EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Synthesizing images of tau pathology from cross-modal neuroimaging using deep learning

Jeyeon Lee iD, Brian J Burkett, Hoon-Ki Min, Matthew L Senjem, Ellen Dicks, Nick Corriveau-Lecavalier iD, Carly T Mester, Heather J Wiste, Emily S Lundt, Melissa E Murray iD, Aivi T Nguyen, Ross R Reichard und 12 weitere

Brain · 01.03.2024 · 147 (3) · 980-995

DOI: 10.1093/brain/awad346 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Brain, online erschienen am 07.10.2023. Verfasst von Jeyeon Lee und 23 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Deep Learning, Neuroimaging, Tauopathies. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 102 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Given the prevalence of dementia and the development of pathology-specific disease-modifying therapies, high-value biomarker strategies to inform medical decision-making are critical. In vivo tau-PET is an ideal target as a biomarker for Alzheimer’s disease diagnosis and treatment outcome measure. However, tau-PET is not currently widely accessible to patients compared to other neuroimaging methods. In this study, we present a convolutional neural network (CNN) model that imputes tau-PET images from more widely available cross-modality imaging inputs. Participants (n = 1192) with brain T1-weighted MRI (T1w), fluorodeoxyglucose (FDG)-PET, amyloid-PET and tau-PET were included. We found that a CNN model can impute tau-PET images with high accuracy, the highest being for the FDG-based model followed by amyloid-PET and T1w. In testing implications of artificial intelligence-imputed tau-PET, only the FDG-based model showed a significant improvement of performance in classifying tau positivity and diagnostic groups compared to the original input data, suggesting that application of the model could enhance the utility of the metabolic images. The interpretability experiment revealed that the FDG- and T1w-based models utilized the non-local input from physically remote regions of interest to estimate the tau-PET, but this was not the case for the Pittsburgh compound B-based model. This implies that the model can learn the distinct biological relationship between FDG-PET, T1w and tau-PET from the relationship between amyloid-PET and tau-PET. Our study suggests that extending neuroimaging’s use with artificial intelligence to predict protein specific pathologies has great potential to inform emerging care models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceDeep LearningNeuroimagingTauopathiesHumansAmyloidogenic ProteinsBiomarkersFluorodeoxyglucose F18

Stichwörter der Autor:innen

Alzheimer’s diseaseFDG PETcross-modality imputationdeep learningtau PET

Substanzen

Amyloidogenic ProteinsBiomarkersFluorodeoxyglucose F18

Autor:innen und Institutionen

  • Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA.
  • Department of Biomedical Engineering, Hanyang University, Seoul 04763, Korea.
  • Department of Information Technology, Mayo Clinic, Rochester, MN 55905, USA.
  • Department of Neurology, Mayo Clinic, Rochester, MN 55905, USA.
  • Department of Health Sciences Research, Mayo Clinic, Rochester, MN 55905, USA.
  • Department of Neuroscience, Mayo Clinic, Jacksonville, FL 32224, USA.

ORCID-Profile: Jeyeon Lee, Nick Corriveau-Lecavalier, Melissa E Murray, Hugo Botha, Jonathan Graff-Radford, Christopher G Schwarz, Kejal Kantarci, David S Knopman, Bradley F Boeve, Clifford R Jack, David T Jones

Förderung

  • NIA NIH HHS
  • NIH HHS
  • National Institutes of Health
  • Robert Wood Johnson Foundation
  • Mayo Foundation

Zitieren

APA

Lee, J., Burkett, B. J., Min, H. K., Senjem, M. L., Dicks, E., Corriveau-Lecavalier, N., Mester, C. T., Wiste, H. J., Lundt, E. S., Murray, M. E., Nguyen, A. T., Reichard, R. R., Botha, H., Graff-Radford, J., Barnard, L. R., Gunter, J. L., Schwarz, C. G., Kantarci, K., Knopman, D. S., …, & Jones, D. T. (2024). Synthesizing images of tau pathology from cross-modal neuroimaging using deep learning. Brain, 147(3), 980-995. https://doi.org/10.1093/brain/awad346

Vancouver

Lee J, Burkett BJ, Min HK, Senjem ML, Dicks E, Corriveau-Lecavalier N, et al. Synthesizing images of tau pathology from cross-modal neuroimaging using deep learning. Brain. 2024;147(3):980-995. doi:10.1093/brain/awad346

BibTeX
@article{Lee2024,
  author = {Lee, Jeyeon and Burkett, Brian J and Min, Hoon-Ki and Senjem, Matthew L and Dicks, Ellen and Corriveau-Lecavalier, Nick and Mester, Carly T and Wiste, Heather J and Lundt, Emily S and Murray, Melissa E and Nguyen, Aivi T and Reichard, Ross R and Botha, Hugo and Graff-Radford, Jonathan and Barnard, Leland R and Gunter, Jeffrey L and Schwarz, Christopher G and Kantarci, Kejal and Knopman, David S and Boeve, Bradley F and Lowe, Val J and Petersen, Ronald C and Jack, Clifford R and Jones, David T},
  title = {Synthesizing images of tau pathology from cross-modal neuroimaging using deep learning},
  journal = {Brain},
  year = {2024},
  volume = {147},
  number = {3},
  pages = {980--995},
  doi = {10.1093/brain/awad346}
}
Kostenlos starten →