Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on radiation and plasma medical sciences 2024-04, Vol.8 (4), p.1-1
Main Authors: Onishi, Yuya, Hashimoto, Fumio, Ote, Kibo, Matsubara, Keisuke, Ibaraki, Masanobu
Format: Article
Language:English
Subjects:
Artificial neural networks
Carbon dioxide
Deep image prior
Electronics packaging
Glucose
Image acquisition
Image denoising
Image quality
Image restoration
Medical imaging
Neural networks
Neuroimaging
Noise reduction
Performance enhancement
PET image denoising
Positron emission
Positron emission tomography
pre-training
Radioactive tracers
Robustness
Self-supervised learning
Task analysis
Training
unsupervised learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 pre-training model to improve the DIP-based PET image denoising performance. Our proposed pre-training 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 (18F-florbetapir, 11C-Pittsburgh compound-B, 18F-fluoro-2-deoxy-D-glucose, and 15O-CO2) acquired from different PET scanners. The proposed method using the self-supervised pre-training model achieved robust and state-of-the-art denoising performance while retaining spatial details and quantification accuracy compared to other unsupervised methods and pre-training 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.
ISSN:2469-7311
2469-7303
DOI:10.1109/TRPMS.2023.3280907