Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning.

Journal: European journal of nuclear medicine and molecular imaging
Published Date:

Abstract

PURPOSE: Attenuation correction and scatter compensation (AC/SC) are two main steps toward quantitative PET imaging, which remain challenging in PET-only and PET/MRI systems. These can be effectively tackled via deep learning (DL) methods. However, trustworthy, and generalizable DL models commonly require well-curated, heterogeneous, and large datasets from multiple clinical centers. At the same time, owing to legal/ethical issues and privacy concerns, forming a large collective, centralized dataset poses significant challenges. In this work, we aimed to develop a DL-based model in a multicenter setting without direct sharing of data using federated learning (FL) for AC/SC of PET images.

Authors

  • Isaac Shiri
    Biomedical and Health Informatics, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran.
  • Alireza Vafaei Sadr
  • Azadeh Akhavan
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland.
  • Yazdan Salimi
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
  • Amirhossein Sanaat
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
  • Mehdi Amini
    From the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital.
  • Behrooz Razeghi
    Department of Computer Science.
  • Abdollah Saberi
    Department of Computer Engineering, Islamic Azad University, Tehran, Iran.
  • Hossein Arabi
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland.
  • Sohrab Ferdowsi
    HES-SO University of Applied Sciences and Arts Western Switzerland, Geneva, Switzerland.
  • Slava Voloshynovskiy
    Department of Computer Science.
  • Deniz Gündüz
    Faculty of Engineering, Department of Electrical and Electronic Engineering, Imperial College London, London, United Kingdom.
  • Arman Rahmim
  • Habib Zaidi
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland. habib.zaidi@hcuge.ch.