High-quality Positron Emission Tomography Images Research Articles

IE-CycleGAN: improved cycle consistent adversarial network for unpaired PET image enhancement.

Technological advances in instruments have greatly promoted the development of positron emission tomography (PET) scanners. State-of-the-art PET scanners such as uEXPLORER can collect PET images of significantly higher quality. However, these scanners are not currently available in most local hospitals due to the high cost of manufacturing and maintenance. Our study aims to convert low-quality PET images acquired by common PET scanners into images of comparable quality to those obtained by state-of-the-art scanners without the need for paired low- and high-quality PET images. In this paper, we proposed an improved CycleGAN (IE-CycleGAN) model for unpaired PET image enhancement. The proposedmethod is based on CycleGAN, and the correlation coefficient loss and patient-specific prior loss were added to constrain the structure of the generated images. Furthermore, we defined a normalX-to-advanced training strategy to enhance the generalization ability of the network. The proposedmethod was validated on unpaired uEXPLORER datasets and Biograph Vision local hospital datasets. For the uEXPLORER dataset, the proposedmethod achieved betterresults than non-local mean filtering (NLM), block-matching and 3D filtering (BM3D), and deep image prior (DIP), which are comparable to Unet (supervised) and CycleGAN (supervised). For the Biograph Vision local hospital datasets, the proposedmethod achieved higher contrast-to-noise ratios(CNR) and tumor-to-background SUVmax ratios (TBR) than NLM, BM3D, and DIP. In addition, the proposedmethod showed higher contrast, SUVmax,and TBR than Unet (supervised) and CycleGAN (supervised) when applied to images from different scanners. The proposed unpaired PET image enhancementmethod outperforms NLM, BM3D, and DIP. Moreover, it performs better than the Unet(supervised) and CycleGAN(supervised) when implemented on local hospital datasets, which demonstrates its excellent generalization ability.

Full-dose whole-body PET synthesis from low-dose PET using high-efficiency denoising diffusion probabilistic model: PET consistency model.

Positron Emission Tomography (PET) has been a commonly used imaging modality in broad clinical applications. One of the most important tradeoffs in PET imaging is between image quality and radiation dose: high image quality comes with high radiation exposure. Improving image quality is desirable for all clinical applications while minimizing radiation exposure is needed to reduce risk to patients. We introduce PET Consistency Model (PET-CM), an efficient diffusion-based method for generating high-quality full-dose PET images from low-dose PET images. It employs a two-step process, adding Gaussian noise to full-dose PET images in the forward diffusion, and then denoising them using a PET Shifted-window Vision Transformer (PET-VIT) network in the reverse diffusion. The PET-VIT network learns a consistency function that enables direct denoising of Gaussian noise into clean full-dose PET images. PET-CM achieves state-of-the-art image quality while requiring significantly less computation time than other methods. Evaluation with normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), multi-scale structure similarity index (SSIM), normalized cross-correlation (NCC), and clinical evaluation including Human Ranking Score (HRS) and Standardized Uptake Value (SUV) Error analysis shows its superiority in synthesizing full-dose PET images from low-dose inputs. In experiments comparing eighth-dose to full-dose images, PET-CM demonstrated impressive performance with NMAE of 1.278±0.122%, PSNR of 33.783±0.824dB, SSIM of 0.964±0.009, NCC of 0.968±0.011, HRS of 4.543, and SUV Error of 0.255±0.318%, with an average generation time of 62 s per patient. This is a significant improvement compared to the state-of-the-art diffusion-based model with PET-CM reaching this result 12× faster. Similarly, in the quarter-dose to full-dose image experiments, PET-CM delivered competitive outcomes, achieving an NMAE of 0.973±0.066%, PSNR of 36.172±0.801dB, SSIM of 0.984±0.004, NCC of 0.990±0.005, HRS of 4.428, and SUV Error of 0.151±0.192% using the same generation process, which underlining its high quantitative and clinical precision in both denoising scenario. We propose PET-CM, the first efficient diffusion-model-based method, for estimating full-dose PET images from low-dose images. PET-CM provides comparable quality to the state-of-the-art diffusion model with higher efficiency. By utilizing this approach, it becomes possible to maintain high-quality PET images suitable for clinical use while mitigating the risks associated with radiation. The code is availble at https://github.com/shaoyanpan/Full-dose-Whole-body-PET-Synthesis-from-Low-dose-PET-Using-Consistency-Model.

Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising

Deep image prior (DIP) has been successfully applied to positron emission tomography (PET) image restoration, enabling represent implicit prior using only convolutional neural network architecture without training dataset, whereas the general supervised approach requires massive low-and high-quality PET image pairs. To answer the increased need for PET imaging with DIP, it is indispensable to improve the performance of the underlying DIP itself. Here, we propose a self-supervised pre-training model to improve the DIP-based PET image denoising performance. Our proposed pre-training model acquires transferable and generalizable visual representations from only unlabeled PET images by restoring various degraded PET images in a self-supervised approach. We evaluated the proposed method using clinical brain PET data with various radioactive tracers (18F-florbetapir, 11C-Pittsburgh compound-B, 18F-fluoro-2-deoxy-D-glucose, and 15O-CO2) acquired from different PET scanners. The proposed method using the self-supervised pre-training model achieved robust and state-of-the-art denoising performance while retaining spatial details and quantification accuracy compared to other unsupervised methods and pre-training model. These results highlight the potential that the proposed method is particularly effective against rare diseases and probes and helps reduce the scan time or the radiotracer dose without affecting the patients.

PET/SPECT/spectral-CT/CBCT imaging in a small-animal radiation therapy platform: A Monte Carlo study-Part I: Quad-modal imaging.

In spite of the tremendous potential of game-changing biological image- and/or biologically guided radiation therapy (RT) and adaptive radiation therapy for cancer treatment, existing limited strategies for integrating molecular imaging and/or biological information with RT have impeded the translation of preclinical research findings to clinical applications. Additionally, there is an urgent need for a highly integrated small-animal radiation therapy (SART) platform that can seamlessly combine therapeutic and diagnostic capabilities to comprehensively enhance RT for cancer treatment. We investigated a highly integrated quad-modal on-board imaging configuration combining positron emission tomography (PET), single-photon emission computed tomography (SPECT), photon-counting spectral CT, and cone-beam computed tomography (CBCT) in a SART platform using a Monte Carlo model as a proof-of-concept. The quad-modal on-board imaging configuration of the SART platform was designed and evaluated by using the GATE Monte Carlo code. A partial-ring on-board PET imaging subsystem, utilizing advanced semiconductor thallium bromide detector technology, was designed to achieve high sensitivity and spatial resolution. On-board SPECT, photon-counting spectral-CT, and CBCT imaging were performed using a single cadmium zinc telluride flat detector panel. The absolute peak sensitivity and scatter fraction of the PET subsystem were estimated by using simulated phantoms described in the NEMA NU-4 standard. The spatial resolution of the PET image of the platform was evaluated by imaging a simulated micro-Derenzo hot-rod phantom. To evaluate the quantitative imaging capability of the system's spectral CT, the Bayesian eigentissue decomposition (ETD) method was utilized to quantitatively decompose the virtual noncontrast (VNC) electron densities and iodine contrast agent fractions in the Kidney1 inserts mixed with the iodine contrast agent within the simulated phantoms. The performance of the proposed quad-model imaging in the platform was validated by imaging a simulated phantom with multiple imaging probes, including an iodine contrast agent and radioisotopes of 18F and 99mTc. The PET subsystem demonstrated an absolute peak sensitivity of 18.5% at the scanner center, with an energy window of 175-560KeV, and a scatter fraction of only 3.5% for the mouse phantom, with a default energy window of 480-540KeV. The spatial resolution of PET on-board imaging exceeded 1.2mm. All imaging probes were identified clearly within the phantom. The PET and SPECT images agreed well with the actual spatial distributions of the tracers within the phantom. Average relative errors on electron density and iodine contrast agent fraction in the Kidney1 inserts were less than 3%. High-quality PET images, SPECT images, spectral-CT images (including iodine contrast agent fraction images and VNC electron density images), and CBCT images of the simulated phantom demonstrated the comprehensive multimodal imaging capability of the system. The results demonstrated the feasibility of the proposed quad-modal imaging configuration in a SART platform. The design incorporates anatomical, molecular, and functional information about tumors, thereby facilitating successful translation of preclinical studies into clinical practices.

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.

3D multi-modality Transformer-GAN for high-quality PET reconstruction

Positron emission tomography (PET) scans can reveal abnormal metabolic activities of cells and provide favorable information for clinical patient diagnosis. Generally, standard-dose PET (SPET) images contain more diagnostic information than low-dose PET (LPET) images but higher-dose scans can also bring higher potential radiation risks. To reduce the radiation risk while acquiring high-quality PET images, in this paper, we propose a 3D multi-modality edge-aware Transformer-GAN for high-quality SPET reconstruction using the corresponding LPET images and T1 acquisitions from magnetic resonance imaging (T1-MRI). Specifically, to fully excavate the metabolic distributions in LPET and anatomical structural information in T1-MRI, we first use two separate CNN-based encoders to extract local spatial features from the two modalities, respectively, and design a multimodal feature integration module to effectively integrate the two kinds of features given the diverse contributions of features at different locations. Then, as CNNs can describe local spatial information well but have difficulty in modeling long-range dependencies in images, we further apply a Transformer-based encoder to extract global semantic information in the input images and use a CNN decoder to transform the encoded features into SPET images. Finally, a patch-based discriminator is applied to ensure the similarity of patch-wise data distribution between the reconstructed and real images. Considering the importance of edge information in anatomical structures for clinical disease diagnosis, besides voxel-level estimation error and adversarial loss, we also introduce an edge-aware loss to retain more edge detail information in the reconstructed SPET images. Experiments on the phantom dataset and clinical dataset validate that our proposed method can effectively reconstruct high-quality SPET images and outperform current state-of-the-art methods in terms of qualitative and quantitative metrics.

Semi-Supervised Standard-Dose PET Image Generation via Region-Adaptive Normalization and Structural Consistency Constraint.

Positron Emission Tomography (PET) is an important nuclear medical imaging technique, and has been widely used in clinical applications, e.g., tumor detection and brain disease diagnosis. As PET imaging could put patients at risk of radiation, the acquisition of high-quality PET images with standard-dose tracers should be cautious. However, if dose is reduced in PET acquisition, the imaging quality could become worse and thus may not meet clinical requirement. To safely reduce the tracer dose and also maintain high quality of PET imaging, we propose a novel and effective approach to estimate high-quality Standard-dose PET (SPET) images from Low-dose PET (LPET) images. Specifically, to fully utilize both the rare paired and the abundant unpaired LPET and SPET images, we propose a semi-supervised framework for network training. Meanwhile, based on this framework, we further design a Region-adaptive Normalization (RN) and a structural consistency constraint to track the task-specific challenges. RN performs region-specific normalization in different regions of each PET image to suppress negative impact of large intensity variation across different regions, while the structural consistency constraint maintains structural details during the generation of SPET images from LPET images. Experiments on real human chest-abdomen PET images demonstrate that our proposed approach achieves state-of-the-art performance quantitatively and qualitatively.

Short-axis PET image quality improvement based on a uEXPLORER total-body PET system through deep learning.

The axial field of view (AFOV) of a positron emission tomography (PET) scanner greatly affects the quality of PET images. Although a total-body PET scanner (uEXPLORER) with a large AFOV is more sensitive, it is more expensive and difficult to widely use. Therefore, we attempt to utilize high-quality images generated by uEXPLORER to optimize the quality of images from short-axis PET scanners through deep learning technology while controlling costs. The experiments were conducted using PET images of three anatomical locations (brain, lung, and abdomen) from 335 patients. To simulate PET images from different axes, two protocols were used to obtain PET image pairs (each patient was scanned once). For low-quality PET (LQ-PET) images with a 320-mm AFOV, we applied a 300-mm FOV for brain reconstruction and a 500-mm FOV for lung and abdomen reconstruction. For high-quality PET (HQ-PET) images, we applied a 1940-mm AFOV during the reconstruction process. A 3D Unet was utilized to learn the mapping relationship between LQ-PET and HQ-PET images. In addition, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were employed to evaluate the model performance. Furthermore, two nuclear medicine doctors evaluated the image quality based on clinical readings. The generated PET images of the brain, lung, and abdomen were quantitatively and qualitatively compatible with the HQ-PET images. In particular, our method achieved PSNR values of 35.41 ± 5.45dB (p < 0.05), 33.77 ± 6.18dB (p < 0.05), and 38.58 ± 7.28dB (p < 0.05) for the three beds. The overall mean SSIM was greater than 0.94 for all patients who underwent testing. Moreover, the total subjective quality levels of the generated PET images for three beds were 3.74 ± 0.74, 3.69 ± 0.81, and 3.42 ± 0.99 (the highest possible score was 5, and the minimum score was 1) from two experienced nuclear medicine experts. Additionally, we evaluated the distribution of quantitative standard uptake values (SUV) in the region of interest (ROI). Both the SUV distribution and the peaks of the profile show that our results are consistent with the HQ-PET images, proving the superiority of our approach. The findings demonstrate the potential of the proposed technique for improving the image quality of a PET scanner with a 320mm or even shorter AFOV. Furthermore, this study explored the potential of utilizing uEXPLORER to achieve improved short-axis PET image quality at a limited economic cost, and computer-aided diagnosis systems that are related can help patients and radiologists.

Precision of the PET activity range during irradiation with 10C, 11C, and 12C beams

Objective. Beams of stable ions have been a well-established tool for radiotherapy for many decades. In the case of ion beam therapy with stable 12C ions, the positron emitters 10,11C are produced via projectile and target fragmentation, and their decays enable visualization of the beam via positron emission tomography (PET). However, the PET activity peak matches the Bragg peak only roughly and PET counting statistics is low. These issues can be mitigated by using a short-lived positron emitter as a therapeutic beam. Approach. An experiment studying the precision of the measurement of ranges of positron-emitting carbon isotopes by means of PET has been performed at the FRS fragment-separator facility of GSI Helmholtzzentrum für Schwerionenforschung GmbH, Germany. The PET scanner used in the experiment is a dual-panel version of a Siemens Biograph mCT PET scanner. Main results. High-quality in-beam PET images and activity distributions have been measured from the in-flight produced positron emitting isotopes 11C and 10C implanted into homogeneous PMMA phantoms. Taking advantage of the high statistics obtained in this experiment, we investigated the time evolution of the uncertainty of the range determined by means of PET during the course of irradiation, and show that the uncertainty improves with the inverse square root of the number of PET counts. The uncertainty is thus fully determined by the PET counting statistics. During the delivery of 1.6 × 107 ions in 4 spills for a total duration of 19.2 s, the PET activity range uncertainty for 10C, 11C and 12C is 0.04 mm, 0.7 mm and 1.3 mm, respectively. The gain in precision related to the PET counting statistics is thus much larger when going from 11C to 10C than when going from 12C to 11C. The much better precision for 10C is due to its much shorter half-life, which, contrary to the case of 11C, also enables to include the in-spill data in the image formation. Significance. Our results can be used to estimate the contribution from PET counting statistics to the precision of range determination in a particular carbon therapy situation, taking into account the irradiation scenario, the required dose and the PET scanner characteristics.

High-quality PET image synthesis from ultra-low-dose PET/MRI using bi-task deep learning.

Lowering the dose for positron emission tomography (PET) imaging reduces patients' radiation burden but decreases the image quality by increasing noise and reducing imaging detail and quantifications. This paper introduces a method for acquiring high-quality PET images from an ultra-low-dose state to achieve both high-quality images and a low radiation burden. We developed a two-task-based end-to-end generative adversarial network, named bi-c-GAN, that incorporated the advantages of PET and magnetic resonance imaging (MRI) modalities to synthesize high-quality PET images from an ultra-low-dose input. Moreover, a combined loss, including the mean absolute error, structural loss, and bias loss, was created to improve the trained model's performance. Real integrated PET/MRI data from 67 patients' axial heads (each with 161 slices) were used for training and validation purposes. Synthesized images were quantified by the peak signal-to-noise ratio (PSNR), normalized mean square error (NMSE), structural similarity (SSIM), and contrast noise ratio (CNR). The improvement ratios of these four selected quantitative metrics were used to compare the images produced by bi-c-GAN with other methods. In the four-fold cross-validation, the proposed bi-c-GAN outperformed the other three selected methods (U-net, c-GAN, and multiple input c-GAN). With the bi-c-GAN, in a 5% low-dose PET, the image quality was higher than that of the other three methods by at least 6.7% in the PSNR, 0.6% in the SSIM, 1.3% in the NMSE, and 8% in the CNR. In the hold-out validation, bi-c-GAN improved the image quality compared to U-net and c-GAN in both 2.5% and 10% low-dose PET. For example, the PSNR using bi-C-GAN was at least 4.46% in the 2.5% low-dose PET and at most 14.88% in the 10% low-dose PET. Visual examples also showed a higher quality of images generated from the proposed method, demonstrating the denoising and improving ability of bi-c-GAN. By taking advantage of integrated PET/MR images and multitask deep learning (MDL), the proposed bi-c-GAN can efficiently improve the image quality of ultra-low-dose PET and reduce radiation exposure.

Adaptive rectification based adversarial network with spectrum constraint for high-quality PET image synthesis.

Positron emission tomography (PET) is a typical nuclear imaging technique, which can provide crucial functional information for early brain disease diagnosis. Generally, clinically acceptable PET images are obtained by injecting a standard-dose radioactive tracer into human body, while on the other hand the cumulative radiation exposure inevitably raises concerns about potential health risks. However, reducing the tracer dose will increase the noise and artifacts of the reconstructed PET image. For the purpose of acquiring high-quality PET images while reducing radiation exposure, in this paper, we innovatively present an adaptive rectification based generative adversarial network with spectrum constraint, named AR-GAN, which uses low-dose PET (LPET) image to synthesize standard-dose PET (SPET) image of high-quality. Specifically, considering the existing differences between the synthesized SPET image by traditional GAN and the real SPET image, an adaptive rectification network (AR-Net) is devised to estimate the residual between the preliminarily predicted image and the real SPET image, based on the hypothesis that a more realistic rectified image can be obtained by incorporating both the residual and the preliminarily predicted PET image. Moreover, to address the issue of high-frequency distortions in the output image, we employ a spectral regularization term in the training optimization objective to constrain the consistency of the synthesized image and the real image in the frequency domain, which further preserves the high-frequency detailed information and improves synthesis performance. Validations on both the phantom dataset and the clinical dataset show that the proposed AR-GAN can estimate SPET images from LPET images effectively and outperform other state-of-the-art image synthesis approaches.

Anatomical-guided attention enhances unsupervised PET image denoising performance.

Although supervised convolutional neural networks (CNNs) often outperform conventional alternatives for denoising positron emission tomography (PET) images, they require many low- and high-quality reference PET image pairs. Herein, we propose an unsupervised 3D PET image denoising method based on an anatomical information-guided attention mechanism. The proposed magnetic resonance-guided deep decoder (MR-GDD) utilizes the spatial details and semantic features of MR-guidance image more effectively by introducing encoder-decoder and deep decoder subnetworks. Moreover, the specific shapes and patterns of the guidance image do not affect the denoised PET image, because the guidance image is input to the network through an attention gate. In a Monte Carlo simulation of [18F]fluoro-2-deoxy-D-glucose (FDG), the proposed method achieved the highest peak signal-to-noise ratio and structural similarity (27.92±0.44dB/0.886±0.007), as compared with Gaussian filtering (26.68±0.10dB/0.807±0.004), image guided filtering (27.40±0.11dB/0.849±0.003), deep image prior (DIP) (24.22±0.43dB/0.737±0.017), and MR-DIP (27.65±0.42dB/0.879±0.007). Furthermore, we experimentally visualized the behavior of the optimization process, which is often unknown in unsupervised CNN-based restoration problems. For preclinical (using [18F]FDG and [11C]raclopride) and clinical (using [18F]florbetapir) studies, the proposed method demonstrates state-of-the-art denoising performance while retaining spatial resolution and quantitative accuracy, despite using a common network architecture for various noisy PET images with 1/10th of the full counts. These results suggest that the proposed MR-GDD can reduce PET scan times and PET tracer doses considerably without impacting patients.

Assessment of MicroPET Image Quality Based on Reconstruction Methods and Post-Filtering

The accuracy of positron emission tomography (PET) imaging is hampered by the partial volume effect (PVE), which causes image blurring and sampling. The PVE produces spillover phenomena, making PET analysis difficult. Generally, the PVE values vary based on reconstruction methods and filtering. Thus, selection of the proper reconstruction and filtering method can ensure accurate and high-quality PET images. This study compared the values of factors (recovery coefficient (RC), uniformity, and spillover ratio (SOR)) associated with different reconstruction and post-filtering methods using a mouse image quality phantom (NEMA NU 4), and we present an effective approach for microPET images. The PET images were obtained using a microPET scanner (Inveon, Siemens Medical Solutions, Malvern, PA, USA). PET data were reconstructed and/or post-filtered. For tumors smaller than 3 mm, iterative reconstruction methods provided better image quality. For tumor sizes bigger than 3 mm, reconstruction methods without post-filtering showed better results.

Towards lower-dose PET using physics-based uncertainty-aware multimodal learning with robustness to out-of-distribution data

Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer dose or acquisition time reduces photon counts, which can deteriorate image quality. Recent deep-neural-network (DNN) based methods for image-to-image translation enable the mapping of low-quality PET images (acquired using substantially reduced dose), coupled with the associated magnetic resonance imaging (MRI) images, to high-quality PET images. However, such DNN methods focus on applications involving test data that match the statistical characteristics of the training data very closely and give little attention to evaluating the performance of these DNNs on new out-of-distribution (OOD) acquisitions. We propose a novel DNN formulation that models the (i) underlying sinogram-based physics of the PET imaging system and (ii) the uncertainty in the DNN output through the per-voxel heteroscedasticity of the residuals between the predicted and the high-quality reference images. Our sinogram-based uncertainty-aware DNN framework, namely, suDNN, estimates a standard-dose PET image using multimodal input in the form of (i) a low-dose/low-count PET image and (ii) the corresponding multi-contrast MRI images, leading to improved robustness of suDNN to OOD acquisitions. Results on in vivo simultaneous PET-MRI, and various forms of OOD data in PET-MRI, show the benefits of suDNN over the current state of the art, quantitatively and qualitatively.

Imaging Somatostatin Positive Tumors with Tyr3-Octreotate/Octreotide Conjugated to Desferrioxamine B Squaramide Radiolabeled with either Zirconium-89 or Gallium-68.

Radiolabeled derivatives of Tyr3-octreotide and Tyr3-octreotate, synthetic analogues of the peptide hormone somatostatin, can be used for positron emission tomography (PET) imaging of somatostatin receptor expression in neuroendocrine tumors. In this work, a squaramide ester derivative of desferrioxamine B (H3DFOSq) was used attach either Tyr3-octreotide or Tyr3-octreotate to the metal binding ligand to give H3DFOSq-TIDE and H3DFOSq-TATE. These new peptide-H3DFOSq conjugates form stable complexes with either of the positron-emitting radionuclides gallium-68 (t1/2 = 68 min) or zirconium-89 (t1/2 = 3.3 days). The new complexes were evaluated in an AR42J xenograft model that has endogenous expression of SSTR2. All four agents displayed good tumor uptake and produced high-quality PET images. For both radionuclides, the complexes formed with H3DFOSq-TATE performed better, with higher tumor uptake and retention than the complexes formed with H3DFOSq-TIDE. The versatile ligands presented here can be radiolabeled with either gallium-68 or zirconium-89 at room temperature. The long radioactive half-life of zirconium-89 makes distribution of pre-synthesized tracers produced to certified standards feasible and could increase the number of clinical centers that can perform diagnostic PET imaging of neuroendocrine tumors.

4D deep image prior: dynamic PET image denoising using an unsupervised four-dimensional branch convolutional neural network

Although convolutional neural networks (CNNs) demonstrate the superior performance in denoising positron emission tomography (PET) images, a supervised training of the CNN requires a pair of large, high-quality PET image datasets. As an unsupervised learning method, a deep image prior (DIP) has recently been proposed; it can perform denoising with only the target image. In this study, we propose an innovative procedure for the DIP approach with a four-dimensional (4D) branch CNN architecture in end-to-end training to denoise dynamic PET images. Our proposed 4D CNN architecture can be applied to end-to-end dynamic PET image denoising by introducing a feature extractor and a reconstruction branch for each time frame of the dynamic PET image. In the proposed DIP method, it is not necessary to prepare high-quality and large patient-related PET images. Instead, a subject’s own static PET image is used as additional information, dynamic PET images are treated as training labels, and denoised dynamic PET images are obtained from the CNN outputs. Both simulation with [18F]fluoro-2-deoxy-D-glucose (FDG) and preclinical data with [18F]FDG and [11C]raclopride were used to evaluate the proposed framework. The results showed that our 4D DIP framework quantitatively and qualitatively outperformed 3D DIP and other unsupervised denoising methods. The proposed 4D DIP framework thus provides a promising procedure for dynamic PET image denoising.

Enzyme mediated incorporation of zirconium-89 or copper-64 into a fragment antibody for same day imaging of epidermal growth factor receptor.

Identification of tumors which over-express Epidermal Growth Factor Receptor (EGFR) is important in selecting patients for anti-EGFR therapies. Enzymatic bioconjugation was used to introduce positron-emitting radionuclides (89Zr, 64Cu) into an anti-EGFR antibody fragment for Positron Emission Tomography (PET) imaging the same day as injection. A monovalent antibody fragment with high affinity for EGFR was engineered to include a sequence that is recognized by the transpeptidase sortase A. Two different metal chelators, one for 89ZrIV and one for 64CuII, were modified with a N-terminal glycine to enable them to act as substrates in sortase A mediated bioconjugation to the antibody fragment. Both fragments provided high-quality PET images of EGFR positive tumors in a mouse model at 3 hours post-injection, a significant advantage when compared to radiolabeled full antibodies that require several days between injection of the tracer and imaging. The use of enzymatic bioconjugation gives reproducible homogeneous products with the metal complexes selectively installed on the C-terminus of the antibody potentially simplifying regulatory approval.

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

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

A preclinical PET dual-tracer imaging protocol for ER and HER2 phenotyping in breast cancer xenografts

BackgroundNuclear medicine is on the constant search of precision radiopharmaceutical approaches to improve patient management. Although discordant expression of the estrogen receptor (ER) and the human epidermal growth factor receptor 2 (HER2) in breast cancer is a known dilemma for appropriate patient management, traditional tumor sampling is often difficult or impractical. While 2-deoxy-2[18F]fluoro-D-glucose (18F-FDG)-positron emission tomography (PET) is an option to detect subclinical metastases, it does not provide phenotype information. Radiolabeled antibodies are able to specifically target expressed cell surface receptors. However, their long circulating half-lives (days) require labeling with long-lived isotopes, such as 89Zr, in order to allow sufficient time for tracer clearance from the blood compartment and to accumulate adequately in target tumors and, thus, generate high-quality PET images. The aim of this study was to develop a dual-tracer PET imaging approach consisting of a fast-clearing small molecule and a slow-clearing antibody. This approach was evaluated in a model consisting of mice harboring separate breast cancer xenografts with either an ER+/HER2− or ER−/HER2+ phenotype, comparable to human metastatic disease with intertumor heterogeneity. Lastly, the aim of our study was to determine the feasibility of specifically identifying these two important phenotypes in an acceptable time window.MethodsFemale nude mice were subcutaneously implanted on opposite shoulders with the ER+/HER2− and ER−/HER2+ MCF-7 and JIMT-1 tumor cell lines, respectively. A second model was developed consisting of mice implanted orthotopically with either MCF-7 or JIMT-1 cells. Pharmacokinetic analysis, serial PET imaging, and biodistribution were first performed for [89Zr]Zr-DFO-trastuzumab (89Zr-T) up to 8 days post-injection (p.i.) in JIMT-1 bearing mice. Region-of-interest (ROI) and biodistribution-derived uptake (% injected-activity/gram of tissue [%IA/g]) values and tumor-to-background ratios were obtained. Results were compared in order to validate ROI and identify early time points that provided high contrast tumor images. For the dual-tracer approach, cohorts of tumor-bearing mice were then subjected to sequential tracer PET imaging. On day 1, mice were administered 4-fluoro-11β-methoxy-16α-[18F]-fluoroestradiol (4FMFES) which targets ER and imaged 45 min p.i. This was immediately followed by the injection of 89Zr-T. Mice were then imaged on day 3 or day 7. ROI analysis was performed, and uptake was calculated in tumors and selected healthy organs for all radiotracers. Quality of tumor targeting for all tracers was evaluated by tumor contrast visualization, tumor and normal tissue uptake, and tumor-to-background ratios.Results89Zr-T provided sufficiently high tumor and low background uptake values that furnished high contrast tumor images by 48 h p.i. For the dual-tracer approach, 4FMFES provided tumor uptake values that were significantly increased in MCF-7 tumors. When 89Zr-T-PET was combined with 18F-4FMFES-PET, the entire dual-tracer sequential-imaging procedure provided specific high-quality contrast images of ER+/HER2− MCF-7 and ER−/HER2+ JIMT-1 tumors for 4FMFES and 89Zr-T, respectively, as short as 72 h from start to finish.ConclusionsThis protocol can provide high contrast images of tumors expressing ER or HER2 within 3 days from injection of 4FMFES to final scan of 89Zr-T and, hence, provides a basis for future dual-tracer combinations that include antibodies.

DPIR-Net: Direct PET Image Reconstruction Based on the Wasserstein Generative Adversarial Network

Positron emission tomography (PET) is an advanced medical imaging technique widely used in various clinical applications, such as tumor detection and neurologic disorders. Reducing the radiotracer dose is desirable in PET imaging because it decreases the patient’s radiation exposure. However, reducing the dose can also increase noise, affecting the image quality. Therefore, an advanced image reconstruction algorithm based on low-dose PET data is needed to improve the quality of the reconstructed image. In this article, we propose the use of a direct PET image reconstruction network (DPIR-Net) using an improved Wasserstein generative adversarial network (WGAN) framework to enhance image quality. This article provides two main findings. First, our network uses sinogram data as input and outputs high-quality PET images direct, resulting in shorter reconstruction times compared with traditional model-based reconstruction networks. Second, we combine perceptual loss, mean square error, and the Wasserstein distance as the loss function, which effectively solves the problem of excessive smoothness and loss of detailed information in traditional network image reconstruction. We performed a comparative study using maximum-likelihood expectation maximization (MLEM) with a post-Gaussian filter, a total variation (TV)-norm regularization, a nonlocal means (NLMs) denoising method, a neural network denoising method, a traditional deep learning PET reconstruction network, and our proposed DPIR-Net method and evaluated the proposed method using both human and mouse data. The mouse data were obtained from a small animal PET prototype system developed by our laboratory. The quantitative and qualitative results show that our proposed method outperformed the conventional methods.