Noise In Positron Emission Tomography Images Research Articles

EAMNet: an Alzheimer’s disease prediction model based on representation learning

Objective. Brain 18F-FDG PET images indicate brain lesions’ metabolic status and offer the predictive potential for Alzheimer’s disease (AD). However, the complexity of extracting relevant lesion features and dealing with extraneous information in PET images poses challenges for accurate prediction. Approach. To address these issues, we propose an innovative solution called the efficient adaptive multiscale network (EAMNet) for predicting potential patient populations using positron emission tomography (PET) image slices, enabling effective intervention and treatment. Firstly, we introduce an efficient convolutional strategy to enhance the receptive field of PET images during the feature learning process, avoiding excessive extraction of fine tissue features by deep-level networks while reducing the model’s computational complexity. Secondly, we construct a channel attention module that enables the prediction model to adaptively allocate weights between different channels, compensating for the spatial noise in PET images’ impact on classification. Finally, we use skip connections to merge features from different-scale lesion information. Through visual analysis, the network constructed in this article aligns with the regions of interest of clinical doctors. Main results. Through visualization analysis, our network aligns with regions of interest identified by clinical doctors. Experimental evaluations conducted on the ADNI (Alzheimer’s Disease Neuroimaging Initiative) dataset demonstrate the outstanding classification performance of our proposed method. The accuracy rates for AD versus NC (Normal Controls), AD versus MCI (Mild Cognitive Impairment), MCI versus NC, and AD versus MCI versus NC classifications achieve 97.66%, 96.32%, 95.23%, and 95.68%, respectively. Significance. The proposed method surpasses advanced algorithms in the field, providing a hopeful advancement in accurately predicting and classifying Alzheimer’s Disease using 18F-FDG PET images. The source code has been uploaded to https://github.com/Haoliang-D-AHU/EAMNet/tree/master.

A 3D attention residual encoder–decoder least-square GAN for low-count PET denoising

In this paper, to reduce patient scan times and maintain high image quality, we propose a 3D attention least-square (LS) generative adversarial network (GAN) to estimate positron emission tomography (PET) images with long scan times from short-scan-time images; this network is called 3D a-LSGAN. To explore the structural information between slices, a 3D network implementation is used. We take a low-count 3D PET image scanned for 75 s as the input and generate a high-count (HC) 3D PET image corresponding to an estimated scan time of 150 s. Specifically, a U-Net-like deep learning network is combined with a residual network and self-attention strategy to transfer the important information from the encoder part to the corresponding decoder part of the network. In addition, the mean square error (MSE) loss is added to the adversarial loss to form a new loss function that removes artifacts and yields high-quality PET images. The qualitative and quantitative experimental results show that the proposed 3D a-LSGAN method for low-count PET image noise reduction performs better than the state-of-the-art methods considered.

An efficient wavelet and curvelet-based PET image denoising technique.

Positron emission tomography (PET) image denoising is a challenging task due to the presence of noise and low spatial resolution compared with other imaging techniques such as magnetic resonance imaging (MRI) and computed tomography (CT). PET image noise can hamper further processing and analysis, such as segmentation and disease screening. The wavelet transform-based techniques have often been proposed for PET image denoising to handle isotropic (smooth details) features. The curvelet transform-based PET image denoising techniques have the ability to handle multi-scale and multi-directional properties such as edges and curves (anisotropic features) as compared with wavelet transform-based denoising techniques. The wavelet denoising method is not optimal for anisotropic features, whereas the curvelet denoising method sometimes has difficulty in handling isotropic features. In order to handle the weaknesses of individual wavelet and curvelet-based methods, the present research proposes an efficient PET image denoising technique based on the combination of wavelet and curvelet transforms, along with a new adaptive threshold selection to threshold the wavelet coefficients in each subband (except last level low pass (LL) residual). The proposed threshold utilizes the advantages of adaptive threshold taken from BayesShrink along with the neighborhood window concept. The present method was tested on both simulated phantom and clinical PET datasets. Experimental results show that our method has achieved better results than the existing methods such as VisuShrink, BayesShrink, NeighShrink, ModineighShrink, curvelet, and an existing wavelet curvelet-based method with respect to different noise measurement metrics, such as mean squared error (MSE), signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), and image quality index (IQI). Furthermore, notable performance is achieved in the case of medical applications such as gray matter segmentation and precise tumor region identification. Graphical Abstract Block diagram of the proposed method. (a) Steps of the proposed denoising method and (b) image information generated by each step of (a).

Segmentation improvement through denoising of PET images with 3D-context modelling in wavelet domain

Positron emission tomography (PET) images have been incorporated into the radiotherapy process as a powerful tool to assist in the contouring of lesions, leading to the emergence of a broad spectrum of automatic segmentation schemes for PET images (PET-AS). However, not all proposed PET-AS algorithms take into consideration the previous steps of image preparation. PET image noise has been shown to be one of the most relevant affecting factors in segmentation tasks. This study demonstrates a nonlinear filtering method based on spatially adaptive wavelet shrinkage using three-dimensional context modelling that considers the correlation of each voxel with its neighbours. Using this noise reduction method, excellent edge conservation properties are obtained. To evaluate the influence in the segmentation schemes of this filter, it was compared with a set of Gaussian filters (the most conventional) and with two previously optimised edge-preserving filters. Five segmentation schemes were used (most commonly implemented in commercial software): fixed thresholding, adaptive thresholding, watershed, adaptive region growing and affinity propagation clustering. Segmentation results were evaluated using the Dice similarity coefficient and classification error. A simple metric was also included to improve the characterisation of the filters used for induced blurring evaluation, based on the measurement of the average edge width. The proposed noise reduction procedure improves the results of segmentation throughout the performed settings and was shown to be more stable in low-contrast and high-noise conditions. Thus, the capacity of the segmentation method is reinforced by the denoising plan used.

Noise Reduction in Small Animal PET Images Using a Variational Non-Convex Functional

Positron emission tomography (PET) imaging is widely used in nuclear medicine. However, data acquired by a PET system are generally contaminated with heavy noise, which often persists after image reconstruction. In this paper, a novel non-convex functional is introduced to suitably attenuate noise in PET images. The proposed functional contains a new regularization term defined as a convex combination of two terms: a robust function for border preserving and the $L^{2}$ semi-norm. The combination coefficient depends on the gradient of the noisy image, so that it allows a selective smoothing of image regions according to their local characteristics. The proposed method has been qualitatively and quantitatively tested on both simulated and measured data, demonstrating its better performance against well-established methods for PET denoising.

An Effective Post-Filtering Framework for 3-D PET Image Denoising Based on Noise and Sensitivity Characteristics

Positron emission tomography (PET) images usually suffer from a noticeable amount of statistical noise. In order to reduce this noise, a post-filtering process is usually adopted. However, the performance of this approach is limited because the denoising process is mostly performed on the basis of the Gaussian random noise. It has been reported that in a PET image reconstructed by the expectation-maximization (EM), the noise variance of each voxel depends on its mean value, unlike in the case of Gaussian noise. In addition, we observe that the variance also varies with the spatial sensitivity distribution in a PET system, which reflects both the solid angle determined by a given scanner geometry and the attenuation information of a scanned object. Thus, if a post-filtering process based on the Gaussian random noise is applied to PET images without consideration of the noise characteristics along with the spatial sensitivity distribution, the spatially variant non-Gaussian noise cannot be reduced effectively. In the proposed framework, to effectively reduce the noise in PET images reconstructed by the 3-D ordinary Poisson ordered subset EM (3-D OP-OSEM), we first denormalize an image according to the sensitivity of each voxel so that the voxel mean value can represent its statistical properties reliably. Based on our observation that each noisy denormalized voxel has a linear relationship between the mean and variance, we try to convert this non-Gaussian noise image to a Gaussian noise image. We then apply a block matching 4-D algorithm that is optimized for noise reduction of the Gaussian noise image, and reconvert and renormalize the result to obtain a final denoised image. Using simulated phantom data and clinical patient data, we demonstrate that the proposed framework can effectively suppress the noise over the whole region of a PET image while minimizing degradation of the image resolution.

Postreconstruction Nonlocal Means Filtering of Whole-Body PET With an Anatomical Prior

Positron emission tomography (PET) images usually suffer from poor signal-to-noise ratio (SNR) due to the high level of noise and low spatial resolution, which adversely affect its performance for lesion detection and quantification. The complementary information present in high-resolution anatomical images from multi-modality imaging systems could potentially be used to improve the ability to detect and/or quantify lesions. However, previous methods that use anatomical priors usually require matched organ/lesion boundaries. In this study, we investigated the use of anatomical information to suppress noise in PET images while preserving both quantitative accuracy and the amplitude of prominent signals that do not have corresponding boundaries on computerized tomography (CT). The proposed approach was realized through a postreconstruction filter based on the nonlocal means (NLM) filter, which reduces noise by computing the weighted average of voxels based on the similarity measurement between patches of voxels within the image. Anatomical knowledge obtained from CT was incorporated to constrain the similarity measurement within a subset of voxels. In contrast to other methods that use anatomical priors, the actual number of neighboring voxels and weights used for smoothing were determined from a robust measurement on PET images within the subset. Thus, the proposed approach can be robust to signal mismatches between PET and CT. A 3-D search scheme was also investigated for the volumetric PET/CT data. The proposed anatomically guided median nonlocal means filter (AMNLM) was first evaluated using a computer phantom and a physical phantom to simulate realistic but challenging situations where small lesions are located in homogeneous regions, which can be detected on PET but not on CT. The proposed method was further assessed with a clinical study of a patient with lung lesions. The performance of the proposed method was compared to Gaussian, edge-preserving bilateral and NLM filters, as well as median nonlocal means (MNLM) filtering without an anatomical prior. The proposed AMNLM method yielded improved lesion contrast and SNR compared with other methods even with imperfect anatomical knowledge, such as missing lesion boundaries and mismatched organ boundaries.

Properties of Noise in Positron Emission Tomography Images Reconstructed with Filtered-Backprojection and Row-Action Maximum Likelihood Algorithm

Noise levels observed in positron emission tomography (PET) images complicate their geometric interpretation. Post-processing techniques aimed at noise reduction may be employed to overcome this problem. The detailed characteristics of the noise affecting PET images are, however, often not well known. Typically, it is assumed that overall the noise may be characterized as Gaussian. Other PET-imaging-related studies have been specifically aimed at the reduction of noise represented by a Poisson or mixed Poisson + Gaussian model. The effectiveness of any approach to noise reduction greatly depends on a proper quantification of the characteristics of the noise present. This work examines the statistical properties of noise in PET images acquired with a GEMINI PET/CT scanner. Noise measurements have been performed with a cylindrical phantom injected with (11)C and well mixed to provide a uniform activity distribution. Images were acquired using standard clinical protocols and reconstructed with filtered-backprojection (FBP) and row-action maximum likelihood algorithm (RAMLA). Statistical properties of the acquired data were evaluated and compared to five noise models (Poisson, normal, negative binomial, log-normal, and gamma). Histograms of the experimental data were used to calculate cumulative distribution functions and produce maximum likelihood estimates for the parameters of the model distributions. Results obtained confirm the poor representation of both RAMLA- and FBP-reconstructed PET data by the Poisson distribution. We demonstrate that the noise in RAMLA-reconstructed PET images is very well characterized by gamma distribution followed closely by normal distribution, while FBP produces comparable conformity with both normal and gamma statistics.