Deep learning-based attenuation correction for whole-body PET - a multi-tracer study with F-FDG,  Ga-DOTATATE, and F-Fluciclovine.

Journal: European journal of nuclear medicine and molecular imaging
PMID: 35277742

Abstract

UNLABELLED: A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using F-FDG,  Ga-DOTATATE, and F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT).

Authors

  • Takuya Toyonaga
    Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA.
  • Dan Shao
    Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, China.
  • Luyao Shi
  • Jiazhen Zhang
    Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA.
  • Enette Mae Revilla
    Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA.
  • David Menard
    Yale New Haven Hospital, New Haven, CT, USA.
  • Joseph Ankrah
    Yale New Haven Hospital, New Haven, CT, USA.
  • Kenji Hirata
    Department of Diagnostic Imaging, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan.
  • Ming-Kai Chen
    Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA.
  • John A Onofrey
  • Yihuan Lu

Keywords

External Resources

Popular Topics
Recent Journals