FedFTN: Personalized federated learning with deep feature transformation network for multi-institutional low-count PET denoising

Low-count PET is an efficient way to reduce radiation exposure and acquisition time, but the reconstructed images often suffer from low signal-to-noise ratio (SNR), thus affecting diagnosis and other downstream tasks. Recent advances in deep learning have shown great potential in improving low-count...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Medical image analysis Ročník 90; s. 102993
Hlavní autoři: Zhou, Bo, Xie, Huidong, Liu, Qiong, Chen, Xiongchao, Guo, Xueqi, Feng, Zhicheng, Hou, Jun, Zhou, S. Kevin, Li, Biao, Rominger, Axel, Shi, Kuangyu, Duncan, James S., Liu, Chi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Netherlands Elsevier B.V 01.12.2023
Témata:
Algorithms
Deep reconstruction
Denoising
Humans
Image Processing, Computer-Assisted
Low-count PET
Personalized federated learning
Positron-Emission Tomography
Signal-To-Noise Ratio
Personalized federated learning
41A10
65D05
Deep reconstruction
65D17
Low-count PET
41A05
Denoising
ISSN:1361-8415, 1361-8423, 1361-8423
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Low-count PET is an efficient way to reduce radiation exposure and acquisition time, but the reconstructed images often suffer from low signal-to-noise ratio (SNR), thus affecting diagnosis and other downstream tasks. Recent advances in deep learning have shown great potential in improving low-count PET image quality, but acquiring a large, centralized, and diverse dataset from multiple institutions for training a robust model is difficult due to privacy and security concerns of patient data. Moreover, low-count PET data at different institutions may have different data distribution, thus requiring personalized models. While previous federated learning (FL) algorithms enable multi-institution collaborative training without the need of aggregating local data, addressing the large domain shift in the application of multi-institutional low-count PET denoising remains a challenge and is still highly under-explored. In this work, we propose FedFTN, a personalized federated learning strategy that addresses these challenges. FedFTN uses a local deep feature transformation network (FTN) to modulate the feature outputs of a globally shared denoising network, enabling personalized low-count PET denoising for each institution. During the federated learning process, only the denoising network’s weights are communicated and aggregated, while the FTN remains at the local institutions for feature transformation. We evaluated our method using a large-scale dataset of multi-institutional low-count PET imaging data from three medical centers located across three continents, and showed that FedFTN provides high-quality low-count PET images, outperforming previous baseline FL reconstruction methods across all low-count levels at all three institutions. •We propose a novel personalized federated learning framework for low-count PET denoising.•We collected large-scale multi-institutional low-count PET data across the USA, China, and Europe.•We conducted the first real-world study on federated learning for low-count PET imaging.•We demonstrated that FedFTN can provide high-quality low-count PET across sites and low-count settings.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1361-8415
1361-8423
1361-8423
DOI:10.1016/j.media.2023.102993