Simultaneous reconstruction of activity and attenuation in time-of-flight PET

Feasibility of PET-enabled dual-energy CT imaging: First physical phantom and initial patient study results

PURPOSE

Dual-energy (DE) CT enables material decomposition by using two different x-ray energies and may be combined with PET for improved multimodality imaging. However, this increases radiation dose and may require a hardware upgrade due to the added second x-ray CT scan. The recently proposed PET-enabled DECT method allows dual-energy imaging using a conventional PET/CT scanner without the need to change scanner hardware or increase radiation exposure. Here we demonstrate the first-time physical phantom and patient data evaluation of this method.

METHODS

The PET-enabled DECT method reconstructs a gamma-ray CT (gCT) image at 511 keV from the time-of-flight PET data with the maximum-likelihood attenuation and activity (MLAA) approach and then combines this image with the low-energy x-ray CT images to form a dual-energy image pair for material decomposition. To improve the image quality of gCT, a kernel MLAA method was developed using the x-ray CT as a priori information. Here we developed a general open-source implementation for gCT reconstruction and used this implementation for the first real data validation using both physical phantom study and human-subject study. Results from PET-enabled DECT were compared using x-ray DECT as the reference. Further, we applied the PET-enabled DECT method in another patient study to evaluate bone lesions.

RESULTS

Compared to the standard MLAA, results from the kernel MLAA showed significantly improved image quality. PET-enabled DECT with the kernel MLAA was able to generate fractional images that were comparable to the x-ray DECT, with high correlation coefficients for both the phantom study and human subject study (R > 0.99). The application study also indicates that PET-enabled DECT has potential to characterize bone lesions.

CONCLUSION

Results from this study have demonstrated the feasibility of this PET-enabled method for CT imaging and material decomposition. PET-enabled DECT shows promise to provide comparable results to x-ray DECT.

Joint estimation of activity, attenuation and motion in respiratory-self-gated time-of-flight PET

Objective. Whole-body positron emission tomography (PET) imaging is often hindered by respiratory motion during acquisition, causing significant degradation in the quality of reconstructed activity images. An additional challenge in PET/CT imaging arises from the respiratory phase mismatch between CT-based attenuation correction and PET acquisition, leading to attenuation artifacts. To address these issues, we propose two new, purely data-driven methods for the joint estimation of activity, attenuation, and motion in respiratory self-gated time-of-flight PET. These methods enable the reconstruction of a single activity image free from motion and attenuation artifacts.Approach. The proposed methods were evaluated using data from the anthropomorphic Wilhelm phantom acquired on a Siemens mCT PET/CT system, as well as three clinical [18F]FDG PET/CT datasets acquired on a GE DMI PET/CT system. Image quality was assessed visually to identify motion and attenuation artifacts. Lesion uptake values were quantitatively compared across reconstructions without motion modeling, with motion modeling but 'static' attenuation correction, and with our proposed methods.Main results. For the Wilhelm phantom, the proposed methods delivered image quality closely matching the reference reconstruction from a static acquisition. The lesion-to-background contrast for a liver dome lesion improved from 2.0 (no motion correction) to 5.2 (using our proposed methods), matching the contrast from the static acquisition (5.2). In contrast, motion modeling with 'static' attenuation correction yielded a lower contrast of 3.5. In patient datasets, the proposed methods successfully reduced motion artifacts in lung and liver lesions and mitigated attenuation artifacts, demonstrating superior lesion to background separation.Significance. Our proposed methods enable the reconstruction of a single, high-quality activity image that is motion-corrected and free from attenuation artifacts, without the need for external hardware.

CT-Less Whole-Body Bone Segmentation of PET Images Using a Multimodal Deep Learning Network

In bone cancer imaging, positron emission tomography (PET) is ideal for the diagnosis and staging of bone cancers due to its high sensitivity to malignant tumors. The diagnosis of bone cancer requires tumor analysis and localization, where accurate and automated wholebody bone segmentation (WBBS) is often needed. Current WBBS for PET imaging is based on paired Computed Tomography (CT) images. However, mismatches between CT and PET images often occur due to patient motion, which leads to erroneous bone segmentation and thus, to inaccurate tumor analysis. Furthermore, there are some instances where CT images are unavailable for WBBS. In this work, we propose a novel multimodal fusion network (MMF-Net) for WBBS of PET images, without the need for CT images. Specifically, the tracer activity ($\lambda$-MLAA), attenuation map ($\mu$-MLAA), and synthetic attenuation map ($\mu$-DL) images are introduced into the training data. We first design a multi-encoder structure employed to fully learn modalityspecific encoding representations of the three PET modality images through independent encoding branches. Then, we propose a multimodal fusion module in the decoder to further integrate the complementary information across the three modalities. Additionally, we introduce revised convolution units, SE (Squeeze-and-Excitation) Normalization and deep supervision to improve segmentation performance. Extensive comparisons and ablation experiments, using 130 whole-body PET image datasets, show promising results. We conclude that the proposed method can achieve WBBS with moderate to high accuracy using PET information only, which potentially can be used to overcome the current limitations of CT-based approaches, while minimizing exposure to ionizing radiation.

Single-Subject Deep-Learning Image Reconstruction With a Neural Optimization Transfer Algorithm for PET-Enabled Dual-Energy CT Imaging

Combining dual-energy computed tomography (DECT) with positron emission tomography (PET) offers many potential clinical applications but typically requires expensive hardware upgrades or increases radiation doses on PET/CT scanners due to an extra X-ray CT scan. The recent PET-enabled DECT method allows DECT imaging on PET/CT without requiring a second X-ray CT scan. It combines the already existing X-ray CT image with a 511 keV γ -ray CT (gCT) image reconstructed from time-of-flight PET emission data. A kernelized framework has been developed for reconstructing gCT image but this method has not fully exploited the potential of prior knowledge. Use of deep neural networks may explore the power of deep learning in this application. However, common approaches require a large database for training, which is impractical for a new imaging method like PET-enabled DECT. Here, we propose a single-subject method by using neural-network representation as a deep coefficient prior to improving gCT image reconstruction without population-based pre-training. The resulting optimization problem becomes the tomographic estimation of nonlinear neural-network parameters from gCT projection data. This complicated problem can be efficiently solved by utilizing the optimization transfer strategy with quadratic surrogates. Each iteration of the proposed neural optimization transfer algorithm includes: PET activity image update; gCT image update; and least-square neural-network learning in the gCT image domain. This algorithm is guaranteed to monotonically increase the data likelihood. Results from computer simulation, real phantom data and real patient data have demonstrated that the proposed method can significantly improve gCT image quality and consequent multi-material decomposition as compared to other methods.

Data-driven gated positron emission tomography/computed tomography for radiotherapy

Purpose

Software-based data-driven gated (DDG) positron emission tomography/computed tomography (PET/CT) has replaced hardware-based 4D PET/CT. The purpose of this article was to review DDG PET/CT, which could improve the accuracy of treatment response assessment, tumor motion evaluation, and target tumor contouring with whole-body (WB) PET/CT for radiotherapy (RT).

Material and methods

This review covered the topics of 4D PET/CT with hardware gating, advancements in PET instrumentation, DDG PET, DDG CT, and DDG PET/CT based on a systematic literature review. It included a discussion of the large axial field-of-view (AFOV) PET detector and a review of the clinical results of DDG PET and DDG PET/CT.

Results

DDG PET matched or outperformed 4D PET with hardware gating. DDG CT was more compatible with DDG PET than 4D CT, which required hardware gating. DDG CT could replace 4D CT for RT. DDG PET and DDG CT for DDG PET/CT can be incorporated in a WB PET/CT of less than 15 min scan time on a PET/CT scanner of at least 25 cm AFOV PET detector.

Conclusions

DDG PET/CT could correct the misregistration and tumor motion artifacts in a WB PET/CT and provide the quantitative PET and tumor motion information of a registered PET/CT for RT.

Simultaneous Activity and Attenuation Estimation in TOF-PET With TV-Constrained Nonconvex Optimization

An alternating direction method of multipliers (ADMM) framework is developed for nonsmooth biconvex optimization for inverse problems in imaging. In particular, the simultaneous estimation of activity and attenuation (SAA) problem in time-of-flight positron emission tomography (TOF-PET) has such a structure when maximum likelihood estimation (MLE) is employed. The ADMM framework is applied to MLE for SAA in TOF-PET, resulting in the ADMM-SAA algorithm. This algorithm is extended by imposing total variation (TV) constraints on both the activity and attenuation map, resulting in the ADMM-TVSAA algorithm. The performance of this algorithm is illustrated using the penalized maximum likelihood activity and attenuation estimation (P-MLAA) algorithm as a reference.

Advances and challenges in immunoPET methodology

Immuno-positron emission tomography (immunoPET) enables imaging of specific targets that play a role in targeted therapy and immunotherapy, such as antigens on cell membranes, targets in the disease microenvironment, or immune cells. The most common immunoPET applications use a monoclonal antibody labeled with a relatively long-lived positron emitter such as 89Zr (T 1/2 = 78.4 h), but smaller antibody-based constructs labeled with various other positron emitting radionuclides are also being investigated. This molecular imaging technique can thus guide the development of new drugs and may have a pivotal role in selecting patients for a particular therapy. In early phase immunoPET trials, multiple imaging time points are used to examine the time-dependent biodistribution and to determine the optimal imaging time point, which may be several days after tracer injection due to the slow kinetics of larger molecules. Once this has been established, usually only one static scan is performed and semi-quantitative values are reported. However, total PET uptake of a tracer is the sum of specific and nonspecific uptake. In addition, uptake may be affected by other factors such as perfusion, pre-/co-administration of the unlabeled molecule, and the treatment schedule. This article reviews imaging methodologies used in immunoPET studies and is divided into two parts. The first part summarizes the vast majority of clinical immunoPET studies applying semi-quantitative methodologies. The second part focuses on a handful of studies applying pharmacokinetic models and includes preclinical and simulation studies. Finally, the potential and challenges of immunoPET quantification methodologies are discussed within the context of the recent technological advancements provided by long axial field of view PET/CT scanners.

Attenuation correction and truncation completion for breast PET/MR imaging using deep learning

Objective. Simultaneous PET/MR scanners combine the high sensitivity of MR imaging with the functional imaging of PET. However, attenuation correction of breast PET/MR imaging is technically challenging. The purpose of this study is to establish a robust attenuation correction algorithm for breast PET/MR images that relies on deep learning (DL) to recreate the missing portions of the patient's anatomy (truncation completion), as well as to provide bone information for attenuation correction from only the PET data.Approach. Data acquired from 23 female subjects with invasive breast cancer scanned with18F-fluorodeoxyglucose PET/CT and PET/MR localized to the breast region were used for this study. Three DL models, U-Net with mean absolute error loss (DLMAE) model, U-Net with mean squared error loss (DLMSE) model, and U-Net with perceptual loss (DLPerceptual) model, were trained to predict synthetic CT images (sCT) for PET attenuation correction (AC) given non-attenuation corrected (NAC) PETPET/MRimages as inputs. The DL and Dixon-based sCT reconstructed PET images were compared against those reconstructed from CT images by calculating the percent error of the standardized uptake value (SUV) and conducting Wilcoxon signed rank statistical tests.Main results. sCT images from the DLMAEmodel, the DLMSEmodel, and the DLPerceptualmodel were similar in mean absolute error (MAE), peak-signal-to-noise ratio, and normalized cross-correlation. No significant difference in SUV was found between the PET images reconstructed using the DLMSEand DLPerceptualsCTs compared to the reference CT for AC in all tissue regions. All DL methods performed better than the Dixon-based method according to SUV analysis.Significance. A 3D U-Net with MSE or perceptual loss model can be implemented into a reconstruction workflow, and the derived sCT images allow successful truncation completion and attenuation correction for breast PET/MR images.

Systematic Review on Learning-based Spectral CT

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

Deep learning techniques in PET/CT imaging: A comprehensive review from sinogram to image space

Positron emission tomography/computed tomography (PET/CT) is increasingly used in oncology, neurology, cardiology, and emerging medical fields. The success stems from the cohesive information that hybrid PET/CT imaging offers, surpassing the capabilities of individual modalities when used in isolation for different malignancies. However, manual image interpretation requires extensive disease-specific knowledge, and it is a time-consuming aspect of physicians' daily routines. Deep learning algorithms, akin to a practitioner during training, extract knowledge from images to facilitate the diagnosis process by detecting symptoms and enhancing images. This acquired knowledge aids in supporting the diagnosis process through symptom detection and image enhancement. The available review papers on PET/CT imaging have a drawback as they either included additional modalities or examined various types of AI applications. However, there has been a lack of comprehensive investigation specifically focused on the highly specific use of AI, and deep learning, on PET/CT images. This review aims to fill that gap by investigating the characteristics of approaches used in papers that employed deep learning for PET/CT imaging. Within the review, we identified 99 studies published between 2017 and 2022 that applied deep learning to PET/CT images. We also identified the best pre-processing algorithms and the most effective deep learning models reported for PET/CT while highlighting the current limitations. Our review underscores the potential of deep learning (DL) in PET/CT imaging, with successful applications in lesion detection, tumor segmentation, and disease classification in both sinogram and image spaces. Common and specific pre-processing techniques are also discussed. DL algorithms excel at extracting meaningful features, and enhancing accuracy and efficiency in diagnosis. However, limitations arise from the scarcity of annotated datasets and challenges in explainability and uncertainty. Recent DL models, such as attention-based models, generative models, multi-modal models, graph convolutional networks, and transformers, are promising for improving PET/CT studies. Additionally, radiomics has garnered attention for tumor classification and predicting patient outcomes. Ongoing research is crucial to explore new applications and improve the accuracy of DL models in this rapidly evolving field.

Effect of detector placement on joint estimation in X-ray fluorescence emission tomography

Imaging the spatial distribution of low concentrations of metal is a growing problem of interest with applications in medical and material sciences. X-ray fluorescence emission tomography (XFET) is an emerging metal mapping imaging modality with potential sensitivity improvements and practical advantages over other methods. However, XFET detector placement must first be optimized to ensure accurate metal density quantification and adequate spatial resolution. In this work, we first use singular value decomposition of the imaging model and eigendecomposition of the object-specific Fisher information matrix to study how detector arrangement affects spatial resolution and feature preservation. We then perform joint image reconstructions of a numerical gold phantom. For this phantom, we show that two parallel detectors provide metal quantification with similar accuracy to four detectors, despite the resulting anisotropic spatial resolution in the attenuation map estimate. Two orthogonal detectors provide improved spatial resolution along one axis, but underestimate the metal concentration in distant regions. Therefore, this work demonstrates the minor effect of using fewer, but strategically placed, detectors in the case where detector placement is restricted. This work is a critical investigation into the limitations and capabilities of XFET prior to its translation to preclinical and benchtop uses.

Advancements in Positron Emission Tomography Detectors: From Silicon Photomultiplier Technology to Artificial Intelligence Applications

This review article focuses on PET detector technology, which is the most crucial factor in determining PET image quality. The article highlights the desired properties of PET detectors, including high detection efficiency, spatial resolution, energy resolution, and timing resolution. Recent advancements in PET detectors to improve these properties are also discussed, including the use of silicon photomultiplier technology, advancements in depth-of-interaction and time-of-flight PET detectors, and the use of artificial intelligence for detector development. The article provides an overview of PET detector technology and its recent advancements, which can significantly enhance PET image quality.

The SNR of time-of-flight positron emission tomography data for joint reconstruction of the activity and attenuation images

Objective.Measurement of the time-of-flight (TOF) difference of each coincident pair of photons increases the effective sensitivity of positron emission tomography (PET). Many authors have analyzed the benefit of TOF for quantification and hot spot detection in the reconstructed activity images. However, TOF not only improves the effective sensitivity, it also enables the joint reconstruction of the tracer concentration and attenuation images. This can be used to correct for errors in CT- or MR-derived attenuation maps, or to apply attenuation correction without the help of a second modality. This paper presents an analysis of the effect of TOF on the variance of the jointly reconstructed attenuation and (attenuation corrected) tracer concentration images.Approach.The analysis is performed for PET systems that have a distribution of possibly non-Gaussian TOF-kernels, and includes the conventional Gaussian TOF-kernel as a special case. Non-Gaussian TOF-kernels are often observed in novel detector designs, which make use of two (or more) different mechanisms to convert the incoming 511 keV photon to optical photons. The analytical result is validated with a simple 2D simulation.Main results.We show that if two different TOF-kernels are equivalent for image reconstruction with known attenuation, then they are also equivalent for joint reconstruction of the activity and the attenuation images. The variance increase in the activity, caused by also jointly reconstructing the attenuation image, vanishes when the TOF-resolution approaches perfection.Significance.These results are of interest for PET detector development and for the development of stand-alone PET systems.

Pre-acquired CT-based attenuation correction with automated headrest removal for a brain-dedicated PET system

Attenuation correction (AC) is essential for quantitative positron emission tomography (PET) images. Attenuation coefficient maps (μ-maps) are usually generated from computed tomography (CT) images when PET-CT combined systems are used. If CT has been performed prior to PET imaging, pre-acquired CT can be used for brain PET AC, because the human head is almost rigid. This pre-acquired CT-based AC approach is suitable for stand-alone brain-dedicated PET, such as VRAIN (ATOX Co. Ltd., Tokyo, Japan). However, the headrest of PET is different from the headrest in pre-acquired CT images, which may degrade the PET image quality. In this study, we prepared three different types of μ-maps: (1) based on the pre-acquired CT, where namely the headrest is different from the PET system (μ-map-diffHr); (2) manually removing the headrest from the pre-acquired CT (μ-map-noHr); and (3) artificially replacing the headrest region with the headrest of the PET system (μ-map-sameHr). Phantom images by VRAIN using each μ-map were investigated for uniformity, noise, and quantitative accuracy. Consequently, only the uniformity of the images using μ-map-diffHr was out of the acceptance criteria. We then proposed an automated method for removing the headrest from pre-acquired CT images. In comparisons of standardized uptake values in nine major brain regions from the 18F-fluoro-2-deoxy-D-glucose-PET of 10 healthy volunteers, no significant differences were found between the μ-map-noHr and the μ-map-sameHr. In conclusion, pre-acquired CT-based AC with automated headrest removal is useful for brain-dedicated PET such as VRAIN.

A simulation study of the system characteristics for a long axial FOV PET design based on monolithic BGO flat panels compared with a pixelated LSO cylindrical design

BACKGROUND

Although a new generation of tomographs with a longer axial field-of-view called total-body PET have been developed, they are not widely utilized due to their high cost compared to conventional scanners. The newly designed walk-through total-body PET scanner is introduced as a high-throughput and cost-efficient alternative to total-body PET scanners, by making use of a flat panel geometry and lower cost, depth-of-interaction capable, monolithic BGO detectors. The main aim of the presented study is to evaluate through Monte Carlo simulation the system characteristics of the walk-through total-body PET scanner by comparing it with a Quadra-like total-body PET of similar attributes to the Siemens Biograph Vision Quadra.

METHODS

The walk-through total-body PET is comprised of two flat detector panels, spaced 50 cm apart. Each panel, 70 [Formula: see text] 106 cm[Formula: see text] in size, consists of 280 BGO-based monolithic detectors. The Quadra-like TB-PET has been simulated based on the characteristics of the Biograph Vision Quadra, one of the most common total-body PET scanners with 106 cm of axial field-of-view, which is constructed with pixelated LSO scintillation crystals. The spatial resolution, sensitivity, count rate performance, scatter fractions, and image quality of both scanners are simulated in the GATE simulation toolkit for comparison.

RESULTS

Due to the DOI-capable detectors used in the walk-through total-body PET, the values of the spatial resolution of this scanner were all below 2 mm along directions parallel to the panels, and reached a maximum of 3.36 mm in the direction perpendicular to the panels. This resolution is a large improvement compared to the values of the Quadra-like TB-PET. The walk-through total-body PET uses its maximum sensitivity (154 cps/kBq) for data acquisition and image reconstruction.

CONCLUSION

Based on the combination of very good spatial resolution and high sensitivity of the walk-through total-body PET, along with a 2.2 times lower scintillation crystal volume and 1.8 times lower SiPM surface, this scanner can be a very cost-efficient alternative for total-body PET scanners in cases where concomitant CT is not required.

Hybrid PET/MR in Cardiac Imaging

In the last few years, technological advances in MR imaging, PET detectors, and attenuation correction algorithms have allowed the creation of truly integrated PET/MR imaging systems, for both clinical and research applications. These machines allow a comprehensive investigation of cardiovascular diseases, by offering a wide variety of detailed anatomical and functional data in combination. Despite significant pathophysiologic mechanisms being clarified by this new data, its clinical relevance and prognostic significance have not been demonstrated yet.

Spatio-Temporal Positron Emission Tomography Reconstruction with Attenuation and Motion Correction

The detection of cancer lesions of a comparable size to that of the typical system resolution of modern scanners is a long-standing problem in Positron Emission Tomography. In this paper, the effect of composing an image-registering convolutional neural network with the modeling of the static data acquisition (i.e., the forward model) is investigated. Two algorithms for Positron Emission Tomography reconstruction with motion and attenuation correction are proposed and their performance is evaluated in the detectability of small pulmonary lesions. The evaluation is performed on synthetic data with respect to chosen figures of merit, visual inspection, and an ideal observer. The commonly used figures of merit-Peak Signal-to-Noise Ratio, Recovery Coefficient, and Signal Difference-to-Noise Ration-give inconclusive responses, whereas visual inspection and the Channelised Hotelling Observer suggest that the proposed algorithms outperform current clinical practice.

Deep-learning-based methods of attenuation correction for SPECT and PET

Attenuation correction (AC) is essential for quantitative analysis and clinical diagnosis of single-photon emission computed tomography (SPECT) and positron emission tomography (PET). In clinical practice, computed tomography (CT) is utilized to generate attenuation maps (μ-maps) for AC of hybrid SPECT/CT and PET/CT scanners. However, CT-based AC methods frequently produce artifacts due to CT artifacts and misregistration of SPECT-CT and PET-CT scans. Segmentation-based AC methods using magnetic resonance imaging (MRI) for PET/MRI scanners are inaccurate and complicated since MRI does not contain direct information of photon attenuation. Computational AC methods for SPECT and PET estimate attenuation coefficients directly from raw emission data, but suffer from low accuracy, cross-talk artifacts, high computational complexity, and high noise level. The recently evolving deep-learning-based methods have shown promising results in AC of SPECT and PET, which can be generally divided into two categories: indirect and direct strategies. Indirect AC strategies apply neural networks to transform emission, transmission, or MR images into synthetic μ-maps or CT images which are then incorporated into AC reconstruction. Direct AC strategies skip the intermediate steps of generating μ-maps or CT images and predict AC SPECT or PET images from non-attenuation-correction (NAC) SPECT or PET images directly. These deep-learning-based AC methods show comparable and even superior performance to non-deep-learning methods. In this article, we first discussed the principles and limitations of non-deep-learning AC methods, and then reviewed the status and prospects of deep-learning-based methods for AC of SPECT and PET.

A review of PET attenuation correction methods for PET-MR

Despite being thirteen years since the installation of the first PET-MR system, the scanners constitute a very small proportion of the total hybrid PET systems installed. This is in stark contrast to the rapid expansion of the PET-CT scanner, which quickly established its importance in patient diagnosis within a similar timeframe. One of the main hurdles is the development of an accurate, reproducible and easy-to-use method for attenuation correction. Quantitative discrepancies in PET images between the manufacturer-provided MR methods and the more established CT- or transmission-based attenuation correction methods have led the scientific community in a continuous effort to develop a robust and accurate alternative. These can be divided into four broad categories: (i) MR-based, (ii) emission-based, (iii) atlas-based and the (iv) machine learning-based attenuation correction, which is rapidly gaining momentum. The first is based on segmenting the MR images in various tissues and allocating a predefined attenuation coefficient for each tissue. Emission-based attenuation correction methods aim in utilising the PET emission data by simultaneously reconstructing the radioactivity distribution and the attenuation image. Atlas-based attenuation correction methods aim to predict a CT or transmission image given an MR image of a new patient, by using databases containing CT or transmission images from the general population. Finally, in machine learning methods, a model that could predict the required image given the acquired MR or non-attenuation-corrected PET image is developed by exploiting the underlying features of the images. Deep learning methods are the dominant approach in this category. Compared to the more traditional machine learning, which uses structured data for building a model, deep learning makes direct use of the acquired images to identify underlying features. This up-to-date review goes through the literature of attenuation correction approaches in PET-MR after categorising them. The various approaches in each category are described and discussed. After exploring each category separately, a general overview is given of the current status and potential future approaches along with a comparison of the four outlined categories.

A quantitative clinical evaluation of simultaneous reconstruction of attenuation and activity in time-of-flight PET

BACKGROUND

The maximum likelihood activity and attenuation (MLAA) reconstruction algorithm has been proposed to jointly estimate tracer activity and attenuation at the same time, and proven to be a promising solution to the CT attenuation correction (CT-AC) artifacts in PET images. This study aimed to perform a quantitative evaluation and clinical validation of the MLAA method.

METHODS

A uniform cylinder phantom filled with ¹⁸F-FDG solution was scanned to optimize the reconstruction parameters for the implemented MLAA algorithm. 67 patients who underwent whole-body ¹⁸F-FDG PET/CT scan were retrospectively recruited. PET images were reconstructed using MLAA and clinical standard OSEM algorithm with CT-AC (CT-OSEM). The mean and maximum standardized uptake values (SUVmean and SUVmax) in regions of interest (ROIs) of organs, high uptake lesions and areas affected by metal implants and respiration motion artifacts were quantitatively analyzed.

RESULTS

In quantitative analysis, SUVs in patient's organ ROIs between two methods showed R² ranging from 0.91 to 0.98 and k ranging from 0.90 to 1.06, and the average SUVmax and SUVmean differences between two methods were within 10% range, except for the lung ROI, which was 10.5% and 16.73% respectively. The average SUVmax and SUVmean differences of a total of 117 high uptake lesions were 7.25% and 7.10% respectively. 20 patients were identified to have apparent respiration motion artifacts in the liver in CT-OSEM images, and the SUVs differences between two methods measured at dome of the liver were significantly larger than measured at middle part of the liver. 10 regions with obvious metal artifacts were identified in CT-OSEM images and the average SUVmean and SUVmax differences in metal implants affected regions were reported to be 52.90% and 56.20% respectively.

CONCLUSIONS

PET images reconstructed using MLAA are clinically acceptable in terms of image quality as well as quantification and it is a useful tool in clinical practice, especially when CT-AC may cause respiration motion and metal artifacts. Moreover, this study also provides technical reference and data support for the future iteration and development of PET reconstruction technology of SUV accurate quantification.

Joint Estimation of Metal Density and Attenuation Maps with Pencil Beam XFET

X-ray fluorescence emission tomography (XFET) is an emerging imaging modality that images the spatial distribution of metal without requiring biochemical modification or radioactivity. This work investigates the joint estimation of metal and attenuation maps with a pencil-beam XFET system that allows for direct metal measurement in the absence of attenuation. Using singular value decomposition on a simplified imaging model, we show that reconstructing metal and attenuation voxels far from the detector is an ill-conditioned problem. Using simulated data, we develop and compare two image reconstruction methods for joint estimation. The first method alternates between updating the attenuation map with a separable paraboloidal surrogates algorithm and updating the metal map with a closed-form solution. The second method performs simultaneous joint estimation with conjugate gradients based on a linearized imaging model. The alternating approach outperforms the linearized approach for iron and gold numerical phantom reconstructions. Reconstructing an (8 cm)3 object containing gold concentrations of 5 mg/cm3 and an unknown beam attenuation map using the alternating approach yields an accurate gold map (NRMSE = 0.19) and attenuation map (NRMSE = 0.14). This simulation demonstrates an accurate joint reconstruction of metal and attenuation maps, from emission data, without previous knowledge of any attenuation map.

Deep learning-based attenuation map generation with simultaneously reconstructed PET activity and attenuation and low-dose application

Objective. In PET/CT imaging, CT is used for positron emission tomography (PET) attenuation correction (AC). CT artifacts or misalignment between PET and CT can cause AC artifacts and quantification errors in PET. Simultaneous reconstruction (MLAA) of PET activity (λ-MLAA) and attenuation (μ-MLAA) maps was proposed to solve those issues using the time-of-flight PET raw data only. However,λ-MLAA still suffers from quantification error as compared to reconstruction using the gold-standard CT-based attenuation map (μ-CT). Recently, a deep learning (DL)-based framework was proposed to improve MLAA by predictingμ-DL fromλ-MLAA andμ-MLAA using an image domain loss function (IM-loss). However, IM-loss does not directly measure the AC errors according to the PET attenuation physics. Our preliminary studies showed that an additional physics-based loss function can lead to more accurate PET AC. The main objective of this study is to optimize the attenuation map generation framework for clinical full-dose¹⁸F-FDG studies. We also investigate the effectiveness of the optimized network on predicting attenuation maps for synthetic low-dose oncological PET studies.Approach. We optimized the proposed DL framework by applying different preprocessing steps and hyperparameter optimization, including patch size, weights of the loss terms and number of angles in the projection-domain loss term. The optimization was performed based on 100 skull-to-toe¹⁸F-FDG PET/CT scans with minimal misalignment. The optimized framework was further evaluated on 85 clinical full-dose neck-to-thigh¹⁸F-FDG cancer datasets as well as synthetic low-dose studies with only 10% of the full-dose raw data.Main results. Clinical evaluation of tumor quantification as well as physics-based figure-of-merit metric evaluation validated the promising performance of our proposed method. For both full-dose and low-dose studies, the proposed framework achieved <1% error in tumor standardized uptake value measures.Significance. It is of great clinical interest to achieve CT-less PET reconstruction, especially for low-dose PET studies.

Joint motion estimation and penalized image reconstruction algorithm with anatomical priors for gated TOF-PET/CT

The presence of respiratory motion not only degrades the reconstructed image but also limits the utilization of anatomical priors in emission tomography. In this study, we explore the potential application of a joint motion estimation and penalized image reconstruction algorithm using anatomical priors in gated time-of-flight positron emission tomography/computed tomography (PET/CT). The algorithm is able to warp both the activity image and the attenuation map to align them with the measured data with the facilitation of anatomical information contained in the attenuation map. Five patient datasets, three acquired in single-bed position and two acquired in whole-body continuous-bed-motion mode, are included. For each patient, the attenuation map is derived from a breath-hold CT. The Parallel Levels Sets (PLS) is chosen as a representative anatomical prior. In addition to demonstrating the reliability of the estimated motion and the benefits of incorporating anatomical prior, preliminary results also indicate that the algorithm shows the potential to reconstruct an activity image in the space corresponding to that of the attenuation map, which could be applied to address the potential misalignment issue in applications involving multiple PET acquisitions but a single CT.

Using domain knowledge for robust and generalizable deep learning-based CT-free PET attenuation and scatter correction

Despite the potential of deep learning (DL)-based methods in substituting CT-based PET attenuation and scatter correction for CT-free PET imaging, a critical bottleneck is their limited capability in handling large heterogeneity of tracers and scanners of PET imaging. This study employs a simple way to integrate domain knowledge in DL for CT-free PET imaging. In contrast to conventional direct DL methods, we simplify the complex problem by a domain decomposition so that the learning of anatomy-dependent attenuation correction can be achieved robustly in a low-frequency domain while the original anatomy-independent high-frequency texture can be preserved during the processing. Even with the training from one tracer on one scanner, the effectiveness and robustness of our proposed approach are confirmed in tests of various external imaging tracers on different scanners. The robust, generalizable, and transparent DL development may enhance the potential of clinical translation.

Deep learning-based methods have been proposed to substitute CT-based PET attenuation and scatter correction to achieve CT-free PET imaging. Here, the authors present a simple way to integrate domain knowledge in deep learning for CT-free PET imaging.

Comparison between a dual-time-window protocol and other simplified protocols for dynamic total-body 18F-FDG PET imaging

PURPOSE

Efforts have been made both to avoid invasive blood sampling and to shorten the scan duration for dynamic positron emission tomography (PET) imaging. A total-body scanner, such as the uEXPLORER PET/CT, can relieve these challenges through the following features: First, the whole-body coverage allows for noninvasive input function from the aortic arteries; second, with a dramatic increase in sensitivity, image quality can still be maintained at a high level even with a shorter scan duration than usual. We implemented a dual-time-window (DTW) protocol for a dynamic total-body 18F-FDG PET scan to obtain multiple kinetic parameters. The DTW protocol was then compared to several other simplified quantification methods for total-body FDG imaging that were proposed for conventional setup.

METHODS

The research included 28 patient scans performed on an uEXPLORER PET/CT. By discarding the corresponding data in the middle of the existing full 60-min dynamic scan, the DTW protocol was simulated. Nonlinear fitting was used to estimate the missing data in the interval. The full input function was obtained from 15 subjects using a hybrid approach with a population-based image-derived input function. Quantification was carried out in three areas: the cerebral cortex, muscle, and tumor lesion. Micro- and macro-kinetic parameters for different scan durations were estimated by assuming an irreversible two-tissue compartment model. The visual performance of parametric images and region of interest-based quantification in several parameters were evaluated. Furthermore, simplified quantification methods (DTW, Patlak, fractional uptake ratio [FUR], and standardized uptake value [SUV]) were compared for similarity to the reference net influx rate Ki.

RESULTS

Ki and K1 derived from the DTW protocol showed overall good consistency (P < 0.01) with the reference from the 60-min dynamic scan with 10-min early scan and 5-min late scan (Ki correlation: 0.971, 0.990, and 0.990; K1 correlation: 0.820, 0.940, and 0.975 in the cerebral cortex, muscle, and tumor lesion, respectively). Similar correlationss were found for other micro-parameters. The DTW protocol had the lowest bias relative to standard Ki than any of the quantification methods, followed by FUR and Patlak. SUV had the weakest correlation with Ki. The whole-body Ki and K1 images generated by the DTW protocol were consistent with the reference parametric images.

CONCLUSIONS

Using the DTW protocol, the dynamic total-body FDG scan time can be reduced to 15 min while obtaining accurate Ki and K1 quantification and acceptable visual performance in parametric images. However, the trade-off between quantification accuracy and protocol implementation feasibility must be considered in practice. We recommend that the DTW protocol be used when the clinical task requires reliable visual assessment or quantifying multiple micro-parameters; FUR with a hybrid input function may be a more feasible approach to quantifying regional metabolic rate with a known lesion position or organs of interest.

DeTransUnet: attenuation correction of gated cardiac images without structural information

Objective. Myocardial perfusion imaging (MPI) with positron emission tomography (PET) is a non-invasive imaging method, and it is of great significance to the diagnosis and prognosis of coronary heart disease. Attenuation correction (AC) for PET images is a necessary step for further quantitative analysis. In order not to use magnetic resonance (MR) or computed tomography (CT) images for AC, this work proposes DeTransUnet to obtain AC PET images directly from no-attenuation corrected (NAC) PET images. Approach. The proposed DeTransUnet is a 3D structure which combines the multi-scale deformable transformer layers and the 3D convolutional neural network (CNN). And it integrates the advantages of transformer with long-range dependence and CNN suitable for image calculation. The AC images using CT images for AC and scatter correction (SC) and are considered as training labels, while the NAC images are reconstructed without AC and SC. Standard uptake value (SUV) values are calculated for both NAC and AC images to exclude the influence of weight and injection dose. With NAC SUV images as the inputs of the DeTransUnet, the outputs of DeTransUnet are AC SUV images. Main results. The proposed DeTransUnet was performed on an MPI gated-PET dataset, and the results were compared with Unet2D and Unet2.5D. The metrics of the whole image and the left ventricular myocardium show that the proposed method has advantages over other deep learning methods. Significance. The proposed DeTransUnet is a novel AC framework that does not require CT or MR images. It can be used as an independent AC method on PET/MR instrument. In addition, when CT images contain defects or cannot be registered with PET images on PET/CT instrument, DeTransUnet is able to repair the defects and keep consistent with the NAC images.

Quantitative evaluation of a deep learning-based framework to generate whole-body attenuation maps using LSO background radiation in long axial FOV PET scanners

Purpose

Attenuation correction is a critically important step in data correction in positron emission tomography (PET) image formation. The current standard method involves conversion of Hounsfield units from a computed tomography (CT) image to construct attenuation maps (µ-maps) at 511 keV. In this work, the increased sensitivity of long axial field-of-view (LAFOV) PET scanners was exploited to develop and evaluate a deep learning (DL) and joint reconstruction-based method to generate µ-maps utilizing background radiation from lutetium-based (LSO) scintillators.

Methods

Data from 18 subjects were used to train convolutional neural networks to enhance initial µ-maps generated using joint activity and attenuation reconstruction algorithm (MLACF) with transmission data from LSO background radiation acquired before and after the administration of ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) (µ-map_MLACF-PRE and µ-map_MLACF-POST respectively). The deep learning-enhanced µ-maps (µ-map_DL-MLACF-PRE and µ-map_{DL-MLACF-POST}) were compared against MLACF-derived and CT-based maps (µ-map_CT). The performance of the method was also evaluated by assessing PET images reconstructed using each µ-map and computing volume-of-interest based standard uptake value measurements and percentage relative mean error (rME) and relative mean absolute error (rMAE) relative to CT-based method.

Results

No statistically significant difference was observed in rME values for µ-map_DL-MLACF-PRE and µ-map_{DL-MLACF-POST} both in fat-based and water-based soft tissue as well as bones, suggesting that presence of the radiopharmaceutical activity in the body had negligible effects on the resulting µ-maps. The rMAE values µ-map_{DL-MLACF-POST} were reduced by a factor of 3.3 in average compared to the rMAE of µ-map_MLACF-POST. Similarly, the average rMAE values of PET images reconstructed using µ-map_{DL-MLACF-POST} (PET_{DL-MLACF-POST}) were 2.6 times smaller than the average rMAE values of PET images reconstructed using µ-map_MLACF-POST. The mean absolute errors in SUV values of PET_{DL-MLACF-POST} compared to PET_CT were less than 5% in healthy organs, less than 7% in brain grey matter and 4.3% for all tumours combined.

Conclusion

We describe a deep learning-based method to accurately generate µ-maps from PET emission data and LSO background radiation, enabling CT-free attenuation and scatter correction in LAFOV PET scanners.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-022-05909-3.

Deep learning-based attenuation correction for whole-body PET - a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine

A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT).

METHODS

Clinical whole-body PET/CT datasets of 18F-FDG (N = 113), 68 Ga-DOTATATE (N = 76), and 18F-Fluciclovine (N = 90) were used to train and test tracer-specific neural networks. For each tracer, forty subjects were used to train the neural network to predict attenuation maps (µ-DL). µ-DL and µ-MLAA were compared to the gold-standard µ-CT. PET images reconstructed using the OSEM algorithm with µ-DL (OSEMDL) and µ-MLAA (OSEMMLAA) were compared to the CT-based reconstruction (OSEMCT). Tumor regions of interest were segmented by two radiologists and tumor SUV and volume measures were reported, as well as evaluation using conventional image analysis metrics.

RESULTS

µ-DL yielded high resolution and fine detail recovery of the attenuation map, which was superior in quality as compared to µ-MLAA in all metrics for all tracers. Using OSEMCT as the gold-standard, OSEMDL provided more accurate tumor quantification than OSEMMLAA for all three tracers, e.g., error in SUVmax for OSEMMLAA vs. OSEMDL: - 3.6 ± 4.4% vs. - 1.7 ± 4.5% for 18F-FDG (N = 152), - 4.3 ± 5.1% vs. 0.4 ± 2.8% for 68 Ga-DOTATATE (N = 70), and - 7.3 ± 2.9% vs. - 2.8 ± 2.3% for 18F-Fluciclovine (N = 44). OSEMDL also yielded more accurate tumor volume measures than OSEMMLAA, i.e., - 8.4 ± 14.5% (OSEMMLAA) vs. - 3.0 ± 15.0% for 18F-FDG, - 14.1 ± 19.7% vs. 1.8 ± 11.6% for 68 Ga-DOTATATE, and - 15.9 ± 9.1% vs. - 6.4 ± 6.4% for 18F-Fluciclovine.

CONCLUSIONS

The proposed framework provides accurate and robust attenuation correction for whole-body 18F-FDG, 68 Ga-DOTATATE and 18F-Fluciclovine in tumor SUV measures as well as tumor volume estimation. The proposed method provides clinically equivalent quality as compared to CT in attenuation correction for the three tracers.

Attenuation Coefficient Estimation for PET/MRI With Bayesian Deep Learning Pseudo-CT and Maximum-Likelihood Estimation of Activity and Attenuation

A major remaining challenge for magnetic resonance-based attenuation correction methods (MRAC) is their susceptibility to sources of magnetic resonance imaging (MRI) artifacts (e.g., implants and motion) and uncertainties due to the limitations of MRI contrast (e.g., accurate bone delineation and density, and separation of air/bone). We propose using a Bayesian deep convolutional neural network that in addition to generating an initial pseudo-CT from MR data, it also produces uncertainty estimates of the pseudo-CT to quantify the limitations of the MR data. These outputs are combined with the maximum-likelihood estimation of activity and attenuation (MLAA) reconstruction that uses the PET emission data to improve the attenuation maps. With the proposed approach uncertainty estimation and pseudo-CT prior for robust MLAA (UpCT-MLAA), we demonstrate accurate estimation of PET uptake in pelvic lesions and show recovery of metal implants. In patients without implants, UpCT-MLAA had acceptable but slightly higher root-mean-squared-error (RMSE) than Zero-echotime and Dixon Deep pseudo-CT when compared to CTAC. In patients with metal implants, MLAA recovered the metal implant; however, anatomy outside the implant region was obscured by noise and crosstalk artifacts. Attenuation coefficients from the pseudo-CT from Dixon MRI were accurate in normal anatomy; however, the metal implant region was estimated to have attenuation coefficients of air. UpCT-MLAA estimated attenuation coefficients of metal implants alongside accurate anatomic depiction outside of implant regions.

Performance evaluation of dedicated brain PET scanner with motion correction system

OBJECTIVE

Various motion correction (MC) algorithms for positron emission tomography (PET) have been proposed to accelerate the diagnostic performance and research in brain activity and neurology. We have incorporated MC system-based optical motion tracking into the brain-dedicated time-of-flight PET scanner. In this study, we evaluate the performance characteristics of the developed PET scanner when performing MC in accordance with the standards and guidelines for the brain PET scanner.

METHODS

We evaluate the spatial resolution, scatter fraction, count rate characteristics, sensitivity, and image quality of PET images. The MC evaluation is measured in terms of the spatial resolution and image quality that affect movement.

RESULTS

In the basic performance evaluation, the average spatial resolution by iterative reconstruction was 2.2 mm at 10 mm offset position. The measured peak noise equivalent count rate was 38.0 kcps at 16.7 kBq/mL. The scatter fraction and system sensitivity were 43.9% and 22.4 cps/(Bq/mL), respectively. The image contrast recovery was between 43.2% (10 mm sphere) and 72.0% (37 mm sphere). In the MC performance evaluation, the average spatial resolution was 2.7 mm at 10 mm offset position, when the phantom stage with the point source translates to ± 15 mm along the y-axis. The image contrast recovery was between 34.2 % (10 mm sphere) and 66.8 % (37 mm sphere).

CONCLUSIONS

The reconstructed images using MC were restored to their nearly identical state as those at rest. Therefore, it is concluded that this scanner can observe more natural brain activity.

Evaluation of three methods for delineation and attenuation estimation of the sinus region in MR-based attenuation correction for brain PET-MR imaging

Background

Attenuation correction is crucial in quantitative positron emission tomography-magnetic resonance (PET-MRI) imaging. We evaluated three methods to improve the segmentation and modelling of the attenuation coefficients in the nasal sinus region. Two methods (cuboid and template method) included a MRI-CT conversion model for assigning the attenuation coefficients in the nasal sinus region, whereas one used fixed attenuation coefficient assignment (bulk method).

Methods

The study population consisted of data of 10 subjects which had undergone PET-CT and PET-MRI. PET images were reconstructed with and without time-of-flight (TOF) using CT-based attenuation correction (CTAC) as reference. Comparison was done visually, using DICE coefficients, correlation, analyzing attenuation coefficients, and quantitative analysis of PET and bias atlas images.

Results

The median DICE coefficients were 0.824, 0.853, 0.849 for the bulk, cuboid and template method, respectively. The median attenuation coefficients were 0.0841 cm⁻¹, 0.0876 cm⁻¹, 0.0861 cm⁻¹ and 0.0852 cm⁻¹, for CTAC, bulk, cuboid and template method, respectively. The cuboid and template methods showed error of less than 2.5% in attenuation coefficients. An increased correlation to CTAC was shown with the cuboid and template methods. In the regional analysis, improvement in at least 49% and 80% of VOI was seen with non-TOF and TOF imaging. All methods showed errors less than 2.5% in non-TOF and less than 2% in TOF reconstructions.

Conclusions

We evaluated two proof-of-concept methods for improving quantitative accuracy in PET/MRI imaging and showed that bias can be further reduced by inclusion of TOF. Largest improvements were seen in the regions of olfactory bulb, Heschl's gyri, lingual gyrus and cerebellar vermis. However, the overall effect of inclusion of the sinus region as separate class in MRAC to PET quantification in the brain was considered modest.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00770-0.

Lutetium background radiation in total-body PET-A simulation study on opportunities and challenges in PET attenuation correction

The current generation of total-body positron emission tomography (PET) scanners offer significant sensitivity increase with an extended axial imaging extent. With the large volume of lutetium-based scintillation crystals that are used as detector elements in these scanners, there is an increased flux of background radiation originating from ¹⁷⁶Lu decay in the crystals and higher sensitivity for detecting it. Combined with the ability of scanning the entire body in a single bed position, this allows more effective utilization of the lutetium background as a transmission source for estimating 511 keV attenuation coefficients. In this study, utilization of the lutetium background radiation for attenuation correction in total-body PET was studied using Monte Carlo simulations of a 3D whole-body XCAT phantom in the uEXPLORER PET scanner, with particular focus on ultralow-dose PET scans that are now made possible with these scanners. Effects of an increased acceptance angle, reduced scan durations, and Compton scattering on PET quantification were studied. Furthermore, quantification accuracy of lutetium-based attenuation correction was compared for a 20-min scan of the whole body on the uEXPLORER, a one-meter-long, and a conventional 24-cm-long scanner. Quantification and lesion contrast were minimally affected in both long axial field-of-view scanners and in a whole-body 20-min scan, the mean bias in all analyzed organs of interest were within a ±10% range compared to ground-truth activity maps. Quantification was affected in certain organs, when scan duration was reduced to 5 min or a reduced acceptance angle of 17° was used. Analysis of the Compton scattered events suggests that implementing a scatter correction method for the transmission data will be required, and increasing the energy threshold from 250 keV to 290 keV can reduce the computational costs and data rates, with negligible effects on PET quantification. Finally, the current results can serve as groundwork for transferring lutetium-based attenuation correction into research and clinical practice.

PET respiratory motion correction: quo vadis?

Positron emission tomography (PET) respiratory motion correction has been a subject of great interest for the last twenty years, prompted mainly by the development of multimodality imaging devices such as PET/computed tomography (CT) and PET/magnetic resonance imaging (MRI). PET respiratory motion correction involves a number of steps including acquisition synchronization, motion estimation and finally motion correction. The synchronization steps include the use of different external device systems or data driven approaches which have been gaining ground over the last few years. Patient specific or generic motion models using the respiratory synchronized datasets can be subsequently derived and used for correction either in the image space or within the image reconstruction process. Similar overall approaches can be considered and have been proposed for both PET/CT and PET/MRI devices. Certain variations in the case of PET/MRI include the use of MRI specific sequences for the registration of respiratory motion information. The proposed review includes a comprehensive coverage of all these areas of development in field of PET respiratory motion for different multimodality imaging devices and approaches in terms of synchronization, estimation and subsequent motion correction. Finally, a section on perspectives including the potential clinical usage of these approaches is included.

Comparison of deep learning-based emission-only attenuation correction methods for positron emission tomography

PURPOSE

This study aims to compare two approaches using only emission PET data and a convolution neural network (CNN) to correct the attenuation (μ) of the annihilation photons in PET.

METHODS

One of the approaches uses a CNN to generate μ-maps from the non-attenuation-corrected (NAC) PET images (μ-CNN_NAC). In the other method, CNN is used to improve the accuracy of μ-maps generated using maximum likelihood estimation of activity and attenuation (MLAA) reconstruction (μ-CNN_MLAA). We investigated the improvement in the CNN performance by combining the two methods (μ-CNN_MLAA+NAC) and the suitability of μ-CNN_NAC for providing the scatter distribution required for MLAA reconstruction. Image data from ¹⁸F-FDG (n = 100) or ⁶⁸ Ga-DOTATOC (n = 50) PET/CT scans were used for neural network training and testing.

RESULTS

The error of the attenuation correction factors estimated using μ-CT and μ-CNN_NAC was over 7%, but that of scatter estimates was only 2.5%, indicating the validity of the scatter estimation from μ-CNN_NAC. However, CNN_NAC provided less accurate bone structures in the μ-maps, while the best results in recovering the fine bone structures were obtained by applying CNN_MLAA+NAC. Additionally, the μ-values in the lungs were overestimated by CNN_NAC. Activity images (λ) corrected for attenuation using μ-CNN_MLAA and μ-CNN_MLAA+NAC were superior to those corrected using μ-CNN_NAC, in terms of their similarity to λ-CT. However, the improvement in the similarity with λ-CT by combining the CNN_NAC and CNN_MLAA approaches was insignificant (percent error for lung cancer lesions, λ-CNN_NAC = 5.45% ± 7.88%; λ-CNN_MLAA = 1.21% ± 5.74%; λ-CNN_MLAA+NAC = 1.91% ± 4.78%; percent error for bone cancer lesions, λ-CNN_NAC = 1.37% ± 5.16%; λ-CNN_MLAA = 0.23% ± 3.81%; λ-CNN_MLAA+NAC = 0.05% ± 3.49%).

CONCLUSION

The use of CNN_NAC was feasible for scatter estimation to address the chicken-egg dilemma in MLAA reconstruction, but CNN_MLAA outperformed CNN_NAC.

A CT-less approach to quantitative PET imaging using the LSO intrinsic radiation for long-axial FOV PET scanners

Purpose

Long‐axial field‐of‐view (FOV) positron emission tomography (PET) scanners have gained a lot of interest in the recent years. Such scanners provide increased sensitivity and enable unique imaging opportunities that were not previously feasible. Benefiting from the high sensitivity of a long‐axial FOV PET scanner, we studied a computed tomography (CT)–less reconstruction algorithm for the Siemens Biograph Vision Quadra with an axial FOV of 106 cm.

Methods

In this work, the background radiation from radioisotope lutetium‐176 in the scintillators was used to create an initial estimate of the attenuation maps. Then, joint activity and attenuation reconstruction algorithms were used to create an improved attenuation map of the object. The final attenuation maps were then used to reconstruct quantitative PET images, which were compared against CT‐based PET images. The proposed method was evaluated on data from three patients who underwent a flurodeoxyglucouse PET scan.

Results

Segmentation of the PET images of the three studied patients showed an average quantitative error of 6.5%–8.3% across all studied organs when using attenuation maps from maximum likelihood estimation of attenuation and activity and 5.3%–6.6% when using attenuation maps from maximum likelihood estimation of activity and attenuation correction coefficients.

Conclusions

Benefiting from the background radiation of lutetium‐based scintillators, a quantitative CT‐less PET imaging technique was evaluated in this work.

Generation of attenuation correction factors from time-of-flight PET emission data using high-resolution residual U-net

Attenuation correction of annihilation photons is essential in PET image reconstruction for providing accurate quantitative activity maps. In the absence of an aligned CT device to obtain attenuation information, we propose the high-resolution residual U-net (HRU-Net) to extract attenuation correction factors (ACF) directly from time-of-flight (TOF) PET emission data. HRU-Net is built upon the U-Net encoding-decoding architecture and it utilizes four blocks of modified residual connections in each stage. In each residual block, concatenation is performed to incorporate input and output feature vectors. In addition, flexible and efficient elements of convolutional neural network (CNN) such as dilated convolutions, pre-activation order of a batch normalization (BN) layer, a rectified linear unit (ReLU) layer and a convolution layer, and residual connections are utilized to extract high resolution features. To illustrate the effectiveness of the proposed method, HRU-Net estimated ACF, attenuation maps and activity maps are compared with maximum likelihood ACF (MLACF) algorithm, U-Net, and HC-Net. An ablation study is conducted using non-TOF and TOF sinograms as inputs of networks. The experimental results show that HRU-Net with TOF projections as inputs leads to normalized root mean square error (NRMSE) of 4.84% ± 1.58%, outperforming MLACF, U-Net and HC-Net with NRMSE of 47.82% ± 13.62%, 6.92% ± 1.94%, and 7.99% ± 2.49%, respectively.

Time of Flight in Perspective: Instrumental and Computational Aspects of Time Resolution in Positron Emission Tomography

The first time-of-flight positron emission tomography (TOF-PET) scanners were developed as early as in the 1980s. However, the poor light output and low detection efficiency of TOF-capable detectors available at the time limited any gain in image quality achieved with these TOF-PET scanners over the traditional non-TOF PET scanners. The discovery of LSO and other Lu-based scintillators revived interest in TOF-PET and led to the development of a second generation of scanners with high sensitivity and spatial resolution in the mid-2000s. The introduction of the silicon photomultiplier (SiPM) has recently yielded a third generation of TOF-PET systems with unprecedented imaging performance. Parallel to these instrumentation developments, much progress has been made in the development of image reconstruction algorithms that better utilize the additional information provided by TOF. Overall, the benefits range from a reduction in image variance (SNR increase), through allowing joint estimation of activity and attenuation, to better reconstructing data from limited angle systems. In this work, we review these developments, focusing on three broad areas: 1) timing theory and factors affecting the time resolution of a TOF-PET system; 2) utilization of TOF information for improved image reconstruction; and 3) quantification of the benefits of TOF compared to non-TOF PET. Finally, we offer a brief outlook on the TOF-PET developments anticipated in the short and longer term. Throughout this work, we aim to maintain a clinically driven perspective, treating TOF as one of multiple (and sometimes competitive) factors that can aid in the optimization of PET imaging performance.

2D feasibility study of joint reconstruction of attenuation and activity in limited angle TOF-PET

Several research groups are studying organ-dedicated limited angle positron emission tomography (PET) systems to optimize performance-cost ratio, sensitivity, access to the patient and/or flexibility. Often open systems are considered, typically consisting of two detector panels of various sizes. Such systems provide incomplete sampling due to limited angular coverage and/or truncation, which leads to artefacts in the reconstructed activity images. In addition, these organ-dedicated PET systems are usually stand-alone systems, and as a result, no attenuation information can be obtained from anatomical images acquired in the same imaging session. It has been shown that the use of time-of-flight information reduces incomplete data artefacts and enables the joint estimation of the activity and the attenuation factors. In this work, we explore with simple 2D simulations the performance and stability of a joint reconstruction algorithm, for imaging with a limited angle PET system. The reconstruction is based on the so-called MLACF (Maximum Likelihood Attenuation Correction Factors) algorithm and uses linear attenuation coefficients in a known-tissue-class region to obtain absolute quantification. Different panel sizes and different time-of-flight (TOF) resolutions are considered. The noise propagation is compared to that of MLEM reconstruction with exact attenuation correction (AC) for the same PET system. The results show that with good TOF resolution, images of good visual quality can be obtained. If also a good scatter correction can be implemented, quantitative PET imaging will be possible. Further research, in particular on scatter correction, is required.

Modified kernel MLAA using autoencoder for PET-enabled dual-energy CT

Combined use of PET and dual-energy CT provides complementary information for multi-parametric imaging. PET-enabled dual-energy CT combines a low-energy X-ray CT image with a high-energy γ-ray CT (GCT) image reconstructed from time-of-flight PET emission data to enable dual-energy CT material decomposition on a PET/CT scanner. The maximum-likelihood attenuation and activity (MLAA) algorithm has been used for GCT reconstruction but suffers from noise. Kernel MLAA exploits an X-ray CT image prior through the kernel framework to guide GCT reconstruction and has demonstrated substantial improvements in noise suppression. However, similar to other kernel methods for image reconstruction, the existing kernel MLAA uses image intensity-based features to construct the kernel representation, which is not always robust and may lead to suboptimal reconstruction with artefacts. In this paper, we propose a modified kernel method by using an autoencoder convolutional neural network (CNN) to extract an intrinsic feature set from the X-ray CT image prior. A computer simulation study was conducted to compare the autoencoder CNN-derived feature representation with raw image patches for evaluation of kernel MLAA for GCT image reconstruction and dual-energy multi-material decomposition. The results show that the autoencoder kernel MLAA method can achieve a significant image quality improvement for GCT and material decomposition as compared to the existing kernel MLAA algorithm. A weakness of the proposed method is its potential over-smoothness in a bone region, indicating the importance of further optimization in future work. This article is part of the theme issue 'Synergistic tomographic image reconstruction: part 2'.

Accurate Transmission-Less Attenuation Correction Method for Amyloid-β Brain PET Using Deep Neural Network

The lack of physically measured attenuation maps (μ-maps) for attenuation and scatter correction is an important technical challenge in brain-dedicated stand-alone positron emission tomography (PET) scanners. The accuracy of the calculated attenuation correction is limited by the nonuniformity of tissue composition due to pathologic conditions and the complex structure of facial bones. The aim of this study is to develop an accurate transmission-less attenuation correction method for amyloid-β (Aβ) brain PET studies. We investigated the validity of a deep convolutional neural network trained to produce a CT-derived μ-map (μ-CT) from simultaneously reconstructed activity and attenuation maps using the MLAA (maximum likelihood reconstruction of activity and attenuation) algorithm for Aβ brain PET. The performance of three different structures of U-net models (2D, 2.5D, and 3D) were compared. The U-net models generated less noisy and more uniform μ-maps than MLAA μ-maps. Among the three different U-net models, the patch-based 3D U-net model reduced noise and cross-talk artifacts more effectively. The Dice similarity coefficients between the μ-map generated using 3D U-net and μ-CT in bone and air segments were 0.83 and 0.67. All three U-net models showed better voxel-wise correlation of the μ-maps compared to MLAA. The patch-based 3D U-net model was the best. While the uptake value of MLAA yielded a high percentage error of 20% or more, the uptake value of 3D U-nets yielded the lowest percentage error within 5%. The proposed deep learning approach that requires no transmission data, anatomic image, or atlas/template for PET attenuation correction remarkably enhanced the quantitative accuracy of the simultaneously estimated MLAA μ-maps from Aβ brain PET.

Pitfalls on PET/CT Due to Artifacts and Instrumentation

PET/CT has become a preferred imaging modality over PET-only scanners in clinical practice. However, along with the significant improvement in diagnostic accuracy and patient throughput, pitfalls on PET/CT are reported as well. This review provides a general overview on the potential influence of the limitations with respect to PET/CT instrumentation and artifacts associated with the modality integration on the image appearance and quantitative accuracy of PET. Approaches proposed in literature to address the limitations or minimize the artifacts are discussed as well as their current challenges for clinical applications. Although the CT component can play an important role in assisting clinical diagnosis, we concentrate on the imaging scenarios where CT is used to provide auxiliary information for attenuation compensation and scatter correction in PET.

Imitation learning for improved 3D PET/MR attenuation correction

The assessment of the quality of synthesised/pseudo Computed Tomography (pCT) images is commonly measured by an intensity-wise similarity between the ground truth CT and the pCT. However, when using the pCT as an attenuation map (μ-map) for PET reconstruction in Positron Emission Tomography Magnetic Resonance Imaging (PET/MRI) minimising the error between pCT and CT neglects the main objective of predicting a pCT that when used as μ-map reconstructs a pseudo PET (pPET) which is as similar as possible to the gold standard CT-derived PET reconstruction. This observation motivated us to propose a novel multi-hypothesis deep learning framework explicitly aimed at PET reconstruction application. A convolutional neural network (CNN) synthesises pCTs by minimising a combination of the pixel-wise error between pCT and CT and a novel metric-loss that itself is defined by a CNN and aims to minimise consequent PET residuals. Training is performed on a database of twenty 3D MR/CT/PET brain image pairs. Quantitative results on a fully independent dataset of twenty-three 3D MR/CT/PET image pairs show that the network is able to synthesise more accurate pCTs. The Mean Absolute Error on the pCT (110.98 HU ± 19.22 HU) compared to a baseline CNN (172.12 HU ± 19.61 HU) and a multi-atlas propagation approach (153.40 HU ± 18.68 HU), and subsequently lead to a significant improvement in the PET reconstruction error (4.74% ± 1.52% compared to baseline 13.72% ± 2.48% and multi-atlas propagation 6.68% ± 2.06%).

Deep learning-based attenuation correction for brain PET with various radiotracers

OBJECTIVES

Attenuation correction (AC) is crucial for ensuring the quantitative accuracy of positron emission tomography (PET) imaging. However, obtaining accurate μ-maps from brain-dedicated PET scanners without AC acquisition mechanism is challenging. Therefore, to overcome these problems, we developed a deep learning-based PET AC (deep AC) framework to synthesize transmission computed tomography (TCT) images from non-AC (NAC) PET images using a convolutional neural network (CNN) with a huge dataset of various radiotracers for brain PET imaging.

METHODS

The proposed framework is comprised of three steps: (1) NAC PET image generation, (2) synthetic TCT generation using CNN, and (3) PET image reconstruction. We trained the CNN by combining the mixed image dataset of six radiotracers to avoid overfitting, including [18F]FDG, [18F]BCPP-EF, [11C]Racropride, [11C]PIB, [11C]DPA-713, and [11C]PBB3. We used 1261 brain NAC PET and TCT images (1091 for training and 70 for testing). We did not include [11C]Methionine subjects in the training dataset, but included them in the testing dataset.

RESULTS

The image quality of the synthetic TCT images obtained using the CNN trained on the mixed dataset of six radiotracers was superior to those obtained using the CNN trained on the split dataset generated from each radiotracer. In the [18F]FDG study, the mean relative PET biases of the emission-segmented AC (ESAC) and deep AC were 8.46 ± 5.24 and - 5.69 ± 4.97, respectively. The deep AC PET and TCT AC PET images exhibited excellent correlation for all seven radiotracers (R2 = 0.912-0.982).

CONCLUSION

These results indicate that our proposed deep AC framework can be leveraged to provide quantitatively superior PET images when using the CNN trained on the mixed dataset of PET tracers than when using the CNN trained on the split dataset which means specific for each tracer.

Data-driven respiratory phase-matched PET attenuation correction without CT

We propose a deep learning-based data-driven respiratory phase-matched gated-PET attenuation correction (AC) method that does not need a gated-CT. The proposed method is a multi-step process that consists of data-driven respiratory gating, gated attenuation map estimation using maximum-likelihood reconstruction of attenuation and activity (MLAA) algorithm, and enhancement of the gated attenuation maps using convolutional neural network (CNN). The gated MLAA attenuation maps enhanced by the CNN allowed for the phase-matched AC of gated-PET images. We conducted a non-rigid registration of the gated-PET images to generate motion-free PET images. We trained the CNN by conducting a 3D patch-based learning with 80 oncologic whole-body¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET/CT scan data and applied it to seven regional PET/CT scans that cover the lower lung and upper liver. We investigated the impact of the proposed respiratory phase-matched AC of PET without utilizing CT on tumor size and standard uptake value (SUV) assessment, and PET image quality (%STD). The attenuation corrected gated and motion-free PET images generated using the proposed method yielded sharper organ boundaries and better noise characteristics than conventional gated and ungated PET images. A banana artifact observed in a phase-mismatched CT-based AC was not observed in the proposed approach. By employing the proposed method, the size of tumor was reduced by 12.3% and SUV_90%was increased by 13.3% in tumors with larger movements than 5 mm. %STD of liver uptake was reduced by 11.1%. The deep learning-based data-driven respiratory phase-matched AC method improved the PET image quality and reduced the motion artifacts.

MR-based Attenuation Correction for Brain PET Using 3D Cycle-Consistent Adversarial Network

Attenuation correction (AC) is important for the quantitative merits of positron emission tomography (PET). However, attenuation coefficients cannot be derived from magnetic resonance (MR) images directly for PET/MR systems. In this work, we aimed to derive continuous AC maps from Dixon MR images without the requirement of MR and computed tomography (CT) image registration. To achieve this, a 3D generative adversarial network with both discriminative and cycle-consistency loss (Cycle-GAN) was developed. The modified 3D U-net was employed as the structure of the generative networks to generate the pseudo CT/MR images. The 3D patch-based discriminative networks were used to distinguish the generated pseudo CT/MR images from the true CT/MR images. To evaluate its performance, datasets from 32 patients were used in the experiment. The Dixon segmentation and atlas methods provided by the vendor and the convolutional neural network (CNN) method which utilized registered MR and CT images were employed as the reference methods. Dice coefficients of the pseudo-CT image and the regional quantification in the reconstructed PET images were compared. Results show that the Cycle-GAN framework can generate better AC compared to the Dixon segmentation and atlas methods, and shows comparable performance compared to the CNN method.

Practical joint reconstruction of activity and attenuation with autonomous scaling for time-of-flight PET

Recent research has showed that attenuation images can be determined from emission data, jointly with activity images, up to a scaling constant when utilizing the time-of-flight (TOF) information. We aim to develop practical CT-less joint reconstruction for clinical TOF PET scanners to obtain quantitatively accurate activity and attenuation images. In this work, we present a joint reconstruction of activity and attenuation based on MLAA (maximum likelihood reconstruction of attenuation and activity) with autonomous scaling determination and joint TOF scatter estimation from TOF PET data. Our idea for scaling is to use a selected volume of interest (VOI) in a reconstructed attenuation image with known attenuation, e.g. a liver in patient imaging. First, we construct a unit attenuation medium which has a similar, though not necessarily the same, support to the imaged emission object. All detectable LORs intersecting the unit medium have an attenuation factor of e -1≈ 0.3679, i.e. the line integral of linear attenuation coefficients is one. The scaling factor can then be determined from the difference between the reconstructed attenuation image and the known attenuation within the selected VOI normalized by the unit attenuation medium. A four-step iterative joint reconstruction algorithm is developed. In each iteration, (1) first the activity is updated using TOF OSEM from TOF list-mode data; (2) then the attenuation image is updated using XMLTR-a extended MLTR from non-TOF LOR sinograms; (3) a scaling factor is determined based on the selected VOI and both activity and attenuation images are updated using the estimated scaling; and (4) scatter is estimated using TOF single scatter simulation with the jointly reconstructed activity and attenuation images. The performance of joint reconstruction is studied using simulated data from a generic whole-body clinical TOF PET scanner and a long axial FOV research PET scanner as well as 3D experimental data from the PennPET Explorer scanner. We show that the proposed joint reconstruction with proper autonomous scaling provides low bias results comparable to the reference reconstruction with known attenuation.

PET-enabled dual-energy CT: image reconstruction and a proof-of-concept computer simulation study

Standard dual-energy computed tomography (CT) uses two different x-ray energies to obtain energy-dependent tissue attenuation information to allow quantitative material decomposition. The combined use of dual-energy CT and positron emission tomography (PET) may provide a more comprehensive characterization of disease states in cancer and other diseases. However, the integration of dual-energy CT with PET is not trivial, either requiring costly hardware upgrades or increasing radiation exposure. This paper proposes a different dual-energy CT imaging method that is enabled by PET. Instead of using a second x-ray CT scan with a different energy, this method exploits time-of-flight PET image reconstruction via the maximum likelihood attenuation and activity (MLAA) algorithm to obtain a 511 keV gamma-ray attenuation image from PET emission data. The high-energy gamma-ray attenuation image is then combined with the low-energy x-ray CT of PET/CT to provide a pair of dual-energy CT images. A major challenge with the standard MLAA reconstruction is the high noise present in the reconstructed 511 keV attenuation map, which would not compromise the PET activity reconstruction too much but may significantly affect the performance of the gamma-ray attenuation image for material decomposition. To overcome the problem, we further propose a kernel MLAA algorithm to exploit the prior information from the available x-ray CT image. We conducted a computer simulation to test the concept and algorithm for the task of material decomposition. The simulation results demonstrate that this PET-enabled dual-energy CT method is promising for quantitative material decomposition. The proposed method can be readily implemented on time-of-flight PET/CT scanners to enable simultaneous PET and dual-energy CT imaging.