Abstract
Noise suppression is particularly important in low count positron emission tomography (PET) imaging. Post-smoothing (PS) and regularization methods which aim to reduce noise also tend to reduce resolution and introduce bias. Alternatively, anatomical information from another modality such as magnetic resonance (MR) imaging can be used to improve image quality. Convolutional neural networks (CNNs) are particularly well suited to such joint image processing, but usually require large amounts of training data and have mostly been applied outside the field of medical imaging or focus on classification and segmentation, leaving PET image quality improvement relatively understudied. This article proposes the use of a relatively low-complexity CNN (micro-net) as a post-reconstruction MR-guided image processing step to reduce noise and reconstruction artefacts while also improving resolution in low count PET scans. The CNN is designed to be fully 3-D, robust to very limited amounts of training data, and to accept multiple inputs (including competitive denoising methods). Application of the proposed CNN on simulated low (30 M) count data (trained to produce standard (300 M) count reconstructions) results in a 36% lower normalized root mean squared error (NRMSE, calculated over ten realizations against the ground truth) compared to maximum-likelihood expectation maximization (MLEM) used in clinical practice. In contrast, a decrease of only 25% in NRMSE is obtained when an optimized (using knowledge of the ground truth) PS is performed. A 26% NRMSE decrease is obtained with both RM and optimized PS. Similar improvement is also observed for low count real patient datasets. Overfitting to training data is demonstrated to occur as the network size is increased. In an extreme case, a U-net (which produces better predictions for training data) is shown to completely fail on test data due to overfitting to this case of very limited training data. Meanwhile, the resultant images from the proposed CNN (which has low training data requirements) have lower noise, reduced ringing, and partial volume effects, as well as sharper edges and improved resolution compared to conventional MLEM.
Highlights
P OSITRON emission tomography (PET) image reconstruction is an ill-posed inverse problem, for which maximum likelihood expectation maximization (MLEM) is a commonly used iterative reconstruction method
Convolutional neural networks (CNNs) architectures are well suited to using the increased resolution available in jointly acquired magnetic resonance (MR) or computed tomography (CT) data to reduce the noise in positron emission tomography (PET) reconstructions
XHθ m (k) where θ (k) is the reconstructed image at the kth iteration; H can be used to include an resolution modeling (RM) kernel; X is the rest of the system matrix; m is the sinogram data; represent randoms and scatter, and division is Hadamard
Summary
P OSITRON emission tomography (PET) image reconstruction is an ill-posed inverse problem, for which maximum likelihood expectation maximization (MLEM) is a commonly used iterative reconstruction method. Some proposals include combining DL with an unfiltered backprojection as a faster, comparable alternative to iterative MLEM reconstruction [23], while others suggest 2-D patch-based methods to reduce noise in low-dose PET-CT [24] and PET-MR reconstructions [25]. CNN architectures are well suited to using the increased resolution available in jointly acquired MR or CT data to reduce the noise in PET reconstructions. Such networks typically require large amounts of training data and suffer from computational memory constraints. This article focuses on improving image quality through 3-D CNNs which are flexibly designed to use MR guidance for reduced dose PET imaging, as well as remove reconstruction artefacts. These μ-nets have a comparatively small parameter space and are robust against overfitting on extremely limited training data sets, in stark contrast to the U-nets found in [31] and [32]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE transactions on radiation and plasma medical sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
