Federated Transfer Learning for Low-dose PET Denoising: A Pilot Study with Simulated Heterogeneous Data

• Published in: IEEE transactions on radiation and plasma medical sciences Vol. 7; no. 3; p. 1
• Main Authors: Zhou, Bo, Miao, Tianshun, Mirian, Niloufar, Chen, Xiongchao, Xie, Huidong, Feng, Zhicheng, Guo, Xueqi, Li, Xiaoxiao, Zhou, S. Kevin, Duncan, James S., Liu, Chi
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biomedical imaging; Data privacy; Deep learning; Denoising; Emission analysis; Federated learning; Image reconstruction; Low-dose PET; Machine learning; Noise reduction; Positron emission; Positron emission tomography; Privacy; Radiation; Radiation dosage; Reconstruction; Signal to noise ratio; Task analysis; Training; Transfer learning; Low-dose PET; Federated learning; Transfer learning; Denoising
• ISSN: 2469-7311; 2469-7303
• DOI: 10.1109/TRPMS.2022.3194408

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 non-identical data distribution. While previous federated learning (FL) algorithms enable multi-institution 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 under-explored. 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 multi-institutional 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.