[HTML][HTML] The promise of artificial intelligence and deep learning in PET and SPECT imaging

H Arabi, A AkhavanAllaf, A Sanaat, I Shiri, H Zaidi - Physica Medica, 2021 - Elsevier
This review sets out to discuss the foremost applications of artificial intelligence (AI),
particularly deep learning (DL) algorithms, in single-photon emission computed tomography …

Deep learning for PET image reconstruction

AJ Reader, G Corda, A Mehranian… - … on Radiation and …, 2020 - ieeexplore.ieee.org
This article reviews the use of a subdiscipline of artificial intelligence (AI), deep learning, for
the reconstruction of images in positron emission tomography (PET). Deep learning can be …

MD-Recon-Net: a parallel dual-domain convolutional neural network for compressed sensing MRI

M Ran, W Xia, Y Huang, Z Lu, P Bao… - … on Radiation and …, 2020 - ieeexplore.ieee.org
Compressed sensing magnetic resonance imaging (CS-MRI) is a theoretical framework that
can accurately reconstruct images from undersampled k-space data with a much lower …

Model-based deep learning PET image reconstruction using forward–backward splitting expectation–maximization

A Mehranian, AJ Reader - IEEE transactions on radiation and …, 2020 - ieeexplore.ieee.org
We propose a forward-backward splitting algorithm to integrate deep learning into maximum-
a-posteriori (MAP) positron emission tomography (PET) image reconstruction. The MAP …

DPIR-Net: Direct PET image reconstruction based on the Wasserstein generative adversarial network

Z Hu, H Xue, Q Zhang, J Gao, N Zhang… - … on Radiation and …, 2020 - ieeexplore.ieee.org
Positron emission tomography (PET) is an advanced medical imaging technique widely
used in various clinical applications, such as tumor detection and neurologic disorders …

Anatomical-guided attention enhances unsupervised PET image denoising performance

Y Onishi, F Hashimoto, K Ote, H Ohba, R Ota… - Medical image …, 2021 - Elsevier
Although supervised convolutional neural networks (CNNs) often outperform conventional
alternatives for denoising positron emission tomography (PET) images, they require many …

[HTML][HTML] Approximating anatomically-guided PET reconstruction in image space using a convolutional neural network

G Schramm, D Rigie, T Vahle, A Rezaei, K Van Laere… - Neuroimage, 2021 - Elsevier
In the last two decades, it has been shown that anatomically-guided PET reconstruction can
lead to improved bias-noise characteristics in brain PET imaging. However, despite …

True ultra-low-dose amyloid PET/MRI enhanced with deep learning for clinical interpretation

KT Chen, TN Toueg, MEI Koran, G Davidzon… - European journal of …, 2021 - Springer
Purpose While sampled or short-frame realizations have shown the potential power of deep
learning to reduce radiation dose for PET images, evidence in true injected ultra-low-dose …

High temporal-resolution dynamic PET image reconstruction using a new spatiotemporal kernel method

G Wang - IEEE transactions on medical imaging, 2018 - ieeexplore.ieee.org
Current clinical dynamic PET has an effective temporal resolution of 5-10 seconds, which
can be adequate for traditional compartmental modeling but is inadequate for exploiting the …

Generative Adversarial Network–Enhanced Ultra-Low-Dose [18F]-PI-2620 τ PET/MRI in Aging and Neurodegenerative Populations

KT Chen, R Tesfay, MEI Koran… - American Journal …, 2023 - Am Soc Neuroradiology
BACKGROUND AND PURPOSE: With the utility of hybrid τ PET/MR imaging in the
screening, diagnosis, and follow-up of individuals with neurodegenerative diseases, we …