Publications

BibTex format

@article{Shiri:2022:10.1007/s00259-022-06053-8,
author = {Shiri, I and Sadr, AV and Akhavan, A and Salimi, Y and Sanaat, A and Amini, M and Razeghi, B and Saberi, A and Arabi, H and Ferdowsi, S and Voloshynovskiy, S and Gunduz, D and Rahmim, A and Zaidi, H},
doi = {10.1007/s00259-022-06053-8},
journal = {European Journal of Nuclear Medicine and Molecular Imaging},
pages = {1034--1050},
title = {Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning},
url = {http://dx.doi.org/10.1007/s00259-022-06053-8},
volume = {50},
year = {2022}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.Methods:Non-attenuation/scatter corrected and CT-based attenuation/scatter corrected (CT-ASC) 18F-FDG PET images of 300 patients were enrolled in this study. The dataset consisted of 6 different centers, each with 50 patients, with scanner, image acquisition, and reconstruction protocols varying across the centers. CT-based ASC PET images served as the standard reference. All images were reviewed to include high-quality and artifact-free PET images. Both corrected and uncorrected PET images were converted to standardized uptake values (SUVs). We used a modified nested U-Net utilizing residual U-block in a U-shape architecture. We evaluated two FL models, namely sequential (FL-SQ) and parallel (FL-PL) and compared their performance with the baseline centralized (CZ) learning model wherein the data were pooled to one server, as well as center-based (CB) models where for each center the model was built and evaluated separately. Data from each center were divided to contribute to training (30 patients), validation (10 patients), and test sets (10 patients). Final evaluations and reports were performed on 60 patients (10 patients from each center).Results:In terms of percent SUV absolute relative error (ARE%), both FL-SQ (CI:12.21–14.81%) and FL-PL (CI:11.82–13.84%) models demo
AU  - Shiri,I
AU  - Sadr,AV
AU  - Akhavan,A
AU  - Salimi,Y
AU  - Sanaat,A
AU  - Amini,M
AU  - Razeghi,B
AU  - Saberi,A
AU  - Arabi,H
AU  - Ferdowsi,S
AU  - Voloshynovskiy,S
AU  - Gunduz,D
AU  - Rahmim,A
AU  - Zaidi,H
DO  - 10.1007/s00259-022-06053-8
EP  - 1050
PY  - 2022///
SN  - 0340-6997
SP  - 1034
TI  - Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning
T2  - European Journal of Nuclear Medicine and Molecular Imaging
UR  - http://dx.doi.org/10.1007/s00259-022-06053-8
UR  - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000898295800003&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
UR  - http://hdl.handle.net/10044/1/101897
VL  - 50
ER  -

Download

ProfessorDenizGunduz

Contact

Assistant

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)