Federated Transfer Learning for Low-Dose PET Denoising: A Pilot Study With Simulated Heterogeneous Data
- 27 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radiation and Plasma Medical Sciences
- Vol. 7 (3) , 284-295
Abstract
Positron emission tomography (PET) with a reduced injection dose, i.e., low-dose PET, is an efficient way to reduce radiation dose. However, low-dose PET reconstruction suffers from a low signal-to-noise ratio (SNR), affecting diagnosis and other PET-related applications. Recently, deep learning-based PET denoising methods have demonstrated superior performance in generating high-quality reconstruction. However, these methods require a large amount of representative data for training, which can be difficult to collect and share due to medical data privacy regulations. Moreover, low-dose PET data at different institutions may use different low-dose protocols, leading to nonidentical data distribution. While previous federated learning (FL) algorithms enable multiinstitution collaborative training without the need of aggregating local data, it is challenging for previous methods to address the large domain shift caused by different low-dose PET settings, and the application of FL to PET is still underexplored. In this work, we propose a federated transfer learning (FTL) framework for low-dose PET denoising using heterogeneous low-dose data. Our experimental results on simulated multiinstitutional data demonstrate that our method can efficiently utilize heterogeneous low-dose data without compromising data privacy for achieving superior low-dose PET denoising performance for different institutions with different low-dose settings, as compared to previous FL methods.Keywords
Funding Information
- National Institutes of Health (R01EB025468)
This publication has 53 references indexed in Scilit:
- A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image ReconstructionIEEE Transactions on Medical Imaging, 2018
- Deep auto-context convolutional neural networks for standard-dose PET image estimation from low-dose PET/MRINeurocomputing, 2017
- Deep Models Under the GAN2017
- Deep Learning with Differential Privacy2016
- Noise Reduction in Small Animal PET Images Using a Variational Non-Convex FunctionalIEEE Transactions on Nuclear Science, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Creating Value In Health Care Through Big Data: Opportunities And Policy ImplicationsHealth Affairs, 2014
- Non-Local Means Denoising of Dynamic PET ImagesPLOS ONE, 2013
- Nonlocal Transform-Domain Filter for Volumetric Data Denoising and ReconstructionIEEE Transactions on Image Processing, 2012
- The ALARA (As Low As Reasonably Achievable) Concept in Pediatric Interventional and Fluoroscopic Imaging: Striving to Keep Radiation Doses as Low as Possible during Fluoroscopy of Pediatric Patients—A White Paper Executive SummaryRadiology, 2006