}
}
Kostenlos starten →