Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising
IEEE Transactions on Radiation and Plasma Medical Sciences · 2024-04 · 8 (4) · 348-356
DOI: 10.1109/trpms.2023.3280907 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Radiation and Plasma Medical Sciences, 2024-04. Verfasst von Yuya Onishi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 42 Literaturangaben.
Abstract (Originalsprache)
Deep image prior (DIP) has been successfully applied to positron emission tomography (PET) image restoration, enabling represent implicit prior using only convolutional neural network architecture without training dataset, whereas the general supervised approach requires massive low- and high-quality PET image pairs. To answer the increased need for PET imaging with DIP, it is indispensable to improve the performance of the underlying DIP itself. Here, we propose a self-supervised pretraining model to improve the DIP-based PET image denoising performance. Our proposed pretraining model acquires transferable and generalizable visual representations from only unlabeled PET images by restoring various degraded PET images in a self-supervised approach. We evaluated the proposed method using clinical brain PET data with various radioactive tracers ($^{\mathrm{ 18}}\text{F}$-florbetapir,$^{\mathrm{ 11}}\text{C}$-Pittsburgh compound-B,$^{\mathrm{ 18}}\text{F}$-fluoro-2-deoxy-D-glucose, and$^{\mathrm{ 15}}\text{O}$-CO2) acquired from different PET scanners. The proposed method using the self-supervised pretraining model achieved robust and the state-of-the-art denoising performance while retaining spatial details and quantification accuracy compared to other unsupervised methods and pretraining model. These results highlight the potential that the proposed method is particularly effective against rare diseases and probes and helps reduce the scan time or the radiotracer dose without affecting the patients.
Zitieren
APA
Onishi, Y., Hashimoto, F., Ote, K., Matsubara, K., & Ibaraki, M. (2024). Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising. IEEE Transactions on Radiation and Plasma Medical Sciences, 8(4), 348-356. https://doi.org/10.1109/trpms.2023.3280907
Vancouver
Onishi Y, Hashimoto F, Ote K, Matsubara K, Ibaraki M. Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising. IEEE Transactions on Radiation and Plasma Medical Sciences. 2024;8(4):348-356. doi:10.1109/trpms.2023.3280907
BibTeX
@article{Onishi2024,
author = {Onishi, Yuya and Hashimoto, Fumio and Ote, Kibo and Matsubara, Keisuke and Ibaraki, Masanobu},
title = {Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising},
journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
year = {2024},
volume = {8},
number = {4},
pages = {348--356},
doi = {10.1109/trpms.2023.3280907}
}
EUVIMED