Positron Emission Tomography Data Sets Research Articles

MRI-free processing of tau PET images for early detection

Abstract Tau positron emission tomography (PET) imaging in Alzheimer’s Disease (AD) is becoming increasingly common to assess in vivo tau burden. MR images are often acquired to assist with processing of PET data, including for region-of-interest definitions in native space and for normalization to template space. However, in the real-world setting, corresponding MRIs may not be available and PET processing may require MRI-free pipelines. This is particularly important and challenging as the field moves towards early detection among clinically unimpaired (CU) individuals where changes in tau PET signal are expected to be subtle. We used two independent [18F]Flortaucipir tau PET datasets to evaluate whether MRI-free PET processing can detect subtle tau PET uptake differences in Amyloid+ (A+) CU individuals (preclinical AD) versus A-. Standardized Uptake Value Ratios (SUVRs) from MRI-free compared to MRI-based methods were evaluated using linear regression and linear mixed-effects regression models. Effect size differences between A+/- CU groups in MRI-free processed cross-sectional and longitudinal tau PET SUVRs were compared to differences quantified through MRI-based processing. Regional MRI-free SUVRs were highly correlated with MRI-based SUVRs within CU individuals (average ICC = 0.90 for ADNI CU and 0.81 for A4 CU). MRI-free and MRI-based pipelines resulted in similar estimates of cross-sectional and longitudinal differences between A- and A+ CU, even in early focal regions within the medial temporal lobe.

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

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 diseasediagnosis. 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. 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 Challengedataset. 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 4.1dB 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 3.37dB and 0.02, and the rMSE was reduced by 9.04 compared with theLDPET. 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 PETdatasets.

Medial prefrontal neuroplasticity during extended-release naltrexone treatment of opioid use disorder – a longitudinal structural magnetic resonance imaging study

Opioid use disorder (OUD) has been linked to macroscopic structural alterations in the brain. The monthly injectable, extended-release formulation of μ-opioid antagonist naltrexone (XR-NTX) is highly effective in reducing opioid craving and preventing opioid relapse. Here, we investigated the neuroanatomical effects of XR-NTX by examining changes in cortical thickness during treatment for OUD. Forty-seven OUD patients underwent structural magnetic resonance imaging and subjectively rated their opioid craving ≤1 day before (pre-treatment) and 11 ± 3 days after (on-treatment) the first XR-NTX injection. A sample of fifty-six non-OUD individuals completed a single imaging session and served as the comparison group. A publicly available [¹¹C]carfentanil positron emission tomography dataset was used to assess the relationship between changes in cortical thickness and μ-opioid receptor (MOR) binding potential across brain regions. We found that the thickness of the medial prefrontal and anterior cingulate cortices (mPFC/aCC; regions with high MOR binding potential) was comparable between the non-OUD individuals and the OUD patients at pre-treatment. However, among the OUD patients, mPFC/aCC thickness significantly decreased from pre-treatment to on-treatment. A greater reduction in mPFC/aCC thickness was associated with a greater reduction in opioid craving. Taken together, our study suggests XR-NTX-induced cortical thickness reduction in the mPFC/aCC regions in OUD patients. The reduction in thickness does not appear to indicate a restoration to the non-OUD level but rather reflects XR-NTX’s distinct therapeutic impact on an MOR-rich brain structure. Our findings highlight the neuroplastic effects of XR-NTX that may inform the development of novel OUD interventions.

Anatomically Guided PET Image Reconstruction Using Conditional Weakly-Supervised Multi-Task Learning Integrating Self-Attention.

To address the lack of high-quality training labels in positron emission tomography (PET) imaging, weakly-supervised reconstruction methods that generate network-based mappings between prior images and noisy targets have been developed. However, the learned model has an intrinsic variance proportional to the average variance of the target image. To suppress noise and improve the accuracy and generalizability of the learned model, we propose a conditional weakly-supervised multi-task learning (MTL) strategy, in which an auxiliary task is introduced serving as an anatomical regularizer for the PET reconstruction main task. In the proposed MTL approach, we devise a novel multi-channel self-attention (MCSA) module that helps learn an optimal combination of shared and task-specific features by capturing both local and global channel-spatial dependencies. The proposed reconstruction method was evaluated on NEMA phantom PET datasets acquired at different positions in a PET/CT scanner and 26 clinical whole-body PET datasets. The phantom results demonstrate that our method outperforms state-of-the-art learning-free and weakly-supervised approaches obtaining the best noise/contrast tradeoff with a significant noise reduction of approximately 50.0% relative to the maximum likelihood (ML) reconstruction. The patient study results demonstrate that our method achieves the largest noise reductions of 67.3% and 35.5% in the liver and lung, respectively, as well as consistently small biases in 8 tumors with various volumes and intensities. In addition, network visualization reveals that adding the auxiliary task introduces more anatomical information into PET reconstruction than adding only the anatomical loss, and the developed MCSA can abstract features and retain PET image details.

TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction

Inter-frame motion in dynamic cardiac positron emission tomography (PET) using rubidium-82 (82Rb) myocardial perfusion imaging impacts myocardial blood flow (MBF) quantification and the diagnosis accuracy of coronary artery diseases. However, the high cross-frame distribution variation due to rapid tracer kinetics poses a considerable challenge for inter-frame motion correction, especially for early frames where intensity-based image registration techniques often fail. To address this issue, we propose a novel method called Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) that utilizes an all-to-one mapping to convert early frames into those with tracer distribution similar to the last reference frame. The TAI-GAN consists of a feature-wise linear modulation layer that encodes channel-wise parameters generated from temporal information and rough cardiac segmentation masks with local shifts that serve as anatomical information. Our proposed method was evaluated on a clinical 82Rb PET dataset, and the results show that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, the motion estimation accuracy and subsequent myocardial blood flow (MBF) quantification with both conventional and deep learning-based motion correction methods were improved compared to using the original frames. The code is available at https://github.com/gxq1998/TAI-GAN.

Population-based deep image prior for dynamic PET denoising: A data-driven approach to improve parametric quantification

The high noise level of dynamic Positron Emission Tomography (PET) images degrades the quality of parametric images. In this study, we aim to improve the quality and quantitative accuracy of Ki images by utilizing deep learning techniques to reduce the noise in dynamic PET images. We propose a novel denoising technique, Population-based Deep Image Prior (PDIP), which integrates population-based prior information into the optimization process of Deep Image Prior (DIP). Specifically, the population-based prior image is generated from a supervised denoising model that is trained on a prompts-matched static PET dataset comprising 100 clinical studies. The 3D U-Net architecture is employed for both the supervised model and the following DIP optimization process. We evaluated the efficacy of PDIP for noise reduction in 25%-count and 100%-count dynamic PET images from 23 patients by comparing with two other baseline techniques: the Prompts-matched Supervised model (PS) and a conditional DIP (CDIP) model that employs the mean static PET image as the prior. Both the PS and CDIP models show effective noise reduction but result in smoothing and removal of small lesions. In addition, the utilization of a single static image as the prior in the CDIP model also introduces a similar tracer distribution to the denoised dynamic frames, leading to lower Ki in general as well as incorrect Ki in the descending aorta. By contrast, as the proposed PDIP model utilizes intrinsic image features from the dynamic dataset and a large clinical static dataset, it not only achieves comparable noise reduction as the supervised and CDIP models but also improves lesion Ki predictions.

A multi-instance tumor subtype classification method for small PET datasets using RA-DL attention module guided deep feature extraction with radiomics features

Background:Positron emission tomography (PET) is extensively employed for diagnosing and staging various tumors, including liver cancer, lung cancer, and lymphoma. Accurate subtype classification of tumors plays a crucial role in formulating effective treatment plans for patients. Notably, lymphoma comprises subtypes like diffuse large B-cell lymphoma and Hodgkin’s lymphoma, while lung cancer encompasses adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. Similarly, liver cancer consists of subtypes such as cholangiocarcinoma and hepatocellular carcinoma. Consequently, the subtype classification of tumors based on PET images holds immense clinical significance. However, in clinical practice, the number of cases available for each subtype is often limited and imbalanced. Therefore, the primary challenge lies in achieving precise subtype classification using a small dataset. Method:This paper presents a novel approach for tumor subtype classification in small datasets using RA-DL (Radiomics-DeepLearning) attention. To address the limited sample size, Support Vector Machines (SVM) is employed as the classifier for tumor subtypes instead of deep learning methods. Emphasizing the importance of texture information in tumor subtype recognition, radiomics features are extracted from the tumor regions during the feature extraction stage. These features are compressed using an autoencoder to reduce redundancy. In addition to radiomics features, deep features are also extracted from the tumors to leverage the feature extraction capabilities of deep learning. In contrast to existing methods, our proposed approach utilizes the RA-DL-Attention mechanism to guide the deep network in extracting complementary deep features that enhance the expressive capacity of the final features while minimizing redundancy. To address the challenges of limited and imbalanced data, our method avoids using classification labels during deep feature extraction and instead incorporates 2D Region of Interest (ROI) segmentation and image reconstruction as auxiliary tasks. Subsequently, all lesion features of a single patient are aggregated into a feature vector using a multi-instance aggregation layer. Result:Validation experiments were conducted on three PET datasets, specifically the liver cancer dataset, lung cancer dataset, and lymphoma dataset. In the context of lung cancer, our proposed method achieved impressive performance with Area Under Curve (AUC) values of 0.82, 0.84, and 0.83 for the three-classification task. For the binary classification task of lymphoma, our method demonstrated notable results with AUC values of 0.95 and 0.75. Moreover, in the binary classification task of liver tumor, our method exhibited promising performance with AUC values of 0.84 and 0.86. Conclusion:The experimental results clearly indicate that our proposed method outperforms alternative approaches significantly. Through the extraction of complementary radiomics features and deep features, our method achieves a substantial improvement in tumor subtype classification performance using small PET datasets.

An iterative reconstruction algorithm for unsupervised PET image

Objective. In recent years, convolutional neural networks (CNNs) have shown great potential in positron emission tomography (PET) image reconstruction. However, most of them rely on many low-quality and high-quality reference PET image pairs for training, which are not always feasible in clinical practice. On the other hand, many works improve the quality of PET image reconstruction by adding explicit regularization or optimizing the network structure, which may lead to complex optimization problems. Approach. In this paper, we develop a novel iterative reconstruction algorithm by integrating the deep image prior (DIP) framework, which only needs the prior information (e.g. MRI) and sinogram data of patients. To be specific, we construct the objective function as a constrained optimization problem and utilize the existing PET image reconstruction packages to streamline calculations. Moreover, to further improve both the reconstruction quality and speed, we introduce the Nesterov’s acceleration part and the restart mechanism in each iteration. Main results. 2D experiments on PET data sets based on computer simulations and real patients demonstrate that our proposed algorithm can outperform existing MLEM-GF, KEM and DIPRecon methods. Significance. Unlike traditional CNN methods, the proposed algorithm does not rely on large data sets, but only leverages inter-patient information. Furthermore, we enhance reconstruction performance by optimizing the iterative algorithm. Notably, the proposed method does not require much modification of the basic algorithm, allowing for easy integration into standard implementations.

Partial volume correction of PET image data using geometric transfer matrices based on uniform B-splines

Objective. Most methods for partial volume correction (PVC) of positron emission tomography (PET) data employ anatomical segmentation of images into regions of interest. This approach is not optimal for exploratory functional imaging beyond regional hypotheses. Here, we describe a novel method for unbiased voxel-wise PVC. Approach. B-spline basis functions were combined with geometric transfer matrices to enable a method (bsGTM) that provides PVC or alternatively provides smoothing with minimal regional crosstalk. The efficacy of the proposed method was evaluated using Monte Carlo simulations, human PET data, and murine functional PET data. Main results. In simulations, bsGTM provided recovery of partial volume signal loss comparable to iterative deconvolution, while demonstrating superior resilience to noise. In a real murine PET dataset, bsGTM yielded much higher sensitivity for detecting amphetamine-induced reduction of [11C]raclopride binding potential. In human PET data, bsGTM smoothing enabled increased signal-to-noise ratios with less degradation of binding potentials relative to Gaussian convolution or non-local means. Significance. bsGTM offers improved performance for PVC relative to iterative deconvolution, the current method of choice for voxel-wise PVC, especially in the common PET regime of low signal-to-noise ratio. The new method provides an anatomically unbiased way to compensate partial volume errors in cases where anatomical segmentation is unavailable or of questionable relevance or accuracy.

Comparison of simple augmentation transformations for a convolutional neural network classifying medical images

Simple image augmentation techniques, such as reflection, rotation, or translation, might work differently for medical images than they do for regular photographs due to the fundamental properties of medical imaging techniques and the bilateral symmetry of the human body. Here, we compare the predictions of a convolutional neural network (CNN) trained for binary classification by using either no augmentation or one of seven usual types augmentation. We have 11 different medical data sets, mostly related to lung infections or cancer, with X-rays, ultrasound (US) images, and images from positron emission tomography (PET) and magnetic resonance imaging (MRI). According to our results, the augmentation types do not produce statistically significant differences for US and PET data sets, but, for X-rays and MRI images, the best augmentation technique is adding Gaussian blur to images.

A Review of Machine Learning Approaches for Brain Positron Emission Tomography Data Analysis.

Positron emission tomography (PET) imaging has moved forward the development of medical diagnostics and research across various domains, including cardiology, neurology, infection detection, and oncology. The integration of machine learning (ML) algorithms into PET data analysis has further enhanced their capabilities of including disease diagnosis and classification, image segmentation, and quantitative analysis. ML algorithms empower researchers and clinicians to extract valuable insights from complex big PET datasets, which enabling automated pattern recognition, predictive health outcome modeling, and more efficient data analysis. This review explains the basic knowledge of PET imaging, statistical methods for PET image analysis, and challenges of PET data analysis. We also discussed the improvement of analysis capabilities by combining PET data with machine learning algorithms and the application of this combination in various aspects of PET image research. This review also highlights current trends and future directions in PET imaging, emphasizing the driving and critical role of machine learning and big PET image data analytics in improving diagnostic accuracy and personalized medical approaches. Integration between PET imaging will shape the future of medical diagnosis and research.

Accurate brain pharmacokinetic parametric imaging using the blood input function extracted from the cavernous sinus.

Brain pharmacokinetic parametric imaging based on dynamic positron emission tomography (PET) scan is valuable in the diagnosis of brain tumor and neurodegenerative diseases. For short-axis PET system, standard blood input function (BIF) of the descending aorta is not acquirable during the dynamic brain scan. BIF extracted from the intracerebral vascular is inaccurate, making the brain parametric imaging task challenging. This study introduces a novel technique tailored for brain pharmacokinetic parameter imaging in short-axis PET in which the head BIF (hBIF) is acquired from the cavernous sinus. The proposed method optimizes the hBIF within the Patlak model via data fitting, curve correction and Patlak graphical model rewriting. The proposed method was built and evaluated using dynamic PET datasets of 67 patients acquired by uEXPLORER PET/CT, among which 64 datasets were used for data fitting and model construction, and 3 were used for method testing; using cross-validation, a total of 15 patient datasets were finally used to test the model. The performance of the new method was evaluated via visual inspection, root-mean-square error (RMSE) measurements and VOI-based accuracy analysis using linear regression and Person's correlation coefficients (PCC). Compared to directly using the cavernous sinus BIF directly for parameter imaging, the new method achieves higher accuracy in parametric analysis, including the generation of Patlak plots closer to the standard plots, better visual effects and lower RMSE values in the Ki (P = 0.0012) and V (P = 0.0042) images. VOI-based analysis shows regression lines with slopes closer to 1 (P = 0.0019 for Ki ) and smaller intercepts (P = 0.0085 for V). The proposed method is capable of achieving accurate brain pharmacokinetic parametric imaging using cavernous sinus BIF with short-axis PET scan. This may facilitate the application of this imaging technology in the clinical diagnosis of brain diseases.

Evidence for inflammation in normal-appearing brain regions in patients with growing sporadic vestibular schwannoma: A PET study.

Nonauditory symptoms can be a prominent feature in patients with sporadic vestibular schwannoma (VS), but the cause of these symptoms is unknown. Inflammation is hypothesized to play a key role in the growth and symptomatic presentation of sporadic VS, and in this study, we investigated through translocator protein (TSPO) positron emission tomography (PET) whether inflammation occurred within the "normal appearing" brain of such patients and its association with tumor growth. Dynamic PET datasets from 15 patients with sporadic VS (8 static and 7 growing) who had been previously imaged using the TSPO tracer [11C](R)-PK11195 were included. Parametric images of [11C](R)-PK11195 binding potential (BPND) and the distribution volume ratio (DVR) were derived and compared across VS growth groups within both contralateral and ipsilateral gray (GM) and white matter (WM) regions. Voxel-wise cluster analysis was additionally performed to identify anatomical regions of increased [11C](R)-PK11195 binding. Compared with static tumors, growing VS demonstrated significantly higher cortical (GM, 1.070 vs. 1.031, P = .03) and whole brain (GM & WM, 1.045 vs. 1.006, P = .03) [11C](R)-PK11195 DVR values. The voxel-wise analysis supported the region-based analysis and revealed clusters of high TSPO binding within the precentral, postcentral, and prefrontal cortex in patients with growing VS. We present the first in vivo evidence of increased TSPO expression and inflammation within the brains of patients with growing sporadic VS. These results provide a potential mechanistic insight into the development of nonauditory symptoms in these patients and highlight the need for further studies interrogating the role of neuroinflammation in driving VS symptomatology.

Deep learning approach using SPECT-to-PET translation for attenuation correction in CT-less myocardial perfusion SPECT imaging

ObjectiveDeep learning approaches have attracted attention for improving the scoring accuracy in computed tomography-less single photon emission computed tomography (SPECT). In this study, we proposed a novel deep learning approach referring to positron emission tomography (PET). The aims of this study were to analyze the agreement of representative voxel values and perfusion scores of SPECT-to-PET translation model-generated SPECT (SPECTSPT) against PET in 17 segments according to the American Heart Association (AHA).MethodsThis retrospective study evaluated the patient-to-patient stress, resting SPECT, and PET datasets of 71 patients. The SPECTSPT generation model was trained (stress: 979 image pairs, rest: 987 image pairs) and validated (stress: 421 image pairs, rest: 425 image pairs) using 31 cases of SPECT and PET image pairs using an image-to-image translation network. Forty of 71 cases of left ventricular base-to-apex short-axis images were translated to SPECTSPT in the stress and resting state (stress: 1830 images, rest: 1856 images). Representative voxel values of SPECT and SPECTSPT in the 17 AHA segments against PET were compared. The stress, resting, and difference scores of 40 cases of SPECT and SPECTSPT were also compared in each of the 17 segments.ResultsFor AHA 17-segment-wise analysis, stressed SPECT but not SPECTSPT voxel values showed significant error from PET at basal anterior regions (segments #1, #6), and at mid inferoseptal regions (segments #8, #9, and #10). SPECT, but not SPECTSPT, voxel values at resting state showed significant error at basal anterior regions (segments #1, #2, and #6), and at mid inferior regions (segments #8, #9, and #11). Significant SPECT overscoring was observed against PET in basal-to-apical inferior regions (segments #4, #10, and #15) during stress. No significant overscoring was observed in SPECTSPT at stress, and only moderate over and underscoring in the basal inferior region (segment #4) was found in the resting and difference states.ConclusionsOur PET-supervised deep learning model is a new approach to correct well-known inferior wall attenuation in SPECT myocardial perfusion imaging. As standalone SPECT systems are used worldwide, the SPECTSPT generation model may be applied as a low-cost and practical clinical tool that provides powerful auxiliary information for the diagnosis of myocardial blood flow.

Positron emission tomography dataset of [11C]carbon dioxide storage in coal for geo-sequestration application

Positron Emission Tomography (PET) imaging has demonstrated its capability in providing time-lapse fluid flow visualisation for improving the understanding of flow properties of geologic media. To investigate the process of CO2 geo-sequestration using PET imaging technology, [11C]CO2 is the most optimal and direct radiotracer. However, it has not been extensively used due to the short half-life of Carbon-11 (20.4 minutes). In this work, a novel laboratory protocol is developed to use [11C]CO2 as radiolabelled tracer to visualise and quantify in-situ CO2 adsorption, spreading, diffusion, and advection flow in coal. This protocol consists of generation and delivering of [11C]CO2, lab-based PET scanning, subsequent micro-CT scanning, and data processing. The lab-based PET scanning setup integrates in-situ core flooding tests with PET scanning. The real-time PET images are acquired under different storage conditions, including early gas production stage, depleted stage, and late storage stage. These datasets can be used to study across-scale theoretical and experimental study of CO2 flow behaviour in coal with the application to CO2 geo-sequestration.

PET/CT Fluoroscopy during PET/CT-Guided Interventions: Initial Experience

This study assessed the feasibility and functionality of the use of a high-speed image fusion technology to generate and display positron emission tomography (PET)/computed tomography (CT) fluoroscopic images during PET/CT-guided tumor ablation procedures. Thirteen patients underwent 14 PET/CT-guided ablations for the treatment of 20 tumors. A Food and Drug Administration–cleared multimodal image fusion platform received images pushed from a scanner, followed by near–real-time, nonrigid image registration. The most recent intraprocedural PET dataset was fused to each single-rotation CT fluoroscopy dataset as it arrived, and the fused images were displayed on an in-room monitor. PET/CT fluoroscopic images were generated and displayed in all procedures and enabled more confident targeting in 3 procedures. The mean lag time from CT fluoroscopic image acquisition to the in-room display of the fused PET/CT fluoroscopic image was 21 seconds ± 8. The registration accuracy was visually satisfactory in 13 of 14 procedures. In conclusion, PET/CT fluoroscopy was feasible and may have the potential to facilitate PET/CT-guided procedures.

PET scatter estimation using deep learning U-Net architecture

Objective. Positron emission tomography (PET) image reconstruction needs to be corrected for scatter in order to produce quantitatively accurate images. Scatter correction is traditionally achieved by incorporating an estimated scatter sinogram into the forward model during image reconstruction. Existing scatter estimated methods compromise between accuracy and computing time. Nowadays scatter estimation is routinely performed using single scatter simulation (SSS), which does not accurately model multiple scatter and scatter from outside the field-of-view, leading to reduced qualitative and quantitative PET reconstructed image accuracy. On the other side, Monte-Carlo (MC) methods provide a high precision, but are computationally expensive and time-consuming, even with recent progress in MC acceleration. Approach. In this work we explore the potential of deep learning (DL) for accurate scatter correction in PET imaging, accounting for all scatter coincidences. We propose a network based on a U-Net convolutional neural network architecture with 5 convolutional layers. The network takes as input the emission and computed tomography (CT)-derived attenuation factor (AF) sinograms and returns the estimated scatter sinogram. The network training was performed using MC simulated PET datasets. Multiple anthropomorphic extended cardiac-torso phantoms of two different regions (lung and pelvis) were created, considering three different body sizes and different levels of statistics. In addition, two patient datasets were used to assess the performance of the method in clinical practice. Main results. Our experiments showed that the accuracy of our method, namely DL-based scatter estimation (DLSE), was independent of the anatomical region (lungs or pelvis). They also showed that the DLSE-corrected images were similar to that reconstructed from scatter-free data and more accurate than SSS-corrected images. Significance. The proposed method is able to estimate scatter sinograms from emission and attenuation data. It has shown a better accuracy than the SSS, while being faster than MC scatter estimation methods.

TAI-GAN: Temporally and Anatomically Informed GAN for Early-to-Late Frame Conversion in Dynamic Cardiac PET Motion Correction.

The rapid tracer kinetics of rubidium-82 (82Rb) and high variation of cross-frame distribution in dynamic cardiac positron emission tomography (PET) raise significant challenges for inter-frame motion correction, particularly for the early frames where conventional intensity-based image registration techniques are not applicable. Alternatively, a promising approach utilizes generative methods to handle the tracer distribution changes to assist existing registration methods. To improve frame-wise registration and parametric quantification, we propose a Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) to transform the early frames into the late reference frame using an all-to-one mapping. Specifically, a feature-wise linear modulation layer encodes channel-wise parameters generated from temporal tracer kinetics information, and rough cardiac segmentations with local shifts serve as the anatomical information. We validated our proposed method on a clinical 82Rb PET dataset and found that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, motion estimation accuracy and clinical myocardial blood flow (MBF) quantification were improved compared to using the original frames. Our code is published at https://github.com/gxq1998/TAI-GAN.

Virtual high-count PET image generation using a deep learning method.

Recently, deep learning-based methods have been established to denoise the low-count positron emission tomography (PET) images and predict their standard-count image counterparts, which could achieve reduction of injected dosage and scan time, and improve image quality for equivalent lesion detectability and clinical diagnosis. In clinical settings, the majority scans are still acquired using standard injection dose with standard scan time. In this work, we applied a 3D U-Net network to reduce the noise of standard-count PET images to obtain the virtual-high-count (VHC) PET images for identifying the potential benefits of the obtained VHC PETimages. The training datasets, including down-sampled standard-count PET images as the network input and high-count images as the desired network output, were derived from 27 whole-body PET datasets, which were acquired using 90-min dynamic scan. The down-sampled standard-count PET images were rebinned with matched noise level of 195 clinical static PET datasets, by matching the normalized standard derivation (NSTD) inside 3D liver region of interests (ROIs). Cross-validation was performed on 27 PET datasets. Normalized mean square error (NMSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and standard uptake value (SUV) bias of lesions were used for evaluation on standard-count and VHC PET images, with real-high-count PET image of 90 min as the gold standard. In addition, the network trained with 27 dynamic PET datasets was applied to 195 clinical static datasets to obtain VHC PET images. The NSTD and mean/max SUV of hypermetabolic lesions in standard-count and VHC PET images were evaluated. Three experienced nuclear medicine physicians evaluated the overall image quality of randomly selected 50 out of 195 patients' standard-count and VHC images and conducted 5-score ranking. A Wilcoxon signed-rank test was used to compare differences in the grading of standard-count and VHCimages. The cross-validation results showed that VHC PET images had improved quantitative metrics scores than the standard-count PET images. The mean/max SUVs of 35 lesions in the standard-count and true-high-count PET images did not show significantly statistical difference. Similarly, the mean/max SUVs of VHC and true-high-count PET images did not show significantly statistical difference. For the 195 clinical data, the VHC PET images had a significantly lower NSTD than the standard-count images. The mean/max SUVs of 215 hypermetabolic lesions in the VHC and standard-count images showed no statistically significant difference. In the image quality evaluation by three experienced nuclear medicine physicians, standard-count images and VHC images received scores with mean and standard deviation of 3.34±0.80 and 4.26 ± 0.72 from Physician 1, 3.02 ± 0.87 and 3.96 ± 0.73 from Physician 2, and 3.74 ± 1.10 and 4.58 ± 0.57 from Physician 3, respectively. The VHC images were consistently ranked higher than the standard-count images. The Wilcoxon signed-rank test also indicated that the image quality evaluation between standard-count and VHC images had significantdifference. A DL method was proposed to convert the standard-count images to the VHC images. The VHC images had reduced noise level. No significant difference in mean/max SUV to the standard-count images was observed. VHC images improved image quality for better lesion detectability and clinicaldiagnosis.

Kernel graph filtering-A new method for dynamic sinogram denoising.

Low count PET (positron emission tomography) imaging is often desirable in clinical diagnosis and biomedical research, but its images are generally very noisy, due to the very weak signals in the sinograms used in image reconstruction. To address this issue, this paper presents a novel kernel graph filtering method for dynamic PET sinogram denoising. This method is derived from treating the dynamic sinograms as the signals on a graph, and learning the graph adaptively from the kernel principal components of the sinograms to construct a lowpass kernel graph spectrum filter. The kernel graph filter thus obtained is then used to filter the original sinogram time frames to obtain the denoised sinograms for PET image reconstruction. Extensive tests and comparisons on the simulated and real life in-vivo dynamic PET datasets show that the proposed method outperforms the existing methods in sinogram denoising and image enhancement of dynamic PET at all count levels, especially at low count, with a great potential in real life applications of dynamic PET imaging.