PET image denoising based on denoising diffusion probabilistic model.

PURPOSE: Due to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic model (DDPM) was a distribution learning-based model, which tried to transform a normal distribution into a specific data distribution based on iterative refinements. In this work, we proposed and evaluated different DDPM-based methods for PET image denoising. METHODS: Under the DDPM framework, one way to perform PET image denoising was to provide the PET image and/or the prior image as the input. Another way was to supply the prior image as the network input with the PET image included in the refinement steps, which could fit for scenarios of different noise levels. 150 brain [[Formula: see text]F]FDG datasets and 140 brain [[Formula: see text]F]MK-6240 (imaging neurofibrillary tangles deposition) datasets were utilized to evaluate the proposed DDPM-based methods. RESULTS: Quantification showed that the DDPM-based frameworks with PET information included generated better results than the nonlocal mean, Unet and generative adversarial network (GAN)-based denoising methods. Adding additional MR prior in the model helped achieved better performance and further reduced the uncertainty during image denoising. Solely relying on MR prior while ignoring the PET information resulted in large bias. Regional and surface quantification showed that employing MR prior as the network input while embedding PET image as a data-consistency constraint during inference achieved the best performance. CONCLUSION: DDPM-based PET image denoising is a flexible framework, which can efficiently utilize prior information and achieve better performance than the nonlocal mean, Unet and GAN-based denoising methods.

Deep learning-based techniques for estimating high-quality full-dose positron emission tomography images from low-dose scans: a systematic review.

This systematic review aimed to evaluate the potential of deep learning algorithms for converting low-dose Positron Emission Tomography (PET) images to full-dose PET images in different body regions. A total of 55 articles published between 2017 and 2023 by searching PubMed, Web of Science, Scopus and IEEE databases were included in this review, which utilized various deep learning models, such as generative adversarial networks and UNET, to synthesize high-quality PET images. The studies involved different datasets, image preprocessing techniques, input data types, and loss functions. The evaluation of the generated PET images was conducted using both quantitative and qualitative methods, including physician evaluations and various denoising techniques. The findings of this review suggest that deep learning algorithms have promising potential in generating high-quality PET images from low-dose PET images, which can be useful in clinical practice.

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

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 cases is lacking. Therefore, we evaluated deep learning enhancement using a significantly reduced injected radiotracer protocol for amyloid PET/MRI. METHODS: Eighteen participants underwent two separate 18F-florbetaben PET/MRI studies in which an ultra-low-dose (6.64 ± 3.57 MBq, 2.2 ± 1.3% of standard) or a standard-dose (300 ± 14 MBq) was injected. The PET counts from the standard-dose list-mode data were also undersampled to approximate an ultra-low-dose session. A pre-trained convolutional neural network was fine-tuned using MR images and either the injected or sampled ultra-low-dose PET as inputs. Image quality of the enhanced images was evaluated using three metrics (peak signal-to-noise ratio, structural similarity, and root mean square error), as well as the coefficient of variation (CV) for regional standard uptake value ratios (SUVRs). Mean cerebral uptake was correlated across image types to assess the validity of the sampled realizations. To judge clinical performance, four trained readers scored image quality on a five-point scale (using 15% non-inferiority limits for proportion of studies rated 3 or better) and classified cases into amyloid-positive and negative studies. RESULTS: The deep learning-enhanced PET images showed marked improvement on all quality metrics compared with the low-dose images as well as having generally similar regional CVs as the standard-dose. All enhanced images were non-inferior to their standard-dose counterparts. Accuracy for amyloid status was high (97.2% and 91.7% for images enhanced from injected and sampled ultra-low-dose data, respectively) which was similar to intra-reader reproducibility of standard-dose images (98.6%). CONCLUSION: Deep learning methods can synthesize diagnostic-quality PET images from ultra-low injected dose simultaneous PET/MRI data, demonstrating the general validity of sampled realizations and the potential to reduce dose significantly for amyloid imaging.

3D conditional generative adversarial networks for high-quality PET image estimation at low dose.

Positron emission tomography (PET) is a widely used imaging modality, providing insight into both the biochemical and physiological processes of human body. Usually, a full dose radioactive tracer is required to obtain high-quality PET images for clinical needs. This inevitably raises concerns about potential health hazards. On the other hand, dose reduction may cause the increased noise in the reconstructed PET images, which impacts the image quality to a certain extent. In this paper, in order to reduce the radiation exposure while maintaining the high quality of PET images, we propose a novel method based on 3D conditional generative adversarial networks (3D c-GANs) to estimate the high-quality full-dose PET images from low-dose ones. Generative adversarial networks (GANs) include a generator network and a discriminator network which are trained simultaneously with the goal of one beating the other. Similar to GANs, in the proposed 3D c-GANs, we condition the model on an input low-dose PET image and generate a corresponding output full-dose PET image. Specifically, to render the same underlying information between the low-dose and full-dose PET images, a 3D U-net-like deep architecture which can combine hierarchical features by using skip connection is designed as the generator network to synthesize the full-dose image. In order to guarantee the synthesized PET image to be close to the real one, we take into account of the estimation error loss in addition to the discriminator feedback to train the generator network. Furthermore, a concatenated 3D c-GANs based progressive refinement scheme is also proposed to further improve the quality of estimated images. Validation was done on a real human brain dataset including both the normal subjects and the subjects diagnosed as mild cognitive impairment (MCI). Experimental results show that our proposed 3D c-GANs method outperforms the benchmark methods and achieves much better performance than the state-of-the-art methods in both qualitative and quantitative measures.

MPGAN: Multi Pareto Generative Adversarial Network for the denoising and quantitative analysis of low-dose PET images of human brain.

Positron emission tomography (PET) imaging is widely used in medical imaging for analyzing neurological disorders and related brain diseases. Usually, full-dose imaging for PET ensures image quality but raises concerns about potential health risks of radiation exposure. The contradiction between reducing radiation exposure and maintaining diagnostic performance can be effectively addressed by reconstructing low-dose PET (L-PET) images to the same high-quality as full-dose (F-PET). This paper introduces the Multi Pareto Generative Adversarial Network (MPGAN) to achieve 3D end-to-end denoising for the L-PET images of human brain. MPGAN consists of two key modules: the diffused multi-round cascade generator (GDmc) and the dynamic Pareto-efficient discriminator (DPed), both of which play a zero-sum game for n(n∈1,2,3) rounds to ensure the quality of synthesized F-PET images. The Pareto-efficient dynamic discrimination process is introduced in DPed to adaptively adjust the weights of sub-discriminators for improved discrimination output. We validated the performance of MPGAN using three datasets, including two independent datasets and one mixed dataset, and compared it with 12 recent competing models. Experimental results indicate that the proposed MPGAN provides an effective solution for 3D end-to-end denoising of L-PET images of the human brain, which meets clinical standards and achieves state-of-the-art performance on commonly used metrics.

Noise-assisted hybrid attention networks for low-dose PET and CT denoising.

BACKGROUND: Positron emission tomography (PET) and computed tomography (CT) play a vital role in tumor-related medical diagnosis, assessment, and treatment planning. However, full-dose PET and CT pose the risk of excessive radiation exposure to patients, whereas low-dose images compromise image quality, impacting subsequent tumor recognition and disease diagnosis. PURPOSE: To solve such problems, we propose a Noise-Assisted Hybrid Attention Network (NAHANet) to reconstruct full-dose PET and CT images from low-dose PET (LDPET) and CT (LDCT) images to reduce patient radiation risks while ensuring the performance of subsequent tumor recognition. METHODS: NAHANet contains two branches: the noise feature prediction branch (NFPB) and the cascaded reconstruction branch. Among them, NFPB providing noise features for the cascade reconstruction branch. The cascaded reconstruction branch comprises a shallow feature extraction module and a reconstruction module which contains a series of cascaded noise feature fusion blocks (NFFBs). Among these, the NFFB fuses the features extracted from low-dose images with the noise features obtained by NFPB to improve the feature extraction capability. To validate the effectiveness of the NAHANet method, we performed experiments using two public available datasets: the Ultra-low Dose PET Imaging Challenge dataset and Low Dose CT Grand Challenge dataset. RESULTS: As a result, the proposed NAHANet achieved higher performance on common indicators. For example, on the CT dataset, the PSNR and SSIM indicators were improved by 4.1 dB and 0.06 respectively, and the rMSE indicator was reduced by 5.46 compared with the LDCT; on the PET dataset, the PSNR and SSIM was improved by 3.37 dB and 0.02, and the rMSE was reduced by 9.04 compared with the LDPET. CONCLUSIONS: This paper proposes a transformer-based denoising algorithm, which utilizes hybrid attention to extract high-level features of low dose images and fuses noise features to optimize the denoising performance of the network, achieving good performance improvements on low-dose CT and PET datasets.

Adversarial EM for variational deep learning: Application to semi-supervised image quality enhancement in low-dose PET and low-dose CT.

In positron emission tomography (PET) and X-ray computed tomography (CT), reducing radiation dose can cause significant degradation in image quality. For image quality enhancement in low-dose PET and CT, we propose a novel theoretical adversarial and variational deep neural network (DNN) framework relying on expectation maximization (EM) based learning, termed adversarial EM (AdvEM). AdvEM proposes an encoder-decoder architecture with a multiscale latent space, and generalized-Gaussian models enabling datum-specific robust statistical modeling in latent space and image space. The model robustness is further enhanced by including adversarial learning in the training protocol. Unlike typical variational-DNN learning, AdvEM proposes latent-space sampling from the posterior distribution, and uses a Metropolis-Hastings scheme. Unlike existing schemes for PET or CT image enhancement which train using pairs of low-dose images with their corresponding normal-dose versions, we propose a semi-supervised AdvEM (ssAdvEM) framework that enables learning using a small number of normal-dose images. AdvEM and ssAdvEM enable per-pixel uncertainty estimates for their outputs. Empirical analyses on real-world PET and CT data involving many baselines, out-of-distribution data, and ablation studies show the benefits of the proposed framework.

Federated Transfer Learning for Low-dose PET Denoising: A Pilot Study with Simulated Heterogeneous Data.

Positron emission tomography (PET) with a reduced injection dose, i.e., low-dose PET, is an efficient way to reduce radiation dose. However, low-dose PET reconstruction suffers from a low signal-to-noise ratio (SNR), affecting diagnosis and other PET-related applications. Recently, deep learning-based PET denoising methods have demonstrated superior performance in generating high-quality reconstruction. However, these methods require a large amount of representative data for training, which can be difficult to collect and share due to medical data privacy regulations. Moreover, low-dose PET data at different institutions may use different low-dose protocols, leading to non-identical data distribution. While previous federated learning (FL) algorithms enable multi-institution collaborative training without the need of aggregating local data, it is challenging for previous methods to address the large domain shift caused by different low-dose PET settings, and the application of FL to PET is still under-explored. In this work, we propose a federated transfer learning (FTL) framework for low-dose PET denoising using heterogeneous low-dose data. Our experimental results on simulated multi-institutional data demonstrate that our method can efficiently utilize heterogeneous low-dose data without compromising data privacy for achieving superior low-dose PET denoising performance for different institutions with different low-dose settings, as compared to previous FL methods.

AIGAN: Attention-encoding Integrated Generative Adversarial Network for the reconstruction of low-dose CT and low-dose PET images.

X-ray computed tomography (CT) and positron emission tomography (PET) are two of the most commonly used medical imaging technologies for the evaluation of many diseases. Full-dose imaging for CT and PET ensures the image quality but usually raises concerns about the potential health risks of radiation exposure. The contradiction between reducing the radiation exposure and remaining diagnostic performance can be addressed effectively by reconstructing the low-dose CT (L-CT) and low-dose PET (L-PET) images to the same high-quality ones as full-dose (F-CT and F-PET). In this paper, we propose an Attention-encoding Integrated Generative Adversarial Network (AIGAN) to achieve efficient and universal full-dose reconstruction for L-CT and L-PET images. AIGAN consists of three modules: the cascade generator, the dual-scale discriminator and the multi-scale spatial fusion module (MSFM). A sequence of consecutive L-CT (L-PET) slices is first fed into the cascade generator that integrates with a generation-encoding-generation pipeline. The generator plays the zero-sum game with the dual-scale discriminator for two stages: the coarse and fine stages. In both stages, the generator generates the estimated F-CT (F-PET) images as like the original F-CT (F-PET) images as possible. After the fine stage, the estimated fine full-dose images are then fed into the MSFM, which fully explores the inter- and intra-slice structural information, to output the final generated full-dose images. Experimental results show that the proposed AIGAN achieves the state-of-the-art performances on commonly used metrics and satisfies the reconstruction needs for clinical standards.

A Lightweight Low-dose PET Image Super-resolution Reconstruction Method based on Convolutional Neural Network.

BACKGROUND: PET imaging is one of the most widely used neurological disease screening and diagnosis techniques. AIMS: Since PET involves the radiation and tolerance of different people, the improvement that has always been focused on is to cut down radiation, in the meantime, ensuring that the generated images with low-dose tracer and generated images with standard-dose tracer have the same details of images. METHODS: We propose a lightweight low-dose PET super-resolution network (SRPET-Net) based on a convolutional neural network. In this research, We propose a method for accurately recovering highresolution (HR) PET images from low-resolution (LR) PET images. The network learns the details and structure of the image between low-dose PET images and standard-dose PET images and, afterward, reconstructs the PET image by the trained network model. RESULTS: The experiments indicate that the SRPET-Net can achieve a superior peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) values. Moreover, our method has less memory consumption and lower computational cost. CONCLUSION: In our follow-up work, the technology can be applied to medical imaging in many different directions.

Self-supervised deep learning for joint 3D low-dose PET/CT image denoising.

Deep learning (DL)-based denoising of low-dose positron emission tomography (LDPET) and low-dose computed tomography (LDCT) has been widely explored. However, previous methods have focused only on single modality denoising, neglecting the possibility of simultaneously denoising LDPET and LDCT using only one neural network, i.e., joint LDPET/LDCT denoising. Moreover, DL-based denoising methods generally require plenty of well-aligned LD-normal-dose (LD-ND) sample pairs, which can be difficult to obtain. To this end, we propose a self-supervised two-stage training framework named MAsk-then-Cycle (MAC), to achieve self-supervised joint LDPET/LDCT denoising. The first stage of MAC is masked autoencoder (MAE)-based pre-training and the second stage is self-supervised denoising training. Specifically, we propose a self-supervised denoising strategy named cycle self-recombination (CSR), which enables denoising without well-aligned sample pairs. Unlike other methods that treat noise as a homogeneous whole, CSR disentangles noise into signal-dependent and independent noises. This is more in line with the actual imaging process and allows for flexible recombination of noises and signals to generate new samples. These new samples contain implicit constraints that can improve the network's denoising ability. Based on these constraints, we design multiple loss functions to enable self-supervised training. Then we design a CSR-based denoising network to achieve joint 3D LDPET/LDCT denoising. Existing self-supervised methods generally lack pixel-level constraints on networks, which can easily lead to additional artifacts. Before denoising training, we perform MAE-based pre-training to indirectly impose pixel-level constraints on networks. Experiments on an LDPET/LDCT dataset demonstrate its superiority over existing methods. Our method is the first self-supervised joint LDPET/LDCT denoising method. It does not require any prior assumptions and is therefore more robust.

Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising.

Due to the widespread use of positron emission tomography (PET) in clinical practice, the potential risk of PET-associated radiation dose to patients needs to be minimized. However, with the reduction in the radiation dose, the resultant images may suffer from noise and artifacts that compromise diagnostic performance. In this paper, we propose a parameter-transferred Wasserstein generative adversarial network (PT-WGAN) for low-dose PET image denoising. The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural details, and ii) a task-specific initialization based on transfer learning is developed to train PT-WGAN using trainable parameters transferred from a pretrained model, which significantly improves the training efficiency of PT-WGAN. The experimental results on clinical data show that the proposed network can suppress image noise more effectively while preserving better image fidelity than recently published state-of-the-art methods. We make our code available at https://github.com/90n9-yu/PT-WGAN.

Low dose positron emission tomography emulation from decimated high statistics: A clinical validation study.

PURPOSE: The fundamental nature of positron emission tomography (PET), as an event detection system, provides some flexibility for data handling, including retrospective data manipulation. The reorganization of acquisition data allows the emulation of new scans arising from identical radiotracer spatial distributions, but with different statistical compositions, and is especially useful for evaluating the stability and reproducibility of reconstruction algorithms or when investigating extremely low count conditions. This approach is ubiquitous in the research literature but has only been validated, from the point of view of the noise properties, with numerical simulations and phantom data. We present here the first experiment comparing PET images of the same human subjects generated with two separate injections of radiotracer, using actual low dose (LD) data to validate a randomly decimated emulation from a standard dose scan. A key point of the work is focused on the randoms fractions, which scale differently than the trues at varying activity levels. METHODS: Eleven patients with non-small cell lung cancer were enrolled in the study. Each imaging session consisted of two independent FDG-PET/CT scans: a LD scan followed by a standard dose (SD) scan. Images were first reconstructed, using filtered back-projection (FBP) and OSEM incorporating time-of-flight information and point-spread function modeling (PSFTOF), from the LD and SD datasets comprising all counts from each scanned bed position. The number of true counts was recorded for all LD scans, and independent, count-matched emulations (ELD) were reconstructed from the SD data. Noise distribution within the liver and standardized uptake value reproducibility within a population of contoured, tracer-avid lesion volumes were evaluated across scans and statistics. RESULTS: The randoms fraction estimates were 17.4 ± 1.6% (14.9-19.4) in the LD data and 42 ± 2.3% (37.1-45.5) in the SD data. Eleven lesions were identified and volumes of interest were generated with a 50% threshold isocontour for each lesion, in every image. The distributions of metabolic volumes, means and maxima defined by the contoured volumes-of-interest (VOIs) were similar between the LD and SD sets. A two-tailed, matched t-test was performed on the populations of region statistics for both LD and ELD reconstructions, and the t-statistics were 1.1 (P = 0.267) and -0.22 (P = 0.828) for the background liver VOIs and -0.54 (P = 0.603) and 0.23 (P = 0.821) for the lesion VOIs, for FBP and PSFTOF respectively. In every test, the null hypothesis that the two populations had the same mean could not be rejected at the 5% significance level. CONCLUSIONS: Our results demonstrate that clinical LD PET scans can indeed be accurately emulated by the statistical decimation of standard dose scans, and this was achieved through validation by images generated with unbiased random coincidence estimations.

Ultra-low-dose PET reconstruction using generative adversarial network with feature matching and task-specific perceptual loss.

PURPOSE: Our goal was to use a generative adversarial network (GAN) with feature matching and task-specific perceptual loss to synthesize standard-dose amyloid Positron emission tomography (PET) images of high quality and including accurate pathological features from ultra-low-dose PET images only. METHODS: Forty PET datasets from 39 participants were acquired with a simultaneous PET/MRI scanner following injection of 330 ± 30 MBq of the amyloid radiotracer 18F-florbetaben. The raw list-mode PET data were reconstructed as the standard-dose ground truth and were randomly undersampled by a factor of 100 to reconstruct 1% low-dose PET scans. A 2D encoder-decoder network was implemented as the generator to synthesize a standard-dose image and a discriminator was used to evaluate them. The two networks contested with each other to achieve high-visual quality PET from the ultra-low-dose PET. Multi-slice inputs were used to reduce noise by providing the network with 2.5D information. Feature matching was applied to reduce hallucinated structures. Task-specific perceptual loss was designed to maintain the correct pathological features. The image quality was evaluated by peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and root mean square error (RMSE) metrics with and without each of these modules. Two expert radiologists were asked to score image quality on a 5-point scale and identified the amyloid status (positive or negative). RESULTS: With only low-dose PET as input, the proposed method significantly outperformed Chen et al.'s method (Chen et al. Radiology. 2018;290:649-656) (which shows the best performance in this task) with the same input (PET-only model) by 1.87 dB in PSNR, 2.04% in SSIM, and 24.75% in RMSE. It also achieved comparable results to Chen et al.'s method which used additional magnetic resonance imaging (MRI) inputs (PET-MR model). Experts' reading results showed that the proposed method could achieve better overall image quality and maintain better pathological features indicating amyloid status than both PET-only and PET-MR models proposed by Chen et al. CONCLUSION: Standard-dose amyloid PET images can be synthesized from ultra-low-dose images using GAN. Applying adversarial learning, feature matching, and task-specific perceptual loss are essential to ensure image quality and the preservation of pathological features.

Positron Emission Mammography Image Interpretation for Reduced Image Count Levels.

UNLABELLED: We studied the effects of reduced (18)F-FDG injection activity on interpretation of positron emission mammography (PEM) images and compared image interpretation between 2 postinjection imaging times. METHODS: We performed a receiver-operating-characteristic (ROC) study using PEM images reconstructed with different count levels expected from injected activities between 23 and 185 MBq. Thirty patients received 2 PEM scans at postinjection times of 60 and 120 min. Half of the patients were scanned with a standard protocol; the others received one-half of the standard activity. Images were reconstructed using 100%, 50%, and 25% of the total counts acquired. Eight radiologists used a 5-point confidence scale to score 232 PEM images for the presence of up to 3 malignant lesions. Paired images were analyzed with conditional logistic regression and ROC analysis to investigate changes in interpretation. RESULTS: There was a trend for increasing lesion detection sensitivity with increased image counts: odds ratios were 2.2 (P = 0.01) and 1.9 (P = 0.04) per doubling of image counts for 60- and 120-min uptake images, respectively, without significant difference between time points (P = 0.7). The area under the ROC curve (AUC) was highest for the 100%-count, 60-min images (0.83 vs. 0.75 for 50%-counts, P = 0.02). The 120-min images had a similar trend but did not reach statistical significance (AUC = 0.79 vs. 0.73, P = 0.1). Our data did not yield significant trends between specificity and image counts. Lesion-to-background ratios increased between 60- and 120-min scans (P < 0.001). CONCLUSION: Reducing the image counts relative to the standard protocol decreased diagnostic accuracy. The increase in lesion-to-background ratio between 60- and 120-min uptake times was not enough to improve detection sensitivity in this study, perhaps in part due to fewer counts in the later scan.

Clinical impact of contrast-enhanced computed tomography combined with low-dose (18)F-fluorodeoxyglucose positron emission tomography/computed tomography on routine lymphoma patient management.

This study evaluated the clinical impact of contrast-enhanced computed tomography (CECT) on routine management of patients with lymphoma. Over a 1-year period, 237 CECT scans were performed prospectively in 163 patients after low-dose (18)F-fluorodeoxyglucose positron emission tomography/computed tomography ((18)F-FDG PET/CT). Scans were performed at staging (n = 41), interim (n = 73), post-therapy (n = 115) and follow-up (n = 8). Clinical impact was determined from the multidisciplinary committee reports. CECT had no clinical impact in 219 cases (92%). A clear impact was noted in only 3%, i.e. up-staging of lymphoma (n = 2) and diagnosis of deep vein thrombosis (n = 5). A debatable impact was noted in the remaining 11 cases, consisting of additional investigations, either without therapeutic impact (n = 8), or resulting in delay of therapy onset (n = 2) or ablative surgery (n = 1). CECT delivered an average 33.5 ± 3.8 mSv vs. 17.7 ± 2.8 mSv for PET/CT. In conclusion, the clinical impact of CECT seems limited, although scarce, life-threatening conditions were diagnosed. Imaging of lymphoma needs optimization to reduce radiation exposure.